=== 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: aecd330b8c27e8066c26f3d7eb60ac611177003f


################# 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,
#              HDF5 1.14.2, LIBINT 2.6.0, LIBPEXSI 1.2.0,
#              LIBXC 6.2.2, LIBVORI 220621, LIBXSMM 1.17,
#              PLUMED 2.9.0, 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: 04.10.2023
#
# \
   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_HDF5       := 1.14.2
USE_LIBINT     := 2.6.0
USE_LIBPEXSI   := 1.2.0
USE_LIBVORI    := 220621
USE_LIBXC      := 6.2.2
USE_LIBXSMM    := 1.17
USE_PLUMED     := 2.9.0
#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
# 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))
   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__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
endif

ifneq ($(USE_HDF5),)
   USE_HDF5       := $(strip $(USE_HDF5))
   HDF5_INC       := $(INSTALL_PATH)/hdf5-$(USE_HDF5)/include
   HDF5_LIB       := $(INSTALL_PATH)/hdf5-$(USE_HDF5)/lib
   CFLAGS         += -I$(HDF5_INC)
   DFLAGS         += -D__HDF5
   LIBS           += $(HDF5_LIB)/libhdf5_fortran.a
   LIBS           += $(HDF5_LIB)/libhdf5_hl.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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/01
 job id: 49897211
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/02
 job id: 49897213
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/03
 job id: 49897216
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/04
 job id: 49897219
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/05
 job id: 49897221
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/06
 job id: 49897222
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/07
 job id: 49897224
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/08
 job id: 49897225
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/09
 job id: 49897226
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/10
 job id: 49897227
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/11
 job id: 49897230
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/12
 job id: 49897231
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/13
 job id: 49897233
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/14
 job id: 49897234
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/15
 job id: 49897235
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/16
 job id: 49897236
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/17
 job id: 49897237
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/18
 job id: 49897238
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/19
 job id: 49897239
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/20
 job id: 49897240
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/21
 job id: 49897241
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/22
 job id: 49897242
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/23
 job id: 49897243
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/24
 job id: 49897244
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/25
 job id: 49897245
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/26
 job id: 49897246
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/27
 job id: 49897247
 --- 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_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    0.018    0.032  135.622  135.623
 farming_run                          1  2.0  135.161  135.163  135.595  135.598
 -------------------------------------------------------------------------------


 @@@@@@@@@@ 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               1.500824E+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  115.262  115.263
 qs_energies                          1  2.0    0.000    0.000  115.046  115.049
 mp2_main                             1  3.0    0.000    0.000  112.837  112.839
 mp2_gpw_main                         1  4.0    0.027    0.034  111.758  111.760
 mp2_ri_gpw_compute_in                1  5.0    0.171    0.172   92.686   93.186
 mp2_ri_gpw_compute_in_loop           1  6.0    0.004    0.004   54.599   55.099
 mp2_eri_3c_integrate_gpw           272  7.0    0.153    0.165   40.998   46.210
 get_2c_integrals                     1  6.0    0.032    0.033   37.205   37.916
 integrate_v_rspace                 273  8.0    0.440    0.455   24.589   29.532
 pw_transfer                       6555 10.6    0.379    0.396   26.809   27.709
 fft_wrap_pw1pw2                   5465 11.4    0.045    0.049   25.424   26.273
 grid_integrate_task_list           273  9.0   20.501   25.899   20.501   25.899
 fft_wrap_pw1pw2_100               2178 12.4    1.127    1.410   22.973   23.789
 compute_2c_integrals                 1  7.0    0.002    0.002   19.655   19.655
 rpa_ri_compute_en                    1  5.0    0.019    0.021   18.967   19.125
 compute_2c_integrals_loop_lm         1  8.0    0.002    0.003   18.653   19.064
 mp2_eri_2c_integrate_gpw             1  9.0    2.388    2.434   18.651   19.063
 cp_fm_cholesky_decompose            12  8.2   17.524   18.247   17.524   18.247
 cholesky_decomp                      1  7.0    0.000    0.000   16.374   17.100
 fft3d_s                           5443 13.4   16.128   16.439   16.150   16.462
 ao_to_mo_and_store_B_mult_1        272  7.0   10.769   15.299   10.769   15.299
 calculate_wavefunction             272  8.0    5.426    5.571   12.323   12.991
 rpa_num_int                          1  6.0    0.000    0.001   10.730   10.730
 rpa_num_int_RPA_matrix_operati       8  7.0    0.000    0.000   10.663   10.702
 calc_mat_Q                           8  8.0    0.000    0.000    9.473    9.590
 contract_S_to_Q                      8  9.0    0.000    0.000    8.899    9.010
 calc_potential_gpw                 544  9.5    0.005    0.005    8.191    8.631
 parallel_gemm_fm                    14  9.1    0.000    0.000    8.497    8.597
 parallel_gemm_fm_cosma              14 10.1    8.497    8.597    8.497    8.597
 mp2_eri_2c_integrate_gpw_pot_l     272 10.0    0.001    0.002    8.095    8.414
 potential_pw2rs                    545 10.0    0.106    0.108    7.532    8.264
 create_integ_mat                     1  6.0    0.034    0.038    7.644    7.644
 collocate_single_gaussian          272 10.0    0.039    0.041    7.362    7.609
 array2fm                             1  7.0    0.000    0.000    6.631    7.082
 pw_scatter_s                      2720 13.7    4.332    4.612    4.332    4.612
 pw_gather_s                       2722 13.2    3.431    3.796    3.431    3.796
 array2fm_buffer_send                 1  8.0    2.920    3.119    2.920    3.119
 pw_poisson_solve                   545 10.5    1.127    1.205    2.216    2.362
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="10", plot="h2o_32_ri_rpa_mp2", label="RI-RPA (8n/2r/6t)", y=111.757098, yerr=0.000000
PlotPoint: name="11", plot="h2o_32_ri_rpa_mp2_mem", label="RI-RPA (8n/2r/6t)", y=2813.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_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    0.023    0.035  422.088  422.089
 farming_run                          1  2.0  421.370  421.374  422.054  422.057
 -------------------------------------------------------------------------------


 @@@@@@@@@@ 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               1.248625E+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                2393214.
 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    0.012    0.035  217.673  217.673
 qs_energies                          1  2.0    0.000    0.000  217.435  217.450
 scf_env_do_scf                       1  3.0    0.000    0.000  114.656  114.656
 qs_ks_update_qs_env                  5  5.0    0.000    0.000  113.774  113.781
 rebuild_ks_matrix                    4  6.0    0.000    0.000  113.773  113.779
 qs_ks_build_kohn_sham_matrix         4  7.0    0.054    0.060  113.773  113.779
 hfx_ks_matrix                        4  8.0    0.001    0.001  113.429  113.433
 integrate_four_center                4  9.0    0.152    0.470  113.428  113.432
 integrate_four_center_main           4 10.0    0.117    0.641  101.872  105.194
 integrate_four_center_bin          265 11.0  101.756  105.180  101.756  105.180
 mp2_main                             1  3.0    0.000    0.000  102.475  102.490
 mp2_gpw_main                         1  4.0    0.048    0.070  101.638  101.654
 init_scf_loop                        1  4.0    0.000    0.000   96.318   96.319
 mp2_ri_gpw_compute_in                1  5.0    0.064    0.064   74.267   75.278
 mp2_ri_gpw_compute_in_loop           1  6.0    0.002    0.002   53.804   54.813
 mp2_eri_3c_integrate_gpw            91  7.0    0.143    0.167   41.487   46.401
 integrate_v_rspace                  95  8.0    0.396    0.562   27.954   32.692
 pw_transfer                       2240 10.6    0.147    0.186   29.490   29.915
 mp2_ri_gpw_compute_en                1  5.0    0.064    0.079   27.225   29.283
 ao_to_mo_and_store_B_mult_1         91  7.0   10.644   28.957   10.644   28.957
 fft_wrap_pw1pw2                   1868 11.4    0.018    0.023   28.507   28.904
 grid_integrate_task_list            95  9.0   23.373   28.337   23.373   28.337
 fft_wrap_pw1pw2_100                730 12.4    1.265    1.463   26.268   26.664
 mp2_ri_gpw_compute_en_RI_loop        1  6.0    1.833    1.881   25.552   25.561
 get_2c_integrals                     1  6.0    0.002    0.019   20.379   20.400
 compute_2c_integrals                 1  7.0    0.002    0.003   19.364   19.370
 compute_2c_integrals_loop_lm         1  8.0    0.001    0.001   18.606   18.889
 mp2_eri_2c_integrate_gpw             1  9.0    1.741    1.852   18.606   18.888
 fft3d_s                           1823 13.4   18.484   18.822   18.498   18.836
 scf_env_do_scf_inner_loop            4  4.0    0.000    0.001   18.335   18.335
 mp2_ri_gpw_compute_en_expansio     172  7.0    0.559    0.587    9.104    9.945
 calculate_wavefunction              91  8.0    2.018    2.045    9.624    9.861
 local_gemm                         172  8.0    8.545    9.388    8.545    9.388
 potential_pw2rs                    186 10.0    0.033    0.035    8.415    8.951
 mp2_ri_gpw_compute_en_comm          22  7.0    0.502    0.521    8.232    8.937
 mp2_eri_2c_integrate_gpw_pot_l      91 10.0    0.001    0.001    8.143    8.506
 calc_potential_gpw                 182  9.5    0.002    0.002    7.898    8.181
 collocate_single_gaussian           91 10.0    0.016    0.019    7.733    7.995
 mp_sync                             37 10.5    3.513    7.382    3.513    7.382
 mp_sendrecv_dm3                   2068  8.0    6.260    6.990    6.260    6.990
 integrate_four_center_load           4 10.0    0.000    0.000    6.775    6.778
 hfx_load_balance                     1 11.0    0.000    0.000    6.775    6.778
 mp2_ri_gpw_compute_en_ener         172  7.0    6.338    6.414    6.338    6.414
 pw_gather_s                        912 13.2    4.487    5.040    4.487    5.040
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="20", plot="h2o_32_ri_rpa_mp2", label="RI-MP2 (8n/6r/2t)", y=101.619416, yerr=0.000000
PlotPoint: name="21", plot="h2o_32_ri_rpa_mp2_mem", label="RI-MP2 (8n/6r/2t)", y=1508.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_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             452.460544E+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                1352877.
 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    0.050    0.071   54.923   54.925
 qs_mol_dyn_low                       1  2.0    0.003    0.003   54.672   54.683
 qs_forces                           11  3.9    0.014    0.019   54.609   54.610
 qs_energies                         11  4.9    0.002    0.002   53.091   53.110
 scf_env_do_scf                      11  5.9    0.001    0.013   46.621   46.621
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.007   44.399   44.400
 qs_scf_new_mos                     108  7.5    0.000    0.000   34.047   34.380
 qs_scf_loop_do_ot                  108  8.5    0.000    0.001   34.047   34.380
 dbcsr_multiply_generic            2286 12.5    0.093    0.098   33.689   34.089
 ot_scf_mini                        108  9.5    0.002    0.002   32.314   32.497
 multiply_cannon                   2286 13.5    0.192    0.206   26.155   27.526
 multiply_cannon_loop              2286 14.5    1.832    1.935   25.412   26.857
 velocity_verlet                     10  3.0    0.001    0.001   26.718   26.719
 ot_mini                            108 10.5    0.001    0.001   19.216   19.488
 qs_ot_get_derivative               108 11.5    0.001    0.001   16.241   16.446
 mp_waitall_1                    245248 16.5    8.359   14.329    8.359   14.329
 multiply_cannon_metrocomm3       54864 15.5    0.073    0.081    5.899   12.525
 multiply_cannon_multrec          54864 15.5    3.635    5.687    7.621   11.058
 qs_ot_get_p                        119 10.4    0.001    0.001    8.238    8.529
 rebuild_ks_matrix                  119  8.3    0.000    0.000    8.068    8.232
 qs_ks_build_kohn_sham_matrix       119  9.3    0.010    0.011    8.067    8.232
 qs_ks_update_qs_env                119  7.6    0.001    0.001    7.114    7.277
 mp_sum_l                          7287 12.8    5.333    7.044    5.333    7.044
 multiply_cannon_sync_h2d         54864 15.5    5.182    6.286    5.182    6.286
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    5.575    6.030
 dbcsr_mm_accdrv_process          76910 16.1    1.848    2.889    3.899    5.557
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    5.370    5.471
 qs_ot_p2m_diag                      50 11.0    0.004    0.006    5.373    5.420
 init_scf_run                        11  5.9    0.000    0.001    5.091    5.092
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.091    5.091
 sum_up_and_integrate               119 10.3    0.001    0.001    4.613    4.619
 integrate_v_rspace                 119 11.3    0.002    0.002    4.602    4.610
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    4.539    4.539
 qs_rho_update_rho_low              119  7.7    0.000    0.001    4.315    4.448
 calculate_rho_elec                 119  8.7    0.011    0.016    4.315    4.447
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    4.284    4.285
 cp_fm_redistribute_end              50 14.0    2.183    4.250    2.193    4.254
 cp_fm_diag_elpa_base                50 14.0    2.054    4.129    2.059    4.137
 calculate_dm_sparse                119  9.5    0.000    0.000    3.009    3.166
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.940    3.115
 apply_single                       119 13.6    0.000    0.000    2.940    3.115
 acc_transpose_blocks             54864 15.5    0.228    0.256    2.274    2.809
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.780    2.784
 ot_diis_step                       108 11.5    0.006    0.006    2.717    2.717
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    2.606    2.666
 jit_kernel_multiply                 13 15.8    1.987    2.586    1.987    2.586
 multiply_cannon_metrocomm1       54864 15.5    0.056    0.062    1.681    2.584
 density_rs2pw                      119  9.7    0.004    0.004    2.342    2.422
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.272    2.274
 wfi_extrapolate                     11  7.9    0.001    0.001    2.229    2.229
 init_scf_loop                       11  6.9    0.000    0.000    2.189    2.190
 grid_integrate_task_list           119 12.3    2.018    2.091    2.018    2.091
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.940    1.986
 pw_transfer                       1439 11.6    0.052    0.057    1.902    1.981
 potential_pw2rs                    119 12.3    0.004    0.004    1.959    1.977
 make_m2s                          4572 13.5    0.053    0.056    1.885    1.933
 fft_wrap_pw1pw2                   1201 12.6    0.007    0.007    1.826    1.907
 mp_sum_d                          4135 12.0    1.283    1.884    1.283    1.884
 make_images                       4572 14.5    0.133    0.138    1.803    1.851
 mp_alltoall_d11v                  2130 13.8    1.405    1.659    1.405    1.659
 fft3d_ps                          1201 14.6    0.371    0.479    1.541    1.618
 transfer_rs2pw                     487 10.6    0.005    0.006    1.459    1.561
 fft_wrap_pw1pw2_140                487 13.2    0.140    0.155    1.415    1.497
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.001    1.449    1.478
 acc_transpose_blocks_sync       164592 16.5    1.208    1.436    1.208    1.436
 mp_waitany                       12084 13.8    1.249    1.422    1.249    1.422
 grid_collocate_task_list           119  9.7    1.352    1.413    1.352    1.413
 transfer_pw2rs                     487 13.2    0.006    0.007    1.393    1.411
 parallel_gemm_fm                    81  9.0    0.000    0.000    1.278    1.283
 parallel_gemm_fm_cosma              81 10.0    1.278    1.283    1.278    1.283
 dbcsr_dot_sd                      1205 11.9    0.049    0.059    0.702    1.104
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="100", plot="h2o_64_md", label="(8n/12r/1t)", y=54.925000, yerr=0.000000
PlotPoint: name="101", plot="h2o_64_md_mem", label="(8n/12r/1t)", y=431.181818, yerr=1.113404
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_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             490.082304E+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                1467768.
