=== This is the CP2K Performance-Test ===


Already up to date.
Current branch master is up to date.


Already up to date.
Current branch master is up to date.

 GIT Revision: 3b580084b3fdad7e3b92fe812ea749cecfaba215


################# ARCHITECTURE FILE ##################
#!/bin/bash
#
# CP2K arch file for Cray-XC50 (Piz Daint, CSCS, GPU partition)
#
# Tested with: GNU 9.3.0, Cray-MPICH 7.7.18, Cray-libsci 20.09.1, Cray-FFTW 3.3.8.10,
#              COSMA 2.6.6, ELPA 2023.05.001, LIBINT 2.6.0, LIBPEXSI 1.2.0,
#              LIBXC 6.2.2, LIBVORI 220621, LIBXSMM 1.17, PLUMED 2.8.2,
#              SIRIUS 7.4.3, SPGLIB 1.16.2
#
# Usage: Source this arch file and then run make as instructed.
#        A full toolchain installation is performed as default.
#        Replace or adapt the "module add" commands below if needed.
#
# Last update: 21.06.2023
#
# \
   if [ "${0}" = "${BASH_SOURCE}" ]; then \
      echo "ERROR: Script ${0##*/} must be sourced"; \
      echo "Usage: source ${0##*/}"; \
      exit 1; \
   fi; \
   this_file=${BASH_SOURCE##*/}; \
   if [ -n "${1}" ]; then \
      gcc_version="${1}"; \
   else \
      gcc_version="9.3.0"; \
   fi; \
   module add daint-gpu; \
   module rm PrgEnv-cray; \
   module add PrgEnv-gnu; \
   module rm gcc; \
   module add gcc/${gcc_version}; \
   module add cray-fftw/3.3.8.10; \
   module add cudatoolkit; \
   echo "Expected setup:"; \
   echo "   cray-mpich/7.7.18"; \
   echo "   craype-haswell"; \
   echo "   daint-gpu/21.09"; \
   echo "   craype/2.7.10"; \
   echo "   cray-libsci/20.09.1"; \
   echo "   PrgEnv-gnu/6.0.10"; \
   echo "   gcc/${gcc_version}"; \
   echo "   cray-fftw/3.3.8.10"; \
   echo "   cudatoolkit/11.0.2_3.38-8.1__g5b73779"; \
   module list; \
   module -f save cp2k_gpu_gnu_psmp; \
   echo "To load the required modules in your batch job script, use:"; \
   echo "   module restore cp2k_gpu_gnu_psmp"; \
   cd tools/toolchain; \
   ./install_cp2k_toolchain.sh --enable-cuda=yes --gpu-ver=P100 -j${maxtasks} --no-arch-files --with-gcc=system --with-libvdwxc --with-pexsi --with-plumed; \
   cd ../..; \
   printf "Sourcing ${PWD}/tools/toolchain/install/setup ... "; \
   source ${PWD}/tools/toolchain/install/setup; \
   printf "done\n"; \
   echo "Check the output above for error messages and consistency!"; \
   echo; \
   echo "If everything is OK, you can build a CP2K production binary with"; \
   echo "   make -j ARCH=${this_file%.*} VERSION=${this_file##*.}"; \
   echo; \
   echo "Alternatively, you can add further checks, e.g. for regression testing, with"; \
   echo "   make -j ARCH=${this_file%.*} VERSION=${this_file##*.} DO_CHECKS=yes"; \
   echo "or build CP2K as a library with"; \
   echo "   make -j ARCH=${this_file%.*} VERSION=${this_file##*.} libcp2k"; \
   echo; \
   return

# Set options
DO_CHECKS      := no
USE_ACC        := yes
USE_COSMA      := 2.6.6
USE_ELPA       := 2023.05.001
USE_LIBINT     := 2.6.0
USE_LIBPEXSI   := 1.2.0
USE_LIBVORI    := 220621
USE_LIBXC      := 6.2.2
USE_LIBXSMM    := 1.17
USE_PLUMED     := 2.8.2
#USE_QUIP       := 0.9.10
USE_SIRIUS     := 7.4.3
USE_SPGLIB     := 1.16.2
# Only needed for SIRIUS
LIBVDWXC_VER   := 0.4.0
SPFFT_VER      := 1.0.6
SPLA_VER       := 1.5.5
HDF5_VER       := 1.12.0
# Only needed for LIBPEXSI
SCOTCH_VER     := 6.0.0
SUPERLU_VER    := 6.1.0

LMAX           := 5
MAX_CONTR      := 4

GPUVER         := P100
OFFLOAD_TARGET := cuda

CC             := cc
CXX            := CC
OFFLOAD_CC     := nvcc
FC             := ftn
LD             := ftn
AR             := ar -r

# cc, CC, and ftn include already the proper -march flag
CFLAGS         := -O2 -fopenmp -fopenmp-simd -ftree-vectorize -funroll-loops -g

DFLAGS         := -D__parallel
DFLAGS         += -D__SCALAPACK
DFLAGS         += -D__FFTW3
DFLAGS         += -D__MAX_CONTR=$(strip $(MAX_CONTR))

INSTALL_PATH   := $(PWD)/tools/toolchain/install

ifeq ($(DO_CHECKS), yes)
   DFLAGS         += -D__CHECK_DIAG
endif

ifeq ($(USE_ACC), yes)
   DFLAGS         += -D__DBCSR_ACC
   DFLAGS         += -D__OFFLOAD_CUDA
# Possibly no performance gain with PW_CUDA currently
   DFLAGS         += -D__NO_OFFLOAD_PW
endif

ifneq ($(USE_PLUMED),)
   USE_PLUMED     := $(strip $(USE_PLUMED))
   PLUMED_LIB     := $(INSTALL_PATH)/plumed-$(USE_PLUMED)/lib
   DFLAGS         += -D__PLUMED2
   USE_GSL        := 2.7
   LIBS           += $(PLUMED_LIB)/libplumed.a
endif

ifneq ($(USE_ELPA),)
   USE_ELPA       := $(strip $(USE_ELPA))
   TARGET         := nvidia
   ELPA_INC       := $(INSTALL_PATH)/elpa-$(USE_ELPA)/$(TARGET)/include/elpa-$(USE_ELPA)
   ELPA_LIB       := $(INSTALL_PATH)/elpa-$(USE_ELPA)/$(TARGET)/lib
   CFLAGS         += -I$(ELPA_INC)/elpa -I$(ELPA_INC)/modules
   DFLAGS         += -D__ELPA
   ifeq ($(TARGET), nvidia)
      DFLAGS         += -D__ELPA_NVIDIA_GPU
   endif
   LIBS           += $(ELPA_LIB)/libelpa.a
endif

ifneq ($(USE_QUIP),)
   USE_QUIP       := $(strip $(USE_QUIP))
   QUIP_INC       := $(INSTALL_PATH)/quip-$(USE_QUIP)/include
   QUIP_LIB       := $(INSTALL_PATH)/quip-$(USE_QUIP)/lib
   CFLAGS         += -I$(QUIP_INC)
   DFLAGS         += -D__QUIP
   LIBS           += $(QUIP_LIB)/libquip_core.a
   LIBS           += $(QUIP_LIB)/libatoms.a
   LIBS           += $(QUIP_LIB)/libFoX_sax.a
   LIBS           += $(QUIP_LIB)/libFoX_common.a
   LIBS           += $(QUIP_LIB)/libFoX_utils.a
   LIBS           += $(QUIP_LIB)/libFoX_fsys.a
endif

ifneq ($(USE_LIBPEXSI),)
   USE_LIBPEXSI   := $(strip $(USE_LIBPEXSI))
   SCOTCH_VER     := $(strip $(SCOTCH_VER))
   SUPERLU_VER    := $(strip $(SUPERLU_VER))
   LIBPEXSI_INC   := $(INSTALL_PATH)/pexsi-$(USE_LIBPEXSI)/include
   LIBPEXSI_LIB   := $(INSTALL_PATH)/pexsi-$(USE_LIBPEXSI)/lib
   SCOTCH_INC     := $(INSTALL_PATH)/scotch-$(SCOTCH_VER)/include
   SCOTCH_LIB     := $(INSTALL_PATH)/scotch-$(SCOTCH_VER)/lib
   SUPERLU_INC    := $(INSTALL_PATH)/superlu_dist-$(SUPERLU_VER)/include
   SUPERLU_LIB    := $(INSTALL_PATH)/superlu_dist-$(SUPERLU_VER)/lib
   CFLAGS         += -I$(LIBPEXSI_INC) -I$(SCOTCH_INC) -I$(SUPERLU_INC)
   DFLAGS         += -D__LIBPEXSI
   LIBS           += $(LIBPEXSI_LIB)/libpexsi.a
   LIBS           += $(SUPERLU_LIB)/libsuperlu_dist.a
   LIBS           += $(SCOTCH_LIB)/libptscotchparmetis.a
   LIBS           += $(SCOTCH_LIB)/libptscotch.a
   LIBS           += $(SCOTCH_LIB)/libptscotcherr.a
   LIBS           += $(SCOTCH_LIB)/libscotchmetis.a
   LIBS           += $(SCOTCH_LIB)/libscotch.a
endif

ifneq ($(USE_LIBVORI),)
   USE_LIBVORI    := $(strip $(USE_LIBVORI))
   LIBVORI_LIB    := $(INSTALL_PATH)/libvori-$(USE_LIBVORI)/lib
   DFLAGS         += -D__LIBVORI
   LIBS           += $(LIBVORI_LIB)/libvori.a
endif

ifneq ($(USE_LIBXC),)
   USE_LIBXC      := $(strip $(USE_LIBXC))
   LIBXC_INC      := $(INSTALL_PATH)/libxc-$(USE_LIBXC)/include
   LIBXC_LIB      := $(INSTALL_PATH)/libxc-$(USE_LIBXC)/lib
   CFLAGS         += -I$(LIBXC_INC)
   DFLAGS         += -D__LIBXC
   LIBS           += $(LIBXC_LIB)/libxcf03.a
   LIBS           += $(LIBXC_LIB)/libxc.a
endif

ifneq ($(USE_LIBINT),)
   USE_LIBINT     := $(strip $(USE_LIBINT))
   LMAX           := $(strip $(LMAX))
   LIBINT_INC     := $(INSTALL_PATH)/libint-v$(USE_LIBINT)-cp2k-lmax-$(LMAX)/include
   LIBINT_LIB     := $(INSTALL_PATH)/libint-v$(USE_LIBINT)-cp2k-lmax-$(LMAX)/lib
   CFLAGS         += -I$(LIBINT_INC)
   DFLAGS         += -D__LIBINT
   LIBS           += $(LIBINT_LIB)/libint2.a
endif

ifneq ($(USE_SPGLIB),)
   USE_SPGLIB     := $(strip $(USE_SPGLIB))
   SPGLIB_INC     := $(INSTALL_PATH)/spglib-$(USE_SPGLIB)/include
   SPGLIB_LIB     := $(INSTALL_PATH)/spglib-$(USE_SPGLIB)/lib
   CFLAGS         += -I$(SPGLIB_INC)
   DFLAGS         += -D__SPGLIB
   LIBS           += $(SPGLIB_LIB)/libsymspg.a
endif

ifneq ($(USE_LIBXSMM),)
   USE_LIBXSMM    := $(strip $(USE_LIBXSMM))
   LIBXSMM_INC    := $(INSTALL_PATH)/libxsmm-$(USE_LIBXSMM)/include
   LIBXSMM_LIB    := $(INSTALL_PATH)/libxsmm-$(USE_LIBXSMM)/lib
   CFLAGS         += -I$(LIBXSMM_INC)
   DFLAGS         += -D__LIBXSMM
   LIBS           += $(LIBXSMM_LIB)/libxsmmf.a
   LIBS           += $(LIBXSMM_LIB)/libxsmm.a
endif

ifneq ($(USE_SIRIUS),)
   USE_SIRIUS     := $(strip $(USE_SIRIUS))
   HDF5_VER       := $(strip $(HDF5_VER))
   HDF5_LIB       := $(INSTALL_PATH)/hdf5-$(HDF5_VER)/lib
   LIBVDWXC_VER   := $(strip $(LIBVDWXC_VER))
   LIBVDWXC_INC   := $(INSTALL_PATH)/libvdwxc-$(LIBVDWXC_VER)/include
   LIBVDWXC_LIB   := $(INSTALL_PATH)/libvdwxc-$(LIBVDWXC_VER)/lib
   SPFFT_VER      := $(strip $(SPFFT_VER))
   SPFFT_INC      := $(INSTALL_PATH)/SpFFT-$(SPFFT_VER)/include
   SPLA_VER       := $(strip $(SPLA_VER))
   SPLA_INC       := $(INSTALL_PATH)/SpLA-$(SPLA_VER)/include/spla
   ifeq ($(USE_ACC), yes)
      DFLAGS         += -D__OFFLOAD_GEMM
      SPFFT_LIB      := $(INSTALL_PATH)/SpFFT-$(SPFFT_VER)/lib/cuda
      SPLA_LIB       := $(INSTALL_PATH)/SpLA-$(SPLA_VER)/lib/cuda
      SIRIUS_INC     := $(INSTALL_PATH)/sirius-$(USE_SIRIUS)/include/cuda
      SIRIUS_LIB     := $(INSTALL_PATH)/sirius-$(USE_SIRIUS)/lib/cuda
   else
      SPFFT_LIB      := $(INSTALL_PATH)/SpFFT-$(SPFFT_VER)/lib
      SPLA_LIB       := $(INSTALL_PATH)/SpLA-$(SPLA_VER)/lib
      SIRIUS_INC     := $(INSTALL_PATH)/sirius-$(USE_SIRIUS)/include
      SIRIUS_LIB     := $(INSTALL_PATH)/sirius-$(USE_SIRIUS)/lib
   endif
   CFLAGS         += -I$(LIBVDWXC_INC)
   CFLAGS         += -I$(SPFFT_INC)
   CFLAGS         += -I$(SPLA_INC)
   CFLAGS         += -I$(SIRIUS_INC)
   DFLAGS         += -D__HDF5
   DFLAGS         += -D__LIBVDWXC
   DFLAGS         += -D__SPFFT
   DFLAGS         += -D__SPLA
   DFLAGS         += -D__SIRIUS
   LIBS           += $(SIRIUS_LIB)/libsirius.a
   LIBS           += $(SPLA_LIB)/libspla.a
   LIBS           += $(SPFFT_LIB)/libspfft.a
   LIBS           += $(LIBVDWXC_LIB)/libvdwxc.a
   LIBS           += $(HDF5_LIB)/libhdf5.a
endif

ifneq ($(USE_COSMA),)
   USE_COSMA      := $(strip $(USE_COSMA))
   ifeq ($(USE_ACC), yes)
      USE_COSMA      := $(USE_COSMA)-cuda
   endif
   COSMA_INC      := $(INSTALL_PATH)/COSMA-$(USE_COSMA)/include
   COSMA_LIB      := $(INSTALL_PATH)/COSMA-$(USE_COSMA)/lib
   CFLAGS         += -I$(COSMA_INC)
   DFLAGS         += -D__COSMA
   LIBS           += $(COSMA_LIB)/libcosma_prefixed_pxgemm.a
   LIBS           += $(COSMA_LIB)/libcosma.a
   LIBS           += $(COSMA_LIB)/libcosta.a
   LIBS           += $(COSMA_LIB)/libTiled-MM.a
endif

ifneq ($(USE_GSL),)
   USE_GSL        := $(strip $(USE_GSL))
   GSL_INC        := $(INSTALL_PATH)/gsl-$(USE_GSL)/include
   GSL_LIB        := $(INSTALL_PATH)/gsl-$(USE_GSL)/lib
   CFLAGS         += -I$(GSL_INC)
   DFLAGS         += -D__GSL
   LIBS           += $(GSL_LIB)/libgsl.a
endif

CFLAGS         += $(DFLAGS)

CXXFLAGS       := $(CFLAGS) -std=c++11

OFFLOAD_FLAGS  := $(DFLAGS) -O3 -Xcompiler="-fopenmp" -arch sm_60 --std=c++11

FCFLAGS        := $(CFLAGS)
ifeq ($(shell [ $(shell gcc -dumpversion | cut -d. -f1) -gt 9 ] && echo yes), yes)
   FCFLAGS        += -fallow-argument-mismatch
endif
FCFLAGS        += -fbacktrace
FCFLAGS        += -ffree-form
FCFLAGS        += -ffree-line-length-none
FCFLAGS        += -fno-omit-frame-pointer
FCFLAGS        += -std=f2008

ifneq ($(CUDA_HOME),)
   CUDA_LIB       := $(CUDA_HOME)/lib64
   LDFLAGS        := $(FCFLAGS) -L$(CUDA_LIB) -Wl,-rpath=$(CUDA_LIB)
else
   LDFLAGS        := $(FCFLAGS)
endif

LIBS           += -lcusolver -lcudart -lnvrtc -lcuda -lcufft -lcublas -lrt
LIBS           += -lz -ldl -lpthread -lstdc++

