=== 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: fdb0e7a97118f01e42b96d3a441284ab6d74f5d5


################# 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,
#              LIBGRPP 20231215
#
# 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: 15.12.2023
#
# \
   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_LIBGRPP    := 20231215
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_LIBGRPP),)
   USE_LIBGRPP    := $(strip $(USE_LIBGRPP))
   LIBGRPP_INC    := $(INSTALL_PATH)/libgrpp-main-$(USE_LIBGRPP)/include
   LIBGRPP_LIB    := $(INSTALL_PATH)/libgrpp-main-$(USE_LIBGRPP)/lib
   CFLAGS         += -I$(LIBGRPP_INC)
   DFLAGS         += -D__LIBGRPP
   LIBS           += $(LIBGRPP_LIB)/liblibgrpp.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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/01
 job id: 50569568
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/02
 job id: 50569569
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/03
 job id: 50569570
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/04
 job id: 50569571
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/05
 job id: 50569572
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/06
 job id: 50569573
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/07
 job id: 50569574
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/08
 job id: 50569575
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/09
 job id: 50569576
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/10
 job id: 50569577
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/11
 job id: 50569580
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/12
 job id: 50569581
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/13
 job id: 50569582
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/14
 job id: 50569583
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/15
 job id: 50569584
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/16
 job id: 50569585
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/17
 job id: 50569587
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/18
 job id: 50569588
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/19
 job id: 50569590
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/20
 job id: 50569593
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/21
 job id: 50569598
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/22
 job id: 50569601
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/23
 job id: 50569605
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/24
 job id: 50569607
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/25
 job id: 50569611
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/26
 job id: 50569614
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/27
 job id: 50569617
 --- 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/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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                 172669.
 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    0.033  134.462  134.463
 farming_run                          1  2.0  133.914  133.916  134.435  134.439
 -------------------------------------------------------------------------------


 @@@@@@@@@@ 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               1.486877E+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    0.025  115.034  115.035
 qs_energies                          1  2.0    0.000    0.000  114.764  114.767
 mp2_main                             1  3.0    0.000    0.000  112.638  112.641
 mp2_gpw_main                         1  4.0    0.033    0.040  111.634  111.637
 mp2_ri_gpw_compute_in                1  5.0    0.172    0.179   92.857   92.967
 mp2_ri_gpw_compute_in_loop           1  6.0    0.003    0.004   54.568   54.678
 mp2_eri_3c_integrate_gpw           272  7.0    0.152    0.169   40.979   45.754
 get_2c_integrals                     1  6.0    0.008    0.009   36.991   38.115
 integrate_v_rspace                 273  8.0    0.436    0.451   24.546   29.021
 pw_transfer                       6555 10.6    0.380    0.391   26.735   26.888
 fft_wrap_pw1pw2                   5465 11.4    0.047    0.048   25.357   25.551
 grid_integrate_task_list           273  9.0   20.462   25.359   20.462   25.359