 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    0.016    0.034   39.995   39.996
 qs_mol_dyn_low                       1  2.0    0.005    0.020   39.262   39.272
 qs_forces                           11  3.9    0.013    0.034   39.180   39.188
 qs_energies                         11  4.9    0.001    0.001   37.461   37.481
 scf_env_do_scf                      11  5.9    0.001    0.001   31.576   31.576
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   29.180   29.181
 dbcsr_multiply_generic            2286 12.5    0.101    0.103   22.800   23.153
 qs_scf_new_mos                     108  7.5    0.001    0.001   20.616   20.846
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   20.616   20.845
 ot_scf_mini                        108  9.5    0.002    0.003   19.700   19.864
 multiply_cannon                   2286 13.5    0.209    0.218   17.737   19.282
 velocity_verlet                     10  3.0    0.001    0.002   18.240   18.242
 multiply_cannon_loop              2286 14.5    1.193    1.251   16.587   18.078
 ot_mini                            108 10.5    0.001    0.001   12.215   12.444
 mp_waitall_1                    200699 16.5    5.776   11.351    5.776   11.351
 multiply_cannon_metrocomm3       27432 15.5    0.071    0.074    4.288   10.127
 qs_ot_get_derivative               108 11.5    0.001    0.001    9.849   10.014
 multiply_cannon_multrec          27432 15.5    1.840    4.283    6.378    9.216
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.782    6.930
 qs_ks_build_kohn_sham_matrix       119  9.3    0.016    0.027    6.782    6.929
 dbcsr_mm_accdrv_process          47894 16.0    3.629    5.972    4.457    6.609
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.925    6.059
 qs_ot_get_p                        119 10.4    0.001    0.001    4.578    4.792
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    3.777    4.629
 init_scf_run                        11  5.9    0.000    0.001    4.563    4.563
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    4.563    4.563
 mp_sum_l                          7287 12.8    2.032    4.113    2.032    4.113
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    3.016    4.070
 apply_single                       119 13.6    0.000    0.000    3.016    4.070
 sum_up_and_integrate               119 10.3    0.001    0.001    3.683    3.702
 integrate_v_rspace                 119 11.3    0.002    0.003    3.669    3.690
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.574    3.607
 calculate_rho_elec                 119  8.7    0.021    0.024    3.573    3.606
 calculate_first_density_matrix       1  7.0    0.000    0.000    3.064    3.065
 qs_ot_p2m_diag                      50 11.0    0.009    0.013    2.956    2.975
 make_m2s                          4572 13.5    0.052    0.053    2.587    2.919
 make_images                       4572 14.5    0.206    0.244    2.500    2.833
 acc_transpose_blocks             27432 15.5    0.113    0.118    1.982    2.785
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    2.559    2.560
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.002    2.483    2.485
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    2.328    2.417
 init_scf_loop                       11  6.9    0.000    0.000    2.374    2.374
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.294    2.333
 ot_diis_step                       108 11.5    0.011    0.011    2.318    2.318
 calculate_dm_sparse                119  9.5    0.000    0.001    2.207    2.284
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    2.233    2.233
 multiply_cannon_sync_h2d         27432 15.5    1.707    2.233    1.707    2.233
 cp_fm_redistribute_end              50 14.0    1.133    2.209    1.136    2.212
 cp_fm_diag_elpa_base                50 14.0    1.044    2.123    1.072    2.158
 density_rs2pw                      119  9.7    0.004    0.004    1.855    1.933
 grid_integrate_task_list           119 12.3    1.843    1.930    1.843    1.930
 pw_transfer                       1439 11.6    0.065    0.069    1.836    1.885
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.744    1.797
 jit_kernel_multiply                  8 16.3    0.771    1.759    0.771    1.759
 acc_transpose_blocks_kernels     27432 16.5    0.187    0.275    1.025    1.699
 make_images_data                  4572 15.5    0.047    0.053    1.237    1.596
 prepare_preconditioner              11  7.9    0.000    0.000    1.495    1.521
 make_preconditioner                 11  8.9    0.000    0.000    1.495    1.521
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.397    1.456
 hybrid_alltoall_any               4725 16.4    0.053    0.115    1.097    1.453
 potential_pw2rs                    119 12.3    0.006    0.006    1.429    1.449
 fft_wrap_pw1pw2_140                487 13.2    0.160    0.169    1.393    1.444
 wfi_extrapolate                     11  7.9    0.001    0.001    1.442    1.442
 fft3d_ps                          1201 14.6    0.518    0.571    1.379    1.426
 jit_kernel_transpose                 5 15.5    0.837    1.423    0.837    1.423
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.399    1.407
 grid_collocate_task_list           119  9.7    1.289    1.350    1.289    1.350
 mp_alltoall_d11v                  2130 13.8    1.213    1.291    1.213    1.291
 transfer_rs2pw                     487 10.6    0.005    0.006    1.149    1.267
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.194    1.241
 qs_energies_init_hamiltonians       11  5.9    0.005    0.042    1.059    1.077
 mp_sum_d                          4135 12.0    0.534    1.007    0.534    1.007
 mp_allgather_i34                  2286 14.5    0.574    0.980    0.574    0.980
 acc_transpose_blocks_sync        82296 16.5    0.818    0.942    0.818    0.942
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.913    0.927
 transfer_pw2rs                     487 13.2    0.005    0.006    0.895    0.906
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="102", plot="h2o_64_md", label="(8n/6r/2t)", y=39.996000, yerr=0.000000
PlotPoint: name="103", plot="h2o_64_md_mem", label="(8n/6r/2t)", y=466.636364, yerr=2.100767
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_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             521.523200E+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                1607811.
 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    0.023    0.051   34.155   34.155
 qs_mol_dyn_low                       1  2.0    0.003    0.003   33.717   33.725
 qs_forces                           11  3.9    0.002    0.002   33.294   33.298
 qs_energies                         11  4.9    0.001    0.001   31.696   31.701
 scf_env_do_scf                      11  5.9    0.000    0.001   26.894   26.894
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   24.246   24.247
 dbcsr_multiply_generic            2286 12.5    0.096    0.097   17.488   17.580
 qs_scf_new_mos                     108  7.5    0.001    0.001   16.308   16.327
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   16.307   16.327
 velocity_verlet                     10  3.0    0.007    0.018   16.007   16.020
 ot_scf_mini                        108  9.5    0.002    0.002   15.535   15.547
 multiply_cannon                   2286 13.5    0.193    0.197   13.999   14.680
 multiply_cannon_loop              2286 14.5    0.862    0.891   13.203   14.006
 ot_mini                            108 10.5    0.001    0.001    9.570    9.580
 qs_ot_get_derivative               108 11.5    0.001    0.001    8.058    8.073
 multiply_cannon_multrec          18288 15.5    1.957    3.031    7.262    7.443
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.230    6.246
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    6.229    6.245
 dbcsr_mm_accdrv_process          38222 16.0    5.090    6.060    5.212    6.126
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.462    5.476
 mp_waitall_1                    158411 16.6    2.799    4.050    2.799    4.050
 sum_up_and_integrate               119 10.3    0.001    0.001    3.717    3.731
 integrate_v_rspace                 119 11.3    0.002    0.003    3.705    3.720
 qs_ot_get_p                        119 10.4    0.001    0.001    3.682    3.697
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    3.112    3.678
 init_scf_run                        11  5.9    0.000    0.001    3.596    3.596
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.596    3.596
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.432    3.437
 calculate_rho_elec                 119  8.7    0.031    0.031    3.431    3.436
 multiply_cannon_metrocomm3       18288 15.5    0.047    0.048    1.642    2.837
 init_scf_loop                       11  6.9    0.000    0.000    2.627    2.628
 qs_ot_p2m_diag                      50 11.0    0.012    0.013    2.466    2.474
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    1.985    2.368
 apply_single                       119 13.6    0.000    0.000    1.985    2.368
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.334    2.336
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    2.154    2.155
 density_rs2pw                      119  9.7    0.004    0.004    1.997    2.095
 make_m2s                          4572 13.5    0.044    0.045    1.929    2.077
 make_images                       4572 14.5    0.193    0.207    1.844    1.992
 pw_transfer                       1439 11.6    0.065    0.069    1.925    1.952
 grid_integrate_task_list           119 12.3    1.804    1.896    1.804    1.896
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.869    1.878
 cp_fm_diag_elpa_base                50 14.0    1.845    1.855    1.867    1.876
 calculate_dm_sparse                119  9.5    0.000    0.000    1.860    1.868
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.833    1.861
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.848    1.857
 acc_transpose_blocks             18288 15.5    0.080    0.082    1.669    1.820
 prepare_preconditioner              11  7.9    0.000    0.000    1.772    1.775
 make_preconditioner                 11  8.9    0.000    0.000    1.772    1.775
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.739    1.740
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.627    1.709
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.581    1.587
 mp_sum_l                          7287 12.8    1.171    1.582    1.171    1.582
 potential_pw2rs                    119 12.3    0.007    0.008    1.502    1.522
 ot_diis_step                       108 11.5    0.011    0.012    1.488    1.488
 fft_wrap_pw1pw2_140                487 13.2    0.211    0.217    1.436    1.462
 fft3d_ps                          1201 14.6    0.527    0.544    1.402    1.429
 grid_collocate_task_list           119  9.7    1.233    1.316    1.233    1.316
 wfi_extrapolate                     11  7.9    0.001    0.001    1.208    1.208
 transfer_rs2pw                     487 10.6    0.005    0.005    1.109    1.204
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.187    1.192
 multiply_cannon_sync_h2d         18288 15.5    1.001    1.150    1.001    1.150
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.989    1.007
 make_images_data                  4572 15.5    0.047    0.051    0.827    0.994
 acc_transpose_blocks_kernels     18288 16.5    0.216    0.223    0.821    0.957
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    0.947    0.951
 transfer_pw2rs                     487 13.2    0.004    0.004    0.929    0.940
 hybrid_alltoall_any               4725 16.4    0.058    0.116    0.715    0.908
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.838    0.841
 mp_alltoall_d11v                  2130 13.8    0.721    0.809    0.721    0.809
 acc_transpose_blocks_sync        54864 16.5    0.748    0.803    0.748    0.803
 mp_alltoall_z22v                  1201 16.6    0.711    0.788    0.711    0.788
 cp_fm_cholesky_invert               11 10.9    0.767    0.771    0.767    0.771
 jit_kernel_transpose                 5 15.6    0.605    0.735    0.605    0.735
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.669    0.727
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="104", plot="h2o_64_md", label="(8n/4r/3t)", y=34.155000, yerr=0.000000
PlotPoint: name="105", plot="h2o_64_md_mem", label="(8n/4r/3t)", y=496.000000, yerr=1.954017
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_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             556.138496E+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    0.124    0.149   39.649   39.655
 qs_mol_dyn_low                       1  2.0    0.003    0.004   38.905   39.316
 qs_forces                           11  3.9    0.002    0.003   38.815   38.816
 qs_energies                         11  4.9    0.001    0.002   37.060   37.069
 scf_env_do_scf                      11  5.9    0.008    0.185   31.731   31.733
 scf_env_do_scf_inner_loop          108  6.5    0.111    0.131   27.455   27.455
 dbcsr_multiply_generic            2286 12.5    0.099    0.103   20.622   20.755
 velocity_verlet                     10  3.0    0.001    0.002   19.366   19.368
 qs_scf_new_mos                     108  7.5    0.001    0.001   18.662   18.788
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   18.662   18.788
 ot_scf_mini                        108  9.5    0.002    0.003   17.615   17.763
 multiply_cannon                   2286 13.5    0.217    0.226   16.497   16.922
 multiply_cannon_loop              2286 14.5    1.515    1.615   15.500   15.886
 ot_mini                            108 10.5    0.001    0.001   10.786   10.944
 multiply_cannon_multrec          27432 15.5    2.464    3.138    9.018    9.273
 qs_ot_get_derivative               108 11.5    0.001    0.001    8.905    9.051
 dbcsr_mm_accdrv_process          47916 15.9    6.095    7.640    6.451    7.789
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.667    6.724
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    6.667    6.723
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.909    5.959
 qs_ot_get_p                        119 10.4    0.001    0.001    4.371    4.448
 init_scf_loop                       11  6.9    0.000    0.000    4.071    4.071
 init_scf_run                        11  5.9    0.000    0.001    3.981    3.981
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.980    3.981
 sum_up_and_integrate               119 10.3    0.001    0.001    3.806    3.814
 integrate_v_rspace                 119 11.3    0.003    0.003    3.794    3.802
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.738    3.782
 calculate_rho_elec                 119  8.7    0.040    0.046    3.737    3.781
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    3.262    3.687
 mp_waitall_1                    137007 16.6    2.243    2.849    2.243    2.849
 acc_transpose_blocks             27432 15.5    0.118    0.122    2.662    2.832
 prepare_preconditioner              11  7.9    0.000    0.000    2.755    2.763
 make_preconditioner                 11  8.9    0.000    0.000    2.755    2.763
 make_m2s                          4572 13.5    0.054    0.055    2.563    2.702
 make_full_inverse_cholesky          11  9.9    0.000    0.000    2.352    2.686
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.174    2.601
 apply_single                       119 13.6    0.000    0.000    2.174    2.600
 make_images                       4572 14.5    0.274    0.336    2.455    2.592
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    2.454    2.481
 calculate_dm_sparse                119  9.5    0.000    0.000    2.398    2.461
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.454    2.456
 qs_ot_p2m_diag                      50 11.0    0.015    0.023    2.422    2.435
 density_rs2pw                      119  9.7    0.004    0.004    2.187    2.286
 pw_transfer                       1439 11.6    0.065    0.070    2.037    2.075
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    2.007    2.007
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.944    1.986
 grid_integrate_task_list           119 12.3    1.831    1.926    1.831    1.926
 ot_diis_step                       108 11.5    0.012    0.012    1.839    1.840
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.839    1.839
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.725    1.735
 cp_fm_diag_elpa_base                50 14.0    1.688    1.707    1.723    1.733
 mp_sum_l                          7287 12.8    1.136    1.715    1.136    1.715
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.644    1.656
 fft_wrap_pw1pw2_140                487 13.2    0.245    0.258    1.560    1.605
 potential_pw2rs                    119 12.3    0.009    0.009    1.593    1.604
 acc_transpose_blocks_sync        82296 16.5    1.405    1.550    1.405    1.550
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.484    1.497
 fft3d_ps                          1201 14.6    0.553    0.606    1.465    1.495
 wfi_extrapolate                     11  7.9    0.001    0.001    1.469    1.469
 multiply_cannon_metrocomm3       27432 15.5    0.040    0.042    0.783    1.392
 transfer_rs2pw                     487 10.6    0.004    0.005    1.241    1.338
 grid_collocate_task_list           119  9.7    1.248    1.328    1.248    1.328
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.308    1.323
 cp_fm_upper_to_full                 72 14.2    0.827    1.180    0.827    1.180
 acc_transpose_blocks_kernels     27432 16.5    0.270    0.279    1.110    1.165
 jit_kernel_multiply                  6 16.0    0.291    1.164    0.291    1.164
 make_images_data                  4572 15.5    0.047    0.051    0.981    1.161
 dbcsr_complete_redistribute        329 12.2    0.122    0.152    0.827    1.118
 hybrid_alltoall_any               4725 16.4    0.065    0.154    0.818    1.078
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    1.072    1.073
 transfer_pw2rs                     487 13.2    0.004    0.004    0.995    1.006
 mp_alltoall_i22                    627 13.8    0.625    0.950    0.625    0.950
 arnoldi_extremal                   119 11.4    0.002    0.002    0.906    0.932
 arnoldi_normal_ev                  119 12.4    0.372    0.444    0.904    0.930
 mp_alltoall_d11v                  2130 13.8    0.812    0.928    0.812    0.928
 mp_sum_d                          4133 12.0    0.501    0.917    0.501    0.917
 jit_kernel_transpose                 5 15.6    0.840    0.891    0.840    0.891
 cp_fm_cholesky_invert               11 10.9    0.879    0.882    0.879    0.882
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    0.597    0.881
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.799    0.877
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.847    0.852
 mp_alltoall_z22v                  1201 16.6    0.794    0.824    0.794    0.824
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="106", plot="h2o_64_md", label="(8n/3r/4t)", y=39.655000, yerr=0.000000