# End
############### END ARCHITECTURE FILE ################


===== TESTS (description) =====
 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-32 RI-RPA/RI-MP2 correlation energy
 input file: benchmarks/QS_mp2_rpa/32-H2O/RI-RPA.inp
 required files: ['benchmarks/QS_mp2_rpa/32-H2O/BASIS_H2O', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32.xyz', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32-PBE-TZ.inp', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32-RI-dRPA-TZ.inp']
 output file: result.log
 # nodes = 8
 # ranks/node = 2
 # threads/rank = 6
 nrepeat = 1
 time[min] = 15
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/01
 job id: 48273092
 --- Point ---
 name: 10
 plot: h2o_32_ri_rpa_mp2
 regex: Total RI-RPA Time= 
 label: RI-RPA (8n/2r/6t)
 --- Point ---
 name: 11
 plot: h2o_32_ri_rpa_mp2_mem
 regex: Estimated peak process memory 
 label: RI-RPA (8n/2r/6t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-32 RI-RPA/RI-MP2 correlation energy
 input file: benchmarks/QS_mp2_rpa/32-H2O/RI-MP2.inp
 required files: ['benchmarks/QS_mp2_rpa/32-H2O/BASIS_H2O', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32.xyz', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32-PBE-TZ.inp', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32-HF-TZ.inp', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32-RI-MP2-TZ.inp']
 output file: result.log
 # nodes = 8
 # ranks/node = 6
 # threads/rank = 2
 nrepeat = 1
 time[min] = 15
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/02
 job id: 48273094
 --- Point ---
 name: 20
 plot: h2o_32_ri_rpa_mp2
 regex: Total MP2 Time= 
 label: RI-MP2 (8n/6r/2t)
 --- Point ---
 name: 21
 plot: h2o_32_ri_rpa_mp2_mem
 regex: Estimated peak process memory 
 label: RI-MP2 (8n/6r/2t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-64 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-64.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 12
 # threads/rank = 1
 nrepeat = 1
 time[min] = 5
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/03
 job id: 48273099
 --- Point ---
 name: 100
 plot: h2o_64_md
 regex: CP2K  
 label: (8n/12r/1t)
 --- Point ---
 name: 101
 plot: h2o_64_md_mem
 regex: Estimated peak process memory 
 label: (8n/12r/1t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-64 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-64.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 6
 # threads/rank = 2
 nrepeat = 1
 time[min] = 5
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/04
 job id: 48273103
 --- Point ---
 name: 102
 plot: h2o_64_md
 regex: CP2K  
 label: (8n/6r/2t)
 --- Point ---
 name: 103
 plot: h2o_64_md_mem
 regex: Estimated peak process memory 
 label: (8n/6r/2t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-64 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-64.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 4
 # threads/rank = 3
 nrepeat = 1
 time[min] = 5
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/05
 job id: 48273105
 --- Point ---
 name: 104
 plot: h2o_64_md
 regex: CP2K  
 label: (8n/4r/3t)
 --- Point ---
 name: 105
 plot: h2o_64_md_mem
 regex: Estimated peak process memory 
 label: (8n/4r/3t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-64 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-64.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 3
 # threads/rank = 4
 nrepeat = 1
 time[min] = 5
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/06
 job id: 48273107
 --- Point ---
 name: 106
 plot: h2o_64_md
 regex: CP2K  
 label: (8n/3r/4t)
 --- Point ---
 name: 107
 plot: h2o_64_md_mem
 regex: Estimated peak process memory 
 label: (8n/3r/4t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-64 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-64.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 2
 # threads/rank = 6
 nrepeat = 1
 time[min] = 5
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/07
 job id: 48273109
 --- Point ---
 name: 108
 plot: h2o_64_md
 regex: CP2K  
 label: (8n/2r/6t)
 --- Point ---
 name: 109
 plot: h2o_64_md_mem
 regex: Estimated peak process memory 
 label: (8n/2r/6t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-64 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-64.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 1
 # threads/rank = 12
 nrepeat = 1
 time[min] = 5
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/08
 job id: 48273112
 --- Point ---
 name: 110
 plot: h2o_64_md
 regex: CP2K  
 label: (8n/1r/12t)
 --- Point ---
 name: 111
 plot: h2o_64_md_mem
 regex: Estimated peak process memory 
 label: (8n/1r/12t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-128 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-128.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 12
 # threads/rank = 1
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/09
 job id: 48273115
 --- Point ---
 name: 200
 plot: h2o_128_md
 regex: CP2K  
 label: (8n/12r/1t)
 --- Point ---
 name: 201
 plot: h2o_128_md_mem
 regex: Estimated peak process memory 
 label: (8n/12r/1t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-128 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-128.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 6
 # threads/rank = 2
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/10
 job id: 48273118
 --- Point ---
 name: 202
 plot: h2o_128_md
 regex: CP2K  
 label: (8n/6r/2t)
 --- Point ---
 name: 203
 plot: h2o_128_md_mem
 regex: Estimated peak process memory 
 label: (8n/6r/2t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-128 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-128.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 4
 # threads/rank = 3
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/11
 job id: 48273119
 --- Point ---
 name: 204
 plot: h2o_128_md
 regex: CP2K  
 label: (8n/4r/3t)
 --- Point ---
 name: 205
 plot: h2o_128_md_mem
 regex: Estimated peak process memory 
 label: (8n/4r/3t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-128 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-128.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 3
 # threads/rank = 4
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/12
 job id: 48273120
 --- Point ---
 name: 206
 plot: h2o_128_md
 regex: CP2K  
 label: (8n/3r/4t)
 --- Point ---
 name: 207
 plot: h2o_128_md_mem
 regex: Estimated peak process memory 
 label: (8n/3r/4t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-128 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-128.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 2
 # threads/rank = 6
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/13
 job id: 48273121
 --- Point ---
 name: 208
 plot: h2o_128_md
 regex: CP2K  
 label: (8n/2r/6t)
 --- Point ---
 name: 209
 plot: h2o_128_md_mem
 regex: Estimated peak process memory 
 label: (8n/2r/6t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-128 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-128.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 1
 # threads/rank = 12
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/14
 job id: 48273122
 --- Point ---
 name: 210
 plot: h2o_128_md
 regex: CP2K  
 label: (8n/1r/12t)
 --- Point ---
 name: 211
 plot: h2o_128_md_mem
 regex: Estimated peak process memory 
 label: (8n/1r/12t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-256 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-256.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 12
 # threads/rank = 1
 nrepeat = 1
 time[min] = 30
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/15
 job id: 48273123
 --- Point ---
 name: 400
 plot: h2o_256_md
 regex: CP2K  
 label: (8n/12r/1t)
 --- Point ---
 name: 401
 plot: h2o_256_md_mem
 regex: Estimated peak process memory 
 label: (8n/12r/1t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-256 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-256.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 6
 # threads/rank = 2
 nrepeat = 1
 time[min] = 30
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/16
 job id: 48273124
 --- Point ---
 name: 402
 plot: h2o_256_md
 regex: CP2K  
 label: (8n/6r/2t)
 --- Point ---
 name: 403
 plot: h2o_256_md_mem
 regex: Estimated peak process memory 
 label: (8n/6r/2t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-256 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-256.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 4
 # threads/rank = 3
 nrepeat = 1
 time[min] = 30
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/17
 job id: 48273125
 --- Point ---
 name: 404
 plot: h2o_256_md
 regex: CP2K  
 label: (8n/4r/3t)
 --- Point ---
 name: 405
 plot: h2o_256_md_mem
 regex: Estimated peak process memory 
 label: (8n/4r/3t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-256 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-256.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 3
 # threads/rank = 4
 nrepeat = 1
 time[min] = 30
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/18
 job id: 48273126
 --- Point ---
 name: 406
 plot: h2o_256_md
 regex: CP2K  
 label: (8n/3r/4t)
 --- Point ---
 name: 407
 plot: h2o_256_md_mem
 regex: Estimated peak process memory 
 label: (8n/3r/4t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-256 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-256.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 2
 # threads/rank = 6
 nrepeat = 1
 time[min] = 30
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/19
 job id: 48273127
 --- Point ---
 name: 408
 plot: h2o_256_md
 regex: CP2K  
 label: (8n/2r/6t)
 --- Point ---
 name: 409
 plot: h2o_256_md_mem
 regex: Estimated peak process memory 
 label: (8n/2r/6t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-256 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-256.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 1
 # threads/rank = 12
 nrepeat = 1
 time[min] = 30
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/20
 job id: 48273128
 --- Point ---
 name: 410
 plot: h2o_256_md
 regex: CP2K  
 label: (8n/1r/12t)
 --- Point ---
 name: 411
 plot: h2o_256_md_mem
 regex: Estimated peak process memory 
 label: (8n/1r/12t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-32 (NREP 3) linear scaling test (864 H2O)
 input file: benchmarks/QS_DM_LS/H2O-dft-ls.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 12
 # threads/rank = 1
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/21
 job id: 48273129
 --- Point ---
 name: 500
 plot: h2o_32_nrep3_ls
 regex: CP2K  
 label: (8n/12r/1t)
 --- Point ---
 name: 501
 plot: h2o_32_nrep3_ls_mem
 regex: Estimated peak process memory 
 label: (8n/12r/1t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-32 (NREP 3) linear scaling test (864 H2O)
 input file: benchmarks/QS_DM_LS/H2O-dft-ls.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 6
 # threads/rank = 2
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/22
 job id: 48273131
 --- Point ---
 name: 502
 plot: h2o_32_nrep3_ls
 regex: CP2K  
 label: (8n/6r/2t)
 --- Point ---
 name: 503
 plot: h2o_32_nrep3_ls_mem
 regex: Estimated peak process memory 
 label: (8n/6r/2t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-32 (NREP 3) linear scaling test (864 H2O)
 input file: benchmarks/QS_DM_LS/H2O-dft-ls.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 4
 # threads/rank = 3
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/23
 job id: 48273132
 --- Point ---
 name: 504
 plot: h2o_32_nrep3_ls
 regex: CP2K  
 label: (8n/4r/3t)
 --- Point ---
 name: 505
 plot: h2o_32_nrep3_ls_mem
 regex: Estimated peak process memory 
 label: (8n/4r/3t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-32 (NREP 3) linear scaling test (864 H2O)
 input file: benchmarks/QS_DM_LS/H2O-dft-ls.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 3
 # threads/rank = 4
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/24
 job id: 48273133
 --- Point ---
 name: 506
 plot: h2o_32_nrep3_ls
 regex: CP2K  
 label: (8n/3r/4t)
 --- Point ---
 name: 507
 plot: h2o_32_nrep3_ls_mem
 regex: Estimated peak process memory 
 label: (8n/3r/4t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-32 (NREP 3) linear scaling test (864 H2O)
 input file: benchmarks/QS_DM_LS/H2O-dft-ls.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 2
 # threads/rank = 6
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/25
 job id: 48273135
 --- Point ---
 name: 508
 plot: h2o_32_nrep3_ls
 regex: CP2K  
 label: (8n/2r/6t)
 --- Point ---
 name: 509
 plot: h2o_32_nrep3_ls_mem
 regex: Estimated peak process memory 
 label: (8n/2r/6t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-32 (NREP 3) linear scaling test (864 H2O)
 input file: benchmarks/QS_DM_LS/H2O-dft-ls.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 1
 # threads/rank = 12
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/26
 job id: 48273136
 --- Point ---
 name: 510
 plot: h2o_32_nrep3_ls
 regex: CP2K  
 label: (8n/1r/12t)
 --- Point ---
 name: 511
 plot: h2o_32_nrep3_ls_mem
 regex: Estimated peak process memory 
 label: (8n/1r/12t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: 512 H2O (4 NVE MD steps on 64 nodes)
 input file: benchmarks/QS/00512_H2O/H2O-512_md.inp
 required files: []
 output file: result.log
 # nodes = 64
 # ranks/node = 12
 # threads/rank = 1
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/27
 job id: 48273137
 --- Point ---
 name: 601
 plot: h2o_512_md
 regex: CP2K  
 label: (64n/12r/1t)
 --- Point ---
 name: 602
 plot: h2o_512_md_mem
 regex: Estimated peak process memory 
 label: (64n/12r/1t)
 ~~~~~~~ END TEST ~~~~~~~

=== END TESTS (description) ===


===== PLOTS (description) =====
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_32_ri_rpa_mp2", title="32 H2O molecules (RI-MP2, RI-RPA)", xlabel="Revision", ylabel="Time [s]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_32_ri_rpa_mp2_mem", title="32 H2O molecules (RI-MP2, RI-RPA)", xlabel="Revision", ylabel="Est. peak process memory [MiB]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_64_md", title="64 H2O molecules (10 MD steps)", xlabel="Revision", ylabel="Time [s]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_64_md_mem", title="64 H2O molecules (10 MD steps)", xlabel="Revision", ylabel="Est. peak process memory [MiB]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_128_md", title="128 H2O molecules (10 MD steps)", xlabel="Revision", ylabel="Time [s]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_128_md_mem", title="128 H2O molecules (10 MD steps)", xlabel="Revision", ylabel="Est. peak process memory [MiB]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_256_md", title="256 H2O molecules (10 MD steps)", xlabel="Revision", ylabel="Time [s]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_256_md_mem", title="256 H2O molecules (10 MD steps)", xlabel="Revision", ylabel="Est. peak process memory [MiB]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_32_nrep3_ls", title="864 H2O molecules (LS SCF)", xlabel="Revision", ylabel="Time [s]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_32_nrep3_ls_mem", title="864 H2O molecules (LS SCF)", xlabel="Revision", ylabel="Est. peak process memory [MiB]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_512_md", title="512 H2O (4 NVE MD steps on 64 nodes)", xlabel="Revision", ylabel="Time [s]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_512_md_mem", title="512 H2O (4 NVE MD steps on 64 nodes)", xlabel="Revision", ylabel="Est. peak process memory [MiB]"
=== END PLOTS (description) ===


============ RESULTS ============
 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/01/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         0.000000E+00       0.0%      0.0%      0.0%
 flops max/rank                      0.000000E+00       0.0%      0.0%      0.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                                  0       0.0%      0.0%      0.0%
 number of processed stacks                     0       0.0%      0.0%      0.0%
 average stack size                                     0.0       0.0       0.0
 marketing flops                     0.000000E+00
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast                1                     12.
 MP_Allreduce           19                     21.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               15                 177869.
 MP_Allreduce          424                      8.
 MP_Sync                 3
 MP_comm_split           1
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.024    0.046  134.352  134.353
 farming_run                          1  2.0  133.831  133.835  134.312  134.315
 -------------------------------------------------------------------------------


 @@@@@@@@@@ Run number: 2 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32              4194304       0.0%      0.0%    100.0%
 flops    14 x    32 x    32            154140672       0.0%      0.0%    100.0%
 flops    29 x    32 x    32            159645696       0.0%      0.0%    100.0%
 flops    14 x    14 x    32            208732160       0.0%      0.0%    100.0%
 flops    29 x    14 x    32            212860928       0.0%      0.0%    100.0%
 flops    14 x    29 x    32            212860928       0.0%      0.0%    100.0%
 flops    29 x    29 x    32            227352576       0.0%      0.0%    100.0%
 flops    14 x    32 x    14         896801644032       0.0%      0.0%    100.0%
 flops    29 x    32 x    14         928925089792       0.0%      0.0%    100.0%
 flops    14 x    32 x    29         928925089792       0.0%      0.0%    100.0%
 flops    29 x    32 x    29         962100985856       0.0%      0.0%    100.0%
 flops    32 x    32 x    14        1693169221632       0.0%      0.0%    100.0%
 flops    32 x    32 x    29        1753639550976       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         7.164741E+12       0.0%      0.0%    100.0%
 flops max/rank                    447.801317E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          249492158       0.0%      0.0%    100.0%
 number of processed stacks                164328       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1518.3
 marketing flops                     7.165779E+12
 -------------------------------------------------------------------------------
 # multiplications                           1160
 max memory usage/rank               1.502249E+09
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                    2592
 MPI messages size (bytes):
  total size                         1.140326E+09
  min size                           0.000000E+00
  max size                           1.663488E+06
  average size                     439.940750E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                 132                        0
       128 < size <=     8192                 348                  2850816
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                1536                179306496
    131072 < size <=  4194304                 576                958169088
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         2308                     54.
 MP_Alltoall          4670                 822215.
 MP_ISend             2604                  90577.
 MP_IRecv             2604                  90574.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group               12
 MP_Bcast              230                1134128.
 MP_Allreduce          571                1938539.
 MP_Sync                25
 MP_Alltoall            38                9316958.
 MP_SendRecv           120                 384007.
 MP_ISendRecv           45                 235435.
 MP_Wait               191
 MP_comm_split          10
 MP_ISend              127                3867574.
 MP_IRecv              127                3866554.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.006    0.024  115.554  115.555
 qs_energies                          1  2.0    0.000    0.000  115.353  115.356
 mp2_main                             1  3.0    0.000    0.000  113.284  113.286
 mp2_gpw_main                         1  4.0    0.028    0.034  112.216  112.219
 mp2_ri_gpw_compute_in                1  5.0    0.172    0.174   93.206   93.572
 mp2_ri_gpw_compute_in_loop           1  6.0    0.005    0.005   55.009   55.374
 mp2_eri_3c_integrate_gpw           272  7.0    0.151    0.161   41.391   46.452
 get_2c_integrals                     1  6.0    0.008    0.009   37.225   38.023
 integrate_v_rspace                 273  8.0    0.437    0.453   24.729   29.618
 pw_transfer                       6555 10.6    0.378    0.399   27.474   27.888
 fft_wrap_pw1pw2                   5465 11.4    0.046    0.048   26.088   26.479
 grid_integrate_task_list           273  9.0   20.527   25.882   20.527   25.882
 fft_wrap_pw1pw2_100               2178 12.4    1.194    1.376   23.601   23.996
 compute_2c_integrals                 1  7.0    0.002    0.003   19.714   19.715
 compute_2c_integrals_loop_lm         1  8.0    0.008    0.014   18.935   19.444
 mp2_eri_2c_integrate_gpw             1  9.0    2.359    2.423   18.927   19.430
 rpa_ri_compute_en                    1  5.0    0.034    0.037   18.892   19.066
 cp_fm_cholesky_decompose            12  8.2   17.473   18.291   17.473   18.291
 cholesky_decomp                      1  7.0    0.000    0.000   16.355   17.176
 fft3d_s                           5443 13.4   16.194   16.537   16.216   16.558
 ao_to_mo_and_store_B_mult_1        272  7.0   10.776   15.314   10.776   15.314
 calculate_wavefunction             272  8.0    5.436    5.580   12.557   13.190
 rpa_num_int                          1  6.0    0.001    0.009   10.634   10.635
 rpa_num_int_RPA_matrix_operati       8  7.0    0.000    0.000   10.601   10.607
 calc_mat_Q                           8  8.0    0.000    0.000    9.471    9.559
 contract_S_to_Q                      8  9.0    0.000    0.000    8.893    8.983
 calc_potential_gpw                 544  9.5    0.005    0.006    8.285    8.738
 parallel_gemm_fm                    14  9.1    0.000    0.000    8.477    8.585
 parallel_gemm_fm_cosma              14 10.1    8.477    8.585    8.477    8.585
 mp2_eri_2c_integrate_gpw_pot_l     272 10.0    0.001    0.002    8.244    8.563
 potential_pw2rs                    545 10.0    0.108    0.110    7.728    8.342
 create_integ_mat                     1  6.0    0.021    0.028    7.783    7.784
 collocate_single_gaussian          272 10.0    0.040    0.042    7.509    7.774
 array2fm                             1  7.0    0.000    0.000    6.786    7.192
 pw_scatter_s                      2720 13.7    4.422    4.663    4.422    4.663
 pw_gather_s                       2722 13.2    3.863    4.173    3.863    4.173
 array2fm_buffer_send                 1  8.0    2.995    3.157    2.995    3.157
 pw_poisson_solve                   545 10.5    1.102    1.158    2.195    2.414
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="10", plot="h2o_32_ri_rpa_mp2", label="RI-RPA (8n/2r/6t)", y=112.218852, yerr=0.000000
PlotPoint: name="11", plot="h2o_32_ri_rpa_mp2_mem", label="RI-RPA (8n/2r/6t)", y=2818.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/02/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         0.000000E+00       0.0%      0.0%      0.0%
 flops max/rank                      0.000000E+00       0.0%      0.0%      0.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                                  0       0.0%      0.0%      0.0%
 number of processed stacks                     0       0.0%      0.0%      0.0%
 average stack size                                     0.0       0.0       0.0
 marketing flops                     0.000000E+00
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast                1                     12.
 MP_Allreduce           19                     21.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               22                 205321.
 MP_Allreduce          424                      9.
 MP_Sync                 4
 MP_comm_split           1
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.030    0.041  422.302  422.303
 farming_run                          1  2.0  421.194  421.223  422.263  422.266
 -------------------------------------------------------------------------------


 @@@@@@@@@@ Run number: 2 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32             16777216       0.0%      0.0%    100.0%
 flops    14 x    32 x    32            565182464       0.0%      0.0%    100.0%
 flops    29 x    32 x    32            585367552       0.0%      0.0%    100.0%
 flops    14 x    14 x    32            626196480       0.0%      0.0%    100.0%
 flops    29 x    14 x    32            638582784       0.0%      0.0%    100.0%
 flops    14 x    29 x    32            638582784       0.0%      0.0%    100.0%
 flops    29 x    29 x    32            682057728       0.0%      0.0%    100.0%
 flops    14 x    32 x    14         897827141120       0.0%      0.0%    100.0%
 flops    29 x    32 x    14         929989394432       0.0%      0.0%    100.0%
 flops    14 x    32 x    29         929989394432       0.0%      0.0%    100.0%
 flops    29 x    32 x    29         963203301376       0.0%      0.0%    100.0%
 flops    32 x    32 x    14        1693481172992       0.0%      0.0%    100.0%
 flops    32 x    32 x    29        1753962643456       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         7.172206E+12       0.0%      0.0%    100.0%
 flops max/rank                    150.696064E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          249788822       0.0%      0.0%    100.0%
 number of processed stacks                 98736       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    2529.9
 marketing flops                     7.174951E+12
 -------------------------------------------------------------------------------
 # multiplications                           1140
 max memory usage/rank               1.239835E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                   61440
 MPI messages size (bytes):
  total size                         6.073508E+09
  min size                           0.000000E+00
  max size                         642.960000E+03
  average size                      98.852664E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               32004                        0
       128 < size <=     8192                1820                 14909440
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072               18640               1081442304
    131072 < size <=  4194304                8976               4977156096
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         1003                     44.
 MP_Alltoall          1797                 713538.
 MP_ISend             3686                  54943.
 MP_IRecv             3622                  54292.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group               12
 MP_Bcast              757                 478553.
 MP_Allreduce         2021                  21391.
 MP_Sync                37
 MP_Alltoall            77
 MP_SendRecv          2876                2171486.
 MP_ISendRecv         1034                 172620.
 MP_Wait              1346
 MP_comm_split           7
 MP_ISend              264                 362227.
 MP_IRecv              264                 362718.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.013    0.037  218.289  218.289
 qs_energies                          1  2.0    0.001    0.011  218.037  218.049
 scf_env_do_scf                       1  3.0    0.000    0.000  115.536  115.537
 qs_ks_update_qs_env                  5  5.0    0.000    0.000  114.606  114.613
 rebuild_ks_matrix                    4  6.0    0.000    0.000  114.605  114.611
 qs_ks_build_kohn_sham_matrix         4  7.0    0.055    0.061  114.605  114.611
 hfx_ks_matrix                        4  8.0    0.001    0.001  114.209  114.214
 integrate_four_center                4  9.0    0.152    0.464  114.208  114.213
 integrate_four_center_main           4 10.0    0.109    0.401  101.727  106.045
 integrate_four_center_bin          267 11.0  101.618  105.769  101.618  105.769
 mp2_main                             1  3.0    0.001    0.013  102.205  102.218
 mp2_gpw_main                         1  4.0    0.050    0.112  101.348  101.361
 init_scf_loop                        1  4.0    0.000    0.000   97.100   97.100
 mp2_ri_gpw_compute_in                1  5.0    0.070    0.122   74.374   75.491
 mp2_ri_gpw_compute_in_loop           1  6.0    0.002    0.004   53.972   55.086
 mp2_eri_3c_integrate_gpw            91  7.0    0.143    0.157   41.600   46.536
 integrate_v_rspace                  95  8.0    0.395    0.567   27.993   32.746
 pw_transfer                       2240 10.6    0.144    0.170   29.912   30.405
 fft_wrap_pw1pw2                   1868 11.4    0.018    0.021   28.932   29.321
 mp2_ri_gpw_compute_en                1  5.0    0.065    0.142   26.777   28.370
 grid_integrate_task_list            95  9.0   23.283   28.266   23.283   28.266
 ao_to_mo_and_store_B_mult_1         91  7.0   10.692   27.301   10.692   27.301
 fft_wrap_pw1pw2_100                730 12.4    1.264    1.442   26.632   26.962
 mp2_ri_gpw_compute_en_RI_loop        1  6.0    1.842    1.895   24.983   24.994
 get_2c_integrals                     1  6.0    0.004    0.034   20.291   20.336
 compute_2c_integrals                 1  7.0    0.003    0.008   19.271   19.281
 compute_2c_integrals_loop_lm         1  8.0    0.002    0.008   18.837   19.155
 mp2_eri_2c_integrate_gpw             1  9.0    1.740    1.840   18.835   19.153
 fft3d_s                           1823 13.4   18.446   18.894   18.459   18.907
 scf_env_do_scf_inner_loop            4  4.0    0.000    0.000   18.434   18.434
 calculate_wavefunction              91  8.0    2.015    2.041    9.738   10.020
 potential_pw2rs                    186 10.0    0.033    0.035    8.624    9.218
 mp2_ri_gpw_compute_en_expansio     172  7.0    0.556    0.608    8.728    9.137
 mp2_ri_gpw_compute_en_comm          22  7.0    0.488    0.510    8.022    8.724
 mp2_eri_2c_integrate_gpw_pot_l      91 10.0    0.001    0.001    8.233    8.651
 local_gemm                         172  8.0    8.172    8.587    8.172    8.587
 calc_potential_gpw                 182  9.5    0.002    0.002    7.916    8.136
 collocate_single_gaussian           91 10.0    0.018    0.039    7.868    8.123
 mp_sync                             37 10.5    4.468    7.296    4.468    7.296
 mp_sendrecv_dm3                   2068  8.0    6.080    6.789    6.080    6.789
 integrate_four_center_load           4 10.0    0.000    0.000    6.765    6.770
 hfx_load_balance                     1 11.0    0.000    0.000    6.765    6.770
 mp2_ri_gpw_compute_en_ener         172  7.0    6.345    6.412    6.345    6.412
 pw_gather_s                        912 13.2    4.895    5.413    4.895    5.413
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="20", plot="h2o_32_ri_rpa_mp2", label="RI-MP2 (8n/6r/2t)", y=101.349878, yerr=0.000000