 fft_wrap_pw1pw2_100               2178 12.4    0.029    0.031   22.877   23.071
 compute_2c_integrals                 1  7.0    0.002    0.002   19.020   19.026
 cp_fm_cholesky_decompose            12  8.2   17.924   19.026   17.924   19.026
 compute_2c_integrals_loop_lm         1  8.0    0.002    0.003   18.564   18.750
 mp2_eri_2c_integrate_gpw             1  9.0    2.391    2.430   18.563   18.749
 rpa_ri_compute_en                    1  5.0    0.019    0.023   18.665   18.744
 cholesky_decomp                      1  7.0    0.000    0.000   16.831   17.937
 fft3d_s                           5443 13.4   16.038   16.213   16.059   16.233
 ao_to_mo_and_store_B_mult_1        272  7.0   10.765   15.305   10.765   15.305
 calculate_wavefunction             272  8.0    5.433    5.514   12.342   13.073
 rpa_num_int                          1  6.0    0.001    0.010   10.611   10.621
 rpa_num_int_RPA_matrix_operati       8  7.0    0.000    0.000   10.584   10.614
 calc_mat_Q                           8  8.0    0.000    0.000    9.457    9.534
 contract_S_to_Q                      8  9.0    0.000    0.000    8.880    8.956
 calc_potential_gpw                 544  9.5    0.004    0.005    8.229    8.693
 parallel_gemm_fm                    14  9.1    0.000    0.000    8.472    8.574
 parallel_gemm_fm_cosma              14 10.1    8.472    8.574    8.472    8.574
 mp2_eri_2c_integrate_gpw_pot_l     272 10.0    0.001    0.001    8.056    8.270
 potential_pw2rs                    545 10.0    0.107    0.108    7.462    8.058
 create_integ_mat                     1  6.0    0.027    0.043    7.849    7.859
 collocate_single_gaussian          272 10.0    0.040    0.043    7.310    7.561
 array2fm                             1  7.0    0.000    0.000    6.628    7.206
 pw_scatter_s                      2720 13.7    4.341    4.500    4.341    4.500
 pw_gather_s                       2722 13.2    3.448    3.807    3.448    3.807
 array2fm_buffer_send                 1  8.0    2.952    3.079    2.952    3.079
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="10", plot="h2o_32_ri_rpa_mp2", label="RI-RPA (8n/2r/6t)", y=111.637474, yerr=0.000000
PlotPoint: name="11", plot="h2o_32_ri_rpa_mp2_mem", label="RI-RPA (8n/2r/6t)", y=2788.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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                 200775.
 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    0.044    0.083  422.809  422.811
 farming_run                          1  2.0  421.940  421.947  422.748  422.772
 -------------------------------------------------------------------------------


 @@@@@@@@@@ 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         897827128576       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                          249788821       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               1.236648E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                   61440
 MPI messages size (bytes):
  total size                         6.073508E+09
  min size                           0.000000E+00
  max size                         642.960000E+03
  average size                      98.852664E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               32004                        0
       128 < size <=     8192                1820                 14909440
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072               18640               1081442304
    131072 < size <=  4194304                8976               4977156096
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         1003                     44.
 MP_Alltoall          1797                 713538.
 MP_ISend             3686                  54943.
 MP_IRecv             3622                  54292.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group               12
 MP_Bcast              757                 478553.
 MP_Allreduce         2021                  21391.
 MP_Sync                37
 MP_Alltoall            77
 MP_SendRecv          2876                2171486.
 MP_ISendRecv         1034                 172620.
 MP_Wait              1346
 MP_comm_split           7
 MP_ISend              264                 362227.