PlotPoint: name="107", plot="h2o_64_md_mem", label="(8n/3r/4t)", y=529.000000, yerr=2.412091
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_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             622.956544E+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    0.009    0.027   28.380   28.381
 qs_mol_dyn_low                       1  2.0    0.003    0.004   28.217   28.225
 qs_forces                           11  3.9    0.002    0.003   28.157   28.158
 qs_energies                         11  4.9    0.001    0.001   26.466   26.469
 scf_env_do_scf                      11  5.9    0.001    0.001   21.531   21.531
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.006   19.111   19.111
 velocity_verlet                     10  3.0    0.001    0.002   14.428   14.431
 dbcsr_multiply_generic            2286 12.5    0.092    0.098   13.306   13.373
 qs_scf_new_mos                     108  7.5    0.001    0.001   11.652   11.681
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   11.652   11.681
 multiply_cannon                   2286 13.5    0.222    0.228   10.840   11.305
 ot_scf_mini                        108  9.5    0.002    0.002   10.954   10.980
 multiply_cannon_loop              2286 14.5    0.644    0.677    9.964   10.109
 multiply_cannon_multrec           9144 15.5    1.894    2.078    6.184    6.400
 ot_mini                            108 10.5    0.001    0.001    6.362    6.394
 rebuild_ks_matrix                  119  8.3    0.000    0.000    5.668    5.687
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    5.667    5.687
 qs_ot_get_derivative               108 11.5    0.001    0.001    5.089    5.116
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.039    5.056
 dbcsr_mm_accdrv_process          12550 15.8    3.582    4.202    4.178    4.248
 init_scf_run                        11  5.9    0.000    0.001    3.509    3.509
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.509    3.509
 sum_up_and_integrate               119 10.3    0.001    0.001    3.376    3.382
 integrate_v_rspace                 119 11.3    0.003    0.003    3.365    3.371
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.247    3.252
 calculate_rho_elec                 119  8.7    0.060    0.061    3.246    3.252
 qs_ot_get_p                        119 10.4    0.001    0.001    2.737    2.773
 init_scf_loop                       11  6.9    0.000    0.000    2.400    2.402
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.385    2.387
 grid_integrate_task_list           119 12.3    1.866    1.956    1.866    1.956
 pw_transfer                       1439 11.6    0.065    0.068    1.937    1.946
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.844    1.854
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.851    1.852
 make_m2s                          4572 13.5    0.034    0.035    1.721    1.849
 acc_transpose_blocks              9144 15.5    0.041    0.043    1.739    1.797
 qs_ot_p2m_diag                      50 11.0    0.022    0.023    1.772    1.774
 make_images                       4572 14.5    0.270    0.301    1.634    1.760
 density_rs2pw                      119  9.7    0.003    0.004    1.667    1.744
 calculate_dm_sparse                119  9.5    0.000    0.000    1.724    1.742
 mp_waitall_1                    115863 16.7    1.229    1.741    1.229    1.741
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.701    1.709
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    1.686    1.706
 prepare_preconditioner              11  7.9    0.000    0.000    1.682    1.692
 make_preconditioner                 11  8.9    0.000    0.000    1.682    1.692
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.572    1.598
 fft_wrap_pw1pw2_140                487 13.2    0.322    0.330    1.530    1.542
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.531    1.531
 jit_kernel_multiply                  8 15.6    0.557    1.461    0.557    1.461
 grid_collocate_task_list           119  9.7    1.296    1.361    1.296    1.361
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.324    1.339
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.278    1.286
 cp_fm_diag_elpa_base                50 14.0    1.251    1.267    1.277    1.285
 fft3d_ps                          1201 14.6    0.558    0.569    1.259    1.265
 ot_diis_step                       108 11.5    0.013    0.013    1.261    1.261
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    1.210    1.240
 apply_single                       119 13.6    0.000    0.000    1.209    1.239
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    1.218    1.218
 potential_pw2rs                    119 12.3    0.010    0.011    1.193    1.196
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.122    1.126
 wfi_extrapolate                     11  7.9    0.001    0.001    1.073    1.073
 acc_transpose_blocks_kernels      9144 16.5    0.118    0.119    0.957    0.959
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.875    0.925
 hybrid_alltoall_any               4725 16.4    0.065    0.175    0.717    0.892
 make_images_data                  4572 15.5    0.042    0.046    0.729    0.872
 transfer_rs2pw                     487 10.6    0.004    0.004    0.758    0.844
 jit_kernel_transpose                 5 15.6    0.839    0.841    0.839    0.841
 cp_fm_cholesky_invert               11 10.9    0.838    0.841    0.838    0.841
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.809    0.816
 mp_alltoall_d11v                  2130 13.8    0.697    0.813    0.697    0.813
 acc_transpose_blocks_sync        27432 16.5    0.725    0.781    0.725    0.781
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.750    0.752
 qs_env_update_s_mstruct             11  6.9    0.000    0.001    0.666    0.716
 multiply_cannon_metrocomm3        9144 15.5    0.020    0.021    0.324    0.649
 transfer_pw2rs                     487 13.2    0.003    0.004    0.636    0.637
 mp_alltoall_z22v                  1201 16.6    0.574    0.605    0.574    0.605
 mp_allgather_i34                  2286 14.5    0.195    0.587    0.195    0.587
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="108", plot="h2o_64_md", label="(8n/2r/6t)", y=28.381000, yerr=0.000000
PlotPoint: name="109", plot="h2o_64_md_mem", label="(8n/2r/6t)", y=588.636364, yerr=8.238190
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_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             777.908224E+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    0.012    0.034   42.459   42.461
 qs_mol_dyn_low                       1  2.0    0.003    0.004   42.236   42.243
 qs_forces                           11  3.9    0.002    0.003   42.081   42.083
 qs_energies                         11  4.9    0.013    0.028   40.079   40.083
 scf_env_do_scf                      11  5.9    0.001    0.002   34.040   34.040
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.007   26.323   26.325
 velocity_verlet                     10  3.0    0.002    0.002   23.757   23.774
 dbcsr_multiply_generic            2286 12.5    0.099    0.103   19.000   19.143
 qs_scf_new_mos                     108  7.5    0.001    0.001   17.044   17.141
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   17.044   17.140
 multiply_cannon                   2286 13.5    0.297    0.306   15.193   16.011
 ot_scf_mini                        108  9.5    0.002    0.002   15.872   15.970
 multiply_cannon_loop              2286 14.5    0.872    0.883   13.958   14.808
 ot_mini                            108 10.5    0.001    0.001    9.668    9.783
 multiply_cannon_multrec           9144 15.5    3.427    4.777    8.828    8.924
 qs_ot_get_derivative               108 11.5    0.001    0.001    7.636    7.736
 init_scf_loop                       11  6.9    0.000    0.000    7.690    7.694
 rebuild_ks_matrix                  119  8.3    0.000    0.001    7.067    7.209
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.013    7.067    7.209
 prepare_preconditioner              11  7.9    0.000    0.000    6.711    6.725
 make_preconditioner                 11  8.9    0.000    0.000    6.711    6.725
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.277    6.607
 dbcsr_mm_accdrv_process          12550 15.8    4.664    6.552    5.262    6.584
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.358    6.487
 cp_fm_upper_to_full                 72 14.2    3.146    4.529    3.146    4.529
 qs_rho_update_rho_low              119  7.7    0.001    0.001    4.022    4.079
 calculate_rho_elec                 119  8.7    0.118    0.121    4.021    4.079
 init_scf_run                        11  5.9    0.000    0.001    3.961    3.961
 scf_env_initial_rho_setup           11  6.9    0.022    0.045    3.960    3.960
 sum_up_and_integrate               119 10.3    0.001    0.001    3.742    3.751
 integrate_v_rspace                 119 11.3    0.003    0.004    3.731    3.741
 qs_ot_get_p                        119 10.4    0.001    0.001    3.284    3.418
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.808    3.207
 mp_waitall_1                     94719 16.7    2.238    3.165    2.238    3.165
 dbcsr_complete_redistribute        329 12.2    0.285    0.289    1.947    2.749
 pw_transfer                       1439 11.6    0.069    0.069    2.547    2.555
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.460    2.535
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.181    2.489
 apply_single                       119 13.6    0.000    0.000    2.180    2.489
 calculate_dm_sparse                119  9.5    0.000    0.000    2.409    2.462
 fft_wrap_pw1pw2                   1201 12.6    0.009    0.009    2.449    2.457
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    1.653    2.451
 make_m2s                          4572 13.5    0.037    0.038    2.287    2.431
 make_images                       4572 14.5    0.356    0.390    2.168    2.310
 mp_alltoall_i22                    627 13.8    1.471    2.289    1.471    2.289
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.429    2.219
 multiply_cannon_metrocomm3        9144 15.5    0.021    0.022    1.356    2.205
 grid_integrate_task_list           119 12.3    2.084    2.121    2.084    2.121
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    2.044    2.094
 fft_wrap_pw1pw2_140                487 13.2    0.576    0.580    2.078    2.086
 density_rs2pw                      119  9.7    0.003    0.004    1.998    2.019
 ot_diis_step                       108 11.5    0.014    0.014    2.006    2.006
 acc_transpose_blocks              9144 15.5    0.043    0.044    1.932    1.957
 qs_ot_p2m_diag                      50 11.0    0.043    0.044    1.934    1.936
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.922    1.923
 qs_energies_init_hamiltonians       11  5.9    0.002    0.002    1.772    1.773
 mp_sum_l                          7287 12.8    0.977    1.741    0.977    1.741
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.611    1.637
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.578    1.579
 grid_collocate_task_list           119  9.7    1.525    1.555    1.525    1.555
 fft3d_ps                          1201 14.6    0.593    0.603    1.544    1.550
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.400    1.451
 cp_fm_cholesky_invert               11 10.9    1.377    1.380    1.377    1.380
 wfi_extrapolate                     11  7.9    0.001    0.001    1.365    1.365
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.310    1.332
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.305    1.305
 cp_fm_diag_elpa_base                50 14.0    1.160    1.213    1.304    1.304
 potential_pw2rs                    119 12.3    0.014    0.014    1.249    1.254
 mp_alltoall_d11v                  2130 13.8    1.188    1.252    1.188    1.252
 hybrid_alltoall_any               4725 16.4    0.090    0.149    1.037    1.246
 acc_transpose_blocks_sync        27432 16.5    1.117    1.138    1.117    1.138
 make_images_data                  4572 15.5    0.046    0.049    0.955    1.136
 qs_env_update_s_mstruct             11  6.9    0.001    0.001    1.100    1.120
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.001    0.994    1.023
 qs_create_task_list                 11  7.9    0.001    0.001    0.930    0.941
 generate_qs_task_list               11  8.9    0.367    0.387    0.929    0.940
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.920    0.932
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="110", plot="h2o_64_md", label="(8n/1r/12t)", y=42.461000, yerr=0.000000
PlotPoint: name="111", plot="h2o_64_md_mem", label="(8n/1r/12t)", y=732.545455, yerr=12.390345
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_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             499.748864E+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                1125451.
 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    0.019    0.058   83.607   83.609
 qs_mol_dyn_low                       1  2.0    0.003    0.007   82.831   83.211
 qs_forces                           11  3.9    0.003    0.004   82.631   82.633
 qs_energies                         11  4.9    0.001    0.001   79.758   79.780
 scf_env_do_scf                      11  5.9    0.000    0.001   70.647   70.649
 scf_env_do_scf_inner_loop           99  6.5    0.075    0.297   65.225   65.225
 dbcsr_multiply_generic            2055 12.4    0.106    0.109   51.761   52.063
 qs_scf_new_mos                      99  7.5    0.000    0.001   47.659   47.812
 qs_scf_loop_do_ot                   99  8.5    0.000    0.001   47.659   47.812
 ot_scf_mini                         99  9.5    0.002    0.002   45.240   45.346
 multiply_cannon                   2055 13.4    0.183    0.187   43.002   44.062
 velocity_verlet                     10  3.0    0.001    0.001   43.178   43.178
 multiply_cannon_loop              2055 14.4    1.799    1.838   42.031   43.146
 ot_mini                             99 10.5    0.001    0.001   26.759   26.879
 qs_ot_get_derivative                99 11.5    0.001    0.001   19.971   20.095
 multiply_cannon_multrec          49320 15.4   11.344   12.040   17.537   18.350
 rebuild_ks_matrix                  110  8.3    0.000    0.000   14.441   14.640
 qs_ks_build_kohn_sham_matrix       110  9.3    0.011    0.012   14.441   14.640
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.636   12.820
 mp_waitall_1                    220248 16.4   10.957   12.225   10.957   12.225
 multiply_cannon_sync_h2d         49320 15.4    9.558   10.072    9.558   10.072
 qs_ot_get_p                        110 10.4    0.001    0.001    9.858   10.016
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    7.611    8.168
 multiply_cannon_metrocomm3       49320 15.4    0.084    0.088    6.656    7.951
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    7.191    7.683
 apply_single                       110 13.6    0.000    0.000    7.191    7.683
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.810    7.058
 calculate_rho_elec                 110  8.6    0.020    0.025    6.809    7.057
 init_scf_run                        11  5.9    0.000    0.001    7.041    7.041
 scf_env_initial_rho_setup           11  6.9    0.000    0.001    7.040    7.041
 sum_up_and_integrate               110 10.3    0.002    0.003    6.992    7.007
 integrate_v_rspace                 110 11.3    0.003    0.003    6.967    6.987
 qs_ot_p2m_diag                      48 11.0    0.012    0.019    6.700    6.744
 ot_diis_step                        99 11.5    0.006    0.006    6.581    6.581
 dbcsr_mm_accdrv_process          87628 16.1    3.051    3.145    6.063    6.315
 cp_dbcsr_syevd                      48 12.0    0.002    0.003    5.739    5.739
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    5.508    5.565
 mp_sum_l                          6594 12.7    4.456    5.454    4.456    5.454
 init_scf_loop                       11  6.9    0.000    0.000    5.393    5.394
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    5.169    5.198
 cp_fm_diag_elpa_base                48 14.0    5.155    5.183    5.167    5.196
 wfi_extrapolate                     11  7.9    0.001    0.001    4.038    4.038
 make_m2s                          4110 13.4    0.060    0.065    3.874    3.974
 calculate_dm_sparse                110  9.5    0.001    0.001    3.782    3.891
 make_images                       4110 14.4    0.177    0.189    3.779    3.883
 cp_dbcsr_sm_fm_multiply             37  9.5    0.003    0.024    3.857    3.861
 multiply_cannon_metrocomm1       49320 15.4    0.065    0.068    2.462    3.730
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    3.507    3.577
 density_rs2pw                      110  9.6    0.004    0.005    3.327    3.506
 grid_integrate_task_list           110 12.3    3.259    3.405    3.259    3.405
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    3.348    3.403
 prepare_preconditioner              11  7.9    0.000    0.000    3.250    3.269
 make_preconditioner                 11  8.9    0.000    0.000    3.250    3.269
 mp_alltoall_d11v                  2046 13.8    2.555    3.192    2.555    3.192
 pw_transfer                       1331 11.6    0.055    0.066    3.058    3.135
 make_full_inverse_cholesky          11  9.9    0.000    0.000    3.048    3.093
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    2.969    3.049
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.894    2.908
 jit_kernel_multiply                 13 15.9    2.734    2.748    2.734    2.748
 acc_transpose_blocks             49320 15.4    0.212    0.218    2.694    2.746
 fft_wrap_pw1pw2_140                451 13.1    0.389    0.430    2.540    2.639
 potential_pw2rs                    110 12.3    0.005    0.006    2.592    2.610
 fft3d_ps                          1111 14.6    0.795    0.882    2.265    2.321
 grid_collocate_task_list           110  9.6    2.161    2.276    2.161    2.276
 mp_waitany                       14300 13.8    1.825    2.134    1.825    2.134
 transfer_rs2pw                     451 10.6    0.005    0.006    1.882    2.035
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.934    1.955
 make_images_data                  4110 15.4    0.043    0.047    1.757    1.885
 cp_fm_cholesky_invert               11 10.9    1.806    1.810    1.806    1.810
 mp_sum_d                          3889 11.9    1.317    1.804    1.317    1.804
 hybrid_alltoall_any               4261 16.3    0.085    0.483    1.516    1.790
 transfer_pw2rs                     451 13.1    0.006    0.007    1.763    1.772
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.651    1.696
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="200", plot="h2o_128_md", label="(8n/12r/1t)", y=83.609000, yerr=0.000000
PlotPoint: name="201", plot="h2o_128_md_mem", label="(8n/12r/1t)", y=475.000000, yerr=1.858641
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_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             593.330176E+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                2629382.