PlotPoint: name="21", plot="h2o_32_ri_rpa_mp2_mem", label="RI-MP2 (8n/6r/2t)", y=1498.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/03/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                     29.277748E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               5055360       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      29.1
 marketing flops                     2.107592E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             452.763648E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 9436608
 MPI messages size (bytes):
  total size                       333.233553E+09
  min size                           0.000000E+00
  max size                         315.840000E+03
  average size                      35.312852E+03
 MPI breakdown and total messages size (bytes):
             size <=      128             4913240                        0
       128 < size <=     8192             1155432               9465298944
      8192 < size <=    32768             1984512              54190407680
     32768 < size <=   131072              551296              42776657920
    131072 < size <=  4194304              832128             226802306368
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3683                  62379.
 MP_Allreduce        10329                    270.
 MP_Sync               530
 MP_Alltoall          2083
 MP_SendRecv         22610                   5520.
 MP_ISendRecv        22610                   5520.
 MP_Wait             37876
 MP_comm_split          50
 MP_ISend            20771                  42672.
 MP_IRecv            20771                  42672.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.014    0.027   54.511   54.512
 qs_mol_dyn_low                       1  2.0    0.003    0.005   54.219   54.227
 qs_forces                           11  3.9    0.011    0.033   53.978   53.983
 qs_energies                         11  4.9    0.001    0.002   52.475   52.487
 scf_env_do_scf                      11  5.9    0.000    0.001   45.686   45.687
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   43.579   43.579
 dbcsr_multiply_generic            2286 12.5    0.093    0.099   33.552   33.990
 qs_scf_new_mos                     108  7.5    0.000    0.001   33.195   33.505
 qs_scf_loop_do_ot                  108  8.5    0.000    0.001   33.195   33.505
 ot_scf_mini                        108  9.5    0.002    0.002   31.470   31.696
 multiply_cannon                   2286 13.5    0.188    0.199   26.487   28.098
 multiply_cannon_loop              2286 14.5    1.836    1.950   25.803   27.438
 velocity_verlet                     10  3.0    0.001    0.002   26.779   26.781
 ot_mini                            108 10.5    0.001    0.001   18.765   19.018
 qs_ot_get_derivative               108 11.5    0.001    0.002   15.771   15.952
 mp_waitall_1                    245248 16.5    8.637   14.409    8.637   14.409
 multiply_cannon_metrocomm3       54864 15.5    0.074    0.082    6.249   12.821
 multiply_cannon_multrec          54864 15.5    3.690    5.796    7.677   11.216
 qs_ot_get_p                        119 10.4    0.001    0.001    8.042    8.312
 rebuild_ks_matrix                  119  8.3    0.000    0.000    8.018    8.160
 qs_ks_build_kohn_sham_matrix       119  9.3    0.010    0.013    8.017    8.160
 qs_ks_update_qs_env                119  7.6    0.001    0.001    7.068    7.201
 mp_sum_l                          7287 12.8    5.024    6.535    5.024    6.535
 multiply_cannon_sync_h2d         54864 15.5    5.188    6.108    5.188    6.108
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    5.533    5.974
 dbcsr_mm_accdrv_process          76910 16.1    1.828    2.910    3.900    5.689
 init_scf_run                        11  5.9    0.000    0.001    5.500    5.501
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.500    5.500
 qs_ot_p2m_diag                      50 11.0    0.004    0.007    5.185    5.226
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    4.928    5.031
 sum_up_and_integrate               119 10.3    0.012    0.014    4.584    4.591
 integrate_v_rspace                 119 11.3    0.002    0.003    4.572    4.580
 qs_rho_update_rho_low              119  7.7    0.001    0.001    4.395    4.548
 calculate_rho_elec                 119  8.7    0.012    0.017    4.394    4.547
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    4.425    4.425
 cp_fm_diag_elpa                     50 13.0    0.000    0.001    4.211    4.211
 cp_fm_redistribute_end              50 14.0    2.148    4.183    2.154    4.186
 cp_fm_diag_elpa_base                50 14.0    2.026    4.084    2.030    4.092
 calculate_first_density_matrix       1  7.0    0.000    0.001    3.173    3.178
 multiply_cannon_metrocomm1       54864 15.5    0.058    0.064    1.674    3.136
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.924    3.110
 apply_single                       119 13.6    0.000    0.000    2.924    3.110
 calculate_dm_sparse                119  9.5    0.000    0.001    2.948    3.095
 jit_kernel_multiply                 13 15.8    2.008    3.055    2.008    3.055
 rs_pw_transfer                     974 11.9    0.012    0.013    2.851    2.964
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.880    2.882
 acc_transpose_blocks             54864 15.5    0.234    0.264    2.229    2.774
 ot_diis_step                       108 11.5    0.006    0.006    2.738    2.738
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.546    2.629
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    2.465    2.525
 density_rs2pw                      119  9.7    0.004    0.004    2.288    2.405
 wfi_extrapolate                     11  7.9    0.001    0.001    2.248    2.248
 grid_integrate_task_list           119 12.3    2.013    2.124    2.013    2.124
 init_scf_loop                       11  6.9    0.000    0.000    2.091    2.091
 mp_sum_d                          4135 12.0    1.310    1.966    1.310    1.966
 potential_pw2rs                    119 12.3    0.004    0.004    1.924    1.943
 pw_transfer                       1439 11.6    0.052    0.056    1.784    1.861
 fft_wrap_pw1pw2                   1201 12.6    0.007    0.007    1.708    1.786
 make_m2s                          4572 13.5    0.054    0.056    1.732    1.781
 make_images                       4572 14.5    0.133    0.138    1.650    1.699
 mp_alltoall_d11v                  2130 13.8    1.384    1.552    1.384    1.552
 mp_waitany                       12084 13.8    1.287    1.479    1.287    1.479
 acc_transpose_blocks_sync       164592 16.5    1.208    1.465    1.208    1.465
 fft3d_ps                          1201 14.6    0.372    0.478    1.352    1.428
 grid_collocate_task_list           119  9.7    1.351    1.426    1.351    1.426
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.001    1.378    1.402
 fft_wrap_pw1pw2_140                487 13.2    0.183    0.202    1.318    1.393
 mp_alltoall_i22                    627 13.8    0.707    1.297    0.707    1.297
 acc_transpose_blocks_kernels     54864 16.5    0.249    0.390    0.741    1.133
 dbcsr_dot_sd                      1205 11.9    0.049    0.061    0.730    1.102
 parallel_gemm_fm                    81  9.0    0.000    0.000    1.096    1.100
 parallel_gemm_fm_cosma              81 10.0    1.096    1.100    1.096    1.100
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="100", plot="h2o_64_md", label="(8n/12r/1t)", y=54.512000, yerr=0.000000
PlotPoint: name="101", plot="h2o_64_md_mem", label="(8n/12r/1t)", y=431.090909, yerr=1.239835
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/04/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                     57.173320E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               3066240       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      47.9
 marketing flops                     2.107592E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             490.266624E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 2194560
 MPI messages size (bytes):
  total size                       310.646604E+09
  min size                           0.000000E+00
  max size                           1.145520E+06
  average size                     141.553031E+03
 MPI breakdown and total messages size (bytes):
             size <=      128              724648                        0
       128 < size <=     8192              253512               2076770304
      8192 < size <=    32768              281952               4619501568
     32768 < size <=   131072              494448              39143342080
    131072 < size <=  4194304              440000             264807943488
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3672                  62658.
 MP_Allreduce        10306                    303.
 MP_Sync                54
 MP_Alltoall          2060                 901744.
 MP_SendRecv         16779                  37093.
 MP_ISendRecv        16779                  37093.
 MP_Wait             23539
 MP_comm_split          50
 MP_ISend             5720                 128509.
 MP_IRecv             5720                 128509.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.019    0.055   39.875   39.877
 qs_mol_dyn_low                       1  2.0    0.003    0.003   39.608   39.616
 qs_forces                           11  3.9    0.002    0.003   39.520   39.521
 qs_energies                         11  4.9    0.001    0.002   37.795   37.799
 scf_env_do_scf                      11  5.9    0.000    0.001   32.380   32.380
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.007   29.878   29.878
 dbcsr_multiply_generic            2286 12.5    0.101    0.104   22.409   22.758
 qs_scf_new_mos                     108  7.5    0.001    0.001   20.674   20.900
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   20.673   20.899
 ot_scf_mini                        108  9.5    0.002    0.003   19.755   19.921
 velocity_verlet                     10  3.0    0.001    0.002   18.797   18.798
 multiply_cannon                   2286 13.5    0.209    0.218   17.244   18.685
 multiply_cannon_loop              2286 14.5    1.193    1.256   16.056   17.500
 ot_mini                            108 10.5    0.001    0.001   12.250   12.480
 mp_waitall_1                    200699 16.5    5.705   11.004    5.705   11.004
 qs_ot_get_derivative               108 11.5    0.005    0.033    9.891   10.059
 multiply_cannon_metrocomm3       27432 15.5    0.073    0.077    4.135    9.725
 multiply_cannon_multrec          27432 15.5    1.811    4.235    6.277    9.288
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.276    7.413
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.014    7.276    7.413
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.405    6.528
 dbcsr_mm_accdrv_process          47894 16.0    3.572    6.150    4.386    6.515
 qs_ot_get_p                        119 10.4    0.001    0.001    4.596    4.814
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    3.727    4.637
 init_scf_run                        11  5.9    0.000    0.001    4.210    4.210
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    4.210    4.210
 sum_up_and_integrate               119 10.3    0.024    0.028    4.181    4.189
 integrate_v_rspace                 119 11.3    0.002    0.003    4.157    4.166
 mp_sum_l                          7287 12.8    2.077    4.089    2.077    4.089
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.831    3.866
 calculate_rho_elec                 119  8.7    0.021    0.024    3.831    3.866
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    3.064    3.736
 apply_single                       119 13.6    0.000    0.000    3.063    3.736
 rs_pw_transfer                     974 11.9    0.010    0.011    2.572    3.065
 make_m2s                          4572 13.5    0.052    0.054    2.655    3.006
 qs_ot_p2m_diag                      50 11.0    0.009    0.013    2.957    2.976
 make_images                       4572 14.5    0.206    0.247    2.567    2.921
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.670    2.671
 density_rs2pw                      119  9.7    0.004    0.004    2.095    2.604
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    2.555    2.555
 init_scf_loop                       11  6.9    0.000    0.000    2.482    2.482
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    2.331    2.418
 ot_diis_step                       108 11.5    0.011    0.011    2.313    2.314
 multiply_cannon_sync_h2d         27432 15.5    1.692    2.276    1.692    2.276
 cp_fm_diag_elpa                     50 13.0    0.001    0.001    2.235    2.236
 cp_fm_redistribute_end              50 14.0    1.133    2.210    1.136    2.213
 calculate_dm_sparse                119  9.5    0.000    0.001    2.115    2.194
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.166    2.169
 cp_fm_diag_elpa_base                50 14.0    1.045    2.120    1.073    2.155
 acc_transpose_blocks             27432 15.5    0.117    0.126    1.714    2.115
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.970    2.012
 pw_transfer                       1439 11.6    0.065    0.070    1.923    1.950
 potential_pw2rs                    119 12.3    0.006    0.006    1.908    1.916
 grid_integrate_task_list           119 12.3    1.829    1.912    1.829    1.912
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.831    1.862
 jit_kernel_multiply                  9 16.4    0.755    1.823    0.755    1.823
 make_images_data                  4572 15.5    0.048    0.054    1.275    1.662
 prepare_preconditioner              11  7.9    0.000    0.000    1.541    1.567
 make_preconditioner                 11  8.9    0.000    0.000    1.541    1.567
 hybrid_alltoall_any               4725 16.4    0.054    0.117    1.124    1.520
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.439    1.496
 fft_wrap_pw1pw2_140                487 13.2    0.204    0.213    1.453    1.485
 wfi_extrapolate                     11  7.9    0.001    0.001    1.481    1.481
 grid_collocate_task_list           119  9.7    1.280    1.428    1.280    1.428
 fft3d_ps                          1201 14.6    0.520    0.578    1.379    1.402
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.308    1.317
 mp_alltoall_d11v                  2130 13.8    1.184    1.268    1.184    1.268
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.196    1.245
 mp_allgather_i34                  2286 14.5    0.610    1.048    0.610    1.048
 rs_pw_transfer_RS2PW_140           130 11.5    0.139    0.148    0.532    1.023
 acc_transpose_blocks_kernels     27432 16.5    0.189    0.277    0.750    1.022
 mp_waitany                        5720 13.7    0.511    1.005    0.511    1.005
 mp_sum_d                          4135 12.0    0.527    0.997    0.527    0.997
 acc_transpose_blocks_sync        82296 16.5    0.821    0.950    0.821    0.950
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.927    0.941
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    0.938    0.939
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="102", plot="h2o_64_md", label="(8n/6r/2t)", y=39.877000, yerr=0.000000
PlotPoint: name="103", plot="h2o_64_md_mem", label="(8n/6r/2t)", y=467.454545, yerr=1.157084
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/05/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                     59.051995E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               3143552       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      46.8
 marketing flops                     2.107587E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             522.952704E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                  950976
 MPI messages size (bytes):
  total size                       203.844256E+09
  min size                           0.000000E+00
  max size                           1.638400E+06
  average size                     214.352688E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192              253512               2076770304
      8192 < size <=    32768              179424               2939682816
     32768 < size <=   131072              181440              14863564800
    131072 < size <=  4194304              330176             183964913216
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3622                  63490.
 MP_Allreduce        10155                    305.
 MP_Sync                54
 MP_Alltoall          1821                 513563.
 MP_SendRecv         11067                  57667.
 MP_ISendRecv        11067                  57667.
 MP_Wait             21987
 MP_ISend             9880                  92618.
 MP_IRecv             9880                  92618.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.012    0.029   33.521   33.522
 qs_mol_dyn_low                       1  2.0    0.003    0.003   33.279   33.286
 qs_forces                           11  3.9    0.005    0.007   33.214   33.219
 qs_energies                         11  4.9    0.001    0.002   31.606   31.611
 scf_env_do_scf                      11  5.9    0.000    0.001   26.469   26.469
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   24.019   24.020
 dbcsr_multiply_generic            2286 12.5    0.094    0.096   17.479   17.580
 velocity_verlet                     10  3.0    0.001    0.002   15.771   15.773
 qs_scf_new_mos                     108  7.5    0.001    0.001   15.661   15.677
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   15.660   15.677
 multiply_cannon                   2286 13.5    0.194    0.195   14.149   14.937
 ot_scf_mini                        108  9.5    0.002    0.002   14.893   14.911
 multiply_cannon_loop              2286 14.5    0.854    0.874   13.339   14.163
 ot_mini                            108 10.5    0.001    0.001    9.236    9.260
 qs_ot_get_derivative               108 11.5    0.001    0.001    7.713    7.730
 multiply_cannon_multrec          18288 15.5    1.874    2.846    7.343    7.623
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.470    6.488
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.012    6.469    6.488
 dbcsr_mm_accdrv_process          38222 16.0    5.317    6.157    5.376    6.222
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.701    5.718
 sum_up_and_integrate               119 10.3    0.031    0.032    4.031    4.036
 integrate_v_rspace                 119 11.3    0.002    0.003    4.000    4.009
 init_scf_run                        11  5.9    0.000    0.001    3.905    3.905
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    3.905    3.905
 mp_waitall_1                    158411 16.6    2.760    3.825    2.760    3.825
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.530    3.540
 calculate_rho_elec                 119  8.7    0.031    0.032    3.530    3.539
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.950    3.523
 qs_ot_get_p                        119 10.4    0.001    0.001    3.400    3.427
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.630    2.631
 rs_pw_transfer                     974 11.9    0.009    0.010    2.340    2.598
 multiply_cannon_metrocomm3       18288 15.5    0.048    0.049    1.527    2.493
 init_scf_loop                       11  6.9    0.000    0.000    2.433    2.435
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.007    2.370
 apply_single                       119 13.6    0.000    0.000    2.007    2.370
 density_rs2pw                      119  9.7    0.004    0.004    2.015    2.269
 qs_ot_p2m_diag                      50 11.0    0.012    0.013    2.260    2.266
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.108    2.110
 make_m2s                          4572 13.5    0.044    0.045    1.860    1.999
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.956    1.957
 pw_transfer                       1439 11.6    0.065    0.070    1.930    1.942
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.910    1.923
 make_images                       4572 14.5    0.194    0.206    1.775    1.913
 grid_integrate_task_list           119 12.3    1.803    1.905    1.803    1.905
 calculate_dm_sparse                119  9.5    0.000    0.001    1.847    1.854
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.837    1.852
 potential_pw2rs                    119 12.3    0.007    0.008    1.776    1.782
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.755    1.766
 cp_fm_diag_elpa                     50 13.0    0.000    0.001    1.704    1.714
 cp_fm_diag_elpa_base                50 14.0    1.680    1.691    1.702    1.712
 acc_transpose_blocks             18288 15.5    0.080    0.082    1.633    1.689
 prepare_preconditioner              11  7.9    0.000    0.000    1.646    1.649
 make_preconditioner                 11  8.9    0.000    0.000    1.646    1.649
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.504    1.585
 mp_sum_l                          7287 12.8    1.082    1.510    1.082    1.510
 ot_diis_step                       108 11.5    0.011    0.011    1.503    1.503
 fft_wrap_pw1pw2_140                487 13.2    0.255    0.261    1.463    1.476
 grid_collocate_task_list           119  9.7    1.242    1.403    1.242    1.403
 fft3d_ps                          1201 14.6    0.531    0.554    1.321    1.337
 wfi_extrapolate                     11  7.9    0.001    0.001    1.220    1.220
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.179    1.185
 multiply_cannon_sync_h2d         18288 15.5    1.045    1.155    1.045    1.155
 qs_energies_init_hamiltonians       11  5.9    0.043    0.045    0.998    1.001
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.957    0.976
 make_images_data                  4572 15.5    0.047    0.051    0.805    0.949
 hybrid_alltoall_any               4725 16.4    0.058    0.117    0.696    0.882
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.838    0.842
 acc_transpose_blocks_kernels     18288 16.5    0.218    0.225    0.794    0.805
 acc_transpose_blocks_sync        54864 16.5    0.738    0.795    0.738    0.795
 mp_alltoall_d11v                  2130 13.8    0.675    0.789    0.675    0.789
 mp_waitany                        9880 13.7    0.520    0.776    0.520    0.776
 rs_pw_transfer_RS2PW_140           130 11.5    0.117    0.120    0.507    0.756
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.677    0.736
 mp_alltoall_z22v                  1201 16.6    0.641    0.720    0.641    0.720
 cp_fm_cholesky_invert               11 10.9    0.698    0.701    0.698    0.701
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="104", plot="h2o_64_md", label="(8n/4r/3t)", y=33.522000, yerr=0.000000
PlotPoint: name="105", plot="h2o_64_md_mem", label="(8n/4r/3t)", y=497.454545, yerr=2.189381
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/06/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                    114.044384E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               3805952       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      38.6
 marketing flops                     2.107592E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             556.601344E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1042416
 MPI messages size (bytes):
  total size                       150.443262E+09
  min size                           0.000000E+00
  max size                           1.188816E+06
  average size                     144.321719E+03
 MPI breakdown and total messages size (bytes):
             size <=      128              228256                        0
       128 < size <=     8192              126888               1039466496
      8192 < size <=    32768              191472               3137077248
     32768 < size <=   131072              295800              25899827200
    131072 < size <=  4194304              200000             120367247040
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3622                  63489.
 MP_Allreduce        10154                    346.
 MP_Sync                54
 MP_Alltoall          1582                2412273.
 MP_SendRecv          8211                  74133.
 MP_ISendRecv         8211                  74133.
 MP_Wait             16271
 MP_ISend             7280                 135929.
 MP_IRecv             7280                 135929.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.044    0.162   38.042   38.111
 qs_mol_dyn_low                       1  2.0    0.003    0.004   37.678   37.713
 qs_forces                           11  3.9    0.003    0.006   37.618   37.621
 qs_energies                         11  4.9    0.005    0.015   35.872   35.878
 scf_env_do_scf                      11  5.9    0.001    0.002   30.667   30.668
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.008   27.118   27.118
 dbcsr_multiply_generic            2286 12.5    0.100    0.108   20.219   20.313
 velocity_verlet                     10  3.0    0.002    0.002   19.060   19.062
 qs_scf_new_mos                     108  7.5    0.001    0.001   18.363   18.426
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   18.363   18.425
 ot_scf_mini                        108  9.5    0.003    0.005   17.324   17.380
 multiply_cannon                   2286 13.5    0.218    0.227   16.318   16.783
 multiply_cannon_loop              2286 14.5    1.531    1.611   15.322   15.660
 ot_mini                            108 10.5    0.001    0.001   10.577   10.637
 multiply_cannon_multrec          27432 15.5    2.462    3.162    9.019    9.396
 qs_ot_get_derivative               108 11.5    0.001    0.001    8.713    8.767
 dbcsr_mm_accdrv_process          47916 15.9    5.993    7.731    6.455    7.794
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.831    6.875
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.015    6.831    6.874
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.077    6.112
 sum_up_and_integrate               119 10.3    0.035    0.038    3.959    3.966
 qs_ot_get_p                        119 10.4    0.001    0.001    3.857    3.939
 integrate_v_rspace                 119 11.3    0.003    0.003    3.924    3.932
 init_scf_run                        11  5.9    0.000    0.001    3.799    3.800
 scf_env_initial_rho_setup           11  6.9    0.001    0.003    3.799    3.800
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.659    3.689
 calculate_rho_elec                 119  8.7    0.040    0.047    3.658    3.688
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    3.154    3.546
 init_scf_loop                       11  6.9    0.002    0.007    3.529    3.530
 mp_waitall_1                    137007 16.6    2.040    2.696    2.040    2.696
 prepare_preconditioner              11  7.9    0.000    0.000    2.609    2.617
 make_preconditioner                 11  8.9    0.000    0.001    2.608    2.617
 make_m2s                          4572 13.5    0.054    0.056    2.418    2.557
 acc_transpose_blocks             27432 15.5    0.122    0.124    2.442    2.543
 make_full_inverse_cholesky          11  9.9    0.000    0.000    2.208    2.535
 make_images                       4572 14.5    0.273    0.332    2.309    2.446
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    2.402    2.433
 qs_ot_p2m_diag                      50 11.0    0.016    0.023    2.388    2.398
 calculate_first_density_matrix       1  7.0    0.001    0.002    2.391    2.395
 rs_pw_transfer                     974 11.9    0.009    0.009    2.159    2.365
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.111    2.234
 apply_single                       119 13.6    0.000    0.000    2.111    2.234
 calculate_dm_sparse                119  9.5    0.000    0.000    2.157    2.211
 density_rs2pw                      119  9.7    0.004    0.004    1.988    2.184
 pw_transfer                       1439 11.6    0.066    0.070    2.064    2.101
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.971    2.012
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.975    1.975
 grid_integrate_task_list           119 12.3    1.814    1.900    1.814    1.900
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.883    1.885
 ot_diis_step                       108 11.5    0.012    0.012    1.822    1.823
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.699    1.714
 potential_pw2rs                    119 12.3    0.008    0.009    1.699    1.702
 cp_fm_diag_elpa                     50 13.0    0.001    0.001    1.673    1.683
 cp_fm_diag_elpa_base                50 14.0    1.635    1.651    1.670    1.680
 fft_wrap_pw1pw2_140                487 13.2    0.291    0.305    1.616    1.659
 acc_transpose_blocks_sync        82296 16.5    1.460    1.556    1.460    1.556
 multiply_cannon_metrocomm3       27432 15.5    0.041    0.042    0.850    1.470
 fft3d_ps                          1201 14.6    0.558    0.608    1.404    1.434
 grid_collocate_task_list           119  9.7    1.249    1.372    1.249    1.372
 mp_sum_l                          7287 12.8    1.063    1.361    1.063    1.361
 wfi_extrapolate                     11  7.9    0.001    0.001    1.352    1.352
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.314    1.330
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.249    1.258
 cp_fm_upper_to_full                 72 14.2    0.819    1.164    0.819    1.164
 qs_energies_init_hamiltonians       11  5.9    0.002    0.004    1.121    1.122
 dbcsr_complete_redistribute        329 12.2    0.132    0.162    0.818    1.092
 make_images_data                  4572 15.5    0.048    0.052    0.914    1.060
 hybrid_alltoall_any               4725 16.4    0.066    0.156    0.810    1.022
 mp_alltoall_d11v                  2130 13.8    0.856    1.008    0.856    1.008
 jit_kernel_multiply                  5 16.3    0.396    0.937    0.396    0.937
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    0.800    0.878
 copy_fm_to_dbcsr                   176 11.2    0.001    0.002    0.591    0.861
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.849    0.853
 acc_transpose_blocks_kernels     27432 16.5    0.273    0.280    0.830    0.841
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="106", plot="h2o_64_md", label="(8n/3r/4t)", y=38.111000, yerr=0.000000
PlotPoint: name="107", plot="h2o_64_md_mem", label="(8n/3r/4t)", y=529.000000, yerr=3.104249
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/07/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                    117.977176E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               1384136       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     106.2
 marketing flops                     2.107587E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             631.291904E+06
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  219456
 MPI messages size (bytes):
  total size                        97.042514E+09
  min size                           0.000000E+00
  max size                           3.276800E+06
  average size                     442.195750E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768              101892               3336634368
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304              116112              93705670464
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         8156                     20.
 MP_Alltoall          8655                  64935.