 MP_IRecv              264                 362718.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.011    0.031  217.043  217.044
 qs_energies                          1  2.0    0.006    0.022  216.759  216.813
 scf_env_do_scf                       1  3.0    0.000    0.000  114.731  114.731
 qs_ks_update_qs_env                  5  5.0    0.000    0.000  113.790  113.797
 rebuild_ks_matrix                    4  6.0    0.000    0.000  113.789  113.796
 qs_ks_build_kohn_sham_matrix         4  7.0    0.054    0.062  113.789  113.796
 hfx_ks_matrix                        4  8.0    0.001    0.001  113.445  113.450
 integrate_four_center                4  9.0    0.154    0.460  113.445  113.449
 integrate_four_center_main           4 10.0    0.143    0.596  102.051  105.382
 integrate_four_center_bin          264 11.0  101.908  105.365  101.908  105.365
 mp2_main                             1  3.0    0.034    0.158  101.714  101.752
 mp2_gpw_main                         1  4.0    0.080    0.172  100.768  100.796
 init_scf_loop                        1  4.0    0.000    0.000   96.805   96.805
 mp2_ri_gpw_compute_in                1  5.0    0.078    0.122   73.932   74.992
 mp2_ri_gpw_compute_in_loop           1  6.0    0.002    0.010   53.755   54.818
 mp2_eri_3c_integrate_gpw            91  7.0    0.143    0.159   41.529   46.555
 integrate_v_rspace                  95  8.0    0.396    0.562   27.985   32.845
 pw_transfer                       2240 10.6    0.144    0.160   29.492   29.980
 fft_wrap_pw1pw2                   1868 11.4    0.018    0.020   28.507   29.021
 ao_to_mo_and_store_B_mult_1         91  7.0   10.560   28.807   10.560   28.807
 grid_integrate_task_list            95  9.0   23.411   28.470   23.411   28.470
 mp2_ri_gpw_compute_en                1  5.0    0.060    0.070   26.530   28.125
 fft_wrap_pw1pw2_100                730 12.4    0.013    0.014   26.248   26.652
 mp2_ri_gpw_compute_en_RI_loop        1  6.0    1.844    1.890   24.831   24.839
 get_2c_integrals                     1  6.0    0.009    0.049   20.047   20.110
 compute_2c_integrals                 1  7.0    0.004    0.012   19.024   19.047
 compute_2c_integrals_loop_lm         1  8.0    0.001    0.001   18.624   18.910
 mp2_eri_2c_integrate_gpw             1  9.0    1.733    1.874   18.623   18.908
 fft3d_s                           1823 13.4   18.479   18.765   18.492   18.779
 scf_env_do_scf_inner_loop            4  4.0    0.000    0.000   17.925   17.925
 calculate_wavefunction              91  8.0    2.027    2.060    9.635    9.839
 mp2_ri_gpw_compute_en_expansio     172  7.0    0.558    0.590    8.735    9.007
 potential_pw2rs                    186 10.0    0.033    0.035    8.387    8.934
 mp2_eri_2c_integrate_gpw_pot_l      91 10.0    0.001    0.001    8.159    8.570
 local_gemm                         172  8.0    8.177    8.453    8.177    8.453
 mp2_ri_gpw_compute_en_comm          22  7.0    0.495    0.511    7.866    8.173
 calc_potential_gpw                 182  9.5    0.002    0.002    7.937    8.143
 collocate_single_gaussian           91 10.0    0.019    0.062    7.748    7.966
 integrate_four_center_load           4 10.0    0.000    0.000    6.753    6.756
 hfx_load_balance                     1 11.0    0.000    0.000    6.753    6.756
 mp_sync                             37 10.5    3.390    6.675    3.390    6.675
 mp2_ri_gpw_compute_en_ener         172  7.0    6.342    6.400    6.342    6.400
 mp_sendrecv_dm3                   2068  8.0    5.912    6.197    5.912    6.197
 pw_gather_s                        912 13.2    4.451    4.984    4.451    4.984
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="20", plot="h2o_32_ri_rpa_mp2", label="RI-MP2 (8n/6r/2t)", y=100.779810, yerr=0.000000
PlotPoint: name="21", plot="h2o_32_ri_rpa_mp2_mem", label="RI-MP2 (8n/6r/2t)", y=1496.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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             453.734400E+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                 592243.
 MP_SendRecv         22610                   5520.
 MP_ISendRecv        22610                   5520.
 MP_Wait             37876
 MP_comm_split          50
 MP_ISend            20771                  42672.