 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    0.012    0.029   69.931   69.931
 qs_mol_dyn_low                       1  2.0    0.003    0.004   69.637   69.646
 qs_forces                           11  3.9    0.003    0.003   69.556   69.557
 qs_energies                         11  4.9    0.001    0.002   66.198   66.202
 scf_env_do_scf                      11  5.9    0.000    0.001   57.363   57.366
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.007   49.588   49.589
 dbcsr_multiply_generic            2055 12.4    0.116    0.120   38.361   38.490
 velocity_verlet                     10  3.0    0.001    0.001   36.558   36.560
 qs_scf_new_mos                      99  7.5    0.001    0.001   33.567   33.693
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   33.566   33.692
 multiply_cannon                   2055 13.4    0.223    0.245   31.607   32.630
 ot_scf_mini                         99  9.5    0.003    0.003   31.889   32.004
 multiply_cannon_loop              2055 14.4    1.163    1.189   30.332   31.210
 ot_mini                             99 10.5    0.001    0.001   18.569   18.699
 multiply_cannon_multrec          24660 15.4    7.014    8.471   14.249   15.593
 rebuild_ks_matrix                  110  8.3    0.000    0.000   13.632   13.725
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.014   13.631   13.725
 qs_ot_get_derivative                99 11.5    0.001    0.001   12.800   12.918
 qs_ks_update_qs_env                110  7.6    0.001    0.001   11.983   12.061
 mp_waitall_1                    176588 16.5    7.570    9.789    7.570    9.789
 init_scf_loop                       11  6.9    0.000    0.000    7.737    7.738
 multiply_cannon_metrocomm3       24660 15.4    0.071    0.075    5.070    7.612
 dbcsr_mm_accdrv_process          52282 16.1    5.724    6.575    7.064    7.383
 multiply_cannon_sync_h2d         24660 15.4    6.324    7.383    6.324    7.383
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    6.453    7.063
 apply_single                       110 13.6    0.000    0.001    6.452    7.063
 qs_ot_get_p                        110 10.4    0.001    0.001    6.699    6.841
 sum_up_and_integrate               110 10.3    0.001    0.002    6.484    6.496
 integrate_v_rspace                 110 11.3    0.003    0.003    6.457    6.468
 init_scf_run                        11  5.9    0.000    0.002    6.428    6.428
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    6.427    6.428
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.012    6.022
 calculate_rho_elec                 110  8.6    0.039    0.047    6.011    6.022
 ot_diis_step                        99 11.5    0.010    0.011    5.719    5.720
 prepare_preconditioner              11  7.9    0.000    0.000    5.672    5.687
 make_preconditioner                 11  8.9    0.000    0.000    5.671    5.687
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    4.787    5.504
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.245    5.397
 make_m2s                          4110 13.4    0.057    0.060    4.335    4.776
 qs_ot_p2m_diag                      48 11.0    0.029    0.044    4.722    4.742
 make_images                       4110 14.4    0.411    0.471    4.226    4.662
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    4.258    4.258
 pw_transfer                       1331 11.6    0.066    0.076    3.626    3.770
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.675    3.687
 cp_fm_diag_elpa_base                48 14.0    3.628    3.649    3.673    3.683
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.009    3.519    3.667
 wfi_extrapolate                     11  7.9    0.001    0.001    3.547    3.547
 density_rs2pw                      110  9.6    0.004    0.005    3.255    3.441
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.002    3.420    3.421
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.296    3.377
 grid_integrate_task_list           110 12.3    3.160    3.347    3.160    3.347
 calculate_dm_sparse                110  9.5    0.001    0.001    3.130    3.154
 fft_wrap_pw1pw2_140                451 13.1    0.459    0.474    2.954    3.102
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    3.059    3.090
 hybrid_alltoall_any               4261 16.3    0.106    0.463    2.029    2.812
 make_images_data                  4110 15.4    0.048    0.053    2.346    2.787
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.785    2.786
 fft3d_ps                          1111 14.6    1.113    1.337    2.617    2.774
 cp_fm_cholesky_invert               11 10.9    2.672    2.679    2.672    2.679
 mp_sum_l                          6594 12.7    1.804    2.442    1.804    2.442
 potential_pw2rs                    110 12.3    0.008    0.009    2.354    2.367
 grid_collocate_task_list           110  9.6    2.166    2.319    2.166    2.319
 acc_transpose_blocks             24660 15.4    0.115    0.119    2.149    2.178
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.981    2.006
 mp_alltoall_d11v                  2046 13.8    1.807    1.978    1.807    1.978
 jit_kernel_multiply                  9 16.4    0.978    1.943    0.978    1.943
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    1.892    1.893
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.806    1.818
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.688    1.698
 transfer_rs2pw                     451 10.6    0.006    0.007    1.519    1.645
 mp_allgather_i34                  2055 14.4    0.584    1.618    0.584    1.618
 multiply_cannon_metrocomm4       22605 15.4    0.078    0.083    0.789    1.594
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.387    1.492
 mp_irecv_dv                      57340 16.2    0.662    1.472    0.662    1.472
 dbcsr_complete_redistribute        325 12.2    0.243    0.295    1.154    1.423
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="202", plot="h2o_128_md", label="(8n/6r/2t)", y=69.931000, yerr=0.000000
PlotPoint: name="203", plot="h2o_128_md_mem", label="(8n/6r/2t)", y=559.818182, yerr=7.732084
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_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             667.820032E+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    0.040    0.061   61.784   61.785
 qs_mol_dyn_low                       1  2.0    0.003    0.003   61.406   61.419
 qs_forces                           11  3.9    0.003    0.003   61.319   61.321
 qs_energies                         11  4.9    0.002    0.003   58.059   58.064
 scf_env_do_scf                      11  5.9    0.000    0.001   49.577   49.577
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.006   40.693   40.694
 velocity_verlet                     10  3.0    0.001    0.002   33.409   33.412
 dbcsr_multiply_generic            2055 12.4    0.107    0.112   29.655   29.983
 qs_scf_new_mos                      99  7.5    0.001    0.001   25.850   25.981
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   25.850   25.980
 ot_scf_mini                         99  9.5    0.002    0.003   24.582   24.722
 multiply_cannon                   2055 13.4    0.210    0.218   23.169   24.510
 multiply_cannon_loop              2055 14.4    0.816    0.843   21.939   23.174
 ot_mini                             99 10.5    0.001    0.001   14.035   14.180
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.351   12.517
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.014   12.350   12.517
 multiply_cannon_multrec          16440 15.4    3.557    4.732   10.206   11.293
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.844   10.994
 mp_waitall_1                    139946 16.5    7.391   10.291    7.391   10.291
 qs_ot_get_derivative                99 11.5    0.001    0.001    9.496    9.637
 init_scf_loop                       11  6.9    0.000    0.000    8.840    8.841
 multiply_cannon_metrocomm3       16440 15.4    0.045    0.047    4.653    7.669
 prepare_preconditioner              11  7.9    0.000    0.000    7.017    7.039
 make_preconditioner                 11  8.9    0.000    0.000    7.017    7.039
 make_full_inverse_cholesky          11  9.9    0.000    0.000    6.361    6.726
 dbcsr_mm_accdrv_process          34862 16.1    5.800    6.270    6.495    6.678
 sum_up_and_integrate               110 10.3    0.001    0.002    6.386    6.399
 integrate_v_rspace                 110 11.3    0.003    0.003    6.360    6.373
 init_scf_run                        11  5.9    0.000    0.007    6.003    6.004
 scf_env_initial_rho_setup           11  6.9    0.005    0.007    6.003    6.003
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.858    5.868
 calculate_rho_elec                 110  8.6    0.059    0.059    5.858    5.867
 qs_ot_get_p                        110 10.4    0.001    0.001    5.626    5.781
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    5.008    5.519
 apply_single                       110 13.6    0.000    0.000    5.008    5.519
 make_m2s                          4110 13.4    0.049    0.051    4.327    4.715
 make_images                       4110 14.4    0.401    0.527    4.213    4.603
 ot_diis_step                        99 11.5    0.011    0.011    4.504    4.505
 qs_ot_p2m_diag                      48 11.0    0.042    0.044    3.937    3.942
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.278    3.893
 multiply_cannon_sync_h2d         16440 15.4    3.180    3.734    3.180    3.734
 pw_transfer                       1331 11.6    0.066    0.073    3.629    3.642
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.544    3.544
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.009    3.522    3.536
 grid_integrate_task_list           110 12.3    3.192    3.397    3.192    3.397
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    3.292    3.294
 density_rs2pw                      110  9.6    0.004    0.005    3.078    3.250
 fft_wrap_pw1pw2_140                451 13.1    0.579    0.586    3.031    3.050
 wfi_extrapolate                     11  7.9    0.001    0.001    3.019    3.019
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    2.978    2.987
 cp_fm_diag_elpa_base                48 14.0    2.911    2.943    2.976    2.985
 hybrid_alltoall_any               4261 16.3    0.109    0.377    2.241    2.982
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.911    2.971
 make_images_data                  4110 15.4    0.045    0.049    2.461    2.911
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.891    2.897
 cp_fm_cholesky_invert               11 10.9    2.787    2.794    2.787    2.794
 multiply_cannon_metrocomm4       14385 15.4    0.048    0.053    0.906    2.595
 calculate_dm_sparse                110  9.5    0.001    0.001    2.546    2.577
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.502    2.575
 fft3d_ps                          1111 14.6    1.090    1.100    2.465    2.481
 mp_irecv_dv                      48980 15.7    0.831    2.460    0.831    2.460
 grid_collocate_task_list           110  9.6    2.225    2.416    2.225    2.416
 mp_sum_l                          6594 12.7    1.543    2.240    1.543    2.240
 potential_pw2rs                    110 12.3    0.011    0.012    2.202    2.212
 mp_alltoall_d11v                  2046 13.8    1.906    2.135    1.906    2.135
 qs_energies_init_hamiltonians       11  5.9    0.009    0.022    2.011    2.012
 dbcsr_complete_redistribute        325 12.2    0.346    0.415    1.497    1.937
 cp_fm_upper_to_full                 70 14.2    1.409    1.775    1.409    1.775
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.701    1.719
 mp_allgather_i34                  2055 14.4    0.546    1.685    0.546    1.685
 cp_fm_cholesky_decompose            22 10.9    1.650    1.669    1.650    1.669
 acc_transpose_blocks             16440 15.4    0.076    0.078    1.582    1.648
 transfer_rs2pw                     451 10.6    0.005    0.006    1.337    1.521
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.472    1.485
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.355    1.484
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    1.006    1.454
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.321    1.329
 mp_waitany                       17072 13.8    1.121    1.274    1.121    1.274
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="204", plot="h2o_128_md", label="(8n/4r/3t)", y=61.785000, yerr=0.000000
PlotPoint: name="205", plot="h2o_128_md_mem", label="(8n/4r/3t)", y=630.636364, yerr=7.854040
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_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             734.781440E+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    0.010    0.034   66.976   66.981
 qs_mol_dyn_low                       1  2.0    0.003    0.003   66.265   66.277
 qs_forces                           11  3.9    0.003    0.003   66.197   66.198
 qs_energies                         11  4.9    0.001    0.001   62.821   62.825
 scf_env_do_scf                      11  5.9    0.000    0.001   54.293   54.296
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.008   42.123   42.124
 velocity_verlet                     10  3.0    0.002    0.002   36.954   36.957
 dbcsr_multiply_generic            2055 12.4    0.120    0.127   31.206   31.414
 qs_scf_new_mos                      99  7.5    0.001    0.001   27.619   27.724
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   27.619   27.724
 ot_scf_mini                         99  9.5    0.002    0.003   25.944   26.055
 multiply_cannon                   2055 13.4    0.237    0.254   24.115   25.379
 multiply_cannon_loop              2055 14.4    1.401    1.469   22.675   23.278
 ot_mini                             99 10.5    0.001    0.001   15.102   15.224
 multiply_cannon_multrec          24660 15.4    4.213    7.113   13.684   14.806
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.659   12.783
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.013   12.659   12.783
 init_scf_loop                       11  6.9    0.000    0.000   12.131   12.132
 qs_ks_update_qs_env                110  7.6    0.001    0.001   11.270   11.379
 qs_ot_get_derivative                99 11.5    0.001    0.001   10.916   11.022
 dbcsr_mm_accdrv_process          52304 16.0    7.960    9.461    9.313   10.357
 prepare_preconditioner              11  7.9    0.000    0.000    9.658    9.675
 make_preconditioner                 11  8.9    0.000    0.000    9.658    9.675
 make_full_inverse_cholesky          11  9.9    0.000    0.000    7.917    9.347
 sum_up_and_integrate               110 10.3    0.001    0.002    6.272    6.587
 integrate_v_rspace                 110 11.3    0.003    0.003    6.246    6.560
 make_m2s                          4110 13.4    0.059    0.063    5.464    5.877
 qs_ot_get_p                        110 10.4    0.001    0.001    5.686    5.836
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.768    5.778
 calculate_rho_elec                 110  8.6    0.078    0.081    5.767    5.777
 mp_waitall_1                    121746 16.5    4.127    5.776    4.127    5.776
 init_scf_run                        11  5.9    0.000    0.002    5.772    5.773
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.772    5.773
 make_images                       4110 14.4    0.581    0.706    5.323    5.732
 cp_fm_upper_to_full                 70 14.2    3.315    4.790    3.315    4.790
 ot_diis_step                        99 11.5    0.011    0.011    4.146    4.146
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.047    4.136
 apply_single                       110 13.6    0.000    0.000    4.047    4.136
 pw_transfer                       1331 11.6    0.066    0.075    3.712    4.043
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.605    3.939
 qs_ot_p2m_diag                      48 11.0    0.055    0.064    3.837    3.853
 dbcsr_complete_redistribute        325 12.2    0.472    0.526    2.668    3.778
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.492    3.541
 fft_wrap_pw1pw2_140                451 13.1    0.610    0.633    3.120    3.456
 grid_integrate_task_list           110 12.3    3.277    3.452    3.277    3.452
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.319    3.375
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.279    3.279
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    2.157    3.254
 hybrid_alltoall_any               4261 16.3    0.122    0.456    2.287    3.186
 make_images_data                  4110 15.4    0.049    0.053    2.720    3.133
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    3.082    3.084
 calculate_dm_sparse                110  9.5    0.001    0.001    3.006    3.043
 multiply_cannon_metrocomm3       24660 15.4    0.037    0.039    1.372    3.008
 density_rs2pw                      110  9.6    0.004    0.004    2.880    2.996
 wfi_extrapolate                     11  7.9    0.001    0.001    2.984    2.984
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.732    2.813
 fft3d_ps                          1111 14.6    1.085    1.115    2.486    2.800
 mp_alltoall_i22                    605 13.7    1.620    2.794    1.620    2.794
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    2.751    2.760
 cp_fm_diag_elpa_base                48 14.0    2.608    2.664    2.749    2.758
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.695    2.697
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.653    2.689
 cp_fm_cholesky_invert               11 10.9    2.582    2.593    2.582    2.593
 multiply_cannon_sync_h2d         24660 15.4    2.367    2.581    2.367    2.581
 acc_transpose_blocks             24660 15.4    0.113    0.116    2.381    2.505
 grid_collocate_task_list           110  9.6    2.264    2.448    2.264    2.448
 potential_pw2rs                    110 12.3    0.012    0.013    2.082    2.384
 qs_energies_init_hamiltonians       11  5.9    0.009    0.024    2.252    2.253
 jit_kernel_multiply                  8 15.7    1.008    2.182    1.008    2.182
 mp_alltoall_d11v                  2046 13.8    1.785    2.068    1.785    2.068
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.785    1.824
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.611    1.707
 mp_allgather_i34                  2055 14.4    0.523    1.664    0.523    1.664
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.631    1.643
 cp_fm_cholesky_decompose            22 10.9    1.582    1.639    1.582    1.639
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.573    1.593
 mp_alltoall_z22v                  1111 16.6    1.185    1.530    1.185    1.530
 mp_sum_l                          6594 12.7    0.932    1.520    0.932    1.520
 multiply_cannon_metrocomm4       20550 15.4    0.062    0.066    0.855    1.500
 acc_transpose_blocks_sync        73980 16.4    1.367    1.487    1.367    1.487
 mp_irecv_dv                      62702 16.1    0.750    1.413    0.750    1.413
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="206", plot="h2o_128_md", label="(8n/3r/4t)", y=66.981000, yerr=0.000000
PlotPoint: name="207", plot="h2o_128_md_mem", label="(8n/3r/4t)", y=696.090909, yerr=9.317184
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_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             848.445440E+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    0.016    0.037   55.714   55.715
 qs_mol_dyn_low                       1  2.0    0.003    0.003   55.454   55.467
 qs_forces                           11  3.9    0.003    0.003   55.373   55.375
 qs_energies                         11  4.9    0.001    0.002   51.744   51.750
 scf_env_do_scf                      11  5.9    0.000    0.001   43.189   43.189
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.007   35.120   35.120
 velocity_verlet                     10  3.0    0.002    0.002   31.090   31.094
 dbcsr_multiply_generic            2055 12.4    0.105    0.110   23.553   23.696
 qs_scf_new_mos                      99  7.5    0.001    0.001   20.634   20.684
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   20.634   20.683
 ot_scf_mini                         99  9.5    0.002    0.002   19.382   19.403
 multiply_cannon                   2055 13.4    0.236    0.247   17.961   19.313
 multiply_cannon_loop              2055 14.4    0.601    0.623   16.680   16.939
 rebuild_ks_matrix                  110  8.3    0.000    0.000   11.911   11.937
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.013   11.911   11.937
 ot_mini                             99 10.5    0.001    0.001   10.678   10.690
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.630   10.654
 multiply_cannon_multrec           8220 15.4    3.174    4.331    7.950    8.908
 init_scf_loop                       11  6.9    0.000    0.000    8.023    8.023
 mp_waitall_1                    103326 16.6    5.804    7.356    5.804    7.356
 qs_ot_get_derivative                99 11.5    0.001    0.001    6.992    7.010
 sum_up_and_integrate               110 10.3    0.001    0.002    6.178    6.190
 integrate_v_rspace                 110 11.3    0.003    0.003    6.151    6.163
 prepare_preconditioner              11  7.9    0.000    0.000    6.049    6.053
 make_preconditioner                 11  8.9    0.000    0.000    6.049    6.053
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.943    5.956
 calculate_rho_elec                 110  8.6    0.114    0.114    5.942    5.955
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.627    5.710
 dbcsr_mm_accdrv_process          17442 15.9    3.037    4.133    4.637    5.589
 init_scf_run                        11  5.9    0.000    0.002    5.429    5.429
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.429    5.429
 qs_ot_get_p                        110 10.4    0.001    0.001    4.747    4.761
 make_m2s                          4110 13.4    0.038    0.039    4.250    4.542
 make_images                       4110 14.4    0.654    0.715    4.121    4.413
 multiply_cannon_metrocomm3        8220 15.4    0.019    0.019    2.941    4.193
 pw_transfer                       1331 11.6    0.066    0.071    3.828    3.835
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    3.729    3.785
 apply_single                       110 13.6    0.000    0.000    3.729    3.784
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.720    3.729
 ot_diis_step                        99 11.5    0.012    0.012    3.661    3.661
 grid_integrate_task_list           110 12.3    3.361    3.523    3.361    3.523
 qs_ot_p2m_diag                      48 11.0    0.081    0.084    3.375    3.380
 fft_wrap_pw1pw2_140                451 13.1    0.777    0.787    3.214    3.232
 density_rs2pw                      110  9.6    0.004    0.004    2.920    3.043
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.036    3.036
 cp_fm_cholesky_invert               11 10.9    2.923    2.927    2.923    2.927
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.911    2.912
 hybrid_alltoall_any               4261 16.3    0.201    0.855    2.306    2.838
 wfi_extrapolate                     11  7.9    0.001    0.001    2.686    2.686
 make_images_data                  4110 15.4    0.041    0.047    2.283    2.682
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    2.660    2.661
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.647    2.649
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.551    2.559
 grid_collocate_task_list           110  9.6    2.369    2.552    2.369    2.552
 calculate_dm_sparse                110  9.5    0.001    0.001    2.475    2.511
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    2.473    2.480
 cp_fm_diag_elpa_base                48 14.0    2.416    2.437    2.471    2.479
 multiply_cannon_sync_h2d          8220 15.4    2.387    2.477    2.387    2.477
 fft3d_ps                          1111 14.6    1.138    1.179    2.385    2.400
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    2.010    2.037
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.788    1.987
 potential_pw2rs                    110 12.3    0.015    0.015    1.979    1.982
 mp_alltoall_d11v                  2046 13.8    1.739    1.954    1.739    1.954
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    1.922    1.936
 jit_kernel_multiply                  8 15.6    1.289    1.793    1.289    1.793
 cp_fm_cholesky_decompose            22 10.9    1.662    1.684    1.662    1.684
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.609    1.611
 qs_env_update_s_mstruct             11  6.9    0.001    0.001    1.487    1.599
 mp_allgather_i34                  2055 14.4    0.451    1.545    0.451    1.545
 dbcsr_complete_redistribute        325 12.2    0.564    0.583    1.420    1.520
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.428    1.443
 acc_transpose_blocks              8220 15.4    0.039    0.040    1.375    1.412
 qs_create_task_list                 11  7.9    0.001    0.001    1.207    1.306
 generate_qs_task_list               11  8.9    0.372    0.439    1.206    1.305
 transfer_rs2pw                     451 10.6    0.005    0.005    1.124    1.272
 mp_waitany                        9240 13.8    1.063    1.212    1.063    1.212
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.194    1.211
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="208", plot="h2o_128_md", label="(8n/2r/6t)", y=55.715000, yerr=0.000000
PlotPoint: name="209", plot="h2o_128_md_mem", label="(8n/2r/6t)", y=801.363636, yerr=10.890135
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_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               1.360257E+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    0.071    0.260   87.602   87.670
 qs_mol_dyn_low                       1  2.0    0.003    0.003   87.032   87.044
 qs_forces                           11  3.9    0.003    0.004   86.955   86.956
 qs_energies                         11  4.9    0.002    0.002   82.851   82.854
 scf_env_do_scf                      11  5.9    0.001    0.001   72.529   72.529
 velocity_verlet                     10  3.0    0.002    0.003   55.512   55.519
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.007   44.072   44.074
 dbcsr_multiply_generic            2055 12.4    0.119    0.124   29.808   29.910
 init_scf_loop                       11  6.9    0.000    0.000   28.384   28.388
 qs_scf_new_mos                      99  7.5    0.001    0.001   26.898   26.927
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   26.897   26.926
 prepare_preconditioner              11  7.9    0.000    0.000   26.244   26.253
 make_preconditioner                 11  8.9    0.000    0.000   26.244   26.253
 make_full_inverse_cholesky          11  9.9    0.000    0.000   20.429   25.718
 ot_scf_mini                         99  9.5    0.002    0.002   25.099   25.131
 multiply_cannon                   2055 13.4    0.335    0.361   22.616   23.338
 multiply_cannon_loop              2055 14.4    0.821    0.837   20.846   21.292
 cp_fm_upper_to_full                 70 14.2   12.763   18.302   12.763   18.302
 ot_mini                             99 10.5    0.001    0.001   14.225   14.256
 rebuild_ks_matrix                  110  8.3    0.000    0.001   13.666   13.702
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.014   13.666   13.702
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.405   12.437
 dbcsr_complete_redistribute        325 12.2    1.013    1.041    7.369   10.586
 multiply_cannon_multrec           8220 15.4    4.045    4.176    9.963   10.074
 qs_ot_get_derivative                99 11.5    0.001    0.001    9.669    9.695
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    6.358    9.573
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    5.799    8.981
 mp_alltoall_i22                    605 13.7    5.412    8.650    5.412    8.650
 mp_waitall_1                     84994 16.7    7.432    8.267    7.432    8.267
 qs_rho_update_rho_low              110  7.6    0.001    0.001    7.067    7.104
 calculate_rho_elec                 110  8.6    0.224    0.225    7.066    7.103
 sum_up_and_integrate               110 10.3    0.002    0.002    6.688    6.703
 integrate_v_rspace                 110 11.3    0.004    0.004    6.660    6.675
 init_scf_run                        11  5.9    0.000    0.001    5.981    5.981
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.981    5.981
 dbcsr_mm_accdrv_process          11614 15.7    3.874    4.115    5.771    5.962
 make_m2s                          4110 13.4    0.044    0.044    5.330    5.810
 qs_ot_get_p                        110 10.4    0.001    0.001    5.605    5.637
 make_images                       4110 14.4    0.891    0.947    5.141    5.620
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.864    5.355
 apply_single                       110 13.6    0.000    0.000    4.863    5.355
 cp_fm_cholesky_invert               11 10.9    5.207    5.211    5.207    5.211
 multiply_cannon_metrocomm3        8220 15.4    0.019    0.020    4.802    5.116
 pw_transfer                       1331 11.6    0.075    0.076    4.909    4.914
 fft_wrap_pw1pw2                   1111 12.6    0.009    0.010    4.792    4.797
 ot_diis_step                        99 11.5    0.015    0.015    4.540    4.540
 fft_wrap_pw1pw2_140                451 13.1    1.280    1.284    4.186    4.192
 qs_ot_p2m_diag                      48 11.0    0.151    0.157    4.041    4.051
 grid_integrate_task_list           110 12.3    3.673    3.738    3.673    3.738
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    3.731    3.732
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.086    3.695
 density_rs2pw                      110  9.6    0.004    0.004    3.526    3.537
 hybrid_alltoall_any               4261 16.3    0.264    0.571    2.803    3.531
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.525    3.526
 make_images_data                  4110 15.4    0.045    0.049    2.783    3.393
 wfi_extrapolate                     11  7.9    0.001    0.001    3.315    3.315
 calculate_dm_sparse                110  9.5    0.001    0.001    3.172    3.203
 multiply_cannon_sync_h2d          8220 15.4    3.128    3.148    3.128    3.148
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    3.144    3.146
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    2.945    2.945
 cp_fm_diag_elpa_base                48 14.0    2.403    2.607    2.943    2.944
 fft3d_ps                          1111 14.6    1.299    1.303    2.843    2.848
 grid_collocate_task_list           110  9.6    2.665    2.675    2.665    2.675
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.642    2.654
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.625    2.640
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.551    2.553
 qs_env_update_s_mstruct             11  6.9    0.001    0.002    2.242    2.309
 potential_pw2rs                    110 12.3    0.021    0.021    2.219    2.221
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    2.101    2.182
 mp_alltoall_d11v                  2046 13.8    2.049    2.102    2.049    2.102
 jit_kernel_multiply                 10 15.2    1.701    1.998    1.701    1.998
 cp_fm_cholesky_decompose            22 10.9    1.954    1.982    1.954    1.982
 qs_create_task_list                 11  7.9    0.001    0.003    1.879    1.926
 generate_qs_task_list               11  8.9    0.731    0.784    1.878    1.925
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.859    1.863
 acc_transpose_blocks              8220 15.4    0.040    0.041    1.770    1.798
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.742    1.783
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="210", plot="h2o_128_md", label="(8n/1r/12t)", y=87.670000, yerr=0.000000
PlotPoint: name="211", plot="h2o_128_md_mem", label="(8n/1r/12t)", y=1229.727273, yerr=52.863617
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/15/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420241154048       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       11528896499712       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                        93.514757E+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                         6755939872       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             631.439360E+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            3175955098256
   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                2529101.