 MP_ISend            36532                 168375.
 MP_IRecv            36532                 168349.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3622                  63488.
 MP_Allreduce        10154                    346.
 MP_Sync                54
 MP_Alltoall          1582                3682667.
 MP_SendRecv          5355                  94533.
 MP_ISendRecv         5355                  94533.
 MP_Wait             11335
 MP_ISend             5200                 225425.
 MP_IRecv             5200                 225425.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.013    0.029   30.062   30.063
 qs_mol_dyn_low                       1  2.0    0.003    0.003   29.518   29.885
 qs_forces                           11  3.9    0.002    0.002   29.436   29.437
 qs_energies                         11  4.9    0.001    0.001   27.697   27.700
 scf_env_do_scf                      11  5.9    0.000    0.001   22.970   22.970
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.007   20.360   20.361
 velocity_verlet                     10  3.0    0.002    0.002   15.377   15.380
 dbcsr_multiply_generic            2286 12.5    0.091    0.097   13.323   13.388
 qs_scf_new_mos                     108  7.5    0.001    0.001   12.111   12.136
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   12.110   12.136
 ot_scf_mini                        108  9.5    0.002    0.002   11.386   11.409
 multiply_cannon                   2286 13.5    0.222    0.228   10.569   11.097
 multiply_cannon_loop              2286 14.5    0.646    0.669    9.622    9.805
 ot_mini                            108 10.5    0.001    0.001    6.510    6.538
 multiply_cannon_multrec           9144 15.5    1.668    1.867    5.959    6.214
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.077    6.097
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    6.077    6.096
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.405    5.422
 qs_ot_get_derivative               108 11.5    0.001    0.001    5.196    5.221
 dbcsr_mm_accdrv_process          12550 15.8    3.663    4.199    4.179    4.255
 sum_up_and_integrate               119 10.3    0.037    0.041    3.720    3.724
 integrate_v_rspace                 119 11.3    0.003    0.003    3.682    3.688
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.581    3.589
 calculate_rho_elec                 119  8.7    0.060    0.061    3.581    3.588
 init_scf_run                        11  5.9    0.000    0.001    3.285    3.285
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.285    3.285
 qs_ot_get_p                        119 10.4    0.001    0.001    2.951    2.990
 init_scf_loop                       11  6.9    0.000    0.000    2.591    2.593
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.112    2.115
 mp_waitall_1                    115863 16.7    1.600    2.101    1.600    2.101
 pw_transfer                       1439 11.6    0.066    0.069    2.077    2.086
 make_m2s                          4572 13.5    0.034    0.035    1.915    2.061
 density_rs2pw                      119  9.7    0.004    0.004    1.885    2.036
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.983    1.995
 make_images                       4572 14.5    0.269    0.301    1.827    1.971
 grid_integrate_task_list           119 12.3    1.871    1.932    1.871    1.932
 qs_ot_p2m_diag                      50 11.0    0.022    0.023    1.898    1.902
 rs_pw_transfer                     974 11.9    0.008    0.008    1.741    1.886
 prepare_preconditioner              11  7.9    0.000    0.000    1.814    1.818
 make_preconditioner                 11  8.9    0.000    0.000    1.814    1.817
 calculate_dm_sparse                119  9.5    0.000    0.000    1.784    1.804
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    1.763    1.783
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.695    1.723
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.646    1.647
 fft_wrap_pw1pw2_140                487 13.2    0.366    0.377    1.630    1.644
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.552    1.553
 acc_transpose_blocks              9144 15.5    0.043    0.044    1.431    1.468
 potential_pw2rs                    119 12.3    0.010    0.011    1.436    1.440
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.421    1.432
 grid_collocate_task_list           119  9.7    1.300    1.418    1.300    1.418
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.384    1.390
 cp_fm_diag_elpa                     50 13.0    0.001    0.001    1.366    1.374
 cp_fm_diag_elpa_base                50 14.0    1.336    1.355    1.364    1.372
 fft3d_ps                          1201 14.6    0.560    0.572    1.315    1.323
 ot_diis_step                       108 11.5    0.013    0.013    1.301    1.301
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    1.239    1.268
 apply_single                       119 13.6    0.000    0.000    1.239    1.268
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    1.229    1.230
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.157    1.162
 wfi_extrapolate                     11  7.9    0.001    0.001    1.119    1.119
 hybrid_alltoall_any               4725 16.4    0.065    0.176    0.822    1.046
 jit_kernel_multiply                  6 15.5    0.477    1.043    0.477    1.043
 make_images_data                  4572 15.5    0.042    0.046    0.854    1.024
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.874    0.920
 cp_fm_cholesky_invert               11 10.9    0.911    0.913    0.911    0.913
 mp_alltoall_d11v                  2130 13.8    0.770    0.858    0.770    0.858
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.841    0.850
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.794    0.796
 acc_transpose_blocks_sync        27432 16.5    0.726    0.760    0.726    0.760
 mp_allgather_i34                  2286 14.5    0.263    0.732    0.263    0.732
 qs_env_update_s_mstruct             11  6.9    0.000    0.001    0.675    0.721
 multiply_cannon_metrocomm3        9144 15.5    0.021    0.021    0.397    0.717
 acc_transpose_blocks_kernels      9144 16.5    0.118    0.120    0.646    0.662
 mp_alltoall_z22v                  1201 16.6    0.629    0.659    0.629    0.659
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="108", plot="h2o_64_md", label="(8n/2r/6t)", y=30.063000, yerr=0.000000
PlotPoint: name="109", plot="h2o_64_md_mem", label="(8n/2r/6t)", y=599.272727, yerr=4.769046
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/08/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                    235.585836E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               1388964       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     105.8
 marketing flops                     2.107587E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             775.053312E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                   91440
 MPI messages size (bytes):
  total size                        85.748679E+09
  min size                           0.000000E+00
  max size                           6.553600E+06
  average size                     937.758938E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                 572                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768               21148                692256768
     32768 < size <=   131072               19224               1259864064
    131072 < size <=  4194304               41040              21941452800
   4194304 < size <= 16777216                9456              61855174464
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3622                  63723.
 MP_Allreduce        10154                    429.
 MP_Sync                54
 MP_Alltoall          1582                7383731.
 MP_SendRecv          2499                 189067.
 MP_ISendRecv         2499                 189067.
 MP_Wait              6399
 MP_ISend             3120                 546875.
 MP_IRecv             3120                 546875.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.015    0.037   43.877   43.879
 qs_mol_dyn_low                       1  2.0    0.003    0.004   43.627   43.634
 qs_forces                           11  3.9    0.002    0.002   43.549   43.550
 qs_energies                         11  4.9    0.004    0.024   41.453   41.458
 scf_env_do_scf                      11  5.9    0.001    0.001   35.693   35.693
 scf_env_do_scf_inner_loop          108  6.5    0.019    0.023   27.643   27.644
 velocity_verlet                     10  3.0    0.021    0.023   24.702   24.707
 dbcsr_multiply_generic            2286 12.5    0.106    0.109   19.214   19.454
 qs_scf_new_mos                     108  7.5    0.001    0.001   17.589   17.684
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   17.588   17.683
 ot_scf_mini                        108  9.5    0.002    0.002   16.410   16.509
 multiply_cannon                   2286 13.5    0.300    0.308   15.112   16.119
 multiply_cannon_loop              2286 14.5    0.865    0.887   13.808   14.857
 ot_mini                            108 10.5    0.001    0.001    9.934   10.048
 multiply_cannon_multrec           9144 15.5    3.375    4.611    8.771    8.882
 init_scf_loop                       11  6.9    0.000    0.000    8.023    8.025
 qs_ot_get_derivative               108 11.5    0.001    0.001    7.846    7.945
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.522    7.668
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.013    7.522    7.667
 prepare_preconditioner              11  7.9    0.000    0.000    6.978    6.991
 make_preconditioner                 11  8.9    0.000    0.000    6.978    6.991
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.747    6.875
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.515    6.865
 dbcsr_mm_accdrv_process          12550 15.8    4.441    5.804    5.258    6.529
 cp_fm_upper_to_full                 72 14.2    3.188    4.592    3.188    4.592
 qs_rho_update_rho_low              119  7.7    0.001    0.001    4.415    4.431
 calculate_rho_elec                 119  8.7    0.118    0.121    4.415    4.431
 sum_up_and_integrate               119 10.3    0.064    0.066    4.143    4.149
 integrate_v_rspace                 119 11.3    0.004    0.004    4.078    4.086
 init_scf_run                        11  5.9    0.000    0.001    3.671    3.671
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.671    3.671
 qs_ot_get_p                        119 10.4    0.001    0.001    3.523    3.657
 mp_waitall_1                     94719 16.7    2.479    3.575    2.479    3.575
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.836    3.288
 dbcsr_complete_redistribute        329 12.2    0.298    0.311    2.043    2.888
 pw_transfer                       1439 11.6    0.069    0.069    2.752    2.756
 make_m2s                          4572 13.5    0.037    0.038    2.477    2.660
 fft_wrap_pw1pw2                   1201 12.6    0.009    0.009    2.653    2.658
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.288    2.578
 apply_single                       119 13.6    0.000    0.000    2.288    2.578
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    1.718    2.545
 make_images                       4572 14.5    0.353    0.384    2.357    2.540
 multiply_cannon_metrocomm3        9144 15.5    0.021    0.022    1.369    2.347
 density_rs2pw                      119  9.7    0.004    0.004    2.282    2.303
 calculate_dm_sparse                119  9.5    0.000    0.000    2.281    2.297
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.457    2.276
 mp_alltoall_i22                    627 13.8    1.438    2.263    1.438    2.263
 fft_wrap_pw1pw2_140                487 13.2    0.619    0.626    2.227    2.234
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    2.119    2.169
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.133    2.136
 grid_integrate_task_list           119 12.3    2.085    2.133    2.085    2.133
 qs_ot_p2m_diag                      50 11.0    0.043    0.044    2.081    2.083
 ot_diis_step                       108 11.5    0.014    0.014    2.062    2.062
 acc_transpose_blocks              9144 15.5    0.045    0.046    1.829    1.875
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.860    1.861
 mp_sum_l                          7287 12.8    1.072    1.832    1.072    1.832
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    1.777    1.778
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.712    1.712
 fft3d_ps                          1201 14.6    0.595    0.608    1.667    1.671
 rs_pw_transfer                     974 11.9    0.009    0.009    1.605    1.644
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.568    1.607
 grid_collocate_task_list           119  9.7    1.527    1.546    1.527    1.546
 cp_fm_cholesky_invert               11 10.9    1.514    1.519    1.514    1.519
 potential_pw2rs                    119 12.3    0.014    0.014    1.473    1.476
 wfi_extrapolate                     11  7.9    0.001    0.001    1.456    1.456
 hybrid_alltoall_any               4725 16.4    0.090    0.150    1.145    1.429
 cp_fm_diag_elpa                     50 13.0    0.001    0.001    1.413    1.413
 cp_fm_diag_elpa_base                50 14.0    1.266    1.321    1.411    1.411
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.336    1.358
 make_images_data                  4572 15.5    0.046    0.049    1.100    1.337
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.268    1.277
 mp_alltoall_d11v                  2130 13.8    1.162    1.197    1.162    1.197
 acc_transpose_blocks_sync        27432 16.5    1.103    1.137    1.103    1.137
 qs_env_update_s_mstruct             11  6.9    0.003    0.006    1.105    1.128
 jit_kernel_multiply                  6 15.5    0.788    1.057    0.788    1.057
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    0.991    1.034
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.987    1.005
 mp_alltoall_z22v                  1201 16.6    0.935    0.954    0.935    0.954
 qs_create_task_list                 11  7.9    0.001    0.004    0.936    0.951
 generate_qs_task_list               11  8.9    0.368    0.388    0.935    0.950
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="110", plot="h2o_64_md", label="(8n/1r/12t)", y=43.879000, yerr=0.000000
PlotPoint: name="111", plot="h2o_64_md_mem", label="(8n/1r/12t)", y=727.272727, yerr=16.679279
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/09/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                    198.287135E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               8410880       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     117.0
 marketing flops                    15.646302E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank             501.235712E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 8483040
 MPI messages size (bytes):
  total size                         1.160510E+12
  min size                           0.000000E+00
  max size                           1.161504E+06
  average size                     136.803609E+03
 MPI breakdown and total messages size (bytes):
             size <=      128             1836752                        0
       128 < size <=     8192             1040592               8524529664
      8192 < size <=    32768             1486976              24362614784
     32768 < size <=   131072             2491776             216971345920
    131072 < size <=  4194304             1626944             910632720448
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3473                  66212.
 MP_Allreduce         9776                    488.
 MP_Sync                52
 MP_Alltoall          1938                 670136.
 MP_SendRecv         20900                   9096.
 MP_ISendRecv        20900                   9096.
 MP_Wait             37268
 MP_ISend            14300                  82312.
 MP_IRecv            14300                  82312.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.016    0.030   84.022   84.024
 qs_mol_dyn_low                       1  2.0    0.003    0.006   83.682   83.692
 qs_forces                           11  3.9    0.003    0.004   83.609   83.611
 qs_energies                         11  4.9    0.001    0.002   80.632   80.649
 scf_env_do_scf                      11  5.9    0.000    0.001   71.581   71.583
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.006   65.902   65.903
 dbcsr_multiply_generic            2055 12.4    0.106    0.108   51.343   51.618
 qs_scf_new_mos                      99  7.5    0.001    0.001   47.919   48.070
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   47.918   48.070
 ot_scf_mini                         99  9.5    0.002    0.002   45.535   45.666
 velocity_verlet                     10  3.0    0.001    0.001   44.340   44.341
 multiply_cannon                   2055 13.4    0.181    0.186   42.738   43.472
 multiply_cannon_loop              2055 14.4    1.817    1.854   41.748   42.473
 ot_mini                             99 10.5    0.001    0.001   26.919   27.036
 qs_ot_get_derivative                99 11.5    0.001    0.001   20.140   20.246
 multiply_cannon_multrec          49320 15.4   11.354   12.116   17.376   18.336
 rebuild_ks_matrix                  110  8.3    0.000    0.000   14.954   15.113
 qs_ks_build_kohn_sham_matrix       110  9.3    0.011    0.011   14.954   15.112
 qs_ks_update_qs_env                110  7.6    0.001    0.001   13.053   13.183
 mp_waitall_1                    220248 16.4   11.107   11.785   11.107   11.785
 qs_ot_get_p                        110 10.4    0.001    0.001   10.114   10.219
 multiply_cannon_sync_h2d         49320 15.4    9.595   10.116    9.595   10.116
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    7.854    8.379
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    7.213    7.688
 apply_single                       110 13.6    0.000    0.001    7.213    7.688
 multiply_cannon_metrocomm3       49320 15.4    0.084    0.087    6.595    7.681
 sum_up_and_integrate               110 10.3    0.036    0.043    7.409    7.423
 integrate_v_rspace                 110 11.3    0.003    0.004    7.373    7.396
 qs_rho_update_rho_low              110  7.6    0.001    0.001    7.094    7.228
 calculate_rho_elec                 110  8.6    0.021    0.026    7.093    7.228
 init_scf_run                        11  5.9    0.000    0.001    6.963    6.963
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    6.963    6.963
 qs_ot_p2m_diag                      48 11.0    0.012    0.019    6.855    6.892
 ot_diis_step                        99 11.5    0.006    0.006    6.578    6.578
 dbcsr_mm_accdrv_process          87628 16.1    3.053    3.136    5.891    6.175
 cp_dbcsr_syevd                      48 12.0    0.002    0.003    5.917    5.917
 init_scf_loop                       11  6.9    0.000    0.000    5.648    5.649
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    5.423    5.487
 cp_fm_diag_elpa                     48 13.0    0.001    0.002    5.308    5.332
 cp_fm_diag_elpa_base                48 14.0    5.290    5.318    5.304    5.330
 mp_sum_l                          6594 12.7    4.069    4.923    4.069    4.923
 rs_pw_transfer                     902 11.9    0.011    0.013    4.164    4.873
 density_rs2pw                      110  9.6    0.004    0.005    3.800    4.450
 make_m2s                          4110 13.4    0.061    0.064    4.092    4.195
 wfi_extrapolate                     11  7.9    0.001    0.001    4.168    4.169
 make_images                       4110 14.4    0.177    0.188    3.996    4.102
 calculate_dm_sparse                110  9.5    0.001    0.001    3.763    3.860
 multiply_cannon_metrocomm1       49320 15.4    0.067    0.069    2.434    3.631
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    3.572    3.576
 prepare_preconditioner              11  7.9    0.000    0.000    3.441    3.457
 make_preconditioner                 11  8.9    0.000    0.000    3.441    3.457
 grid_integrate_task_list           110 12.3    3.261    3.457    3.261    3.457
 pw_transfer                       1331 11.6    0.055    0.067    3.352    3.454
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.009    3.263    3.368
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    3.209    3.267
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    3.200    3.262
 make_full_inverse_cholesky          11  9.9    0.000    0.000    3.219    3.258
 potential_pw2rs                    110 12.3    0.006    0.007    2.865    2.904
 fft_wrap_pw1pw2_140                451 13.1    0.451    0.500    2.740    2.849
 mp_alltoall_d11v                  2046 13.8    2.176    2.792    2.176    2.792
 acc_transpose_blocks             49320 15.4    0.219    0.225    2.598    2.650
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.636    2.648
 jit_kernel_multiply                 13 15.9    2.560    2.630    2.560    2.630
 mp_waitany                       14300 13.8    1.852    2.566    1.852    2.566
 fft3d_ps                          1111 14.6    0.791    0.879    2.459    2.537
 grid_collocate_task_list           110  9.6    2.153    2.427    2.153    2.427
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    2.031    2.058
 make_images_data                  4110 15.4    0.044    0.048    1.834    1.970
 mp_sum_d                          3889 11.9    1.371    1.951    1.371    1.951
 cp_fm_cholesky_invert               11 10.9    1.895    1.900    1.895    1.900
 hybrid_alltoall_any               4261 16.3    0.084    0.485    1.587    1.826
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="200", plot="h2o_128_md", label="(8n/12r/1t)", y=84.024000, yerr=0.000000
PlotPoint: name="201", plot="h2o_128_md_mem", label="(8n/12r/1t)", y=475.545455, yerr=3.085557
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/10/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                    390.715586E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               5019072       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     196.1
 marketing flops                    15.646302E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank             593.727488E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1972800
 MPI messages size (bytes):
  total size                         1.077520E+12
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     546.188250E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               14916                        0
       128 < size <=     8192              222984               1826684928
      8192 < size <=    32768              520356              13399818240
     32768 < size <=   131072              372336              35386294272
    131072 < size <=  4194304              787758             788321309808
   4194304 < size <= 16777216               54450             238588003280
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3473                  66430.
 MP_Allreduce         9775                    566.
 MP_Sync                52
 MP_Alltoall          1717                3433654.
 MP_SendRecv         10340                  26400.
 MP_ISendRecv        10340                  26400.
 MP_Wait             22352
 MP_ISend            10164                 155761.
 MP_IRecv            10164                 155761.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.026    0.075   73.612   73.614
 qs_mol_dyn_low                       1  2.0    0.003    0.004   73.243   73.255
 qs_forces                           11  3.9    0.005    0.014   73.137   73.138
 qs_energies                         11  4.9    0.002    0.005   69.678   69.685
 scf_env_do_scf                      11  5.9    0.001    0.001   60.812   60.815
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.007   52.256   52.257
 dbcsr_multiply_generic            2055 12.4    0.120    0.137   38.995   39.328
 velocity_verlet                     10  3.0    0.001    0.001   38.638   38.640
 qs_scf_new_mos                      99  7.5    0.001    0.001   35.140   35.267
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   35.139   35.266
 ot_scf_mini                         99  9.5    0.003    0.004   33.404   33.535
 multiply_cannon                   2055 13.4    0.224    0.245   31.628   33.324
 multiply_cannon_loop              2055 14.4    1.161    1.196   30.302   31.342
 ot_mini                             99 10.5    0.001    0.001   19.230   19.378
 multiply_cannon_multrec          24660 15.4    6.916    8.323   13.958   15.328
 rebuild_ks_matrix                  110  8.3    0.000    0.000   14.276   14.394
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.014   14.276   14.394
 qs_ot_get_derivative                99 11.5    0.001    0.001   13.350   13.484
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.551   12.657
 mp_waitall_1                    176588 16.5    8.165   10.948    8.165   10.948
 multiply_cannon_metrocomm3       24660 15.4    0.073    0.077    5.481    8.832
 init_scf_loop                       11  6.9    0.002    0.006    8.510    8.512
 qs_ot_get_p                        110 10.4    0.001    0.001    7.394    7.589
 multiply_cannon_sync_h2d         24660 15.4    6.295    7.348    6.295    7.348
 dbcsr_mm_accdrv_process          52282 16.1    5.526    6.475    6.876    7.213
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    6.488    7.068
 apply_single                       110 13.6    0.000    0.001    6.488    7.068
 sum_up_and_integrate               110 10.3    0.052    0.059    7.008    7.021
 integrate_v_rspace                 110 11.3    0.003    0.004    6.956    6.971
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.646    6.656
 calculate_rho_elec                 110  8.6    0.040    0.047    6.645    6.655
 init_scf_run                        11  5.9    0.000    0.001    6.387    6.387
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    6.386    6.387
 prepare_preconditioner              11  7.9    0.000    0.000    6.362    6.380
 make_preconditioner                 11  8.9    0.001    0.004    6.362    6.380
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.892    6.064
 ot_diis_step                        99 11.5    0.010    0.010    5.803    5.804
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    4.940    5.645
 qs_ot_p2m_diag                      48 11.0    0.029    0.044    5.257    5.284
 make_m2s                          4110 13.4    0.057    0.059    4.620    5.028
 make_images                       4110 14.4    0.409    0.467    4.511    4.914
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    4.757    4.758
 density_rs2pw                      110  9.6    0.004    0.005    3.681    4.233
 pw_transfer                       1331 11.6    0.067    0.074    4.011    4.172
 cp_fm_diag_elpa                     48 13.0    0.001    0.001    4.114    4.127
 cp_fm_diag_elpa_base                48 14.0    4.062    4.077    4.110    4.123
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.009    3.904    4.066
 rs_pw_transfer                     902 11.9    0.012    0.014    3.356    3.943
 wfi_extrapolate                     11  7.9    0.001    0.001    3.686    3.686
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.578    3.651
 fft_wrap_pw1pw2_140                451 13.1    0.523    0.540    3.233    3.396
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.002    3.367    3.370
 grid_integrate_task_list           110 12.3    3.154    3.349    3.154    3.349
 cp_fm_cholesky_invert               11 10.9    3.111    3.119    3.111    3.119
 calculate_dm_sparse                110  9.5    0.001    0.001    3.046    3.082
 fft3d_ps                          1111 14.6    1.111    1.339    2.873    3.051
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.999    3.039
 mp_sum_l                          6594 12.7    2.129    2.977    2.129    2.977
 make_images_data                  4110 15.4    0.049    0.054    2.438    2.888
 hybrid_alltoall_any               4261 16.3    0.108    0.456    2.133    2.819
 potential_pw2rs                    110 12.3    0.008    0.009    2.714    2.739
 calculate_first_density_matrix       1  7.0    0.001    0.003    2.591    2.594
 grid_collocate_task_list           110  9.6    2.096    2.538    2.096    2.538
 mp_alltoall_d11v                  2046 13.8    2.030    2.283    2.030    2.283
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    2.092    2.110
 acc_transpose_blocks             24660 15.4    0.119    0.124    1.990    2.019
 multiply_cannon_metrocomm4       22605 15.4    0.079    0.085    0.788    1.975
 qs_energies_init_hamiltonians       11  5.9    0.001    0.003    1.937    1.939
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.894    1.909
 mp_waitany                       10164 13.8    1.348    1.886    1.348    1.886
 mp_irecv_dv                      57340 16.2    0.659    1.753    0.659    1.753
 jit_kernel_multiply                  9 16.4    0.984    1.746    0.984    1.746
 mp_allgather_i34                  2055 14.4    0.634    1.676    0.634    1.676
 rs_pw_transfer_RS2PW_140           121 11.5    0.207    0.225    1.040    1.622
 mp_alltoall_z22v                  1111 16.6    1.497    1.587    1.497    1.587
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.002    1.557    1.569
 dbcsr_complete_redistribute        325 12.2    0.238    0.294    1.288    1.558
 cp_fm_cholesky_decompose            22 10.9    1.528    1.534    1.528    1.534
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.387    1.495
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="202", plot="h2o_128_md", label="(8n/6r/2t)", y=73.614000, yerr=0.000000
PlotPoint: name="203", plot="h2o_128_md_mem", label="(8n/6r/2t)", y=560.727273, yerr=7.828746
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/11/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                    404.681598E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               3346752       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     294.1
 marketing flops                    15.646297E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank             666.275840E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                  854880
 MPI messages size (bytes):
  total size                       708.322787E+09
  min size                           0.000000E+00
  max size                           6.553600E+06
  average size                     828.564000E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768              222984               7302414336
     32768 < size <=   131072              153888              10085203968
    131072 < size <=  4194304              389376             200257044480
   4194304 < size <= 16777216               82208             490679162176
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3473                  66421.
 MP_Allreduce         9774                    562.
 MP_Sync                52
 MP_Alltoall          1496                4511006.
 MP_SendRecv          6820                  27424.