 MP_IRecv            20771                  42672.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.014    0.036   53.960   53.966
 qs_mol_dyn_low                       1  2.0    0.003    0.003   53.559   53.613
 qs_forces                           11  3.9    0.005    0.017   53.492   53.493
 qs_energies                         11  4.9    0.001    0.001   51.975   51.996
 scf_env_do_scf                      11  5.9    0.000    0.001   45.949   45.949
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.007   43.830   43.830
 qs_scf_new_mos                     108  7.5    0.000    0.001   33.621   33.917
 qs_scf_loop_do_ot                  108  8.5    0.000    0.001   33.620   33.917
 dbcsr_multiply_generic            2286 12.5    0.095    0.100   33.109   33.477
 ot_scf_mini                        108  9.5    0.002    0.002   31.953   32.135
 multiply_cannon                   2286 13.5    0.187    0.196   25.902   27.610
 multiply_cannon_loop              2286 14.5    1.844    1.954   25.187   26.905
 velocity_verlet                     10  3.0    0.001    0.002   25.939   25.940
 ot_mini                            108 10.5    0.001    0.001   19.236   19.496
 qs_ot_get_derivative               108 11.5    0.001    0.001   16.229   16.432
 mp_waitall_1                    245248 16.5    8.141   14.196    8.141   14.196
 multiply_cannon_metrocomm3       54864 15.5    0.073    0.080    5.750   12.392
 multiply_cannon_multrec          54864 15.5    3.673    5.854    7.634   11.026
 qs_ot_get_p                        119 10.4    0.001    0.001    8.202    8.475
 rebuild_ks_matrix                  119  8.3    0.000    0.000    8.010    8.171
 qs_ks_build_kohn_sham_matrix       119  9.3    0.010    0.013    8.010    8.171
 qs_ks_update_qs_env                119  7.6    0.001    0.001    7.059    7.214
 mp_sum_l                          7287 12.8    5.115    6.672    5.115    6.672
 multiply_cannon_sync_h2d         54864 15.5    5.181    6.273    5.181    6.273
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    5.551    5.968
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    5.542    5.656
 dbcsr_mm_accdrv_process          76910 16.1    1.850    2.912    3.874    5.547
 qs_ot_p2m_diag                      50 11.0    0.004    0.006    5.423    5.456
 init_scf_run                        11  5.9    0.000    0.001    4.709    4.709
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    4.709    4.709
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    4.638    4.639
 sum_up_and_integrate               119 10.3    0.001    0.002    4.574    4.581
 integrate_v_rspace                 119 11.3    0.002    0.003    4.563    4.572
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    4.421    4.422
 cp_fm_redistribute_end              50 14.0    2.256    4.394    2.264    4.397
 qs_rho_update_rho_low              119  7.7    0.000    0.000    4.196    4.288
 calculate_rho_elec                 119  8.7    0.011    0.016    4.195    4.287
 cp_fm_diag_elpa_base                50 14.0    2.126    4.273    2.131    4.282
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.915    3.097
 apply_single                       119 13.6    0.000    0.000    2.915    3.097
 calculate_dm_sparse                119  9.5    0.000    0.000    2.907    3.041
 multiply_cannon_metrocomm1       54864 15.5    0.056    0.062    1.638    2.888
 acc_transpose_blocks             54864 15.5    0.224    0.247    2.216    2.756
 ot_diis_step                       108 11.5    0.006    0.006    2.727    2.728
 jit_kernel_multiply                 13 15.8    1.960    2.547    1.960    2.547
 calculate_first_density_matrix       1  7.0    0.000    0.001    2.466    2.469
 density_rs2pw                      119  9.7    0.004    0.004    2.257    2.346
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    2.282    2.336
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.229    2.231
 wfi_extrapolate                     11  7.9    0.001    0.001    2.174    2.174
 grid_integrate_task_list           119 12.3    2.013    2.104    2.013    2.104
 init_scf_loop                       11  6.9    0.000    0.000    2.100    2.101
 mp_sum_d                          4137 12.0    1.333    2.002    1.333    2.002
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.895    1.952
 potential_pw2rs                    119 12.3    0.004    0.004    1.927    1.943
 pw_transfer                       1439 11.6    0.051    0.058    1.758    1.835
 make_m2s                          4572 13.5    0.053    0.055    1.781    1.834
 fft_wrap_pw1pw2                   1201 12.6    0.007    0.007    1.683    1.762
 make_images                       4572 14.5    0.133    0.139    1.699    1.751
 transfer_rs2pw                     487 10.6    0.005    0.006    1.431    1.536
 mp_alltoall_d11v                  2130 13.8    1.318    1.490    1.318    1.490
 fft3d_ps                          1201 14.6    0.368    0.472    1.395    1.468
 acc_transpose_blocks_sync       164592 16.5    1.208    1.460    1.208    1.460
 mp_waitany                       12084 13.8    1.283    1.441    1.283    1.441
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.407    1.434
 grid_collocate_task_list           119  9.7    1.350    1.420    1.350    1.420
 transfer_pw2rs                     487 13.2    0.006    0.006    1.406    1.419
 fft_wrap_pw1pw2_140                487 13.2    0.109    0.117    1.306    1.386
 dbcsr_dot_sd                      1205 11.9    0.049    0.060    0.740    1.136
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="100", plot="h2o_64_md", label="(8n/12r/1t)", y=53.966000, yerr=0.000000
PlotPoint: name="101", plot="h2o_64_md_mem", label="(8n/12r/1t)", y=432.000000, yerr=1.414214
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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             489.717760E+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                1032117.