 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    0.010    0.030  207.385  207.386
 qs_mol_dyn_low                       1  2.0    0.003    0.004  206.932  206.946
 qs_forces                           11  3.9    0.005    0.006  206.844  206.846
 qs_energies                         11  4.9    0.002    0.002  201.256  201.270
 scf_env_do_scf                      11  5.9    0.001    0.001  184.690  184.695
 scf_env_do_scf_inner_loop          117  6.6    0.048    0.094  163.841  163.843
 dbcsr_multiply_generic            2507 12.6    0.180    0.184  125.872  126.391
 qs_scf_new_mos                     117  7.6    0.001    0.001  124.487  124.701
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001  124.487  124.700
 velocity_verlet                     10  3.0    0.001    0.002  123.643  123.644
 ot_scf_mini                        117  9.6    0.003    0.003  117.793  117.982
 multiply_cannon                   2507 13.6    0.239    0.247  102.123  103.803
 multiply_cannon_loop              2507 14.6    2.396    2.458   99.934  101.626
 ot_mini                            117 10.6    0.001    0.001   66.491   66.725
 multiply_cannon_multrec          60168 15.6   31.746   33.407   41.729   43.332
 qs_ot_get_derivative               117 11.6    0.001    0.001   41.760   41.957
 rebuild_ks_matrix                  128  8.3    0.001    0.001   33.549   33.994
 qs_ks_build_kohn_sham_matrix       128  9.3    0.018    0.037   33.548   33.993
 mp_waitall_1                    267128 16.5   28.887   32.272   28.887   32.272
 qs_ks_update_qs_env                128  7.6    0.001    0.001   30.108   30.529
 qs_ot_get_p                        128 10.4    0.001    0.001   29.536   29.895
 multiply_cannon_sync_h2d         60168 15.6   26.370   28.290   26.370   28.290
 apply_preconditioner_dbcsr         128 12.6    0.000    0.001   24.251   24.920
 apply_single                       128 13.6    0.001    0.001   24.251   24.920
 ot_diis_step                       117 11.6    0.008    0.008   24.492   24.493
 qs_ot_p2m_diag                      83 11.4    0.079    0.091   22.594   22.685
 init_scf_loop                       11  6.9    0.000    0.000   20.777   20.779
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002   19.633   19.782
 cp_dbcsr_syevd                      83 12.4    0.005    0.005   19.773   19.773
 multiply_cannon_metrocomm3       60168 15.6    0.119    0.124   16.164   17.877
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   16.823   16.863
 cp_fm_diag_elpa_base                83 14.4   16.753   16.795   16.819   16.860
 prepare_preconditioner              11  7.9    0.000    0.000   15.778   15.823
 make_preconditioner                 11  8.9    0.000    0.000   15.778   15.822
 make_full_inverse_cholesky          11  9.9    0.000    0.000   15.016   15.183
 make_m2s                          5014 13.6    0.104    0.115   13.666   14.020
 sum_up_and_integrate               128 10.3    0.002    0.004   13.980   14.018
 integrate_v_rspace                 128 11.3    0.004    0.004   13.922   13.960
 make_images                       5014 14.6    0.396    0.413   13.483   13.847
 qs_rho_update_rho_low              128  7.7    0.001    0.001   13.101   13.265
 calculate_rho_elec                 128  8.7    0.045    0.064   13.100   13.264
 init_scf_run                        11  5.9    0.000    0.002   12.434   12.435
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   12.434   12.435
 mp_sum_l                          7950 12.9    8.830   10.379    8.830   10.379
 dbcsr_mm_accdrv_process         124484 16.2    4.700    4.858    9.551   10.075
 wfi_extrapolate                     11  7.9    0.001    0.001    9.091    9.091
 cp_fm_cholesky_invert               11 10.9    9.028    9.036    9.028    9.036
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    8.494    8.681
 calculate_dm_sparse                128  9.5    0.001    0.001    8.500    8.567
 multiply_cannon_metrocomm1       60168 15.6    0.095    0.099    6.348    8.505
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    8.044    8.150
 pw_transfer                       1547 11.6    0.074    0.095    7.562    7.739
 make_images_data                  5014 15.6    0.066    0.073    6.662    7.585
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.013    7.360    7.537
 grid_integrate_task_list           128 12.3    7.082    7.479    7.082    7.479
 density_rs2pw                      128  9.7    0.006    0.007    6.734    7.465
 hybrid_alltoall_any               5200 16.5    0.297    2.272    5.846    7.172
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.003    6.794    6.809
 fft_wrap_pw1pw2_140                523 13.2    1.127    1.162    6.476    6.656
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.929    6.109
 fft3d_ps                          1291 14.7    2.192    2.843    5.366    5.704
 mp_alltoall_d11v                  2415 14.1    4.282    5.284    4.282    5.284
 grid_collocate_task_list           128  9.7    4.840    5.189    4.840    5.189
 cp_fm_cholesky_decompose            22 10.9    4.579    4.592    4.579    4.592
 potential_pw2rs                    128 12.3    0.009    0.010    4.484    4.522
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="400", plot="h2o_256_md", label="(8n/12r/1t)", y=207.386000, yerr=0.000000
PlotPoint: name="401", plot="h2o_256_md_mem", label="(8n/12r/1t)", y=597.272727, yerr=6.675476
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/16/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1430460020736       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1958505086976       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1986244964352       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1992000282624       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2753956716544       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       11613089636352       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15239146475520       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15239146475520       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19911124992000       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        94.228663E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.199914E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6806316384       0.0%      0.0%    100.0%
 number of processed stacks               6022464       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1130.2
 marketing flops                   145.647559E+12
 -------------------------------------------------------------------------------
 # multiplications                           2527
 max memory usage/rank             843.247616E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 2425920
 MPI messages size (bytes):
  total size                         4.132350E+12
  min size                           0.000000E+00
  max size                          17.653760E+06
  average size                       1.703416E+06
 MPI breakdown and total messages size (bytes):
             size <=      128               14916                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768               71436               2336489472
     32768 < size <=   131072              728832              55956209664
    131072 < size <=  4194304             1386864            1409906900992
   4194304 < size <= 16777216              155760            1473826772352
  16777216 < size                           68112            1190343475200
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4024                  57903.
 MP_Allreduce        11138                    958.
 MP_Sync                87
 MP_Alltoall          1983                5903276.
 MP_SendRecv         12126                  47072.
 MP_ISendRecv        12126                  47072.
 MP_Wait             26114
 MP_ISend            11836                 212447.
 MP_IRecv            11836                 212447.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.036    0.354  191.017  191.326
 qs_mol_dyn_low                       1  2.0    0.003    0.004  190.299  190.386
 qs_forces                           11  3.9    0.006    0.019  190.197  190.199
 qs_energies                         11  4.9    0.007    0.047  183.374  183.402
 scf_env_do_scf                      11  5.9    0.001    0.006  165.955  165.965
 scf_env_do_scf_inner_loop          118  6.6    0.003    0.009  133.141  133.144
 velocity_verlet                     10  3.0    0.002    0.002  120.079  120.081
 dbcsr_multiply_generic            2527 12.6    0.192    0.201   97.792   99.110
 qs_scf_new_mos                     118  7.6    0.001    0.001   94.479   95.024
 qs_scf_loop_do_ot                  118  8.6    0.001    0.001   94.478   95.024
 ot_scf_mini                        118  9.6    0.004    0.005   89.625   90.264
 multiply_cannon                   2527 13.6    0.505    0.561   77.616   81.922
 multiply_cannon_loop              2527 14.6    1.586    1.661   74.690   77.453
 ot_mini                            118 10.6    0.001    0.001   50.381   51.017
 mp_waitall_1                    216438 16.6   24.096   37.870   24.096   37.870
 multiply_cannon_multrec          30324 15.6   21.149   25.568   31.824   36.743
 rebuild_ks_matrix                  129  8.3    0.001    0.001   32.439   33.101
 qs_ks_build_kohn_sham_matrix       129  9.3    0.017    0.019   32.438   33.100
 init_scf_loop                       11  6.9    0.001    0.004   32.721   32.725
 qs_ks_update_qs_env                129  7.6    0.001    0.001   29.125   29.728
 multiply_cannon_metrocomm3       30324 15.6    0.096    0.101   15.740   29.649
 qs_ot_get_derivative               118 11.6    0.001    0.002   28.220   28.857
 prepare_preconditioner              11  7.9    0.000    0.000   28.387   28.460
 make_preconditioner                 11  8.9    0.000    0.002   28.387   28.460
 make_full_inverse_cholesky          11  9.9    0.000    0.000   27.053   27.616
 apply_preconditioner_dbcsr         129 12.6    0.000    0.000   22.238   23.412
 apply_single                       129 13.6    0.001    0.001   22.237   23.412
 qs_ot_get_p                        129 10.4    0.001    0.002   21.253   22.016
 ot_diis_step                       118 11.6    0.015    0.015   21.978   21.980
 multiply_cannon_sync_h2d         30324 15.6   18.117   20.683   18.117   20.683
 cp_fm_cholesky_invert               11 10.9   16.534   16.547   16.534   16.547
 qs_ot_p2m_diag                      83 11.4    0.189    0.216   16.373   16.407
 make_m2s                          5054 13.6    0.090    0.096   14.219   15.443
 make_images                       5054 14.6    1.192    1.395   14.005   15.228
 cp_dbcsr_syevd                      83 12.4    0.006    0.007   15.167   15.168
 sum_up_and_integrate               129 10.3    0.002    0.004   14.149   14.205
 integrate_v_rspace                 129 11.3    0.003    0.004   14.089   14.148
 qs_rho_update_rho_low              129  7.7    0.001    0.001   13.423   13.461
 calculate_rho_elec                 129  8.7    0.088    0.105   13.422   13.460
 init_scf_run                        11  5.9    0.000    0.002   12.322   12.323
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   12.322   12.323
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   11.992   12.026
 cp_fm_diag_elpa_base                83 14.4   11.737   11.822   11.986   12.015
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002   11.104   11.605
 multiply_cannon_metrocomm4       27797 15.6    0.106    0.119    3.883   11.005
 dbcsr_mm_accdrv_process          62734 16.2    5.471    6.281   10.121   10.752
 mp_irecv_dv                      70031 16.3    3.677   10.593    3.677   10.593
 make_images_data                  5054 15.6    0.067    0.077    8.352    9.863
 hybrid_alltoall_any               5240 16.5    0.355    1.523    7.127    9.234
 pw_transfer                       1559 11.6    0.085    0.098    8.709    8.788
 fft_wrap_pw1pw2                   1301 12.7    0.010    0.011    8.483    8.566
 wfi_extrapolate                     11  7.9    0.001    0.001    8.340    8.340
 fft_wrap_pw1pw2_140                527 13.2    1.224    1.251    7.525    7.613
 grid_integrate_task_list           129 12.3    7.231    7.594    7.231    7.594
 density_rs2pw                      129  9.7    0.006    0.007    7.068    7.442
 qs_ot_get_derivative_taylor         41 13.0    0.001    0.001    6.383    7.183
 cp_fm_cholesky_decompose            22 10.9    6.889    6.978    6.889    6.978
 calculate_dm_sparse                129  9.5    0.001    0.001    6.582    6.725
 mp_sum_l                          8010 12.9    4.169    6.518    4.169    6.518
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.387    6.396
 fft3d_ps                          1301 14.7    2.868    3.038    6.022    6.086
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.494    5.663
 qs_ot_get_orbitals                 118 10.6    0.001    0.001    5.412    5.477
 grid_collocate_task_list           129  9.7    5.044    5.369    5.044    5.369
 mp_alltoall_d11v                  2423 14.1    4.239    4.698    4.239    4.698
 potential_pw2rs                    129 12.3    0.016    0.018    4.580    4.616
 mp_allgather_i34                  2527 14.6    1.437    4.567    1.437    4.567
 mp_sum_d                          4499 12.1    2.656    4.049    2.656    4.049
 dbcsr_complete_redistribute        395 12.7    0.772    0.864    3.176    4.028
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="402", plot="h2o_256_md", label="(8n/6r/2t)", y=191.326000, yerr=0.000000
PlotPoint: name="403", plot="h2o_256_md_mem", label="(8n/6r/2t)", y=803.181818, yerr=2.724241
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/17/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                      2.928533E+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               3984192       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1695.7
 marketing flops                   144.579337E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank             933.593088E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                 1042912
 MPI messages size (bytes):
  total size                         2.716210E+12
  min size                           0.000000E+00
  max size                          26.214400E+06
  average size                       2.604448E+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              281856              36943429632
    131072 < size <=  4194304              660064             996105256960
   4194304 < size <= 16777216               65632             931530938576
  16777216 < size                           28672             751619276800
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3992                  58351.
 MP_Allreduce        11057                   1000.
 MP_Sync                87
 MP_Alltoall          1712                9388896.
 MP_SendRecv          7936                  75008.
 MP_ISendRecv         7936                  75008.
 MP_Wait             21820
 MP_ISend            11748                 275205.