 MP_ISendRecv         6820                  27424.
 MP_Wait             25498
 MP_ISend            17072                 115022.
 MP_IRecv            17072                 115022.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.033    0.082   62.055   62.075
 qs_mol_dyn_low                       1  2.0    0.003    0.004   61.681   61.701
 qs_forces                           11  3.9    0.004    0.009   61.613   61.614
 qs_energies                         11  4.9    0.005    0.008   58.327   58.332
 scf_env_do_scf                      11  5.9    0.001    0.001   50.196   50.197
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.007   41.394   41.395
 velocity_verlet                     10  3.0    0.001    0.002   33.553   33.554
 dbcsr_multiply_generic            2055 12.4    0.108    0.112   29.248   29.640
 qs_scf_new_mos                      99  7.5    0.001    0.001   25.960   26.072
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   25.959   26.072
 ot_scf_mini                         99  9.5    0.002    0.003   24.697   24.827
 multiply_cannon                   2055 13.4    0.212    0.224   22.636   23.849
 multiply_cannon_loop              2055 14.4    0.812    0.864   21.400   22.458
 ot_mini                             99 10.5    0.001    0.001   14.083   14.215
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.642   12.837
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.016   12.642   12.837
 qs_ks_update_qs_env                110  7.6    0.001    0.001   11.115   11.293
 multiply_cannon_multrec          16440 15.4    3.596    4.678    9.779   10.743
 mp_waitall_1                    139946 16.5    7.304   10.293    7.304   10.293
 qs_ot_get_derivative                99 11.5    0.001    0.001    9.543    9.670
 init_scf_loop                       11  6.9    0.001    0.006    8.761    8.762
 multiply_cannon_metrocomm3       16440 15.4    0.046    0.047    4.532    7.283
 prepare_preconditioner              11  7.9    0.000    0.001    6.939    6.957
 make_preconditioner                 11  8.9    0.000    0.001    6.938    6.957
 sum_up_and_integrate               110 10.3    0.059    0.061    6.719    6.736
 integrate_v_rspace                 110 11.3    0.003    0.003    6.659    6.677
 make_full_inverse_cholesky          11  9.9    0.000    0.000    6.254    6.612
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.238    6.250
 calculate_rho_elec                 110  8.6    0.059    0.059    6.238    6.250
 dbcsr_mm_accdrv_process          34862 16.1    5.398    5.718    6.030    6.134
 qs_ot_get_p                        110 10.4    0.001    0.001    5.714    5.898
 init_scf_run                        11  5.9    0.000    0.001    5.640    5.640
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    5.640    5.640
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    5.032    5.495
 apply_single                       110 13.6    0.000    0.000    5.032    5.495
 make_m2s                          4110 13.4    0.050    0.052    4.352    4.738
 make_images                       4110 14.4    0.400    0.523    4.237    4.622
 density_rs2pw                      110  9.6    0.004    0.005    3.291    4.559
 ot_diis_step                        99 11.5    0.011    0.011    4.505    4.505
 rs_pw_transfer                     902 11.9    0.010    0.011    2.902    4.167
 qs_ot_p2m_diag                      48 11.0    0.042    0.044    3.996    4.004
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.249    3.923
 multiply_cannon_sync_h2d         16440 15.4    3.167    3.884    3.167    3.884
 pw_transfer                       1331 11.6    0.066    0.073    3.784    3.795
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.677    3.692
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.607    3.607
 grid_integrate_task_list           110 12.3    3.174    3.370    3.174    3.370
 fft_wrap_pw1pw2_140                451 13.1    0.642    0.648    3.140    3.154
 wfi_extrapolate                     11  7.9    0.001    0.001    3.055    3.055
 cp_fm_diag_elpa                     48 13.0    0.001    0.001    3.019    3.027
 cp_fm_diag_elpa_base                48 14.0    2.950    2.982    3.016    3.025
 make_images_data                  4110 15.4    0.045    0.049    2.486    2.961
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.855    2.857
 hybrid_alltoall_any               4261 16.3    0.110    0.384    2.178    2.846
 cp_fm_cholesky_invert               11 10.9    2.753    2.759    2.753    2.759
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.552    2.625
 mp_waitany                       17072 13.8    1.260    2.591    1.260    2.591
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.518    2.587
 multiply_cannon_metrocomm4       14385 15.4    0.047    0.052    0.894    2.576
 calculate_dm_sparse                110  9.5    0.001    0.001    2.537    2.571
 grid_collocate_task_list           110  9.6    2.126    2.526    2.126    2.526
 fft3d_ps                          1111 14.6    1.094    1.104    2.494    2.503
 calculate_first_density_matrix       1  7.0    0.002    0.016    2.457    2.459
 mp_irecv_dv                      48980 15.7    0.821    2.445    0.821    2.445
 potential_pw2rs                    110 12.3    0.011    0.011    2.404    2.413
 mp_alltoall_d11v                  2046 13.8    1.851    2.264    1.851    2.264
 mp_sum_l                          6594 12.7    1.650    2.208    1.650    2.208
 rs_pw_transfer_RS2PW_140           121 11.5    0.174    0.178    0.935    2.206
 qs_energies_init_hamiltonians       11  5.9    0.001    0.004    2.020    2.022
 dbcsr_complete_redistribute        325 12.2    0.323    0.361    1.503    1.960
 cp_fm_upper_to_full                 70 14.2    1.381    1.763    1.381    1.763
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.724    1.742
 mp_allgather_i34                  2055 14.4    0.549    1.724    0.549    1.724
 acc_transpose_blocks             16440 15.4    0.082    0.085    1.592    1.712
 cp_fm_cholesky_decompose            22 10.9    1.634    1.648    1.634    1.648
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.375    1.493
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.002    1.463    1.478
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    0.986    1.428
 rs_gather_matrices                 110 12.3    0.232    0.258    1.003    1.347
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.321    1.328
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="204", plot="h2o_128_md", label="(8n/4r/3t)", y=62.075000, yerr=0.000000
PlotPoint: name="205", plot="h2o_128_md_mem", label="(8n/4r/3t)", y=631.545455, yerr=8.825208
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/12/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                    601.317074E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               4916280       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     200.2
 marketing flops                    15.646302E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank             731.897856E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                  937080
 MPI messages size (bytes):
  total size                       523.723932E+09
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     558.889250E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6996                        0
       128 < size <=     8192                 264                  2162688
      8192 < size <=    32768              304932               8165326848
     32768 < size <=   131072              110640               6338641920
    131072 < size <=  4194304              489498             400769458320
   4194304 < size <= 16777216               24750             108449092400
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3473                  66419.
 MP_Allreduce         9774                    603.
 MP_Sync                52
 MP_Alltoall          1496                5863162.
 MP_SendRecv          5060                  43184.
 MP_ISendRecv         5060                  43184.
 MP_Wait             20042
 MP_ISend            13376                 163145.
 MP_IRecv            13376                 163145.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.013    0.032   67.250   67.251
 qs_mol_dyn_low                       1  2.0    0.003    0.004   66.981   66.992
 qs_forces                           11  3.9    0.003    0.003   66.819   66.819
 qs_energies                         11  4.9    0.001    0.002   63.181   63.185
 scf_env_do_scf                      11  5.9    0.000    0.001   54.846   54.849
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.007   43.090   43.091
 velocity_verlet                     10  3.0    0.024    0.099   37.964   37.966
 dbcsr_multiply_generic            2055 12.4    0.113    0.119   30.919   31.198
 qs_scf_new_mos                      99  7.5    0.001    0.001   27.993   28.125
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   27.993   28.124
 ot_scf_mini                         99  9.5    0.002    0.003   26.294   26.391
 multiply_cannon                   2055 13.4    0.238    0.256   23.817   24.697
 multiply_cannon_loop              2055 14.4    1.427    1.475   22.425   23.073
 ot_mini                             99 10.5    0.001    0.001   15.101   15.224
 multiply_cannon_multrec          24660 15.4    4.074    6.731   13.012   14.244
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.311   12.417
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.013   12.311   12.416
 init_scf_loop                       11  6.9    0.000    0.000   11.716   11.717
 qs_ot_get_derivative                99 11.5    0.001    0.001   10.911   11.016
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.835   10.931
 prepare_preconditioner              11  7.9    0.000    0.000    9.903    9.921
 make_preconditioner                 11  8.9    0.000    0.000    9.903    9.921
 dbcsr_mm_accdrv_process          52304 16.0    7.814    9.423    8.780    9.727
 make_full_inverse_cholesky          11  9.9    0.000    0.000    8.141    9.606
 sum_up_and_integrate               110 10.3    0.068    0.070    6.568    6.580
 integrate_v_rspace                 110 11.3    0.003    0.003    6.500    6.516
 mp_waitall_1                    121746 16.5    4.417    6.394    4.417    6.394
 qs_ot_get_p                        110 10.4    0.001    0.001    6.040    6.190
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.168    6.179
 calculate_rho_elec                 110  8.6    0.078    0.082    6.167    6.179
 make_m2s                          4110 13.4    0.059    0.062    5.433    5.753
 make_images                       4110 14.4    0.578    0.700    5.292    5.608
 init_scf_run                        11  5.9    0.000    0.001    5.528    5.529
 scf_env_initial_rho_setup           11  6.9    0.002    0.002    5.528    5.529
 cp_fm_upper_to_full                 70 14.2    3.359    4.868    3.359    4.868
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.048    4.197
 apply_single                       110 13.6    0.000    0.000    4.048    4.196
 ot_diis_step                        99 11.5    0.011    0.011    4.153    4.153
 qs_ot_p2m_diag                      48 11.0    0.055    0.064    4.071    4.089
 pw_transfer                       1331 11.6    0.066    0.075    3.784    3.814
 dbcsr_complete_redistribute        325 12.2    0.419    0.463    2.635    3.780
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.677    3.711
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.537    3.588
 density_rs2pw                      110  9.6    0.004    0.004    3.051    3.570
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.494    3.495
 grid_integrate_task_list           110 12.3    3.273    3.471    3.273    3.471
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.400    3.456
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    2.117    3.252
 multiply_cannon_metrocomm3       24660 15.4    0.039    0.040    1.530    3.220
 fft_wrap_pw1pw2_140                451 13.1    0.671    0.694    3.155    3.192
 hybrid_alltoall_any               4261 16.3    0.124    0.464    2.394    3.078
 calculate_dm_sparse                110  9.5    0.001    0.001    3.000    3.041
 wfi_extrapolate                     11  7.9    0.001    0.001    3.033    3.033
 make_images_data                  4110 15.4    0.048    0.052    2.691    3.023
 rs_pw_transfer                     902 11.9    0.010    0.011    2.412    2.934
 cp_fm_diag_elpa                     48 13.0    0.001    0.002    2.924    2.933
 cp_fm_diag_elpa_base                48 14.0    2.758    2.818    2.920    2.929
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.753    2.874
 mp_alltoall_i22                    605 13.7    1.664    2.824    1.664    2.824
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.803    2.804
 cp_fm_cholesky_invert               11 10.9    2.677    2.685    2.677    2.685
 multiply_cannon_sync_h2d         24660 15.4    2.398    2.585    2.398    2.585
 acc_transpose_blocks             24660 15.4    0.114    0.117    2.458    2.538
 grid_collocate_task_list           110  9.6    2.219    2.484    2.219    2.484
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.441    2.483
 fft3d_ps                          1111 14.6    1.084    1.119    2.434    2.447
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.389    2.392
 qs_energies_init_hamiltonians       11  5.9    0.007    0.012    2.290    2.290
 mp_alltoall_d11v                  2046 13.8    1.794    2.265    1.794    2.265
 potential_pw2rs                    110 12.3    0.012    0.013    2.199    2.210
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.838    1.874
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.716    1.725
 cp_fm_cholesky_decompose            22 10.9    1.673    1.716    1.673    1.716
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.612    1.706
 mp_sum_l                          6594 12.7    0.982    1.661    0.982    1.661
 mp_waitany                       13376 13.8    1.073    1.568    1.073    1.568
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.545    1.560
 multiply_cannon_metrocomm4       20550 15.4    0.062    0.065    0.850    1.555
 acc_transpose_blocks_sync        73980 16.4    1.434    1.505    1.434    1.505
 jit_kernel_multiply                  8 15.8    0.618    1.495    0.618    1.495
 mp_irecv_dv                      62702 16.1    0.747    1.474    0.747    1.474
 rs_gather_matrices                 110 12.3    0.265    0.293    0.947    1.355
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="206", plot="h2o_128_md", label="(8n/3r/4t)", y=67.251000, yerr=0.000000
PlotPoint: name="207", plot="h2o_128_md_mem", label="(8n/3r/4t)", y=694.181818, yerr=7.517473
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/13/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                    807.299199E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               1438408       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     684.2
 marketing flops                    15.646297E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank             844.124160E+06
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  197280
 MPI messages size (bytes):
  total size                       339.125567E+09
  min size                           0.000000E+00
  max size                          13.107200E+06
  average size                       1.719006E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 132                  4325376
     32768 < size <=   131072               88656              11620319232
    131072 < size <=  4194304               89424             117209825280
   4194304 < size <= 16777216               17616             210291069504
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         7346                     33.
 MP_Alltoall          8043                 263767.
 MP_ISend            32836                 654203.
 MP_IRecv            32836                 654587.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3473                  66417.
 MP_Allreduce         9774                    644.
 MP_Sync                52
 MP_Alltoall          1496                8504061.
 MP_SendRecv          3300                  54848.
 MP_ISendRecv         3300                  54848.
 MP_Wait             13926
 MP_ISend             9240                 278857.
 MP_IRecv             9240                 278857.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.012    0.029   56.081   56.081
 qs_mol_dyn_low                       1  2.0    0.003    0.003   55.848   55.856
 qs_forces                           11  3.9    0.003    0.003   55.759   55.759
 qs_energies                         11  4.9    0.017    0.050   52.052   52.056
 scf_env_do_scf                      11  5.9    0.000    0.001   43.773   43.774
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.007   35.925   35.926
 velocity_verlet                     10  3.0    0.002    0.003   31.645   31.649
 dbcsr_multiply_generic            2055 12.4    0.104    0.109   23.299   23.439
 qs_scf_new_mos                      99  7.5    0.001    0.001   20.760   20.821
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   20.759   20.820
 ot_scf_mini                         99  9.5    0.002    0.002   19.505   19.561
 multiply_cannon                   2055 13.4    0.237    0.243   17.702   19.022
 multiply_cannon_loop              2055 14.4    0.603    0.625   16.438   16.692
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.005   12.045
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.013   12.004   12.045
 ot_mini                             99 10.5    0.001    0.001   10.803   10.859
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.648   10.682
 multiply_cannon_multrec           8220 15.4    3.138    4.376    7.569    8.631
 init_scf_loop                       11  6.9    0.000    0.000    7.802    7.803
 mp_waitall_1                    103326 16.6    5.934    7.565    5.934    7.565
 qs_ot_get_derivative                99 11.5    0.001    0.001    7.057    7.115
 sum_up_and_integrate               110 10.3    0.079    0.082    6.573    6.587
 integrate_v_rspace                 110 11.3    0.003    0.003    6.494    6.507
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.396    6.410
 calculate_rho_elec                 110  8.6    0.114    0.115    6.395    6.410
 prepare_preconditioner              11  7.9    0.000    0.000    6.111    6.116
 make_preconditioner                 11  8.9    0.000    0.000    6.111    6.116
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.683    5.755
 dbcsr_mm_accdrv_process          17442 15.9    3.122    4.155    4.290    5.225
 init_scf_run                        11  5.9    0.000    0.001    5.098    5.099
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.098    5.098
 qs_ot_get_p                        110 10.4    0.001    0.001    4.726    4.804
 make_m2s                          4110 13.4    0.038    0.039    4.247    4.497
 multiply_cannon_metrocomm3        8220 15.4    0.019    0.020    3.092    4.472
 make_images                       4110 14.4    0.649    0.711    4.118    4.364
 pw_transfer                       1331 11.6    0.066    0.072    3.966    3.975
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.859    3.872
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    3.777    3.808
 apply_single                       110 13.6    0.000    0.000    3.776    3.808
 ot_diis_step                        99 11.5    0.012    0.012    3.724    3.724
 grid_integrate_task_list           110 12.3    3.368    3.579    3.368    3.579
 density_rs2pw                      110  9.6    0.004    0.004    3.091    3.464
 qs_ot_p2m_diag                      48 11.0    0.081    0.084    3.349    3.353
 fft_wrap_pw1pw2_140                451 13.1    0.838    0.851    3.336    3.353
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.008    3.009
 cp_fm_cholesky_invert               11 10.9    2.929    2.933    2.929    2.933
 wfi_extrapolate                     11  7.9    0.001    0.001    2.744    2.744
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    2.676    2.677
 hybrid_alltoall_any               4261 16.3    0.201    0.866    2.243    2.664
 rs_pw_transfer                     902 11.9    0.010    0.010    2.245    2.650
 make_images_data                  4110 15.4    0.041    0.046    2.281    2.603
 grid_collocate_task_list           110  9.6    2.316    2.573    2.316    2.573
 calculate_dm_sparse                110  9.5    0.001    0.001    2.481    2.514
 cp_fm_diag_elpa                     48 13.0    0.001    0.001    2.492    2.499
 cp_fm_diag_elpa_base                48 14.0    2.436    2.458    2.489    2.497
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.492    2.494
 multiply_cannon_sync_h2d          8220 15.4    2.349    2.475    2.349    2.475
 fft3d_ps                          1111 14.6    1.132    1.148    2.397    2.409
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.254    2.256
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.135    2.155
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    2.097    2.143
 potential_pw2rs                    110 12.3    0.015    0.015    2.103    2.105
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.006    2.035
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.783    1.991
 mp_alltoall_d11v                  2046 13.8    1.657    1.901    1.657    1.901
 cp_fm_cholesky_decompose            22 10.9    1.719    1.737    1.719    1.737
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.685    1.691
 qs_env_update_s_mstruct             11  6.9    0.001    0.001    1.494    1.624
 mp_waitany                        9240 13.8    1.088    1.522    1.088    1.522
 dbcsr_complete_redistribute        325 12.2    0.567    0.603    1.430    1.517
 mp_allgather_i34                  2055 14.4    0.437    1.514    0.437    1.514
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.432    1.441
 acc_transpose_blocks              8220 15.4    0.041    0.041    1.405    1.438
 jit_kernel_multiply                  8 15.4    0.851    1.411    0.851    1.411
 qs_create_task_list                 11  7.9    0.000    0.001    1.217    1.325
 generate_qs_task_list               11  8.9    0.374    0.442    1.216    1.324
 multiply_cannon_metrocomm4        6165 15.4    0.018    0.020    0.477    1.254
 rs_pw_transfer_RS2PW_140           121 11.5    0.161    0.165    0.802    1.216
 mp_irecv_dv                      24056 15.7    0.451    1.205    0.451    1.205
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.148    1.188
 rs_gather_matrices                 110 12.3    0.325    0.369    0.934    1.181
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="208", plot="h2o_128_md", label="(8n/2r/6t)", y=56.081000, yerr=0.000000
PlotPoint: name="209", plot="h2o_128_md_mem", label="(8n/2r/6t)", y=793.363636, yerr=10.490452
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/14/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                      1.612391E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               1464624       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     672.0
 marketing flops                    15.646297E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank               1.360703E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                   82200
 MPI messages size (bytes):
  total size                       297.640985E+09
  min size                           0.000000E+00
  max size                          26.214400E+06
  average size                       3.620936E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                 572                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                  44                  1441792
     32768 < size <=   131072               18560               2432696320
    131072 < size <=  4194304               54216              84915781632
   4194304 < size <= 16777216                   0                        0
  16777216 < size                            8808             210291069504
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3462                  67098.
 MP_Allreduce         9752                    812.
 MP_Sync                52
 MP_Alltoall          1474               16505187.
 MP_SendRecv          2310                 360267.
 MP_ISendRecv         2310                 360267.
 MP_Wait              5214
 MP_ISend             2420                1187840.
 MP_IRecv             2420                1187840.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.029    0.066   89.463   89.475
 qs_mol_dyn_low                       1  2.0    0.003    0.003   89.081   89.102
 qs_forces                           11  3.9    0.003    0.003   89.002   89.003
 qs_energies                         11  4.9    0.002    0.004   84.769   84.770
 scf_env_do_scf                      11  5.9    0.001    0.001   74.597   74.598
 velocity_verlet                     10  3.0    0.011    0.021   56.975   56.982
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.007   45.907   45.908
 dbcsr_multiply_generic            2055 12.4    0.119    0.124   30.001   30.151
 init_scf_loop                       11  6.9    0.000    0.000   28.619   28.620
 qs_scf_new_mos                      99  7.5    0.001    0.001   27.405   27.489
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   27.404   27.489
 prepare_preconditioner              11  7.9    0.000    0.000   26.555   26.569
 make_preconditioner                 11  8.9    0.000    0.000   26.555   26.569
 make_full_inverse_cholesky          11  9.9    0.000    0.000   20.707   26.027
 ot_scf_mini                         99  9.5    0.002    0.002   25.591   25.675
 multiply_cannon                   2055 13.4    0.333    0.355   22.723   23.496
 multiply_cannon_loop              2055 14.4    0.841    0.865   20.889   21.264
 cp_fm_upper_to_full                 70 14.2   12.843   18.410   12.843   18.410
 ot_mini                             99 10.5    0.001    0.001   14.415   14.493
 rebuild_ks_matrix                  110  8.3    0.000    0.000   14.337   14.424
 qs_ks_build_kohn_sham_matrix       110  9.3    0.014    0.014   14.337   14.423
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.965   13.043
 dbcsr_complete_redistribute        325 12.2    1.009    1.023    7.392   10.561
 multiply_cannon_multrec           8220 15.4    4.070    4.234    9.790    9.897
 qs_ot_get_derivative                99 11.5    0.001    0.001    9.642    9.726
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    6.388    9.560
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    5.832    8.982
 mp_waitall_1                     84994 16.7    7.755    8.688    7.755    8.688
 mp_alltoall_i22                    605 13.7    5.464    8.624    5.464    8.624
 qs_rho_update_rho_low              110  7.6    0.001    0.001    7.805    7.844
 calculate_rho_elec                 110  8.6    0.225    0.226    7.805    7.844
 sum_up_and_integrate               110 10.3    0.152    0.154    7.428    7.442
 integrate_v_rspace                 110 11.3    0.004    0.004    7.276    7.290
 make_m2s                          4110 13.4    0.043    0.044    5.435    5.951
 qs_ot_get_p                        110 10.4    0.001    0.001    5.834    5.927
 init_scf_run                        11  5.9    0.000    0.001    5.861    5.862
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.861    5.861
 dbcsr_mm_accdrv_process          11614 15.7    3.891    4.130    5.573    5.785
 make_images                       4110 14.4    0.884    0.941    5.247    5.762
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.883    5.400
 apply_single                       110 13.6    0.000    0.000    4.883    5.400
 cp_fm_cholesky_invert               11 10.9    5.366    5.371    5.366    5.371
 multiply_cannon_metrocomm3        8220 15.4    0.019    0.020    4.974    5.254
 pw_transfer                       1331 11.6    0.075    0.076    5.058    5.066
 fft_wrap_pw1pw2                   1111 12.6    0.009    0.009    4.940    4.948
 ot_diis_step                        99 11.5    0.015    0.016    4.755    4.755
 fft_wrap_pw1pw2_140                451 13.1    1.342    1.349    4.306    4.315
 qs_ot_p2m_diag                      48 11.0    0.151    0.155    4.179    4.188
 density_rs2pw                      110  9.6    0.004    0.004    3.755    3.839
 grid_integrate_task_list           110 12.3    3.724    3.800    3.724    3.800
 qs_energies_init_hamiltonians       11  5.9    0.017    0.021    3.701    3.704
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.650    3.650
 hybrid_alltoall_any               4261 16.3    0.264    0.566    2.881    3.633
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.066    3.540
 make_images_data                  4110 15.4    0.045    0.048    2.877    3.540
 wfi_extrapolate                     11  7.9    0.001    0.001    3.388    3.388
 calculate_dm_sparse                110  9.5    0.001    0.001    3.208    3.235
 multiply_cannon_sync_h2d          8220 15.4    3.097    3.125    3.097    3.125
 cp_fm_diag_elpa                     48 13.0    0.010    0.018    3.050    3.050
 cp_fm_diag_elpa_base                48 14.0    2.484    2.682    3.029    3.030
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.961    2.965
 fft3d_ps                          1111 14.6    1.299    1.310    2.860    2.871
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.712    2.756
 grid_collocate_task_list           110  9.6    2.708    2.752    2.708    2.752
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.456    2.485
 potential_pw2rs                    110 12.3    0.021    0.021    2.440    2.448
 rs_pw_transfer                     902 11.9    0.010    0.010    2.323    2.382
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.350    2.352
 qs_env_update_s_mstruct             11  6.9    0.001    0.001    2.183    2.237
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    2.105    2.201
 mp_alltoall_d11v                  2046 13.8    2.019    2.174    2.019    2.174
 cp_fm_cholesky_decompose            22 10.9    1.976    1.993    1.976    1.993
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.969    1.978
 qs_create_task_list                 11  7.9    0.001    0.001    1.886    1.936
 generate_qs_task_list               11  8.9    0.732    0.783    1.885    1.936
 acc_transpose_blocks              8220 15.4    0.042    0.043    1.819    1.871
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.776    1.822
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="210", plot="h2o_128_md", label="(8n/1r/12t)", y=89.475000, yerr=0.000000
PlotPoint: name="211", plot="h2o_128_md_mem", label="(8n/1r/12t)", y=1241.272727, yerr=34.774837
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/15/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420239992832       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528891191296       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514751E+12       0.0%      0.0%    100.0%