 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    0.057    0.108   39.750   39.751
 qs_mol_dyn_low                       1  2.0    0.006    0.016   39.378   39.385
 qs_forces                           11  3.9    0.017    0.060   39.282   39.285
 qs_energies                         11  4.9    0.012    0.031   37.527   37.536
 scf_env_do_scf                      11  5.9    0.010    0.038   32.150   32.151
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.007   29.637   29.638
 dbcsr_multiply_generic            2286 12.5    0.102    0.109   22.155   22.539
 qs_scf_new_mos                     108  7.5    0.001    0.001   20.919   21.144
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   20.918   21.143
 ot_scf_mini                        108  9.5    0.003    0.007   20.005   20.166
 multiply_cannon                   2286 13.5    0.209    0.217   16.960   18.481
 velocity_verlet                     10  3.0    0.001    0.002   18.466   18.469
 multiply_cannon_loop              2286 14.5    1.195    1.255   15.777   17.231
 ot_mini                            108 10.5    0.004    0.026   12.294   12.520
 mp_waitall_1                    200699 16.5    5.670   10.694    5.670   10.694
 qs_ot_get_derivative               108 11.5    0.001    0.002    9.902   10.068
 multiply_cannon_metrocomm3       27432 15.5    0.072    0.075    4.111    9.420
 multiply_cannon_multrec          27432 15.5    1.826    4.188    6.139    8.965
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.816    6.963
 qs_ks_build_kohn_sham_matrix       119  9.3    0.015    0.022    6.816    6.962
 dbcsr_mm_accdrv_process          47894 16.0    3.543    5.601    4.232    6.300
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.000    6.130
 qs_ot_get_p                        119 10.4    0.005    0.013    4.790    5.004
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    3.762    4.593
 mp_sum_l                          7287 12.8    2.133    4.238    2.133    4.238
 init_scf_run                        11  5.9    0.000    0.001    3.935    3.935
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    3.934    3.935
 sum_up_and_integrate               119 10.3    0.002    0.003    3.726    3.731
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    3.007    3.728
 apply_single                       119 13.6    0.000    0.000    3.007    3.728
 integrate_v_rspace                 119 11.3    0.004    0.018    3.711    3.716
 qs_rho_update_rho_low              119  7.7    0.001    0.002    3.666    3.702
 calculate_rho_elec                 119  8.7    0.021    0.024    3.665    3.701
 qs_ot_p2m_diag                      50 11.0    0.009    0.013    3.108    3.132
 make_m2s                          4572 13.5    0.053    0.065    2.648    2.979
 make_images                       4572 14.5    0.206    0.243    2.556    2.893
 cp_dbcsr_syevd                      50 12.0    0.003    0.005    2.702    2.707
 init_scf_loop                       11  6.9    0.007    0.035    2.475    2.483
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    2.357    2.440
 calculate_first_density_matrix       1  7.0    0.002    0.005    2.417    2.419
 ot_diis_step                       108 11.5    0.011    0.014    2.339    2.343
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    2.342    2.343
 cp_fm_redistribute_end              50 14.0    1.188    2.315    1.191    2.318
 cp_fm_diag_elpa_base                50 14.0    1.094    2.224    1.123    2.257
 calculate_dm_sparse                119  9.5    0.000    0.001    2.064    2.144
 multiply_cannon_sync_h2d         27432 15.5    1.660    2.130    1.660    2.130
 density_rs2pw                      119  9.7    0.004    0.004    1.956    2.037
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.979    1.982
 acc_transpose_blocks             27432 15.5    0.115    0.120    1.612    1.946
 grid_integrate_task_list           119 12.3    1.841    1.930    1.841    1.930
 jit_kernel_multiply                 10 16.4    0.630    1.915    0.630    1.915
 pw_transfer                       1439 11.6    0.065    0.069    1.867    1.906