 MP_IRecv            11748                 275205.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.057    0.081  175.344  175.345
 qs_mol_dyn_low                       1  2.0    0.003    0.004  174.457  174.472
 qs_forces                           11  3.9    0.004    0.004  174.364  174.367
 qs_energies                         11  4.9    0.001    0.002  167.595  167.606
 scf_env_do_scf                      11  5.9    0.001    0.002  151.722  151.722
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.008  117.136  117.137
 velocity_verlet                     10  3.0    0.002    0.002  111.769  111.771
 dbcsr_multiply_generic            2507 12.6    0.180    0.184   81.914   83.051
 qs_scf_new_mos                     117  7.6    0.001    0.001   80.127   80.477
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   80.126   80.477
 ot_scf_mini                        117  9.6    0.003    0.004   75.882   76.322
 multiply_cannon                   2507 13.6    0.506    0.528   62.180   67.730
 multiply_cannon_loop              2507 14.6    1.125    1.183   59.248   61.922
 ot_mini                            117 10.6    0.001    0.001   42.582   43.012
 init_scf_loop                       11  6.9    0.000    0.000   34.488   34.488
 mp_waitall_1                    170520 16.6   24.629   33.769   24.629   33.769
 rebuild_ks_matrix                  128  8.3    0.001    0.001   30.424   30.929
 qs_ks_build_kohn_sham_matrix       128  9.3    0.016    0.017   30.423   30.929
 prepare_preconditioner              11  7.9    0.000    0.000   30.500   30.540
 make_preconditioner                 11  8.9    0.000    0.000   30.500   30.540
 make_full_inverse_cholesky          11  9.9    0.000    0.000   28.165   29.591
 qs_ks_update_qs_env                128  7.6    0.001    0.001   27.200   27.664
 multiply_cannon_multrec          20056 15.6   13.150   16.232   22.459   25.585
 multiply_cannon_metrocomm3       20056 15.6    0.062    0.065   15.231   24.401
 qs_ot_get_derivative               117 11.6    0.002    0.002   23.088   23.519
 apply_preconditioner_dbcsr         128 12.6    0.000    0.000   19.565   20.521
 apply_single                       128 13.6    0.001    0.001   19.564   20.520
 ot_diis_step                       117 11.6    0.018    0.018   19.387   19.387
 qs_ot_get_p                        128 10.4    0.001    0.001   18.655   19.177
 make_m2s                          5014 13.6    0.079    0.085   14.681   15.927
 make_images                       5014 14.6    1.158    1.255   14.447   15.684
 multiply_cannon_sync_h2d         20056 15.6   13.747   15.136   13.747   15.136
 qs_ot_p2m_diag                      83 11.4    0.265    0.273   14.357   14.365
 sum_up_and_integrate               128 10.3    0.002    0.003   14.005   14.182
 cp_fm_cholesky_invert               11 10.9   14.118   14.126   14.118   14.126
 integrate_v_rspace                 128 11.3    0.003    0.004   13.946   14.117
 qs_rho_update_rho_low              128  7.7    0.001    0.001   13.476   13.499
 calculate_rho_elec                 128  8.7    0.130    0.145   13.476   13.498
 cp_dbcsr_syevd                      83 12.4    0.005    0.005   13.309   13.309
 init_scf_run                        11  5.9    0.000    0.002   10.885   10.885
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   10.885   10.885
 make_images_data                  5014 15.6    0.062    0.072    8.822   10.506
 hybrid_alltoall_any               5200 16.5    0.449    2.035    7.572   10.203
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   10.124   10.142
 cp_fm_diag_elpa_base                83 14.4    9.720    9.862   10.121   10.140
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002    9.126    9.448
 multiply_cannon_metrocomm4       17549 15.6    0.067    0.076    3.426    9.420
 mp_irecv_dv                      50230 16.2    3.298    9.155    3.298    9.155
 pw_transfer                       1547 11.6    0.085    0.101    8.708    8.967
 dbcsr_mm_accdrv_process          41502 16.2    5.602    5.951    8.764    8.906
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.012    8.484    8.751
 fft_wrap_pw1pw2_140                523 13.2    1.302    1.338    7.561    7.836
 grid_integrate_task_list           128 12.3    7.324    7.731    7.324    7.731
 wfi_extrapolate                     11  7.9    0.001    0.001    7.428    7.428
 cp_fm_cholesky_decompose            22 10.9    7.237    7.264    7.237    7.264
 cp_fm_upper_to_full                105 14.8    5.752    7.247    5.752    7.247
 density_rs2pw                      128  9.7    0.006    0.006    6.816    7.183
 dbcsr_complete_redistribute        395 12.7    1.169    1.200    4.513    6.262
 fft3d_ps                          1291 14.7    2.763    2.987    5.860    6.100
 calculate_dm_sparse                128  9.5    0.001    0.001    5.836    5.943
 grid_collocate_task_list           128  9.7    5.152    5.658    5.152    5.658
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.423    5.429
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    4.630    5.333
 copy_fm_to_dbcsr                   209 11.7    0.002    0.002    3.366    5.107
 mp_alltoall_d11v                  2415 14.1    4.293    4.826    4.293    4.826
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.537    4.655
 mp_sum_l                          7950 12.9    3.226    4.634    3.226    4.634
 mp_allgather_i34                  2507 14.6    1.432    4.573    1.432    4.573
 potential_pw2rs                    128 12.3    0.020    0.022    4.402    4.560
 transfer_fm_to_dbcsr                11  9.9    0.020    0.025    2.316    4.034
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    3.909    3.937
 mp_alltoall_i22                    716 14.1    1.949    3.804    1.949    3.804
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    3.722    3.762
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    3.719    3.720
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="404", plot="h2o_256_md", label="(8n/4r/3t)", y=175.345000, yerr=0.000000
PlotPoint: name="405", plot="h2o_256_md_mem", label="(8n/4r/3t)", y=882.727273, yerr=7.944019
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/18/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1430460020736       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1958505086976       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1986244964352       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1992000282624       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2753956716544       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       11613089636352       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15239146475520       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15239146475520       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19911124992000       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        94.228663E+12       0.0%      0.0%    100.0%
 flops max/rank                      4.387043E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6806316384       0.0%      0.0%    100.0%
 number of processed stacks               6024576       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1129.8
 marketing flops                   145.647559E+12
 -------------------------------------------------------------------------------
 # multiplications                           2527
 max memory usage/rank               1.155740E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1152312
 MPI messages size (bytes):
  total size                         2.039354E+12
  min size                           0.000000E+00
  max size                          17.653760E+06
  average size                       1.769794E+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              321600              36333158400
    131072 < size <=  4194304              721560             792041881600
   4194304 < size <= 16777216               70800             669921260160
  16777216 < size                           30960             541065216000
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4024                  57894.
 MP_Allreduce        11137                   1080.
 MP_Sync                87
 MP_Alltoall          1724               12509439.
 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    0.011    0.031  187.935  187.936
 qs_mol_dyn_low                       1  2.0    0.003    0.003  187.578  187.591
 qs_forces                           11  3.9    0.004    0.004  187.465  187.473
 qs_energies                         11  4.9    0.002    0.002  180.381  180.393
 scf_env_do_scf                      11  5.9    0.001    0.001  163.226  163.236
 velocity_verlet                     10  3.0    0.002    0.002  124.693  124.695
 scf_env_do_scf_inner_loop          118  6.6    0.003    0.008  117.133  117.134
 dbcsr_multiply_generic            2527 12.6    0.189    0.196   81.177   81.915
 qs_scf_new_mos                     118  7.6    0.001    0.001   80.685   81.038
 qs_scf_loop_do_ot                  118  8.6    0.001    0.001   80.685   81.037
 ot_scf_mini                        118  9.6    0.003    0.004   76.081   76.438
 multiply_cannon                   2527 13.6    0.556    0.588   56.241   60.004
 multiply_cannon_loop              2527 14.6    1.822    1.908   52.693   54.279
 init_scf_loop                       11  6.9    0.000    0.000   45.971   45.972
 ot_mini                            118 10.6    0.001    0.001   43.371   43.730
 prepare_preconditioner              11  7.9    0.000    0.000   41.890   41.924
 make_preconditioner                 11  8.9    0.000    0.000   41.890   41.924
 make_full_inverse_cholesky          11  9.9    0.010    0.020   35.529   40.500
 multiply_cannon_multrec          30324 15.6   13.763   18.933   26.758   31.593
 rebuild_ks_matrix                  129  8.3    0.001    0.001   29.431   29.740
 qs_ks_build_kohn_sham_matrix       129  9.3    0.017    0.020   29.431   29.740
 mp_waitall_1                    149060 16.7   17.395   27.115   17.395   27.115
 qs_ks_update_qs_env                129  7.6    0.001    0.001   26.571   26.848
 qs_ot_get_derivative               118 11.6    0.002    0.002   23.654   24.015
 make_m2s                          5054 13.6    0.097    0.101   20.476   21.283
 make_images                       5054 14.6    1.962    2.327   20.165   20.973
 apply_preconditioner_dbcsr         129 12.6    0.000    0.001   19.052   19.610
 apply_single                       129 13.6    0.001    0.001   19.051   19.609
 ot_diis_step                       118 11.6    0.018    0.019   19.588   19.589
 qs_ot_get_p                        129 10.4    0.001    0.001   18.794   19.194
 cp_fm_upper_to_full                105 14.8   11.437   16.804   11.437   16.804
 cp_fm_cholesky_invert               11 10.9   15.935   15.944   15.935   15.944
 multiply_cannon_metrocomm3       30324 15.6    0.049    0.052    6.423   15.023
 qs_ot_p2m_diag                      83 11.4    0.343    0.391   14.551   14.603
 sum_up_and_integrate               129 10.3    0.002    0.003   14.059   14.091
 integrate_v_rspace                 129 11.3    0.003    0.004   13.999   14.031
 qs_rho_update_rho_low              129  7.7    0.001    0.001   13.760   13.809
 calculate_rho_elec                 129  8.7    0.174    0.190   13.759   13.809
 cp_dbcsr_syevd                      83 12.4    0.005    0.006   13.161   13.162
 dbcsr_mm_accdrv_process          62756 16.2    8.449    9.354   12.562   13.106
 dbcsr_complete_redistribute        395 12.7    1.519    1.636    8.974   12.808
 make_images_data                  5054 15.6    0.067    0.073   11.039   12.493
 hybrid_alltoall_any               5240 16.5    0.524    2.108    9.833   11.827
 multiply_cannon_sync_h2d         30324 15.6   10.557   11.366   10.557   11.366
 copy_fm_to_dbcsr                   209 11.7    0.001    0.002    7.593   11.346
 init_scf_run                        11  5.9    0.000    0.002   10.818   10.819
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   10.818   10.819
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002    9.854   10.109
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   10.098   10.109
 cp_fm_diag_elpa_base                83 14.4    9.137    9.443   10.092   10.106
 transfer_fm_to_dbcsr                11  9.9    0.001    0.007    6.338    9.966
 mp_alltoall_i22                    718 14.1    5.599    9.396    5.599    9.396
 pw_transfer                       1559 11.6    0.087    0.103    8.980    9.066
 fft_wrap_pw1pw2                   1301 12.7    0.010    0.011    8.751    8.843
 fft_wrap_pw1pw2_140                527 13.2    1.454    1.480    7.808    7.908
 grid_integrate_task_list           129 12.3    7.555    7.905    7.555    7.905
 wfi_extrapolate                     11  7.9    0.001    0.001    7.600    7.600
 cp_fm_cholesky_decompose            22 10.9    7.419    7.518    7.419    7.518
 density_rs2pw                      129  9.7    0.006    0.006    6.730    7.131
 multiply_cannon_metrocomm4       25270 15.6    0.085    0.094    2.833    7.121
 mp_irecv_dv                      76685 16.2    2.676    6.849    2.676    6.849
 calculate_dm_sparse                129  9.5    0.001    0.001    6.287    6.380
 fft3d_ps                          1301 14.7    2.867    2.956    5.910    5.973
 grid_collocate_task_list           129  9.7    5.325    5.699    5.325    5.699
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.583    5.622
 mp_alltoall_d11v                  2423 14.1    4.869    5.456    4.869    5.456
 qs_energies_init_hamiltonians       11  5.9    0.003    0.003    4.862    4.863
 qs_ot_get_derivative_taylor         41 13.0    0.001    0.001    4.725    4.825
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.484    4.561
 qs_ot_get_orbitals                 118 10.6    0.001    0.001    4.257    4.313
 potential_pw2rs                    129 12.3    0.023    0.023    4.238    4.252
 mp_allgather_i34                  2527 14.6    1.621    4.006    1.621    4.006
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="406", plot="h2o_256_md", label="(8n/3r/4t)", y=187.936000, yerr=0.000000
PlotPoint: name="407", plot="h2o_256_md_mem", label="(8n/3r/4t)", y=1092.454545, yerr=18.132661
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/19/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        1992003932160       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       15239167967232       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15239167967232       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                        94.233007E+12       0.0%      0.0%    100.0%
 flops max/rank                      5.910121E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6806383584       0.0%      0.0%    100.0%
 number of processed stacks               1976928       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    3442.9
 marketing flops                   145.650931E+12
 -------------------------------------------------------------------------------
 # multiplications                           2529
 max memory usage/rank               1.543606E+09
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  242784
 MPI messages size (bytes):
  total size                         1.341806E+12
  min size                           0.000000E+00
  max size                          52.428800E+06
  average size                       5.526748E+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              115008              60297314304
   4194304 < size <= 16777216              105840             554906419200
  16777216 < size                           20352             726592338480
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         9010                     51.
 MP_Alltoall          9724                 794507.
 MP_ISend            40420                2100460.
 MP_IRecv            40420                2099564.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4043                  57624.
 MP_Allreduce        11184                   1163.
 MP_Sync                88
 MP_Alltoall          1724               18848050.
 MP_SendRecv          3870                 122880.
 MP_ISendRecv         3870                 122880.
 MP_Wait             16244
 MP_ISend            10760                 423501.
 MP_IRecv            10760                 423501.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.039    0.067  170.498  170.507
 qs_mol_dyn_low                       1  2.0    0.003    0.003  170.051  170.074
 qs_forces                           11  3.9    0.004    0.005  169.943  169.947
 qs_energies                         11  4.9    0.002    0.002  162.565  162.573
 scf_env_do_scf                      11  5.9    0.001    0.002  144.809  144.820
 velocity_verlet                     10  3.0    0.002    0.002  112.140  112.144
 scf_env_do_scf_inner_loop          118  6.6    0.003    0.008  109.100  109.101
 dbcsr_multiply_generic            2529 12.6    0.182    0.194   72.847   73.301
 qs_scf_new_mos                     118  7.6    0.001    0.001   72.243   72.350
 qs_scf_loop_do_ot                  118  8.6    0.001    0.001   72.242   72.349
 ot_scf_mini                        118  9.6    0.003    0.004   67.806   67.959
 multiply_cannon                   2529 13.6    0.565    0.583   53.999   57.217
 multiply_cannon_loop              2529 14.6    0.818    0.858   51.013   52.006
 ot_mini                            118 10.6    0.001    0.001   37.874   38.019
 init_scf_loop                       11  6.9    0.000    0.000   35.558   35.559
 mp_waitall_1                    126876 16.7   25.289   31.927   25.289   31.927
 prepare_preconditioner              11  7.9    0.000    0.000   31.729   31.771
 make_preconditioner                 11  8.9    0.000    0.000   31.729   31.771
 make_full_inverse_cholesky          11  9.9    0.015    0.025   29.631   29.905
 rebuild_ks_matrix                  129  8.3    0.001    0.001   29.113   29.262
 qs_ks_build_kohn_sham_matrix       129  9.3    0.017    0.018   29.113   29.261
 qs_ks_update_qs_env                129  7.6    0.001    0.001   26.575   26.719
 multiply_cannon_multrec          10116 15.6   10.346   15.488   17.915   22.693
 multiply_cannon_metrocomm3       10116 15.6    0.026    0.027   13.089   20.928
 qs_ot_get_derivative               118 11.6    0.001    0.002   20.575   20.734
 cp_fm_cholesky_invert               11 10.9   18.185   18.192   18.185   18.192
 apply_preconditioner_dbcsr         129 12.6    0.000    0.000   17.308   17.491
 apply_single                       129 13.6    0.001    0.001   17.308   17.490
 ot_diis_step                       118 11.6    0.020    0.020   17.229   17.229
 qs_ot_get_p                        129 10.4    0.001    0.001   17.061   17.201
 make_m2s                          5058 13.6    0.066    0.070   15.021   15.891
 make_images                       5058 14.6    2.198    2.630   14.713   15.586
 sum_up_and_integrate               129 10.3    0.002    0.002   14.117   14.164
 integrate_v_rspace                 129 11.3    0.004    0.004   14.056   14.105
 qs_rho_update_rho_low              129  7.7    0.001    0.001   14.026   14.057
 calculate_rho_elec                 129  8.7    0.258    0.269   14.025   14.057
 qs_ot_p2m_diag                      84 11.4    0.502    0.508   13.301   13.318
 cp_dbcsr_syevd                      84 12.4    0.005    0.006   12.125   12.126
 multiply_cannon_sync_h2d         10116 15.6   10.739   11.452   10.739   11.452
 init_scf_run                        11  5.9    0.000    0.002   10.627   10.627
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   10.626   10.627
 make_images_data                  5058 15.6    0.056    0.065    8.697    9.963
 hybrid_alltoall_any               5245 16.5    0.849    3.811    8.507    9.875
 pw_transfer                       1559 11.6    0.087    0.095    9.238    9.267
 cp_fm_diag_elpa                     84 13.4    0.000    0.000    9.207    9.220
 cp_fm_diag_elpa_base                84 14.4    8.969    9.047    9.204    9.216
 fft_wrap_pw1pw2                   1301 12.7    0.010    0.011    9.013    9.046
 qs_ot_get_derivative_diag           78 12.4    0.002    0.003    8.134    8.250
 grid_integrate_task_list           129 12.3    7.813    8.205    7.813    8.205
 fft_wrap_pw1pw2_140                527 13.2    1.816    1.857    8.003    8.045
 cp_fm_cholesky_decompose            22 10.9    7.863    7.969    7.863    7.969
 dbcsr_mm_accdrv_process          20934 16.1    3.280    4.439    7.216    7.915
 multiply_cannon_metrocomm1       10116 15.6    0.030    0.031    4.296    7.750
 wfi_extrapolate                     11  7.9    0.001    0.001    7.363    7.363
 density_rs2pw                      129  9.7    0.006    0.006    6.651    6.925
 calculate_dm_sparse                129  9.5    0.001    0.001    6.092    6.190
 grid_collocate_task_list           129  9.7    5.620    5.807    5.620    5.807
 multiply_cannon_metrocomm4        7587 15.6    0.026    0.029    1.885    5.770
 fft3d_ps                          1301 14.7    2.791    2.863    5.716    5.752
 mp_irecv_dv                      29102 15.9    1.844    5.676    1.844    5.676
 dbcsr_complete_redistribute        397 12.7    2.118    2.154    5.211    5.579
 qs_energies_init_hamiltonians       11  5.9    0.003    0.003    5.572    5.573
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.437    5.449
 mp_alltoall_d11v                  2429 14.1    4.664    5.043    4.664    5.043
 mp_allgather_i34                  2529 14.6    1.160    4.690    1.160    4.690
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.335    4.397
 potential_pw2rs                    129 12.3    0.026    0.027    4.223    4.229
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    3.581    3.878
 qs_ot_get_orbitals                 118 10.6    0.001    0.001    3.651    3.684
 copy_fm_to_dbcsr                   210 11.7    0.001    0.002    3.375    3.678
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    3.587    3.669
 copy_dbcsr_to_fm                   187 11.8    0.004    0.004    3.444    3.572
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    3.448    3.457
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="408", plot="h2o_256_md", label="(8n/2r/6t)", y=170.507000, yerr=0.000000
PlotPoint: name="409", plot="h2o_256_md_mem", label="(8n/2r/6t)", y=1438.454545, yerr=45.413982
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_performance_tests/20/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        1975684956160       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                        94.245913E+12       0.0%      0.0%    100.0%
 flops max/rank                     11.787674E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6806580192       0.0%      0.0%    100.0%
 number of processed stacks               1982496       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    3433.3
 marketing flops                   145.663816E+12
 -------------------------------------------------------------------------------
 # multiplications                           2535
 max memory usage/rank               3.160375E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                  101400
 MPI messages size (bytes):
  total size                         1.145171E+12
  min size                           0.000000E+00
  max size                         104.857600E+06
  average size                      11.293599E+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               45888              35634806784
   4194304 < size <= 16777216               44720             382939955200
  16777216 < size                           10176             726592540656
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4041                  58586.