 flops max/rank                      1.094965E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755938624       0.0%      0.0%    100.0%
 number of processed stacks              11950464       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     565.3
 marketing flops                   144.580175E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank             630.067200E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                10348896
 MPI messages size (bytes):
  total size                         4.491514E+12
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     434.009000E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               65736                        0
       128 < size <=     8192                1232                 10092544
      8192 < size <=    32768             3576680              95640223744
     32768 < size <=   131072             1294784              74079797248
    131072 < size <=  4194304             5148576            3175954870160
   4194304 < size <= 16777216              261888            1145794321408
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3992                  57905.
 MP_Allreduce        11059                    797.
 MP_Sync                87
 MP_Alltoall          2226                2874145.
 MP_SendRecv         24320                  18752.
 MP_ISendRecv        24320                  18752.
 MP_Wait             42476
 MP_ISend            16020                 108028.
 MP_IRecv            16020                 108028.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.012    0.029  211.083  211.085
 qs_mol_dyn_low                       1  2.0    0.003    0.004  210.577  210.591
 qs_forces                           11  3.9    0.005    0.005  210.483  210.484
 qs_energies                         11  4.9    0.001    0.002  204.763  204.786
 scf_env_do_scf                      11  5.9    0.001    0.001  188.051  188.055
 scf_env_do_scf_inner_loop          117  6.6    0.005    0.013  166.793  166.794
 velocity_verlet                     10  3.0    0.005    0.017  126.870  126.871
 dbcsr_multiply_generic            2507 12.6    0.180    0.184  126.003  126.534
 qs_scf_new_mos                     117  7.6    0.001    0.001  125.767  126.003
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001  125.766  126.003
 ot_scf_mini                        117  9.6    0.003    0.003  119.031  119.329
 multiply_cannon                   2507 13.6    0.238    0.246  101.563  102.957
 multiply_cannon_loop              2507 14.6    2.421    2.483   99.269  100.626
 ot_mini                            117 10.6    0.001    0.001   66.473   66.759
 multiply_cannon_multrec          60168 15.6   31.751   33.287   41.470   43.314
 qs_ot_get_derivative               117 11.6    0.001    0.001   41.582   41.826
 rebuild_ks_matrix                  128  8.3    0.001    0.001   34.291   34.540
 qs_ks_build_kohn_sham_matrix       128  9.3    0.015    0.017   34.290   34.539
 mp_waitall_1                    267128 16.5   29.008   32.239   29.008   32.239
 qs_ks_update_qs_env                128  7.6    0.001    0.001   30.755   31.001
 qs_ot_get_p                        128 10.4    0.001    0.001   30.222   30.483
 multiply_cannon_sync_h2d         60168 15.6   26.345   28.303   26.345   28.303
 apply_preconditioner_dbcsr         128 12.6    0.000    0.001   24.334   25.212
 apply_single                       128 13.6    0.001    0.001   24.333   25.212
 ot_diis_step                       117 11.6    0.008    0.008   24.610   24.611
 qs_ot_p2m_diag                      83 11.4    0.079    0.091   23.535   23.600
 init_scf_loop                       11  6.9    0.000    0.001   21.181   21.182
 cp_dbcsr_syevd                      83 12.4    0.005    0.005   20.701   20.703
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002   19.653   19.860
 multiply_cannon_metrocomm3       60168 15.6    0.119    0.124   15.907   17.694
 cp_fm_diag_elpa                     83 13.4    0.001    0.001   17.630   17.668
 cp_fm_diag_elpa_base                83 14.4   17.553   17.592   17.625   17.665
 prepare_preconditioner              11  7.9    0.000    0.000   16.559   16.604
 make_preconditioner                 11  8.9    0.000    0.000   16.559   16.604
 make_full_inverse_cholesky          11  9.9    0.000    0.000   15.783   15.988
 make_m2s                          5014 13.6    0.104    0.111   14.146   14.620
 sum_up_and_integrate               128 10.3    0.089    0.108   14.583   14.597
 integrate_v_rspace                 128 11.3    0.004    0.004   14.494   14.511
 qs_rho_update_rho_low              128  7.7    0.001    0.001   14.286   14.465
 calculate_rho_elec                 128  8.7    0.046    0.065   14.285   14.465
 make_images                       5014 14.6    0.399    0.418   13.964   14.449
 init_scf_run                        11  5.9    0.000    0.001   12.504   12.505
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   12.504   12.505
 density_rs2pw                      128  9.7    0.006    0.007    7.438   10.868
 mp_sum_l                          7950 12.9    9.034   10.540    9.034   10.540
 dbcsr_mm_accdrv_process         124484 16.2    4.680    4.825    9.284    9.833
 cp_fm_cholesky_invert               11 10.9    9.560    9.568    9.560    9.568
 rs_pw_transfer                    1046 11.9    0.016    0.019    6.083    9.472
 wfi_extrapolate                     11  7.9    0.001    0.001    9.293    9.293
 calculate_dm_sparse                128  9.5    0.001    0.001    8.550    8.671
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    8.335    8.462
 pw_transfer                       1547 11.6    0.074    0.090    8.079    8.260
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    8.146    8.241
 multiply_cannon_metrocomm1       60168 15.6    0.097    0.101    6.365    8.147
 fft_wrap_pw1pw2                   1291 12.7    0.011    0.013    7.876    8.055
 make_images_data                  5014 15.6    0.069    0.074    6.907    7.918
 grid_integrate_task_list           128 12.3    7.028    7.650    7.028    7.650
 hybrid_alltoall_any               5200 16.5    0.296    2.280    6.061    7.303
 fft_wrap_pw1pw2_140                523 13.2    1.271    1.314    6.804    6.983
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.003    6.679    6.690
 mp_waitany                       16020 13.9    2.749    6.244    2.749    6.244
 mp_alltoall_d11v                  2415 14.1    4.560    6.033    4.560    6.033
 fft3d_ps                          1291 14.7    2.147    2.788    5.644    5.977
 grid_collocate_task_list           128  9.7    4.686    5.954    4.686    5.954
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.778    5.873
 rs_pw_transfer_RS2PW_140           139 11.5    0.279    0.299    2.148    5.596
 potential_pw2rs                    128 12.3    0.009    0.011    4.849    4.885
 cp_fm_cholesky_decompose            22 10.9    4.778    4.792    4.778    4.792
 mp_sum_d                          4465 12.1    3.502    4.305    3.502    4.305
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="400", plot="h2o_256_md", label="(8n/12r/1t)", y=211.085000, yerr=0.000000
PlotPoint: name="401", plot="h2o_256_md_mem", label="(8n/12r/1t)", y=596.000000, yerr=5.526794
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/16/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420239992832       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528891191296       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514751E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.183246E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755938624       0.0%      0.0%    100.0%
 number of processed stacks               5975232       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1130.7
 marketing flops                   144.580175E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank             841.265152E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 2406720
 MPI messages size (bytes):
  total size                         4.100942E+12
  min size                           0.000000E+00
  max size                          17.653760E+06
  average size                       1.703955E+06
 MPI breakdown and total messages size (bytes):
             size <=      128               14916                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768               70860               2317615104
     32768 < size <=   131072              722992              55511613440
    131072 < size <=  4194304             1375664            1398181724160
   4194304 < size <= 16777216              154704            1463834332048
  16777216 < size                           67584            1181116006400
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3992                  58357.
 MP_Allreduce        11058                    960.
 MP_Sync                87
 MP_Alltoall          1969                6285798.
 MP_SendRecv         12032                  47072.
 MP_ISendRecv        12032                  47072.
 MP_Wait             25916
 MP_ISend            11748                 212467.
 MP_IRecv            11748                 212467.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.015    0.032  190.811  190.812
 qs_mol_dyn_low                       1  2.0    0.003    0.004  190.445  190.458
 qs_forces                           11  3.9    0.007    0.014  190.359  190.363
 qs_energies                         11  4.9    0.002    0.005  183.492  183.506
 scf_env_do_scf                      11  5.9    0.001    0.001  167.114  167.125
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.008  134.181  134.183
 velocity_verlet                     10  3.0    0.002    0.002  120.223  120.224
 dbcsr_multiply_generic            2507 12.6    0.190    0.195   97.024   98.245
 qs_scf_new_mos                     117  7.6    0.001    0.001   94.372   94.894
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   94.371   94.893
 ot_scf_mini                        117  9.6    0.004    0.004   89.568   90.175
 multiply_cannon                   2507 13.6    0.504    0.571   76.813   81.635
 multiply_cannon_loop              2507 14.6    1.563    1.636   73.911   76.704
 ot_mini                            117 10.6    0.001    0.001   50.266   50.827
 mp_waitall_1                    214728 16.6   23.931   37.096   23.931   37.096
 multiply_cannon_multrec          30084 15.6   21.059   25.449   31.631   36.482
 rebuild_ks_matrix                  128  8.3    0.001    0.001   32.931   33.668
 qs_ks_build_kohn_sham_matrix       128  9.3    0.017    0.018   32.930   33.667
 init_scf_loop                       11  6.9    0.000    0.000   32.845   32.846
 qs_ks_update_qs_env                128  7.6    0.001    0.001   29.568   30.226
 qs_ot_get_derivative               117 11.6    0.001    0.002   28.228   28.843
 prepare_preconditioner              11  7.9    0.000    0.000   28.525   28.592
 make_preconditioner                 11  8.9    0.000    0.000   28.525   28.592
 multiply_cannon_metrocomm3       30084 15.6    0.098    0.104   15.568   28.483
 make_full_inverse_cholesky          11  9.9    0.000    0.000   27.223   27.760
 apply_preconditioner_dbcsr         128 12.6    0.000    0.000   22.132   23.301
 apply_single                       128 13.6    0.001    0.001   22.132   23.300
 qs_ot_get_p                        128 10.4    0.001    0.001   21.464   22.143
 ot_diis_step                       117 11.6    0.015    0.015   21.865   21.868
 multiply_cannon_sync_h2d         30084 15.6   18.061   20.416   18.061   20.416
 cp_fm_cholesky_invert               11 10.9   16.697   16.710   16.697   16.710
 qs_ot_p2m_diag                      83 11.4    0.188    0.216   16.542   16.577
 make_m2s                          5014 13.6    0.088    0.092   14.180   15.348
 cp_dbcsr_syevd                      83 12.4    0.006    0.006   15.332   15.333
 make_images                       5014 14.6    1.180    1.385   13.972   15.141
 sum_up_and_integrate               128 10.3    0.116    0.132   14.752   14.780
 integrate_v_rspace                 128 11.3    0.004    0.004   14.635   14.669
 qs_rho_update_rho_low              128  7.7    0.001    0.001   14.202   14.242
 calculate_rho_elec                 128  8.7    0.088    0.104   14.201   14.242
 cp_fm_diag_elpa                     83 13.4    0.001    0.002   12.159   12.197
 cp_fm_diag_elpa_base                83 14.4   11.903   11.988   12.152   12.185
 qs_ot_get_derivative_diag           77 12.4    0.002    0.003   11.221   11.680
 init_scf_run                        11  5.9    0.000    0.001   11.559   11.561
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   11.559   11.560
 multiply_cannon_metrocomm4       27577 15.6    0.108    0.123    3.828   11.006
 mp_irecv_dv                      69486 16.3    3.620   10.606    3.620   10.606
 dbcsr_mm_accdrv_process          62242 16.2    5.381    6.215   10.017   10.558
 density_rs2pw                      128  9.7    0.007    0.008    7.481    9.924
 make_images_data                  5014 15.6    0.068    0.077    8.340    9.803
 hybrid_alltoall_any               5200 16.5    0.356    1.587    7.046    9.382
 pw_transfer                       1547 11.6    0.086    0.096    8.815    8.864
 fft_wrap_pw1pw2                   1291 12.7    0.011    0.011    8.589    8.639
 wfi_extrapolate                     11  7.9    0.001    0.001    8.365    8.365
 rs_pw_transfer                    1046 11.9    0.014    0.016    5.747    8.208
 fft_wrap_pw1pw2_140                523 13.2    1.340    1.358    7.584    7.642
 grid_integrate_task_list           128 12.3    7.165    7.546    7.165    7.546
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    6.266    7.062
 cp_fm_cholesky_decompose            22 10.9    6.909    6.992    6.909    6.992
 calculate_dm_sparse                128  9.5    0.001    0.001    6.461    6.626
 mp_sum_l                          7950 12.9    4.226    6.170    4.226    6.170
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.107    6.117
 grid_collocate_task_list           128  9.7    4.785    5.956    4.785    5.956
 fft3d_ps                          1291 14.7    2.816    2.975    5.889    5.936
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    5.386    5.454
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.183    5.401
 potential_pw2rs                    128 12.3    0.015    0.017    4.978    5.006
 mp_waitany                       11748 13.9    2.494    4.985    2.494    4.985
 mp_alltoall_d11v                  2415 14.1    4.176    4.923    4.176    4.923
 rs_pw_transfer_RS2PW_140           139 11.5    0.351    0.381    2.104    4.535
 mp_allgather_i34                  2507 14.6    1.422    4.443    1.422    4.443
 dbcsr_complete_redistribute        395 12.7    0.781    0.887    3.171    4.029
 mp_sum_d                          4465 12.1    2.636    3.969    2.636    3.969
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    3.751    3.825
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="402", plot="h2o_256_md", label="(8n/6r/2t)", y=190.812000, yerr=0.000000
PlotPoint: name="403", plot="h2o_256_md_mem", label="(8n/6r/2t)", y=801.818182, yerr=2.208174
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/17/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1430457200640       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1962800054272       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1986252263424       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1992001093632       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2753958699008       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4454954827776       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5444944789504       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5492290093056       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6712799002624       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11613077360640       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15239162695680       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15239162695680       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19911132921856       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        94.232994E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.951022E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6806382528       0.0%      0.0%    100.0%
 number of processed stacks               4017216       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1694.3
 marketing flops                   145.650931E+12
 -------------------------------------------------------------------------------
 # multiplications                           2529
 max memory usage/rank             975.007744E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                 1052064
 MPI messages size (bytes):
  total size                         2.737208E+12
  min size                           0.000000E+00
  max size                          26.214400E+06
  average size                       2.601750E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 264                  8650752
     32768 < size <=   131072              284544              37295751168
    131072 < size <=  4194304              665856            1004519030784
   4194304 < size <= 16777216               66080             937890532432
  16777216 < size                           28896             757491302400
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4043                  57629.
 MP_Allreduce        11184                    996.
 MP_Sync                88
 MP_Alltoall          1724                9394234.
 MP_SendRecv          7998                  75008.
 MP_ISendRecv         7998                  75008.
 MP_Wait             21986
 MP_ISend            11836                 275177.
 MP_IRecv            11836                 275177.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.102    0.182  178.682  178.699
 qs_mol_dyn_low                       1  2.0    0.003    0.004  177.957  177.984
 qs_forces                           11  3.9    0.012    0.069  177.746  177.750
 qs_energies                         11  4.9    0.008    0.055  170.984  170.996
 scf_env_do_scf                      11  5.9    0.001    0.004  155.136  155.137
 scf_env_do_scf_inner_loop          118  6.6    0.005    0.011  119.905  119.906
 velocity_verlet                     10  3.0    0.002    0.002  114.744  114.750
 dbcsr_multiply_generic            2529 12.6    0.182    0.187   82.116   83.279
 qs_scf_new_mos                     118  7.6    0.001    0.001   80.980   81.338
 qs_scf_loop_do_ot                  118  8.6    0.001    0.002   80.979   81.338
 ot_scf_mini                        118  9.6    0.004    0.005   76.764   77.163
 multiply_cannon                   2529 13.6    0.511    0.533   62.508   66.813
 multiply_cannon_loop              2529 14.6    1.135    1.195   59.659   62.462
 ot_mini                            118 10.6    0.001    0.001   42.884   43.273
 init_scf_loop                       11  6.9    0.001    0.006   35.129   35.130
 mp_waitall_1                    172006 16.6   24.820   34.636   24.820   34.636
 rebuild_ks_matrix                  129  8.3    0.001    0.001   31.122   31.610
 qs_ks_build_kohn_sham_matrix       129  9.3    0.016    0.020   31.122   31.610
 prepare_preconditioner              11  7.9    0.000    0.001   31.086   31.144
 make_preconditioner                 11  8.9    0.000    0.001   31.085   31.144
 make_full_inverse_cholesky          11  9.9    0.000    0.000   28.628   30.053
 qs_ks_update_qs_env                129  7.6    0.001    0.001   28.019   28.466
 multiply_cannon_multrec          20232 15.6   13.200   16.527   22.604   26.077
 multiply_cannon_metrocomm3       20232 15.6    0.063    0.067   15.567   25.208
 qs_ot_get_derivative               118 11.6    0.002    0.002   23.023   23.412
 apply_preconditioner_dbcsr         129 12.6    0.000    0.000   19.851   20.929
 apply_single                       129 13.6    0.001    0.001   19.851   20.928
 ot_diis_step                       118 11.6    0.018    0.018   19.750   19.750
 qs_ot_get_p                        129 10.4    0.001    0.001   19.193   19.626
 make_m2s                          5058 13.6    0.079    0.085   14.591   15.560
 multiply_cannon_sync_h2d         20232 15.6   13.584   15.338   13.584   15.338
 make_images                       5058 14.6    1.164    1.263   14.359   15.329
 qs_ot_p2m_diag                      84 11.4    0.268    0.276   14.915   14.924
 sum_up_and_integrate               129 10.3    0.134    0.145   14.821   14.850
 qs_rho_update_rho_low              129  7.7    0.001    0.001   14.735   14.768
 calculate_rho_elec                 129  8.7    0.131    0.146   14.734   14.767
 integrate_v_rspace                 129 11.3    0.004    0.005   14.686   14.719
 cp_fm_cholesky_invert               11 10.9   14.477   14.486   14.477   14.486
 cp_dbcsr_syevd                      84 12.4    0.005    0.006   13.836   13.837
 cp_fm_diag_elpa                     84 13.4    0.001    0.002   10.578   10.598
 cp_fm_diag_elpa_base                84 14.4   10.158   10.329   10.573   10.593
 init_scf_run                        11  5.9    0.000    0.001   10.577   10.578
 scf_env_initial_rho_setup           11  6.9    0.001    0.002   10.577   10.577
 make_images_data                  5058 15.6    0.064    0.074    8.695   10.078
 multiply_cannon_metrocomm4       17703 15.6    0.066    0.078    3.523    9.680
 density_rs2pw                      129  9.7    0.006    0.007    7.343    9.628
 hybrid_alltoall_any               5245 16.5    0.455    2.062    7.482    9.481
 qs_ot_get_derivative_diag           78 12.4    0.002    0.002    9.151    9.432
 mp_irecv_dv                      50659 16.2    3.395    9.421    3.395    9.421
 pw_transfer                       1559 11.6    0.086    0.104    9.043    9.149
 dbcsr_mm_accdrv_process          41846 16.2    5.650    5.993    8.863    9.033
 fft_wrap_pw1pw2                   1301 12.7    0.010    0.011    8.817    8.928
 fft_wrap_pw1pw2_140                527 13.2    1.432    1.453    7.833    7.960
 grid_integrate_task_list           129 12.3    7.342    7.878    7.342    7.878
 rs_pw_transfer                    1054 12.0    0.014    0.015    5.315    7.615
 wfi_extrapolate                     11  7.9    0.001    0.001    7.480    7.480
 cp_fm_cholesky_decompose            22 10.9    7.387    7.424    7.387    7.424
 cp_fm_upper_to_full                106 14.8    5.698    7.255    5.698    7.255
 dbcsr_complete_redistribute        397 12.7    1.174    1.203    4.714    6.491
 fft3d_ps                          1301 14.7    2.766    3.003    5.906    5.995
 grid_collocate_task_list           129  9.7    5.009    5.970    5.009    5.970
 calculate_dm_sparse                129  9.5    0.001    0.001    5.864    5.943
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.418    5.421
 copy_fm_to_dbcsr                   210 11.7    0.002    0.002    3.528    5.302
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    4.611    5.252
 mp_alltoall_d11v                  2429 14.1    4.575    5.205    4.575    5.205
 mp_waitany                       11836 13.9    2.441    4.829    2.441    4.829
 potential_pw2rs                    129 12.3    0.020    0.022    4.805    4.820
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.514    4.677
 mp_sum_l                          8016 12.9    3.213    4.601    3.213    4.601
 mp_allgather_i34                  2529 14.6    1.336    4.367    1.336    4.367
 rs_pw_transfer_RS2PW_140           140 11.5    0.331    0.352    1.980    4.264
 transfer_fm_to_dbcsr                11  9.9    0.018    0.022    2.438    4.167
 qs_ot_get_orbitals                 118 10.6    0.001    0.001    4.027    4.054
 mp_alltoall_i22                    720 14.1    1.964    3.849    1.964    3.849
 qs_energies_init_hamiltonians       11  5.9    0.004    0.012    3.820    3.823
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    3.607    3.648
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="404", plot="h2o_256_md", label="(8n/4r/3t)", y=178.699000, yerr=0.000000
PlotPoint: name="405", plot="h2o_256_md_mem", label="(8n/4r/3t)", y=920.454545, yerr=16.019100
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/18/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1430454546432       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1973537472512       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1986255912960       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1992006770688       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2753958699008       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4454954827776       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5444944789504       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5492290093056       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6712799002624       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11613065416704       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15239182565376       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15239182565376       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19911132921856       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        94.243766E+12       0.0%      0.0%    100.0%
 flops max/rank                      4.387745E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6806547424       0.0%      0.0%    100.0%
 number of processed stacks               6032640       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1128.3
 marketing flops                   145.662591E+12
 -------------------------------------------------------------------------------
 # multiplications                           2534
 max memory usage/rank               1.155465E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1155504
 MPI messages size (bytes):
  total size                         2.039825E+12
  min size                           0.000000E+00
  max size                          17.653760E+06
  average size                       1.765312E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                6996                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 396                  8650752
     32768 < size <=   131072              323336              36533174272
    131072 < size <=  4194304              723016             792311627776
   4194304 < size <= 16777216               70800             669922351760
  16777216 < size                           30960             541065216000
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4043                  57626.
 MP_Allreduce        11184                   1079.
 MP_Sync                88
 MP_Alltoall          1724               12509574.
 MP_SendRecv          5934                  75008.
 MP_ISendRecv         5934                  75008.
 MP_Wait             22612
 MP_ISend            15064                 244788.
 MP_IRecv            15064                 244788.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.027    0.065  192.413  192.415
 qs_mol_dyn_low                       1  2.0    0.003    0.004  191.944  191.956
 qs_forces                           11  3.9    0.007    0.009  191.839  191.845
 qs_energies                         11  4.9    0.006    0.034  184.606  184.615
 scf_env_do_scf                      11  5.9    0.001    0.001  167.484  167.490
 velocity_verlet                     10  3.0    0.002    0.003  127.629  127.632
 scf_env_do_scf_inner_loop          118  6.6    0.003    0.009  120.661  120.662
 qs_scf_new_mos                     118  7.6    0.001    0.001   82.528   82.879
 qs_scf_loop_do_ot                  118  8.6    0.001    0.005   82.527   82.878
 dbcsr_multiply_generic            2534 12.6    0.189    0.196   81.299   81.945
 ot_scf_mini                        118  9.6    0.003    0.005   77.905   78.240
 multiply_cannon                   2534 13.6    0.556    0.587   56.222   59.000
 multiply_cannon_loop              2534 14.6    1.862    1.933   52.696   54.202
 init_scf_loop                       11  6.9    0.001    0.006   46.699   46.700
 ot_mini                            118 10.6    0.001    0.001   43.406   43.738
 prepare_preconditioner              11  7.9    0.000    0.001   42.512   42.532
 make_preconditioner                 11  8.9    0.000    0.001   42.512   42.532
 make_full_inverse_cholesky          11  9.9    0.012    0.022   36.013   41.035
 multiply_cannon_multrec          30408 15.6   13.867   18.556   26.847   31.536
 rebuild_ks_matrix                  129  8.3    0.001    0.001   30.380   30.631
 qs_ks_build_kohn_sham_matrix       129  9.3    0.017    0.021   30.380   30.630
 qs_ks_update_qs_env                129  7.6    0.001    0.001   27.391   27.613
 mp_waitall_1                    149452 16.7   17.331   26.272   17.331   26.272
 qs_ot_get_derivative               118 11.6    0.002    0.006   23.698   24.031
 make_m2s                          5068 13.6    0.095    0.099   20.567   21.178
 make_images                       5068 14.6    1.973    2.311   20.258   20.869
 qs_ot_get_p                        129 10.4    0.001    0.001   20.501   20.854
 apply_preconditioner_dbcsr         129 12.6    0.000    0.001   19.083   19.625
 apply_single                       129 13.6    0.001    0.001   19.083   19.625
 ot_diis_step                       118 11.6    0.018    0.019   19.582   19.583
 cp_fm_upper_to_full                106 14.8   11.391   16.829   11.391   16.829
 cp_fm_cholesky_invert               11 10.9   16.336   16.345   16.336   16.345
 qs_ot_p2m_diag                      84 11.4    0.346    0.395   16.203   16.255
 sum_up_and_integrate               129 10.3    0.141    0.155   14.958   14.984
 qs_rho_update_rho_low              129  7.7    0.001    0.001   14.886   14.929
 calculate_rho_elec                 129  8.7    0.174    0.190   14.885   14.929
 integrate_v_rspace                 129 11.3    0.004    0.004   14.817   14.847
 cp_dbcsr_syevd                      84 12.4    0.005    0.006   14.751   14.753
 multiply_cannon_metrocomm3       30408 15.6    0.051    0.054    6.364   14.575
 dbcsr_complete_redistribute        397 12.7    1.513    1.626    9.278   13.065
 dbcsr_mm_accdrv_process          62840 16.2    8.481    9.232   12.541   13.040
 make_images_data                  5068 15.6    0.067    0.073   10.984   12.160
 copy_fm_to_dbcsr                   210 11.7    0.002    0.002    7.882   11.647
 cp_fm_diag_elpa                     84 13.4    0.001    0.002   11.445   11.458
 cp_fm_diag_elpa_base                84 14.4   10.462   10.797   11.438   11.453
 multiply_cannon_sync_h2d         30408 15.6   10.573   11.371   10.573   11.371
 init_scf_run                        11  5.9    0.000    0.001   11.071   11.072
 scf_env_initial_rho_setup           11  6.9    0.001    0.002   11.070   11.071
 hybrid_alltoall_any               5255 16.5    0.537    2.237    9.791   11.035
 qs_ot_get_derivative_diag           78 12.4    0.002    0.003   10.064   10.301
 transfer_fm_to_dbcsr                11  9.9    0.001    0.005    6.476   10.185
 mp_alltoall_i22                    720 14.1    5.609    9.520    5.609    9.520