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.776    1.817
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.699    1.741
 prepare_preconditioner              11  7.9    0.000    0.000    1.552    1.578
 make_preconditioner                 11  8.9    0.000    0.001    1.552    1.578
 make_images_data                  4572 15.5    0.048    0.054    1.239    1.573
 make_full_inverse_cholesky          11  9.9    0.000    0.001    1.454    1.508
 potential_pw2rs                    119 12.3    0.006    0.006    1.470    1.476
 wfi_extrapolate                     11  7.9    0.001    0.003    1.455    1.455
 hybrid_alltoall_any               4725 16.4    0.053    0.115    1.106    1.451
 fft3d_ps                          1201 14.6    0.520    0.576    1.407    1.441
 fft_wrap_pw1pw2_140                487 13.2    0.127    0.132    1.395    1.434
 grid_collocate_task_list           119  9.7    1.287    1.338    1.287    1.338
 mp_alltoall_d11v                  2130 13.8    1.226    1.326    1.226    1.326
 transfer_rs2pw                     487 10.6    0.005    0.006    1.207    1.322
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.259    1.267
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.213    1.262
 qs_energies_init_hamiltonians       11  5.9    0.012    0.022    1.122    1.127
 mp_sum_d                          4137 12.0    0.632    1.076    0.632    1.076
 mp_allgather_i34                  2286 14.5    0.606    1.018    0.606    1.018
 acc_transpose_blocks_sync        82296 16.5    0.818    0.941    0.818    0.941
 transfer_pw2rs                     487 13.2    0.004    0.005    0.929    0.933
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.874    0.888
 acc_transpose_blocks_kernels     27432 16.5    0.188    0.276    0.655    0.860
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="102", plot="h2o_64_md", label="(8n/6r/2t)", y=39.751000, yerr=0.000000
PlotPoint: name="103", plot="h2o_64_md_mem", label="(8n/6r/2t)", y=465.818182, yerr=0.935966
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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             520.962048E+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    0.008    0.029   33.270   33.273
 qs_mol_dyn_low                       1  2.0    0.003    0.004   32.912   32.939
 qs_forces                           11  3.9    0.002    0.003   32.849   32.849
 qs_energies                         11  4.9    0.002    0.002   31.264   31.266
 scf_env_do_scf                      11  5.9    0.000    0.001   26.400   26.400
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.007   23.878   23.878
 dbcsr_multiply_generic            2286 12.5    0.102    0.118   17.304   17.418
 qs_scf_new_mos                     108  7.5    0.001    0.001   16.010   16.031
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   16.010   16.030
 velocity_verlet                     10  3.0    0.001    0.002   15.554   15.555
 ot_scf_mini                        108  9.5    0.002    0.002   15.225   15.242
 multiply_cannon                   2286 13.5    0.194    0.199   13.787   14.535
 multiply_cannon_loop              2286 14.5    0.868    0.903   12.999   13.836
 ot_mini                            108 10.5    0.001    0.001    9.327    9.353
 qs_ot_get_derivative               108 11.5    0.001    0.001    7.815    7.835
 multiply_cannon_multrec          18288 15.5    1.877    2.947    6.993    7.294
 rebuild_ks_matrix                  119  8.3    0.000    0.001    6.095    6.118
 qs_ks_build_kohn_sham_matrix       119  9.3    0.015    0.036    6.094    6.118
 dbcsr_mm_accdrv_process          38222 16.0    4.963    5.761    5.021    5.826
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.361    5.382
 mp_waitall_1                    158411 16.6    2.801    4.174    2.801    4.174
 init_scf_run                        11  5.9    0.000    0.001    3.654    3.654
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.653    3.653
 qs_ot_get_p                        119 10.4    0.001    0.001    3.611    3.647