 MP_Allreduce        11179                   1500.
 MP_Sync                88
 MP_Alltoall          1724               36993632.
 MP_SendRecv          1806                 218624.
 MP_ISendRecv         1806                 218624.
 MP_Wait              9876
 MP_ISend             6456                1080169.
 MP_IRecv             6456                1080169.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.054    0.084  295.331  295.344
 qs_mol_dyn_low                       1  2.0    0.003    0.004  294.166  294.393
 qs_forces                           11  3.9    0.004    0.005  294.043  294.046
 qs_energies                         11  4.9    0.002    0.002  285.237  285.240
 scf_env_do_scf                      11  5.9    0.001    0.004  262.286  262.291
 velocity_verlet                     10  3.0    0.002    0.002  212.962  212.970
 scf_env_do_scf_inner_loop          118  6.6    0.004    0.009  137.856  137.858
 init_scf_loop                       11  6.9    0.000    0.000  124.152  124.155
 prepare_preconditioner              11  7.9    0.000    0.000  119.288  119.321
 make_preconditioner                 11  8.9    0.000    0.000  119.288  119.321
 make_full_inverse_cholesky          11  9.9    0.038    0.039   95.275  116.356
 qs_scf_new_mos                     118  7.6    0.001    0.001   93.754   93.879
 qs_scf_loop_do_ot                  118  8.6    0.001    0.001   93.753   93.878
 ot_scf_mini                        118  9.6    0.004    0.004   88.765   88.843
 dbcsr_multiply_generic            2535 12.6    0.214    0.227   84.635   85.404
 cp_fm_upper_to_full                106 14.8   52.665   75.684   52.665   75.684
 multiply_cannon                   2535 13.6    0.691    0.723   60.509   61.906
 multiply_cannon_loop              2535 14.6    1.063    1.097   56.098   58.076
 ot_mini                            118 10.6    0.001    0.001   46.086   46.188
 dbcsr_complete_redistribute        397 12.7    3.994    4.047   30.096   43.072
 copy_fm_to_dbcsr                   210 11.7    0.001    0.001   26.523   39.473
 transfer_fm_to_dbcsr                11  9.9    0.030    0.030   23.970   36.785
 mp_alltoall_i22                    720 14.1   21.788   34.927   21.788   34.927
 mp_waitall_1                    104820 16.8   29.470   34.816   29.470   34.816
 rebuild_ks_matrix                  129  8.3    0.001    0.001   34.519   34.646
 qs_ks_build_kohn_sham_matrix       129  9.3    0.018    0.018   34.518   34.645
 cp_fm_cholesky_invert               11 10.9   33.536   33.543   33.536   33.543
 qs_ks_update_qs_env                129  7.6    0.001    0.001   32.078   32.189
 qs_ot_get_p                        129 10.4    0.001    0.001   27.153   27.239
 qs_ot_get_derivative               118 11.6    0.002    0.002   25.507   25.586
 qs_ot_p2m_diag                      84 11.4    0.891    0.897   22.853   22.884
 multiply_cannon_metrocomm3       10140 15.6    0.025    0.027   19.772   21.777
 cp_dbcsr_syevd                      84 12.4    0.006    0.006   21.000   21.002
 make_m2s                          5070 13.6    0.076    0.079   19.173   20.908
 ot_diis_step                       118 11.6    0.022    0.023   20.531   20.531
 make_images                       5070 14.6    3.105    3.315   18.689   20.428
 apply_preconditioner_dbcsr         129 12.6    0.000    0.000   19.710   20.028
 apply_single                       129 13.6    0.001    0.001   19.709   20.027
 multiply_cannon_multrec          10140 15.6   10.413   12.247   18.216   18.261
 cp_fm_diag_elpa                     84 13.4    0.000    0.000   17.698   17.699
 cp_fm_diag_elpa_base                84 14.4   13.209   14.897   17.693   17.694
 qs_rho_update_rho_low              129  7.7    0.001    0.001   16.661   16.668
 calculate_rho_elec                 129  8.7    0.485    0.486   16.661   16.668
 sum_up_and_integrate               129 10.3    0.002    0.002   16.239   16.325
 integrate_v_rspace                 129 11.3    0.004    0.005   16.176   16.261
 multiply_cannon_sync_h2d         10140 15.6   14.406   14.439   14.406   14.439
 hybrid_alltoall_any               5257 16.5    1.322    3.090   11.175   13.741
 make_images_data                  5070 15.6    0.065    0.070   10.923   13.424
 init_scf_run                        11  5.9    0.000    0.001   12.263   12.264
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   12.263   12.264
 pw_transfer                       1559 11.6    0.096    0.097   11.446   11.456
 fft_wrap_pw1pw2                   1301 12.7    0.011    0.012   11.206   11.216
 qs_ot_get_derivative_diag           78 12.4    0.002    0.003   10.110   10.165
 fft_wrap_pw1pw2_140                527 13.2    3.056    3.113    9.963    9.982
 dbcsr_mm_accdrv_process          20958 16.1    4.344    6.067    7.550    9.417
 wfi_extrapolate                     11  7.9    0.001    0.001    9.155    9.155
 cp_fm_cholesky_decompose            22 10.9    8.949    8.971    8.949    8.971
 grid_integrate_task_list           129 12.3    8.617    8.812    8.617    8.812
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    8.467    8.469
 density_rs2pw                      129  9.7    0.005    0.006    7.598    7.646
 mp_alltoall_d11v                  2429 14.1    7.097    7.244    7.097    7.244
 calculate_dm_sparse                129  9.5    0.001    0.001    6.860    6.920
 grid_collocate_task_list           129  9.7    6.467    6.544    6.467    6.544
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.506    6.534
 fft3d_ps                          1301 14.7    2.871    2.887    6.428    6.473
 copy_dbcsr_to_fm                   187 11.8    0.004    0.004    6.308    6.395
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="410", plot="h2o_256_md", label="(8n/1r/12t)", y=295.344000, yerr=0.000000
PlotPoint: name="411", plot="h2o_256_md_mem", label="(8n/1r/12t)", y=2865.636364, yerr=150.735936
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_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               1.259196E+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                2685882.
 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    0.050    0.103   85.147   85.148
 qs_energies                          1  2.0    0.000    0.001   84.347   84.360
 ls_scf                               1  3.0    0.000    0.000   83.428   83.440
 dbcsr_multiply_generic             111  6.7    0.014    0.015   72.438   72.615
 multiply_cannon                    111  7.7    0.017    0.020   55.788   57.056
 multiply_cannon_loop               111  8.7    0.226    0.241   52.394   53.607
 ls_scf_main                          1  4.0    0.000    0.022   52.279   52.290
 density_matrix_trs4                  2  5.0    0.002    0.019   46.753   46.818
 ls_scf_init_scf                      1  4.0    0.000    0.002   28.106   28.108
 ls_scf_init_matrix_S                 1  5.0    0.000    0.001   26.977   27.027
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   24.884   24.902
 mp_waitall_1                     11031 10.9   22.395   24.841   22.395   24.841
 multiply_cannon_multrec           2664  9.7    8.151    8.807   15.537   17.207
 multiply_cannon_sync_h2d          2664  9.7   13.518   15.077   13.518   15.077
 make_m2s                           222  7.7    0.008    0.011   13.045   13.527
 make_images                        222  8.7    0.098    0.108   13.023   13.507
 multiply_cannon_metrocomm1        2664  9.7    0.010    0.011    9.637   12.111
 make_images_data                   222  9.7    0.004    0.005    7.608    8.181
 hybrid_alltoall_any                227 10.6    0.216    1.852    6.534    8.113
 dbcsr_mm_accdrv_process           4760 10.4    0.591    0.727    7.002    7.978
 multiply_cannon_metrocomm3        2664  9.7    0.009    0.010    5.483    7.857
 dbcsr_mm_accdrv_process_sort      4760 11.4    6.209    7.091    6.209    7.091
 calculate_norms                   4752  9.8    5.496    6.132    5.496    6.132
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.028    5.207
 mp_sum_l                           887  5.1    3.130    4.574    3.130    4.574
 make_images_sizes                  222  9.7    0.000    0.000    0.791    3.676
 mp_alltoall_i44                    222 10.7    0.791    3.675    0.791    3.675
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    2.307    3.672
 multiply_cannon_metrocomm4        2442  9.7    0.012    0.015    2.074    3.670
 mp_irecv_dv                       6231 10.9    2.057    3.647    2.057    3.647
 arnoldi_extremal                     4  6.8    0.000    0.000    3.231    3.256
 arnoldi_normal_ev                    4  7.8    0.001    0.003    3.231    3.256
 build_subspace                      16  8.4    0.009    0.012    3.143    3.145
 ls_scf_post                          1  4.0    0.001    0.006    3.043    3.055
 ls_scf_store_result                  1  5.0    0.000    0.000    2.870    2.905
 dbcsr_special_finalize             555  9.7    0.005    0.006    2.295    2.722
 dbcsr_merge_single_wm              555 10.7    0.454    0.567    2.286    2.714
 make_images_pack                   222  9.7    2.205    2.621    2.207    2.622
 dbcsr_matrix_vector_mult           304  9.0    0.006    0.014    2.339    2.584
 dbcsr_sort_data                    658 11.4    2.091    2.482    2.091    2.482
 dbcsr_matrix_vector_mult_local     304 10.0    2.067    2.462    2.069    2.464
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.296    2.416
 buffer_matrices_ensure_size        222  8.7    1.749    2.066    1.749    2.066
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.760    1.761
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.751    1.752
 qs_ks_build_kohn_sham_matrix         3  8.3    0.000    0.001    1.751    1.752
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="500", plot="h2o_32_nrep3_ls", label="(8n/12r/1t)", y=85.148000, 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_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               2.130694E+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    0.022    0.040   92.028   92.028
 qs_energies                          1  2.0    0.000    0.000   91.294   91.298
 ls_scf                               1  3.0    0.000    0.000   89.831   89.835
 dbcsr_multiply_generic             111  6.7    0.015    0.016   75.522   75.825
 multiply_cannon                    111  7.7    0.028    0.042   52.906   58.531
 ls_scf_main                          1  4.0    0.000    0.000   55.442   55.447
 multiply_cannon_loop               111  8.7    0.135    0.147   50.018   53.790
 density_matrix_trs4                  2  5.0    0.002    0.003   49.691   49.957
 ls_scf_init_scf                      1  4.0    0.000    0.000   30.670   30.671
 mp_waitall_1                      9105 10.9   21.237   30.397   21.237   30.397
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   29.270   29.357
 multiply_cannon_multrec           1332  9.7   13.302   17.559   22.586   27.944
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   26.326   26.335
 multiply_cannon_metrocomm3        1332  9.7    0.007    0.008   11.605   21.274
 make_m2s                           222  7.7    0.006    0.008   15.796   16.433
 make_images                        222  8.7    1.366    1.698   15.765   16.403
 dbcsr_mm_accdrv_process           4041 10.4    0.337    0.507    8.879   10.418
 make_images_data                   222  9.7    0.004    0.005    9.121   10.325
 hybrid_alltoall_any                227 10.6    0.541    2.539    8.520   10.126
 dbcsr_mm_accdrv_process_sort      4041 11.4    8.398    9.901    8.398    9.901
 mp_sum_l                           887  5.1    5.343    8.595    5.343    8.595
 multiply_cannon_metrocomm4        1221  9.7    0.007    0.009    3.214    7.847
 mp_irecv_dv                       3311 11.0    3.194    7.788    3.194    7.788
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.988    6.948
 calculate_norms                   2376  9.8    6.051    6.618    6.051    6.618
 multiply_cannon_sync_h2d          1332  9.7    4.922    6.227    4.922    6.227
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.463    5.685
 arnoldi_extremal                     4  6.8    0.000    0.000    4.735    4.748
 arnoldi_normal_ev                    4  7.8    0.001    0.005    4.735    4.748
 build_subspace                      16  8.4    0.014    0.021    4.484    4.487
 ls_scf_post                          1  4.0    0.000    0.000    3.719    3.723
 mp_allgather_i34                   111  8.7    0.877    3.560    0.877    3.560
 ls_scf_store_result                  1  5.0    0.000    0.000    3.423    3.543
 dbcsr_matrix_vector_mult           304  9.0    0.010    0.022    3.197    3.435
 dbcsr_matrix_vector_mult_local     304 10.0    2.766    3.258    2.768    3.260
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.611    2.704
 make_images_pack                   222  9.7    2.048    2.540    2.050    2.542
 dbcsr_data_new                    4174 10.1    2.114    2.406    2.114    2.406
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.004    1.149    2.402
 dbcsr_sort_data                    436 11.2    1.834    2.082    1.834    2.082
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.870    1.872
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.857    1.859
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.001    1.857    1.859
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="502", plot="h2o_32_nrep3_ls", label="(8n/6r/2t)", y=92.028000, 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/aecd330b8c27e8066c26f3d7eb60ac611177003f_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               2.887283E+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    0.097    0.120   93.531   93.531
 qs_energies                          1  2.0    0.000    0.000   92.744   92.748
 ls_scf                               1  3.0    0.000    0.000   91.062   91.065
 dbcsr_multiply_generic             111  6.7    0.016    0.017   74.809   75.238
 ls_scf_main                          1  4.0    0.000    0.000   56.379   56.383
 multiply_cannon                    111  7.7    0.032    0.065   51.676   55.755
 multiply_cannon_loop               111  8.7    0.116    0.127   48.937   52.875
 density_matrix_trs4                  2  5.0    0.002    0.003   50.383   50.522
 mp_waitall_1                      7281 11.0   23.412   33.368   23.412   33.368
 ls_scf_init_scf                      1  4.0    0.000    0.000   30.972   30.974
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   29.775   29.843
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.405   27.415
 multiply_cannon_multrec            888  9.7   12.730   15.339   21.316   24.875
 multiply_cannon_metrocomm3         888  9.7    0.004    0.004   10.555   22.124
 make_m2s                           222  7.7    0.006    0.008   16.548   17.253
 make_images                        222  8.7    1.584    1.850   16.509   17.215
 make_images_data                   222  9.7    0.004    0.004    9.743   10.635
 hybrid_alltoall_any                227 10.6    0.641    2.950    9.151   10.512
 dbcsr_mm_accdrv_process           3754 10.4    0.287    0.501    8.101    9.403
 dbcsr_mm_accdrv_process_sort      3754 11.4    7.665    8.902    7.665    8.902
 mp_sum_l                           887  5.1    4.879    8.170    4.879    8.170
 multiply_cannon_metrocomm1         888  9.7    0.003    0.003    3.753    7.231
 multiply_cannon_sync_h2d           888  9.7    6.082    7.164    6.082    7.164
 multiply_cannon_metrocomm4         777  9.7    0.004    0.005    2.430    6.981
 mp_irecv_dv                       2335 11.1    2.415    6.937    2.415    6.937
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.653    6.421
 arnoldi_extremal                     4  6.8    0.000    0.000    5.460    5.493
 arnoldi_normal_ev                    4  7.8    0.032    0.060    5.460    5.493
 build_subspace                      16  8.4    0.014    0.020    5.106    5.112
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.854    5.079
 calculate_norms                   1584  9.8    4.325    4.708    4.325    4.708
 dbcsr_matrix_vector_mult           304  9.0    0.010    0.021    3.572    3.937
 mp_allgather_i34                   111  8.7    0.844    3.802    0.844    3.802
 ls_scf_post                          1  4.0    0.000    0.000    3.711    3.716
 dbcsr_matrix_vector_mult_local     304 10.0    3.064    3.657    3.066    3.659
 ls_scf_store_result                  1  5.0    0.000    0.000    3.450    3.535
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.863    2.987
 dbcsr_data_new                    4116  9.9    2.110    2.443    2.110    2.443
 dbcsr_sort_data                    325 11.1    1.893    2.203    1.893    2.203
 make_images_sizes                  222  9.7    0.000    0.000    0.957    2.113
 mp_alltoall_i44                    222 10.7    0.957    2.112    0.957    2.112
 dbcsr_finalize                     304  7.8    0.026    0.032    1.613    1.900
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.893    1.895
 make_images_pack                   222  9.7    1.628    1.884    1.631    1.887
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.874    1.876
 qs_ks_build_kohn_sham_matrix         3  8.3    0.000    0.001    1.874    1.876
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="504", plot="h2o_32_nrep3_ls", label="(8n/4r/3t)", y=93.531000, yerr=0.000000
PlotPoint: name="505", plot="h2o_32_nrep3_ls_mem", label="(8n/4r/3t)", y=2242.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_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               3.304518E+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    0.030    0.047   98.331   98.331
 qs_energies                          1  2.0    0.000    0.000   97.351   97.355
 ls_scf                               1  3.0    0.000    0.000   95.707   95.712