 pw_transfer                       1559 11.6    0.088    0.103    9.387    9.457
 fft_wrap_pw1pw2                   1301 12.7    0.010    0.012    9.159    9.235
 density_rs2pw                      129  9.7    0.006    0.006    7.184    8.704
 fft_wrap_pw1pw2_140                527 13.2    1.579    1.620    8.129    8.208
 grid_integrate_task_list           129 12.3    7.583    8.021    7.583    8.021
 wfi_extrapolate                     11  7.9    0.001    0.001    7.845    7.845
 cp_fm_cholesky_decompose            22 10.9    7.566    7.651    7.566    7.651
 multiply_cannon_metrocomm4       25340 15.6    0.084    0.095    2.761    7.299
 mp_irecv_dv                      76866 16.2    2.605    7.018    2.605    7.018
 calculate_dm_sparse                129  9.5    0.001    0.001    6.328    6.403
 rs_pw_transfer                    1054 12.0    0.013    0.014    4.803    6.402
 fft3d_ps                          1301 14.7    2.849    2.926    6.048    6.104
 grid_collocate_task_list           129  9.7    5.185    5.927    5.185    5.927
 mp_alltoall_d11v                  2429 14.1    5.196    5.862    5.196    5.862
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.550    5.619
 potential_pw2rs                    129 12.3    0.024    0.024    4.665    4.678
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    4.504    4.605
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.433    4.501
 qs_energies_init_hamiltonians       11  5.9    0.002    0.004    4.494    4.497
 qs_ot_get_orbitals                 118 10.6    0.001    0.001    4.312    4.376
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="406", plot="h2o_256_md", label="(8n/3r/4t)", y=192.415000, yerr=0.000000
PlotPoint: name="407", plot="h2o_256_md_mem", label="(8n/3r/4t)", y=1092.909091, yerr=15.687022
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/19/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420242647040       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528903135232       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514766E+12       0.0%      0.0%    100.0%
 flops max/rank                      5.865089E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755941440       0.0%      0.0%    100.0%
 number of processed stacks               1960712       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    3445.7
 marketing flops                   144.579337E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank               1.544106E+09
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  240672
 MPI messages size (bytes):
  total size                         1.331455E+12
  min size                           0.000000E+00
  max size                          52.428800E+06
  average size                       5.532238E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                 132                  8650752
    131072 < size <=  4194304              113904              59718500352
   4194304 < size <= 16777216              104976             550376570880
  16777216 < size                           20208             721350232272
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         8931                     51.
 MP_Alltoall          9654                 799394.
 MP_ISend            40068                2102573.
 MP_IRecv            40068                2101676.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4002                  58203.
 MP_Allreduce        11082                   1166.
 MP_Sync                87
 MP_Alltoall          1712               18838222.
 MP_SendRecv          3840                 122880.
 MP_ISendRecv         3840                 122880.
 MP_Wait             16122
 MP_ISend            10680                 423556.
 MP_IRecv            10680                 423556.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.016    0.034  178.984  178.986
 qs_mol_dyn_low                       1  2.0    0.003    0.003  178.560  178.574
 qs_forces                           11  3.9    0.004    0.005  178.371  178.373
 qs_energies                         11  4.9    0.002    0.002  170.647  170.655
 scf_env_do_scf                      11  5.9    0.001    0.001  152.872  152.875
 velocity_verlet                     10  3.0    0.005    0.012  117.429  117.438
 scf_env_do_scf_inner_loop          117  6.6    0.004    0.009  115.613  115.614
 qs_scf_new_mos                     117  7.6    0.001    0.001   75.896   76.000
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   75.895   75.999
 dbcsr_multiply_generic            2507 12.6    0.181    0.193   73.804   74.256
 ot_scf_mini                        117  9.6    0.004    0.004   71.374   71.475
 multiply_cannon                   2507 13.6    0.557    0.594   53.896   57.457
 multiply_cannon_loop              2507 14.6    0.803    0.843   50.837   51.668
 ot_mini                            117 10.6    0.001    0.001   38.748   38.838
 init_scf_loop                       11  6.9    0.000    0.000   37.104   37.106
 prepare_preconditioner              11  7.9    0.000    0.000   33.106   33.130
 make_preconditioner                 11  8.9    0.000    0.000   33.106   33.130
 mp_waitall_1                    125778 16.7   25.847   32.077   25.847   32.077
 make_full_inverse_cholesky          11  9.9    0.012    0.026   30.930   31.258
 rebuild_ks_matrix                  128  8.3    0.001    0.001   30.610   30.680
 qs_ks_build_kohn_sham_matrix       128  9.3    0.017    0.018   30.609   30.680
 qs_ks_update_qs_env                128  7.6    0.001    0.001   27.767   27.832
 qs_ot_get_derivative               117 11.6    0.002    0.002   21.653   21.754
 multiply_cannon_multrec          10028 15.6   10.386   14.240   17.961   20.898
 qs_ot_get_p                        128 10.4    0.001    0.001   19.660   19.766
 multiply_cannon_metrocomm3       10028 15.6    0.026    0.028   12.431   19.584
 cp_fm_cholesky_invert               11 10.9   18.988   18.995   18.988   18.995
 apply_preconditioner_dbcsr         128 12.6    0.000    0.000   17.062   17.217
 apply_single                       128 13.6    0.001    0.001   17.062   17.216
 ot_diis_step                       117 11.6    0.020    0.022   17.024   17.025
 make_m2s                          5014 13.6    0.065    0.069   15.663   16.516
 make_images                       5014 14.6    2.174    2.602   15.358   16.213
 qs_rho_update_rho_low              128  7.7    0.001    0.001   16.012   16.049
 calculate_rho_elec                 128  8.7    0.256    0.267   16.012   16.048
 qs_ot_p2m_diag                      83 11.4    0.495    0.500   15.552   15.567
 sum_up_and_integrate               128 10.3    0.180    0.190   15.415   15.464
 integrate_v_rspace                 128 11.3    0.004    0.004   15.235   15.293
 cp_dbcsr_syevd                      83 12.4    0.005    0.006   14.313   14.314
 cp_fm_diag_elpa                     83 13.4    0.026    0.064   11.306   11.318
 cp_fm_diag_elpa_base                83 14.4   10.971   11.080   11.234   11.247
 multiply_cannon_sync_h2d         10028 15.6   10.882   11.147   10.882   11.147
 init_scf_run                        11  5.9    0.000    0.001   10.831   10.831
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   10.830   10.831
 make_images_data                  5014 15.6    0.056    0.066    9.060   10.542
 hybrid_alltoall_any               5200 16.5    0.844    3.784    8.789   10.287
 pw_transfer                       1547 11.6    0.086    0.095   10.010   10.039
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.011    9.785    9.821
 qs_ot_get_derivative_diag           77 12.4    0.002    0.003    8.606    8.672
 fft_wrap_pw1pw2_140                523 13.2    1.922    1.956    8.521    8.554
 cp_fm_cholesky_decompose            22 10.9    8.357    8.490    8.357    8.490
 density_rs2pw                      128  9.7    0.006    0.006    7.351    8.269
 grid_integrate_task_list           128 12.3    7.733    8.168    7.733    8.168
 multiply_cannon_metrocomm1       10028 15.6    0.030    0.031    5.032    8.120
 dbcsr_mm_accdrv_process          20762 16.1    3.281    4.492    7.223    7.913
 wfi_extrapolate                     11  7.9    0.001    0.001    7.792    7.792
 mp_alltoall_d11v                  2415 14.1    5.460    6.561    5.460    6.561
 calculate_dm_sparse                128  9.5    0.001    0.001    6.200    6.285
 fft3d_ps                          1291 14.7    2.764    2.843    6.247    6.283
 grid_collocate_task_list           128  9.7    5.480    6.177    5.480    6.177
 dbcsr_complete_redistribute        395 12.7    2.104    2.183    5.489    5.882
 rs_pw_transfer                    1046 11.9    0.012    0.013    4.454    5.384
 qs_energies_init_hamiltonians       11  5.9    0.002    0.002    5.372    5.373
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.251    5.278
 mp_allgather_i34                  2507 14.6    1.250    4.936    1.250    4.936
 potential_pw2rs                    128 12.3    0.026    0.026    4.684    4.699
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.106    4.164
 copy_fm_to_dbcsr                   209 11.7    0.002    0.002    3.552    3.928
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    3.591    3.910
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    3.842    3.894
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    3.761    3.773
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    3.673    3.709
 copy_dbcsr_to_fm                   186 11.8    0.004    0.004    3.546    3.637
 multiply_cannon_metrocomm4        7521 15.6    0.026    0.028    1.748    3.616
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="408", plot="h2o_256_md", label="(8n/2r/6t)", y=178.986000, yerr=0.000000
PlotPoint: name="409", plot="h2o_256_md_mem", label="(8n/2r/6t)", y=1446.545455, yerr=28.049838
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/20/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1410022950912       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1924145348608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1957871443968       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1963544850432       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2714615709696       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4377645416448       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5350455508992       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5395653328896       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6594687401984       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11444706349056       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15019187724288       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15019187724288       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19624853225472       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        92.796577E+12       0.0%      0.0%    100.0%
 flops max/rank                     11.606413E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6705500544       0.0%      0.0%    100.0%
 number of processed stacks               1947808       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    3442.6
 marketing flops                   143.507742E+12
 -------------------------------------------------------------------------------
 # multiplications                           2485
 max memory usage/rank               3.131261E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                   99400
 MPI messages size (bytes):
  total size                         1.127422E+12
  min size                           0.000000E+00
  max size                         104.857600E+06
  average size                      11.342272E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                 572                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                  44                  2883584
    131072 < size <=  4194304               44768              34745614336
   4194304 < size <= 16777216               43984             376564613120
  16777216 < size                           10032             716108613552
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3955                  59814.
 MP_Allreduce        10965                   1506.
 MP_Sync                86
 MP_Alltoall          1700               36954426.
 MP_SendRecv          1778                 218624.
 MP_ISendRecv         1778                 218624.
 MP_Wait              9728
 MP_ISend             6360                1080477.
 MP_IRecv             6360                1080477.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.035    0.058  308.571  308.574
 qs_mol_dyn_low                       1  2.0    0.003    0.004  307.988  308.007
 qs_forces                           11  3.9    0.004    0.005  307.871  307.876
 qs_energies                         11  4.9    0.002    0.002  298.253  298.267
 scf_env_do_scf                      11  5.9    0.001    0.001  274.900  274.909
 velocity_verlet                     10  3.0    0.002    0.002  220.786  220.795
 scf_env_do_scf_inner_loop          116  6.6    0.003    0.008  147.282  147.284
 init_scf_loop                       11  6.9    0.000    0.000  127.326  127.329
 prepare_preconditioner              11  7.9    0.000    0.000  122.082  122.102
 make_preconditioner                 11  8.9    0.000    0.000  122.082  122.102
 make_full_inverse_cholesky          11  9.9    0.038    0.039   98.177  119.159
 qs_scf_new_mos                     116  7.6    0.001    0.001   96.128   96.250
 qs_scf_loop_do_ot                  116  8.6    0.001    0.001   96.127   96.249
 ot_scf_mini                        116  9.6    0.004    0.004   91.159   91.249
 dbcsr_multiply_generic            2485 12.5    0.211    0.222   85.526   86.155
 cp_fm_upper_to_full                104 14.8   53.042   75.827   53.042   75.827
 multiply_cannon                   2485 13.5    0.681    0.706   60.611   62.020
 multiply_cannon_loop              2485 14.5    1.038    1.061   56.441   58.304
 ot_mini                            116 10.6    0.001    0.001   46.745   46.875
 dbcsr_complete_redistribute        393 12.7    4.004    4.039   30.058   42.759
 copy_fm_to_dbcsr                   208 11.6    0.001    0.002   26.421   39.079
 rebuild_ks_matrix                  127  8.3    0.001    0.001   38.623   38.712
 qs_ks_build_kohn_sham_matrix       127  9.3    0.017    0.018   38.623   38.711
 transfer_fm_to_dbcsr                11  9.9    0.030    0.030   23.862   36.309
 qs_ks_update_qs_env                127  7.6    0.001    0.001   35.371   35.457
 cp_fm_cholesky_invert               11 10.9   35.295   35.302   35.295   35.302
 mp_waitall_1                    102768 16.8   30.906   35.104   30.906   35.104
 mp_alltoall_i22                    712 14.1   21.632   34.374   21.632   34.374
 qs_ot_get_p                        127 10.4    0.001    0.001   29.006   29.217
 qs_ot_get_derivative               116 11.6    0.002    0.002   26.238   26.333
 qs_ot_p2m_diag                      82 11.4    0.868    0.874   24.486   24.522
 cp_dbcsr_syevd                      82 12.4    0.006    0.006   22.612   22.614
 multiply_cannon_metrocomm3        9940 15.5    0.025    0.027   20.625   22.543
 make_m2s                          4970 13.5    0.074    0.078   19.752   21.305
 qs_rho_update_rho_low              127  7.7    0.001    0.001   21.092   21.109
 calculate_rho_elec                 127  8.7    0.477    0.478   21.092   21.108
 make_images                       4970 14.5    3.043    3.225   19.278   20.834
 ot_diis_step                       116 11.6    0.022    0.022   20.456   20.458
 sum_up_and_integrate               127 10.3    0.319    0.323   20.046   20.128
 apply_preconditioner_dbcsr         127 12.6    0.000    0.000   19.719   19.970
 apply_single                       127 13.6    0.001    0.001   19.718   19.970
 integrate_v_rspace                 127 11.3    0.004    0.004   19.727   19.810
 cp_fm_diag_elpa                     82 13.4    0.001    0.001   19.240   19.242
 cp_fm_diag_elpa_base                82 14.4   14.808   16.355   19.234   19.235
 multiply_cannon_multrec           9940 15.5   10.265   12.072   17.980   18.072
 multiply_cannon_sync_h2d          9940 15.5   14.206   14.240   14.206   14.240
 hybrid_alltoall_any               5155 16.4    1.302    3.021   11.436   13.813
 make_images_data                  4970 15.5    0.063    0.067   11.387   13.812
 init_scf_run                        11  5.9    0.000    0.001   12.834   12.836
 scf_env_initial_rho_setup           11  6.9    0.001    0.002   12.833   12.836
 pw_transfer                       1535 11.6    0.092    0.093   12.135   12.143
 fft_wrap_pw1pw2                   1281 12.7    0.011    0.011   11.902   11.910
 fft_wrap_pw1pw2_140                519 13.2    3.106    3.161   10.492   10.507
 qs_ot_get_derivative_diag           76 12.4    0.002    0.003   10.405   10.473
 cp_fm_cholesky_decompose            22 10.9    9.666    9.690    9.666    9.690
 wfi_extrapolate                     11  7.9    0.001    0.001    9.659    9.659
 dbcsr_mm_accdrv_process          20590 16.0    4.185    6.077    7.468    9.312
 mp_alltoall_d11v                  2401 14.1    8.560    9.197    8.560    9.197
 grid_integrate_task_list           127 12.3    8.553    8.750    8.553    8.750
 density_rs2pw                      127  9.7    0.005    0.005    8.465    8.607
 qs_energies_init_hamiltonians       11  5.9    0.002    0.003    8.242    8.244
 fft3d_ps                          1281 14.7    2.829    2.842    6.958    7.030
 calculate_dm_sparse                127  9.5    0.001    0.001    6.848    6.923
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.514    6.585
 grid_collocate_task_list           127  9.7    6.415    6.488    6.415    6.488
 copy_dbcsr_to_fm                   185 11.7    0.004    0.004    6.372    6.434
 rs_scatter_matrices                138  9.7    3.929    4.806    6.207    6.405
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="410", plot="h2o_256_md", label="(8n/1r/12t)", y=308.574000, yerr=0.000000
PlotPoint: name="411", plot="h2o_256_md_mem", label="(8n/1r/12t)", y=2845.181818, yerr=149.763339
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/21/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    23 x    23 x    23      234439235724792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                       234.439236E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.766000E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         9634225188       0.0%      0.0%    100.0%
 number of processed stacks                419739       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0   22952.9
 marketing flops                     1.742116E+15
 -------------------------------------------------------------------------------
 # multiplications                            111
 max memory usage/rank               1.259610E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                  458208
 MPI messages size (bytes):
  total size                         3.456111E+12
  min size                           0.000000E+00
  max size                          18.735064E+06
  average size                       7.542668E+06
 MPI breakdown and total messages size (bytes):
             size <=      128              112896                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 224                  5687808
     32768 < size <=   131072               10528                813356544
    131072 < size <=  4194304               36422              76284728544
   4194304 < size <= 16777216              294266            3312457683808
  16777216 < size                            3872              66548597808
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 255646.
 MP_Allreduce         3139                   6114.
 MP_Sync                 4
 MP_Alltoall            54
 MP_SendRecv           285                  19200.
 MP_ISendRecv          285                  19200.
 MP_Wait              1017
 MP_ISend              642                 197829.
 MP_IRecv              642                 197607.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.045    0.161   85.641   85.643
 qs_energies                          1  2.0    0.001    0.006   84.854   84.871
 ls_scf                               1  3.0    0.000    0.000   83.777   83.784
 dbcsr_multiply_generic             111  6.7    0.014    0.015   72.520   72.706
 multiply_cannon                    111  7.7    0.017    0.020   55.778   57.089
 multiply_cannon_loop               111  8.7    0.223    0.243   52.391   53.839
 ls_scf_main                          1  4.0    0.000    0.000   52.364   52.364
 density_matrix_trs4                  2  5.0    0.002    0.003   46.763   46.871
 ls_scf_init_scf                      1  4.0    0.000    0.000   28.348   28.349
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   27.131   27.185
 mp_waitall_1                     11031 10.9   22.336   25.652   22.336   25.652
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   24.966   24.979
 multiply_cannon_multrec           2664  9.7    8.145    8.856   15.577   17.373
 multiply_cannon_sync_h2d          2664  9.7   13.613   15.710   13.613   15.710
 make_m2s                           222  7.7    0.009    0.011   13.111   13.553
 make_images                        222  8.7    0.098    0.108   13.089   13.531
 multiply_cannon_metrocomm1        2664  9.7    0.010    0.011    9.633   13.033
 multiply_cannon_metrocomm3        2664  9.7    0.009    0.011    5.365    8.201
 make_images_data                   222  9.7    0.004    0.005    7.663    8.114
 dbcsr_mm_accdrv_process           4760 10.4    0.586    0.715    7.049    8.078
 hybrid_alltoall_any                227 10.6    0.215    1.841    6.634    7.867
 dbcsr_mm_accdrv_process_sort      4760 11.4    6.263    7.182    6.263    7.182
 calculate_norms                   4752  9.8    5.509    6.215    5.509    6.215
 apply_matrix_preconditioner          6  5.3    0.010    0.068    5.088    5.226
 mp_sum_l                           887  5.1    3.102    4.522    3.102    4.522
 make_images_sizes                  222  9.7    0.000    0.000    0.697    3.787
 mp_alltoall_i44                    222 10.7    0.697    3.787    0.697    3.787
 multiply_cannon_metrocomm4        2442  9.7    0.012    0.014    2.043    3.477
 mp_irecv_dv                       6231 10.9    2.027    3.450    2.027    3.450
 arnoldi_extremal                     4  6.8    0.000    0.000    3.316    3.337
 arnoldi_normal_ev                    4  7.8    0.001    0.003    3.316    3.337
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    2.273    3.221
 build_subspace                      16  8.4    0.009    0.012    3.217    3.220
 ls_scf_post                          1  4.0    0.000    0.000    3.065    3.071
 ls_scf_store_result                  1  5.0    0.000    0.000    2.880    2.920
 dbcsr_special_finalize             555  9.7    0.005    0.006    2.399    2.747
 dbcsr_merge_single_wm              555 10.7    0.458    0.584    2.390    2.738
 dbcsr_matrix_vector_mult           304  9.0    0.006    0.013    2.363    2.643
 make_images_pack                   222  9.7    2.205    2.632    2.206    2.633
 dbcsr_matrix_vector_mult_local     304 10.0    2.068    2.506    2.070    2.508
 dbcsr_sort_data                    658 11.4    2.190    2.499    2.190    2.499
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.359    2.460
 buffer_matrices_ensure_size        222  8.7    1.766    2.064    1.766    2.064
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.854    1.855
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.845    1.846
 qs_ks_build_kohn_sham_matrix         3  8.3    0.019    0.032    1.845    1.846
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="500", plot="h2o_32_nrep3_ls", label="(8n/12r/1t)", y=85.643000, yerr=0.000000
PlotPoint: name="501", plot="h2o_32_nrep3_ls_mem", label="(8n/12r/1t)", y=1140.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/22/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    23 x    23 x    23      234439235724792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                       234.439236E+12       0.0%      0.0%    100.0%
 flops max/rank                      5.588524E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         9634225188       0.0%      0.0%    100.0%
 number of processed stacks                368848       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0   26119.8
 marketing flops                     1.742116E+15
 -------------------------------------------------------------------------------
 # multiplications                            111
 max memory usage/rank               2.191389E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                  106560
 MPI messages size (bytes):
  total size                         2.699093E+12
  min size                           0.000000E+00
  max size                          72.286792E+06
  average size                      25.329324E+06
 MPI breakdown and total messages size (bytes):
             size <=      128               23040                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                3264                325830144
    131072 < size <=  4194304                5280               3328561104
   4194304 < size <= 16777216               12709             156766962056
  16777216 < size                           62267            2538670978840
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 266673.
 MP_Allreduce         3138                  10075.
 MP_Sync                 4
 MP_Alltoall            47               15335933.
 MP_SendRecv           141                  57600.
 MP_ISendRecv          141                  57600.
 MP_Wait               687
 MP_ISend              462                 414589.
 MP_IRecv              462                 413870.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.056    0.081   91.256   91.257
 qs_energies                          1  2.0    0.000    0.000   90.522   90.549
 ls_scf                               1  3.0    0.002    0.009   89.050   89.076
 dbcsr_multiply_generic             111  6.7    0.017    0.033   74.895   75.186
 multiply_cannon                    111  7.7    0.027    0.040   52.885   57.423
 ls_scf_main                          1  4.0    0.002    0.027   55.134   55.139
 multiply_cannon_loop               111  8.7    0.135    0.146   50.009   53.388
 density_matrix_trs4                  2  5.0    0.003    0.007   49.389   49.591
 mp_waitall_1                      9105 10.9   21.179   30.823   21.179   30.823
 ls_scf_init_scf                      1  4.0    0.000    0.001   30.200   30.202
 ls_scf_init_matrix_S                 1  5.0    0.000    0.001   28.909   28.997
 multiply_cannon_multrec           1332  9.7   13.209   16.874   22.536   27.377
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   26.489   26.498
 multiply_cannon_metrocomm3        1332  9.7    0.007    0.008   11.656   20.751
 make_m2s                           222  7.7    0.008    0.018   15.369   15.991
 make_images                        222  8.7    1.373    1.701   15.337   15.961
 dbcsr_mm_accdrv_process           4041 10.4    0.324    0.505    8.924   10.499
 dbcsr_mm_accdrv_process_sort      4041 11.4    8.444    9.970    8.444    9.970
 make_images_data                   222  9.7    0.004    0.005    8.989    9.877
 hybrid_alltoall_any                227 10.6    0.541    2.547    8.340    9.726
 mp_sum_l                           887  5.1    5.164    8.416    5.164    8.416
 multiply_cannon_metrocomm4        1221  9.7    0.007    0.009    3.200    7.656
 mp_irecv_dv                       3311 11.0    3.180    7.605    3.180    7.605
 calculate_norms                   2376  9.8    6.060    6.653    6.060    6.653
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.934    6.626
 multiply_cannon_sync_h2d          1332  9.7    4.875    6.368    4.875    6.368
 apply_matrix_preconditioner          6  5.3    0.001    0.001    4.946    5.154
 arnoldi_extremal                     4  6.8    0.000    0.000    4.757    4.773
 arnoldi_normal_ev                    4  7.8    0.002    0.006    4.757    4.773
 build_subspace                      16  8.4    0.014    0.021    4.503    4.506
 ls_scf_post                          1  4.0    0.007    0.030    3.714    3.734
 ls_scf_store_result                  1  5.0    0.000    0.000    3.418    3.525
 dbcsr_matrix_vector_mult           304  9.0    0.010    0.022    3.175    3.402
 dbcsr_matrix_vector_mult_local     304 10.0    2.754    3.238    2.756    3.240
 mp_allgather_i34                   111  8.7    0.862    3.161    0.862    3.161
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.004    1.180    2.812
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.655    2.743
 dbcsr_data_new                    4174 10.1    2.117    2.402    2.117    2.402
 make_images_pack                   222  9.7    1.823    2.128    1.826    2.131
 dbcsr_sort_data                    436 11.2    1.841    2.069    1.841    2.069
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.950    1.952
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.936    1.938
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.002    1.936    1.938
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="502", plot="h2o_32_nrep3_ls", label="(8n/6r/2t)", y=91.257000, yerr=0.000000
PlotPoint: name="503", plot="h2o_32_nrep3_ls_mem", label="(8n/6r/2t)", y=1774.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/23/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    23 x    23 x    23      234439235724792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                       234.439236E+12       0.0%      0.0%    100.0%
 flops max/rank                      8.404608E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         9634225188       0.0%      0.0%    100.0%
 number of processed stacks                353133       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0   27282.1
 marketing flops                     1.742118E+15
 -------------------------------------------------------------------------------
 # multiplications                            111
 max memory usage/rank               2.936717E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                   46176
 MPI messages size (bytes):
  total size                         1.924064E+12
  min size                           0.000000E+00
  max size                         108.059888E+06
  average size                      41.668048E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                9984                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304                3328               1170063360
   4194304 < size <= 16777216                1870              19378539600
  16777216 < size                           30994            1903514987232
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 265448.
 MP_Allreduce         3138                  10896.
 MP_Sync                 4
 MP_Alltoall            47               23526250.
 MP_SendRecv            93                  57600.