 dbcsr_multiply_generic             111  6.7    0.017    0.019   78.979   79.217
 ls_scf_main                          1  4.0    0.000    0.000   59.122   59.123
 multiply_cannon                    111  7.7    0.052    0.127   51.965   56.618
 density_matrix_trs4                  2  5.0    0.002    0.003   52.969   53.093
 multiply_cannon_loop               111  8.7    0.152    0.168   46.798   50.378
 ls_scf_init_scf                      1  4.0    0.000    0.000   33.370   33.372
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   32.111   32.194
 mp_waitall_1                      6369 11.0   22.833   30.689   22.833   30.689
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   29.602   29.614
 multiply_cannon_multrec           1332  9.7   14.139   17.358   22.046   25.158
 make_m2s                           222  7.7    0.007    0.008   21.244   22.684
 make_images                        222  8.7    3.152    3.615   21.193   22.635
 multiply_cannon_metrocomm3        1332  9.7    0.003    0.004    9.287   17.145
 make_images_data                   222  9.7    0.004    0.004   11.868   13.520
 hybrid_alltoall_any                227 10.6    0.796    3.784   11.201   12.892
 dbcsr_mm_accdrv_process           3641 10.4    0.303    0.483    7.544    9.043
 dbcsr_mm_accdrv_process_sort      3641 11.4    7.103    8.545    7.103    8.545
 mp_sum_l                           887  5.1    4.187    7.564    4.187    7.564
 multiply_cannon_sync_h2d          1332  9.7    5.391    6.197    5.391    6.197
 multiply_cannon_metrocomm4        1110  9.7    0.005    0.007    2.088    6.082
 mp_irecv_dv                       3229 10.9    2.063    6.035    2.063    6.035
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.280    5.897
 arnoldi_extremal                     4  6.8    0.000    0.000    5.373    5.390
 arnoldi_normal_ev                    4  7.8    0.023    0.032    5.373    5.390
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.003    2.506    5.277
 build_subspace                      16  8.4    0.014    0.021    5.022    5.030
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.622    4.784
 mp_allgather_i34                   111  8.7    2.179    4.612    2.179    4.612
 calculate_norms                   2376  9.8    4.210    4.604    4.210    4.604
 dbcsr_matrix_vector_mult           304  9.0    0.010    0.021    3.703    3.973
 dbcsr_matrix_vector_mult_local     304 10.0    3.261    3.765    3.263    3.767
 dbcsr_sort_data                    658 11.4    3.078    3.432    3.078    3.432
 dbcsr_special_finalize             555  9.7    0.006    0.007    2.823    3.228
 dbcsr_merge_single_wm              555 10.7    0.538    0.661    2.815    3.220
 ls_scf_post                          1  4.0    0.000    0.000    3.215    3.219
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    3.004    3.055
 ls_scf_store_result                  1  5.0    0.000    0.000    2.945    3.016
 dbcsr_data_release               10477 10.7    1.585    2.388    1.585    2.388
 dbcsr_finalize                     304  7.8    0.049    0.061    1.802    1.980
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="506", plot="h2o_32_nrep3_ls", label="(8n/3r/4t)", y=98.331000, yerr=0.000000
PlotPoint: name="507", plot="h2o_32_nrep3_ls_mem", label="(8n/3r/4t)", y=2773.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_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               4.735697E+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    0.038    0.057   93.038   93.039
 qs_energies                          1  2.0    0.000    0.000   91.888   91.893
 ls_scf                               1  3.0    0.000    0.000   89.947   89.951
 dbcsr_multiply_generic             111  6.7    0.018    0.019   71.121   71.319
 ls_scf_main                          1  4.0    0.000    0.000   56.500   56.500
 multiply_cannon                    111  7.7    0.095    0.149   52.923   55.999
 multiply_cannon_loop               111  8.7    0.088    0.094   49.958   51.096
 density_matrix_trs4                  2  5.0    0.002    0.003   49.530   49.611
 ls_scf_init_scf                      1  4.0    0.000    0.000   30.015   30.018
 mp_waitall_1                      5436 11.0   24.338   29.044   24.338   29.044
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   28.582   28.613
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   26.484   26.496
 multiply_cannon_multrec            444  9.7   13.700   16.571   20.772   22.120
 multiply_cannon_metrocomm1         444  9.7    0.002    0.002   10.977   15.562
 make_m2s                           222  7.7    0.005    0.005   13.472   14.431
 make_images                        222  8.7    2.043    2.484   13.405   14.363
 multiply_cannon_metrocomm3         444  9.7    0.001    0.002    5.977   13.442
 make_images_data                   222  9.7    0.003    0.004    8.201    9.791
 hybrid_alltoall_any                227 10.6    0.802    3.824    8.107    9.504
 dbcsr_mm_accdrv_process           3003 10.4    0.353    0.405    6.764    7.883
 multiply_cannon_sync_h2d           444  9.7    6.738    7.765    6.738    7.765
 dbcsr_mm_accdrv_process_sort      3003 11.4    6.400    7.477    6.400    7.477
 arnoldi_extremal                     4  6.8    0.000    0.000    6.060    6.074
 arnoldi_normal_ev                    4  7.8    0.002    0.005    6.060    6.074
 build_subspace                      16  8.4    0.015    0.020    5.664    5.669
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.475    4.640
 dbcsr_matrix_vector_mult           304  9.0    0.011    0.021    4.343    4.510
 mp_sum_l                           887  5.1    2.734    4.365    2.734    4.365
 dbcsr_matrix_vector_mult_local     304 10.0    3.820    4.297    3.822    4.299
 calculate_norms                    792  9.8    3.623    3.760    3.623    3.760
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    1.913    3.754
 multiply_cannon_metrocomm4         333  9.7    0.001    0.002    1.517    3.680
 mp_irecv_dv                       1241 11.2    1.505    3.659    1.505    3.659
 mp_allgather_i34                   111  8.7    1.172    3.610    1.172    3.610
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    3.506    3.578
 ls_scf_post                          1  4.0    0.000    0.000    3.432    3.437
 make_images_sizes                  222  9.7    0.000    0.000    0.881    3.283
 mp_alltoall_i44                    222 10.7    0.881    3.283    0.881    3.283
 ls_scf_store_result                  1  5.0    0.000    0.000    3.228    3.253
 dbcsr_finalize                     304  7.8    0.062    0.077    2.196    2.314
 dbcsr_data_new                    4608  9.7    1.779    2.196    1.779    2.196
 dbcsr_merge_all                    275  8.9    0.481    0.529    2.055    2.147
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.023    2.023
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.990    1.990
 qs_ks_build_kohn_sham_matrix         3  8.3    0.000    0.001    1.990    1.990
 qs_energies_init_hamiltonians        1  3.0    0.001    0.002    1.925    1.925
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="508", plot="h2o_32_nrep3_ls", label="(8n/2r/6t)", y=93.039000, yerr=0.000000
PlotPoint: name="509", plot="h2o_32_nrep3_ls_mem", label="(8n/2r/6t)", y=3717.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_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               8.879854E+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    0.074    0.095  106.525  106.526
 qs_energies                          1  2.0    0.000    0.000  104.928  104.933
 ls_scf                               1  3.0    0.000    0.000  101.978  101.982
 dbcsr_multiply_generic             111  6.7    0.024    0.027   74.948   75.078
 ls_scf_main                          1  4.0    0.000    0.000   64.086   64.086
 density_matrix_trs4                  2  5.0    0.002    0.003   55.163   55.224
 multiply_cannon                    111  7.7    0.160    0.320   48.405   50.542
 multiply_cannon_loop               111  8.7    0.098    0.100   45.452   46.014
 ls_scf_init_scf                      1  4.0    0.000    0.000   34.092   34.093
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   32.207   32.231
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   29.501   29.509
 mp_waitall_1                      4527 11.1   21.984   25.533   21.984   25.533
 make_m2s                           222  7.7    0.005    0.005   22.791   23.841
 make_images                        222  8.7    3.584    3.899   22.683   23.732
 multiply_cannon_multrec            444  9.7   17.857   18.480   22.499   23.159
 hybrid_alltoall_any                227 10.6    1.654    3.615   12.908   15.899
 make_images_data                   222  9.7    0.003    0.004   13.155   15.278
 multiply_cannon_metrocomm3         444  9.7    0.001    0.002   10.229   10.654
 multiply_cannon_sync_h2d           444  9.7    8.795    8.850    8.795    8.850
 arnoldi_extremal                     4  6.8    0.000    0.000    7.758    7.768
 arnoldi_normal_ev                    4  7.8    0.003    0.009    7.758    7.768
 build_subspace                      16  8.4    0.026    0.036    7.208    7.220
 dbcsr_matrix_vector_mult           304  9.0    0.017    0.033    5.791    5.949
 dbcsr_matrix_vector_mult_local     304 10.0    5.314    5.635    5.317    5.638
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    5.070    5.170
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.849    5.109
 dbcsr_mm_accdrv_process           1814 10.4    0.294    0.368    4.458    4.576
 dbcsr_mm_accdrv_process_sort      1814 11.4    4.116    4.248    4.116    4.248
 ls_scf_post                          1  4.0    0.000    0.000    3.801    3.806
 make_images_sizes                  222  9.7    0.000    0.000    1.497    3.673
 mp_alltoall_i44                    222 10.7    1.497    3.672    1.497    3.672
 ls_scf_store_result                  1  5.0    0.000    0.000    3.517    3.552
 mp_allgather_i34                   111  8.7    1.064    3.374    1.064    3.374
 calculate_norms                    792  9.8    3.224    3.269    3.224    3.269
 dbcsr_finalize                     304  7.8    0.082    0.089    3.075    3.184
 dbcsr_merge_all                    275  8.9    0.885    0.912    2.857    2.959
 qs_energies_init_hamiltonians        1  3.0    0.001    0.001    2.917    2.917
 dbcsr_complete_redistribute          5  7.6    1.426    1.463    2.740    2.862
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.598    2.600
 rebuild_ks_matrix                    3  7.3    0.000    0.000    2.532    2.534
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.001    2.532    2.534
 matrix_ls_to_qs                      2  6.0    0.000    0.000    2.386    2.528
 dbcsr_sort_data                    325 11.1    2.441    2.513    2.441    2.513
 dbcsr_new_transposed                 4  7.5    0.242    0.253    2.302    2.322
 dbcsr_data_new                    6591  9.6    1.832    2.247    1.832    2.247
 dbcsr_frobenius_norm                74  6.6    2.055    2.127    2.202    2.239
 dbcsr_add_d                        103  6.2    0.000    0.000    2.142    2.225
 dbcsr_add_anytype                  103  7.2    0.859    0.890    2.142    2.224
 dbcsr_data_release               12724 10.6    1.983    2.218    1.983    2.218
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="510", plot="h2o_32_nrep3_ls", label="(8n/1r/12t)", y=106.526000, yerr=0.000000
PlotPoint: name="511", plot="h2o_32_nrep3_ls_mem", label="(8n/1r/12t)", y=6997.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/aecd330b8c27e8066c26f3d7eb60ac611177003f_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             588.849152E+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              659536088.
 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    0.019    0.050  228.973  228.974
 qs_mol_dyn_low                       1  2.0    0.004    0.032  227.701  227.724
 qs_forces                            5  3.8    0.004    0.007  227.573  227.575
 qs_energies                          5  4.8    0.002    0.003  224.295  224.315
 scf_env_do_scf                       5  5.8    0.000    0.001  210.555  210.558
 scf_env_do_scf_inner_loop          105  6.6    0.002    0.006  183.328  183.329
 qs_scf_new_mos                     105  7.6    0.000    0.001  142.903  143.144
 qs_scf_loop_do_ot                  105  8.6    0.001    0.001  142.902  143.144
 ot_scf_mini                        105  9.6    0.003    0.004  133.076  133.283
 dbcsr_multiply_generic            1445 12.2    0.354    0.515  132.696  133.076
 multiply_cannon                   1445 13.2    0.275    0.286  113.194  115.217
 multiply_cannon_loop              1445 14.2    2.849    3.010  111.435  112.583
 velocity_verlet                      4  3.0    0.002    0.014  106.360  106.361
 ot_mini                            105 10.6    0.001    0.001   60.259   60.383
 multiply_cannon_multrec          69360 15.2   29.659   34.826   39.956   44.841
 qs_ot_get_p                        112 10.4    0.001    0.001   42.830   43.104
 mp_waitall_1                    488190 16.1   34.746   41.492   34.746   41.492
 qs_ot_get_derivative                55 11.6    0.001    0.001   38.491   38.639
 multiply_cannon_sync_h2d         69360 15.2   29.186   32.828   29.186   32.828
 multiply_cannon_metrocomm3       69360 15.2    0.200    0.211   25.646   32.524
 qs_ot_p2m_diag                      40 11.0    0.020    0.030   31.961   32.054
 rebuild_ks_matrix                  110  8.4    0.000    0.000   29.304   29.492
 qs_ks_build_kohn_sham_matrix       110  9.4    0.011    0.012   29.304   29.491
 cp_dbcsr_syevd                      40 12.0    0.002    0.002   28.593   28.594
 init_scf_loop                        7  6.6    0.000    0.000   27.189   27.190
 qs_ks_update_qs_env                112  7.6    0.001    0.001   26.643   26.816
 cp_fm_syevd                         40 13.0    0.000    0.000   23.414   23.546
 apply_preconditioner_dbcsr          62 12.6    0.000    0.000   23.045   23.257
 apply_single                        62 13.6    0.000    0.000   23.045   23.257
 prepare_preconditioner               7  7.6    0.000    0.000   22.342   22.372
 make_preconditioner                  7  8.6    0.000    0.000   22.342   22.372
 ot_new_cg_direction                 55 11.6    0.001    0.001   21.027   21.027
 cp_fm_redistribute_end              40 14.0    9.340   18.636    9.344   18.637
 cp_fm_syevd_base                    40 14.0    9.285   18.583    9.285   18.583
 qs_rho_update_rho_low              110  7.6    0.001    0.001   17.173   17.540
 calculate_rho_elec                 110  8.6    0.030    0.032   17.173   17.540
 qs_ot_get_orbitals                 105 10.6    0.001    0.001   14.756   14.920
 make_full_inverse_cholesky           7  9.6    0.000    0.000   14.527   14.588
 qs_ot_get_derivative_taylor         37 12.8    0.001    0.001   13.737   13.867
 mp_sum_l                          4764 12.2   11.947   12.797   11.947   12.797
 pw_transfer                       1645 12.4    0.080    0.101   12.139   12.379
 fft_wrap_pw1pw2                   1425 13.5    0.012    0.016   12.000   12.247
 density_rs2pw                      110  9.6    0.005    0.007   11.372   11.950
 calculate_dm_sparse                110  9.5    0.000    0.001   11.440   11.678
 init_scf_run                         5  5.8    0.000    0.001   11.132   11.133
 scf_env_initial_rho_setup            5  6.8    0.005    0.007   11.132   11.133
 dbcsr_mm_accdrv_process         154766 15.8    6.223    6.477   10.164   11.020
 fft_wrap_pw1pw2_240                915 15.0    1.142    1.234   10.582   10.799
 qs_vxc_create                      110 10.4    0.002    0.006   10.523   10.561
 qs_ot_get_derivative_diag           18 12.0    0.000    0.001   10.457   10.546
 cp_fm_cholesky_invert                7 10.6   10.037   10.045   10.037   10.045
 check_diag                          80 13.5    8.683    8.938    9.614    9.746
 fft3d_pb                           915 16.0    2.397    2.630    8.779    9.057
 sum_up_and_integrate                60 10.3    0.001    0.002    8.703    8.759
 integrate_v_rspace                  60 11.3    0.002    0.002    8.686    8.742
 transfer_rs2pw                     445 10.6    0.007    0.008    8.011    8.580
 xc_rho_set_and_dset_create         110 12.4    0.076    0.098    7.421    7.674
 make_m2s                          2890 13.2    0.079    0.088    6.853    7.606
 make_full_single_inverse             7  9.6    0.001    0.001    7.534    7.563
 make_images                       2890 14.2    0.240    0.260    6.746    7.495
 multiply_cannon_metrocomm1       69360 15.2    0.096    0.102    4.543    7.167
 xc_vxc_pw_create                    60 11.3    0.039    0.053    7.042    7.080
 acc_transpose_blocks             69360 15.2    0.350    0.366    6.146    6.466
 cp_dbcsr_sm_fm_multiply             15  9.3    0.002    0.045    6.435    6.452
 xc_pw_derive                       510 13.4    0.005    0.006    6.302    6.366
 calculate_first_density_matrix       1  7.0    0.000    0.001    6.284    6.305
 mp_alltoall_z22v                  2340 17.7    5.810    6.106    5.810    6.106
 cp_dbcsr_sm_fm_multiply_core        15 10.3    0.000    0.000    5.925    5.975
 mp_waitany                        7680 13.5    4.495    5.027    4.495    5.027
 potential_pw2rs                     60 12.3    0.003    0.003    4.942    5.012
 multiply_cannon_metrocomm4       67915 15.2    0.182    0.199    2.022    4.870
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="601", plot="h2o_512_md", label="(64n/12r/1t)", y=228.974000, yerr=0.000000
PlotPoint: name="602", plot="h2o_512_md_mem", label="(64n/12r/1t)", y=560.600000, yerr=1.959592
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


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

CommitSHA: aecd330b8c27e8066c26f3d7eb60ac611177003f
Summary: empty
Status: OK