 MP_ISendRecv           93                  57600.
 MP_Wait               639
 MP_ISend              462                 560046.
 MP_IRecv              462                 560662.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.030    0.048   92.742   92.744
 qs_energies                          1  2.0    0.000    0.000   92.163   92.167
 ls_scf                               1  3.0    0.000    0.000   90.747   90.751
 dbcsr_multiply_generic             111  6.7    0.016    0.016   75.509   75.802
 ls_scf_main                          1  4.0    0.000    0.000   56.711   56.715
 multiply_cannon                    111  7.7    0.030    0.055   52.171   55.961
 multiply_cannon_loop               111  8.7    0.116    0.130   49.398   53.904
 density_matrix_trs4                  2  5.0    0.002    0.003   50.824   51.022
 mp_waitall_1                      7281 11.0   23.539   33.454   23.539   33.454
 ls_scf_init_scf                      1  4.0    0.000    0.000   30.347   30.349
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   29.150   29.220
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   26.781   26.798
 multiply_cannon_multrec            888  9.7   12.676   15.457   21.283   24.627
 multiply_cannon_metrocomm3         888  9.7    0.004    0.004   11.124   23.347
 make_m2s                           222  7.7    0.006    0.006   16.391   17.136
 make_images                        222  8.7    1.585    1.853   16.353   17.098
 make_images_data                   222  9.7    0.004    0.004    9.481   10.662
 hybrid_alltoall_any                227 10.6    0.642    2.944    8.987   10.285
 dbcsr_mm_accdrv_process           3754 10.4    0.303    0.488    8.141    9.375
 dbcsr_mm_accdrv_process_sort      3754 11.4    7.708    8.887    7.708    8.887
 mp_sum_l                           887  5.1    5.234    8.856    5.234    8.856
 multiply_cannon_sync_h2d           888  9.7    6.069    7.365    6.069    7.365
 multiply_cannon_metrocomm4         777  9.7    0.004    0.005    2.512    7.146
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    4.081    7.124
 mp_irecv_dv                       2335 11.1    2.495    7.077    2.495    7.077
 multiply_cannon_metrocomm1         888  9.7    0.003    0.003    3.582    6.778
 arnoldi_extremal                     4  6.8    0.000    0.000    5.043    5.064
 arnoldi_normal_ev                    4  7.8    0.001    0.005    5.042    5.064
 apply_matrix_preconditioner          6  5.3    0.001    0.002    4.745    4.979
 calculate_norms                   1584  9.8    4.357    4.833    4.357    4.833
 build_subspace                      16  8.4    0.014    0.020    4.739    4.746
 mp_allgather_i34                   111  8.7    0.892    3.850    0.892    3.850
 dbcsr_matrix_vector_mult           304  9.0    0.010    0.021    3.440    3.760
 ls_scf_post                          1  4.0    0.000    0.000    3.690    3.694
 dbcsr_matrix_vector_mult_local     304 10.0    3.037    3.605    3.039    3.606
 ls_scf_store_result                  1  5.0    0.000    0.000    3.423    3.516
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.861    2.958
 dbcsr_data_new                    4116  9.9    2.107    2.443    2.107    2.443
 make_images_sizes                  222  9.7    0.000    0.000    1.077    2.318
 mp_alltoall_i44                    222 10.7    1.077    2.318    1.077    2.318
 dbcsr_sort_data                    325 11.1    1.879    2.119    1.879    2.119
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.908    1.910
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.890    1.892
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.001    1.890    1.892
 make_images_pack                   222  9.7    1.632    1.883    1.635    1.886
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="504", plot="h2o_32_nrep3_ls", label="(8n/4r/3t)", y=92.744000, yerr=0.000000
PlotPoint: name="505", plot="h2o_32_nrep3_ls_mem", label="(8n/4r/3t)", y=2244.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/24/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    23 x    23 x    23      234439235724792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                       234.439236E+12       0.0%      0.0%    100.0%
 flops max/rank                     10.747127E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         9634225188       0.0%      0.0%    100.0%
 number of processed stacks                369794       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0   26053.0
 marketing flops                     1.742116E+15
 -------------------------------------------------------------------------------
 # multiplications                            111
 max memory usage/rank               3.358409E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                   50616
 MPI messages size (bytes):
  total size                         1.536549E+12
  min size                           0.000000E+00
  max size                          72.286792E+06
  average size                      30.356986E+06
 MPI breakdown and total messages size (bytes):
             size <=      128               10368                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                1056                104411904
    131072 < size <=  4194304                3168                831638784
   4194304 < size <= 16777216                3103              33613273640
  16777216 < size                           32921            1501999894888
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 266673.
 MP_Allreduce         3138                  13030.
 MP_Sync                 4
 MP_Alltoall            47               30278988.
 MP_SendRecv            69                  86400.
 MP_ISendRecv           69                  86400.
 MP_Wait               531
 MP_ISend              378                 823502.
 MP_IRecv              378                 823753.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.047    0.150   97.071   97.072
 qs_energies                          1  2.0    0.000    0.000   96.236   96.243
 ls_scf                               1  3.0    0.000    0.001   94.537   94.544
 dbcsr_multiply_generic             111  6.7    0.017    0.023   78.156   78.451
 ls_scf_main                          1  4.0    0.005    0.045   58.685   58.686
 multiply_cannon                    111  7.7    0.044    0.117   51.499   55.987
 density_matrix_trs4                  2  5.0    0.002    0.004   52.541   52.667
 multiply_cannon_loop               111  8.7    0.153    0.169   46.425   48.905
 ls_scf_init_scf                      1  4.0    0.000    0.001   32.580   32.582
 ls_scf_init_matrix_S                 1  5.0    0.000    0.001   31.364   31.422
 mp_waitall_1                      6369 11.0   22.568   29.104   22.568   29.104
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   28.847   28.862
 multiply_cannon_multrec           1332  9.7   14.090   17.080   22.027   24.637
 make_m2s                           222  7.7    0.007    0.008   21.118   22.614
 make_images                        222  8.7    3.146    3.610   21.067   22.566
 multiply_cannon_metrocomm3        1332  9.7    0.003    0.004    9.138   16.857
 make_images_data                   222  9.7    0.004    0.005   11.803   13.398
 hybrid_alltoall_any                227 10.6    0.798    3.758   11.164   13.044
 dbcsr_mm_accdrv_process           3641 10.4    0.287    0.481    7.591    9.125
 dbcsr_mm_accdrv_process_sort      3641 11.4    7.151    8.631    7.151    8.631
 mp_sum_l                           887  5.1    3.963    7.532    3.963    7.532
 multiply_cannon_sync_h2d          1332  9.7    5.430    6.090    5.430    6.090
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.033    5.981
 multiply_cannon_metrocomm4        1110  9.7    0.005    0.007    2.092    5.927
 mp_irecv_dv                       3229 10.9    2.067    5.848    2.067    5.848
 arnoldi_extremal                     4  6.8    0.000    0.000    5.290    5.308
 arnoldi_normal_ev                    4  7.8    0.001    0.005    5.289    5.308
 build_subspace                      16  8.4    0.014    0.021    4.942    4.952
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.003    2.460    4.830
 mp_allgather_i34                   111  8.7    2.191    4.728    2.191    4.728
 apply_matrix_preconditioner          6  5.3    0.001    0.001    4.533    4.696
 calculate_norms                   2376  9.8    4.172    4.478    4.172    4.478
 dbcsr_matrix_vector_mult           304  9.0    0.010    0.021    3.637    3.944
 dbcsr_matrix_vector_mult_local     304 10.0    3.213    3.712    3.215    3.714
 dbcsr_sort_data                    658 11.4    3.065    3.414    3.065    3.414
 ls_scf_post                          1  4.0    0.000    0.001    3.272    3.278
 dbcsr_special_finalize             555  9.7    0.006    0.007    2.825    3.195
 dbcsr_merge_single_wm              555 10.7    0.544    0.664    2.816    3.186
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    3.051    3.101
 ls_scf_store_result                  1  5.0    0.000    0.000    3.000    3.075
 dbcsr_data_release               10477 10.7    1.576    2.424    1.576    2.424
 dbcsr_finalize                     304  7.8    0.049    0.061    1.804    1.983
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.941    1.943
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="506", plot="h2o_32_nrep3_ls", label="(8n/3r/4t)", y=97.072000, yerr=0.000000
PlotPoint: name="507", plot="h2o_32_nrep3_ls_mem", label="(8n/3r/4t)", y=2717.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/25/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    23 x    23 x    23      234439235724792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                       234.439236E+12       0.0%      0.0%    100.0%
 flops max/rank                     15.383312E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         9634225188       0.0%      0.0%    100.0%
 number of processed stacks                336818       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0   28603.7
 marketing flops                     1.742118E+15
 -------------------------------------------------------------------------------
 # multiplications                            111
 max memory usage/rank               4.750553E+09
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                   10656
 MPI messages size (bytes):
  total size                         1.149035E+12
  min size                           0.000000E+00
  max size                         203.538048E+06
  average size                     107.829832E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                2304                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304                 768                702038016
   4194304 < size <= 16777216                   0                        0
  16777216 < size                            7584            1148332810224
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast                2                     12.
 MP_Allreduce          705                    128.
 MP_Alltoall           310               12920694.
 MP_ISend             1776               40180424.
 MP_IRecv             1776               40465030.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 265536.
 MP_Allreduce         3129                  15263.
 MP_Sync                 4
 MP_Alltoall            47               46208988.
 MP_SendRecv            45                 115200.
 MP_ISendRecv           45                 115200.
 MP_Wait               528
 MP_ISend              420                 924980.
 MP_IRecv              420                 924528.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.146    0.178   92.533   92.548
 qs_energies                          1  2.0    0.000    0.000   91.405   91.410
 ls_scf                               1  3.0    0.000    0.000   89.460   89.465
 dbcsr_multiply_generic             111  6.7    0.017    0.018   70.922   71.105
 ls_scf_main                          1  4.0    0.000    0.000   56.759   56.760
 multiply_cannon                    111  7.7    0.055    0.102   52.872   55.945
 multiply_cannon_loop               111  8.7    0.088    0.096   50.255   51.666
 density_matrix_trs4                  2  5.0    0.002    0.003   49.714   49.798
 ls_scf_init_scf                      1  4.0    0.000    0.000   29.255   29.256
 mp_waitall_1                      5436 11.0   24.646   28.373   24.646   28.373
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   27.980   28.016
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   25.894   25.906
 multiply_cannon_multrec            444  9.7   13.596   16.574   20.721   22.164
 multiply_cannon_metrocomm1         444  9.7    0.002    0.002   10.864   15.534
 make_m2s                           222  7.7    0.005    0.005   13.464   14.435
 make_images                        222  8.7    2.041    2.488   13.397   14.368
 multiply_cannon_metrocomm3         444  9.7    0.001    0.001    6.391   13.080
 make_images_data                   222  9.7    0.003    0.004    8.210    9.679
 hybrid_alltoall_any                227 10.6    0.801    3.801    8.127    9.643
 dbcsr_mm_accdrv_process           3003 10.4    0.351    0.396    6.820    7.950
 multiply_cannon_sync_h2d           444  9.7    6.723    7.661    6.723    7.661
 dbcsr_mm_accdrv_process_sort      3003 11.4    6.457    7.554    6.457    7.554
 arnoldi_extremal                     4  6.8    0.000    0.000    5.852    5.867
 arnoldi_normal_ev                    4  7.8    0.002    0.005    5.852    5.866
 build_subspace                      16  8.4    0.015    0.020    5.453    5.458
 apply_matrix_preconditioner          6  5.3    0.001    0.002    4.412    4.620
 mp_sum_l                           887  5.1    2.609    4.524    2.609    4.524
 dbcsr_matrix_vector_mult           304  9.0    0.011    0.021    4.169    4.374
 dbcsr_matrix_vector_mult_local     304 10.0    3.710    4.183    3.712    4.185
 multiply_cannon_metrocomm4         333  9.7    0.001    0.002    1.578    3.909
 mp_irecv_dv                       1241 11.2    1.562    3.872    1.562    3.872
 mp_allgather_i34                   111  8.7    1.192    3.768    1.192    3.768
 calculate_norms                    792  9.8    3.635    3.756    3.635    3.756
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    3.610    3.668
 ls_scf_post                          1  4.0    0.000    0.000    3.446    3.451
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    1.802    3.372
 ls_scf_store_result                  1  5.0    0.000    0.000    3.236    3.271
 make_images_sizes                  222  9.7    0.000    0.000    0.865    3.168
 mp_alltoall_i44                    222 10.7    0.865    3.168    0.865    3.168
 dbcsr_finalize                     304  7.8    0.062    0.076    2.197    2.290
 dbcsr_data_new                    4608  9.7    1.822    2.283    1.822    2.283
 dbcsr_merge_all                    275  8.9    0.478    0.526    2.055    2.142
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.099    2.100
 rebuild_ks_matrix                    3  7.3    0.000    0.000    2.067    2.068
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.002    2.067    2.068
 qs_energies_init_hamiltonians        1  3.0    0.001    0.001    1.929    1.929
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="508", plot="h2o_32_nrep3_ls", label="(8n/2r/6t)", y=92.548000, yerr=0.000000
PlotPoint: name="509", plot="h2o_32_nrep3_ls_mem", label="(8n/2r/6t)", y=3736.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/26/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    23 x    23 x    23      234439235724792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                       234.439236E+12       0.0%      0.0%    100.0%
 flops max/rank                     30.358840E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         9634225188       0.0%      0.0%    100.0%
 number of processed stacks                339931       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0   28341.7
 marketing flops                     1.742118E+15
 -------------------------------------------------------------------------------
 # multiplications                            111
 max memory usage/rank               8.824254E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                    4440
 MPI messages size (bytes):
  total size                       770.525954E+09
  min size                           0.000000E+00
  max size                         399.069120E+06
  average size                     173.541888E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                 640                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304                 640                468025344
   4194304 < size <= 16777216                   0                        0
  16777216 < size                            3160             770057961712
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 284089.
 MP_Allreduce         3123                  21388.
 MP_Sync                 4
 MP_Alltoall            47               88727262.
 MP_SendRecv            42                 732600.
 MP_ISendRecv           42                 732600.
 MP_Wait               267
 MP_ISend              180                3337386.
 MP_IRecv              180                3339494.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.122    0.163  107.455  107.462
 qs_energies                          1  2.0    0.000    0.000  105.929  105.933
 ls_scf                               1  3.0    0.000    0.000  102.998  103.002
 dbcsr_multiply_generic             111  6.7    0.024    0.027   76.558   76.695
 ls_scf_main                          1  4.0    0.000    0.000   63.348   63.348
 density_matrix_trs4                  2  5.0    0.002    0.003   54.281   54.341
 multiply_cannon                    111  7.7    0.139    0.250   50.591   52.668
 multiply_cannon_loop               111  8.7    0.099    0.108   47.590   48.214
 ls_scf_init_scf                      1  4.0    0.000    0.000   35.899   35.900
 ls_scf_init_matrix_S                 1  5.0    0.000    0.001   34.320   34.345
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   31.643   31.651
 mp_waitall_1                      4527 11.1   21.673   25.076   21.673   25.076
 make_m2s                           222  7.7    0.005    0.005   22.348   23.442
 make_images                        222  8.7    3.584    3.879   22.241   23.333
 multiply_cannon_multrec            444  9.7   17.798   18.418   22.474   23.101
 hybrid_alltoall_any                227 10.6    1.657    3.627   12.530   15.248
 make_images_data                   222  9.7    0.003    0.004   12.744   14.879
 multiply_cannon_metrocomm3         444  9.7    0.001    0.001   10.346   12.705
 multiply_cannon_sync_h2d           444  9.7    8.790    8.835    8.790    8.835
 arnoldi_extremal                     4  6.8    0.000    0.000    7.427    7.436
 arnoldi_normal_ev                    4  7.8    0.003    0.009    7.427    7.436
 build_subspace                      16  8.4    0.026    0.036    6.872    6.884
 dbcsr_matrix_vector_mult           304  9.0    0.017    0.034    5.503    5.658
 dbcsr_matrix_vector_mult_local     304 10.0    5.066    5.367    5.069    5.370
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    5.184    5.271
 apply_matrix_preconditioner          6  5.3    0.001    0.001    4.838    5.085
 dbcsr_mm_accdrv_process           1814 10.4    0.267    0.355    4.487    4.615
 dbcsr_mm_accdrv_process_sort      1814 11.4    4.151    4.283    4.151    4.283
 ls_scf_post                          1  4.0    0.000    0.000    3.751    3.754
 make_images_sizes                  222  9.7    0.000    0.000    1.462    3.583
 mp_alltoall_i44                    222 10.7    1.461    3.582    1.461    3.582
 mp_allgather_i34                   111  8.7    1.116    3.514    1.116    3.514
 ls_scf_store_result                  1  5.0    0.000    0.000    3.463    3.500
 calculate_norms                    792  9.8    3.231    3.276    3.231    3.276
 dbcsr_finalize                     304  7.8    0.082    0.090    3.075    3.156
 compute_matrix_preconditioner        1  6.0    0.002    0.002    3.048    3.053
 dbcsr_merge_all                    275  8.9    0.882    0.912    2.860    2.935
 qs_energies_init_hamiltonians        1  3.0    0.002    0.002    2.901    2.901
 dbcsr_complete_redistribute          5  7.6    1.428    1.470    2.732    2.847
 acc_transpose_blocks               444  9.7    0.003    0.003    2.269    2.564
 matrix_ls_to_qs                      2  6.0    0.000    0.000    2.397    2.528
 dbcsr_sort_data                    325 11.1    2.444    2.498    2.444    2.498
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.483    2.485
 acc_transpose_blocks_kernels       444 10.7    0.006    0.006    2.186    2.480
 jit_kernel_transpose                 1 13.0    2.180    2.474    2.180    2.474
 rebuild_ks_matrix                    3  7.3    0.000    0.000    2.418    2.419
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.001    2.418    2.419
 dbcsr_new_transposed                 4  7.5    0.241    0.252    2.280    2.292
 dbcsr_data_new                    6591  9.6    1.842    2.291    1.842    2.291
 dbcsr_frobenius_norm                74  6.6    2.053    2.126    2.193    2.223
 dbcsr_add_d                        103  6.2    0.000    0.000    2.123    2.204
 dbcsr_add_anytype                  103  7.2    0.858    0.890    2.123    2.204
 dbcsr_data_release               12724 10.6    1.977    2.181    1.977    2.181
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="510", plot="h2o_32_nrep3_ls", label="(8n/1r/12t)", y=107.462000, yerr=0.000000
PlotPoint: name="511", plot="h2o_32_nrep3_ls_mem", label="(8n/1r/12t)", y=7028.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/3b580084b3fdad7e3b92fe812ea749cecfaba215_performance_tests/27/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32        7009386627072       0.0%      0.0%    100.0%
 flops     9 x     9 x    32        7335108845568       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        9866241589248       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        9884108906496       0.0%      0.0%    100.0%
 flops    22 x    22 x    32       13354440523776       0.0%      0.0%    100.0%
 flops    32 x    32 x     9       20607185977344       0.0%      0.0%    100.0%
 flops    32 x    32 x    22       25186560638976       0.0%      0.0%    100.0%
 flops     9 x    32 x    32       28458319085568       0.0%      0.0%    100.0%
 flops    22 x    32 x    32       34782389993472       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       42881542373376       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       55680402235392       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       55680402235392       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       72328573419520       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                       383.054662E+12       0.0%      0.0%    100.0%
 flops max/rank                    733.641090E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                        26899403712       0.0%      0.0%    100.0%
 number of processed stacks             118860288       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     226.3
 marketing flops                   780.439111E+12
 -------------------------------------------------------------------------------
 # multiplications                           1445
 max memory usage/rank             593.166336E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged               102097920
 MPI messages size (bytes):
  total size                        37.227590E+12
  min size                           0.000000E+00
  max size                           4.551360E+06
  average size                     364.626312E+03
 MPI breakdown and total messages size (bytes):
             size <=      128              731472                        0
       128 < size <=     8192            11922720              97670922240
      8192 < size <=    32768            24718992             614677610496
     32768 < size <=   131072            20000256            1970081366016
    131072 < size <=  4194304            42515668           24886801223040
   4194304 < size <= 16777216             2208812            9656099886720
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4640                  78072.
 MP_Allreduce        13232                   2081.
 MP_Sync              1064
 MP_Alltoall          2588              663447891.
 MP_SendRecv        168740                  11136.
 MP_ISendRecv        92040                  11136.
 MP_Wait            102830
 MP_comm_split          40
 MP_ISend            26090                  85106.
 MP_IRecv            37890                  59644.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.034    0.112  301.463  301.465
 qs_mol_dyn_low                       1  2.0    0.003    0.017  299.916  299.937
 qs_forces                            5  3.8    0.007    0.058  299.758  299.762
 qs_energies                          5  4.8    0.002    0.017  296.103  296.136
 scf_env_do_scf                       5  5.8    0.000    0.004  280.052  280.054
 scf_env_do_scf_inner_loop          105  6.6    0.007    0.049  242.177  242.191
 qs_scf_new_mos                     105  7.6    0.000    0.001  186.711  187.451
 qs_scf_loop_do_ot                  105  8.6    0.001    0.012  186.710  187.450
 ot_scf_mini                        105  9.6    0.004    0.029  176.487  177.007
 dbcsr_multiply_generic            1445 12.2    0.127    0.137  138.814  141.166
 velocity_verlet                      4  3.0    0.009    0.035  125.535  125.536
 multiply_cannon                   1445 13.2    0.278    0.289  116.502  122.412
 multiply_cannon_loop              1445 14.2    2.853    3.011  113.666  118.981
 qs_ot_get_p                        112 10.4    0.001    0.001   81.915   82.393
 qs_ot_p2m_diag                      40 11.0    0.021    0.038   69.261   69.398
 cp_dbcsr_syevd                      40 12.0    0.002    0.002   65.666   65.669
 ot_mini                            105 10.6    0.001    0.023   63.533   63.704
 cp_fm_syevd                         40 13.0    0.005    0.016   59.509   59.679
 mp_waitall_1                    488190 16.1   41.022   57.146   41.022   57.146
 cp_fm_redistribute_end              40 14.0   27.020   53.923   27.035   53.929
 cp_fm_syevd_base                    40 14.0   26.879   53.792   26.879   53.792
 multiply_cannon_metrocomm3       69360 15.2    0.204    0.219   26.981   46.238
 multiply_cannon_multrec          69360 15.2   29.417   34.120   39.298   44.553
 qs_ot_get_derivative                55 11.6    0.001    0.015   41.554   41.900
 init_scf_loop                        7  6.6    0.001    0.013   37.809   37.812
 rebuild_ks_matrix                  110  8.4    0.000    0.000   35.174   35.341
 qs_ks_build_kohn_sham_matrix       110  9.4    0.012    0.026   35.173   35.341
 multiply_cannon_sync_h2d         69360 15.2   28.658   33.078   28.658   33.078
 qs_ks_update_qs_env                112  7.6    0.001    0.001   32.291   32.445
 prepare_preconditioner               7  7.6    0.000    0.001   31.960   32.002
 make_preconditioner                  7  8.6    0.001    0.010   31.960   32.002
 qs_rho_update_rho_low              110  7.6    0.001    0.003   27.490   27.751
 calculate_rho_elec                 110  8.6    0.030    0.033   27.490   27.750
 rs_pw_transfer                     690 11.5    0.011    0.013   24.780   26.160
 make_full_inverse_cholesky           7  9.6    0.000    0.000   23.466   23.538
 apply_preconditioner_dbcsr          62 12.6    0.000    0.001   23.213   23.459
 apply_single                        62 13.6    0.000    0.000   23.213   23.459
 density_rs2pw                      110  9.6    0.006    0.007   20.920   22.155
 ot_new_cg_direction                 55 11.6    0.001    0.012   21.237   21.238
 cp_fm_cholesky_invert                7 10.6   16.146   16.171   16.146   16.171
 qs_ot_get_orbitals                 105 10.6    0.001    0.001   15.535   15.923
 qs_ot_get_derivative_taylor         37 12.8    0.001    0.001   14.831   15.103
 multiply_cannon_metrocomm1       69360 15.2    0.099    0.106    5.067   14.805
 pw_transfer                       1645 12.4    0.084    0.111   13.789   14.121
 mp_sum_l                          4764 12.2   13.101   14.066   13.101   14.066
 fft_wrap_pw1pw2                   1425 13.5    0.013    0.017   13.646   13.981
 sum_up_and_integrate                60 10.3    0.028    0.031   13.740   13.757
 integrate_v_rspace                  60 11.3    0.002    0.002   13.712   13.731
 init_scf_run                         5  5.8    0.000    0.001   13.144   13.145
 scf_env_initial_rho_setup            5  6.8    0.002    0.003   13.144   13.145
 calculate_dm_sparse                110  9.5    0.000    0.001   11.892   12.193
 fft_wrap_pw1pw2_240                915 15.0    1.186    1.277   11.315   11.666
 qs_ot_get_derivative_diag           18 12.0    0.000    0.001   11.408   11.530
 qs_vxc_create                      110 10.4    0.002    0.005   11.171   11.224
 check_diag                          80 13.5    8.593    8.887   10.880   11.060
 rs_pw_transfer_RS2PW_30            110 11.6    1.572    1.665    9.179   10.974
 dbcsr_mm_accdrv_process         154766 15.8    6.187    6.402    9.750   10.560
 mp_sendrecv_dv                  168740 12.6   10.143   10.375   10.143   10.375
 fft3d_pb                           915 16.0    2.367    2.618    9.399    9.766
 potential_pw2rs                     60 12.3    0.003    0.003    9.561    9.690
 make_m2s                          2890 13.2    0.077    0.083    8.767    9.337
 make_images                       2890 14.2    0.241    0.287    8.662    9.231
 make_full_single_inverse             7  9.6    0.001    0.010    8.116    8.158
 acc_transpose_blocks             69360 15.2    0.366    0.382    7.655    8.037
 xc_rho_set_and_dset_create         110 12.4    0.076    0.098    7.697    7.960
 cp_dbcsr_sm_fm_multiply             15  9.3    0.001    0.003    7.618    7.635
 xc_vxc_pw_create                    60 11.3    0.039    0.050    7.566    7.620
 calculate_first_density_matrix       1  7.0    0.000    0.003    7.312    7.324
 mp_alltoall_z22v                  2340 17.7    6.560    7.275    6.560    7.275
 cp_dbcsr_sm_fm_multiply_core        15 10.3    0.000    0.001    6.998    7.054
 xc_pw_derive                       510 13.4    0.005    0.007    6.823    6.897
 cp_fm_cholesky_decompose            14 10.2    6.775    6.784    6.775    6.784
 mp_waitany                        7680 13.5    4.778    6.192    4.778    6.192
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="601", plot="h2o_512_md", label="(64n/12r/1t)", y=301.465000, yerr=0.000000
PlotPoint: name="602", plot="h2o_512_md_mem", label="(64n/12r/1t)", y=562.000000, yerr=3.633180
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


========= END RESULTS ===========

CommitSHA: 3b580084b3fdad7e3b92fe812ea749cecfaba215
Summary: empty
Status: OK