 sum_up_and_integrate               119 10.3    0.001    0.003    3.637    3.641
 integrate_v_rspace                 119 11.3    0.003    0.003    3.624    3.630
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.943    3.571
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.360    3.365
 calculate_rho_elec                 119  8.7    0.031    0.031    3.360    3.365
 multiply_cannon_metrocomm3       18288 15.5    0.048    0.051    1.517    2.805
 init_scf_loop                       11  6.9    0.000    0.000    2.505    2.505
 qs_ot_p2m_diag                      50 11.0    0.012    0.013    2.412    2.419
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.386    2.388
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.049    2.374
 apply_single                       119 13.6    0.000    0.000    2.049    2.374
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    2.093    2.094
 make_m2s                          4572 13.5    0.044    0.045    1.923    2.069
 density_rs2pw                      119  9.7    0.004    0.004    1.915    2.023
 make_images                       4572 14.5    0.192    0.206    1.836    1.982
 pw_transfer                       1439 11.6    0.065    0.069    1.915    1.928
 grid_integrate_task_list           119 12.3    1.809    1.892    1.809    1.892
 calculate_dm_sparse                119  9.5    0.000    0.001    1.876    1.885
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.823    1.835
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.821    1.832
 cp_fm_diag_elpa_base                50 14.0    1.797    1.809    1.819    1.831
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.794    1.808
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.772    1.774
 prepare_preconditioner              11  7.9    0.000    0.000    1.738    1.740
 make_preconditioner                 11  8.9    0.000    0.000    1.738    1.740
 acc_transpose_blocks             18288 15.5    0.079    0.082    1.631    1.710
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.593    1.679
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.573    1.584
 mp_sum_l                          7287 12.8    1.204    1.575    1.204    1.575
 ot_diis_step                       108 11.5    0.011    0.012    1.492    1.492
 fft_wrap_pw1pw2_140                487 13.2    0.178    0.183    1.439    1.451
 potential_pw2rs                    119 12.3    0.007    0.008    1.417    1.422
 fft3d_ps                          1201 14.6    0.546    0.566    1.378    1.390
 grid_collocate_task_list           119  9.7    1.234    1.320    1.234    1.320
 wfi_extrapolate                     11  7.9    0.001    0.001    1.213    1.213
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.190    1.196
 transfer_rs2pw                     487 10.6    0.005    0.005    1.029    1.166
 multiply_cannon_sync_h2d         18288 15.5    1.029    1.124    1.029    1.124
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.995    1.010
 make_images_data                  4572 15.5    0.047    0.051    0.825    0.975
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    0.951    0.952
 hybrid_alltoall_any               4725 16.4    0.058    0.117    0.709    0.888
 transfer_pw2rs                     487 13.2    0.004    0.004    0.881    0.887
 mp_alltoall_d11v                  2130 13.8    0.721    0.847    0.721    0.847
 acc_transpose_blocks_sync        54864 16.5    0.744    0.819    0.744    0.819
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.804    0.807
 acc_transpose_blocks_kernels     18288 16.5    0.217    0.225    0.788    0.797
 cp_fm_cholesky_invert               11 10.9    0.768    0.772    0.768    0.772
 mp_alltoall_z22v                  1201 16.6    0.673    0.743    0.673    0.743
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.003    0.665    0.743
 mp_waitany                        9880 13.7    0.543    0.702    0.543    0.702
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="104", plot="h2o_64_md", label="(8n/4r/3t)", y=33.273000, yerr=0.000000
PlotPoint: name="105", plot="h2o_64_md_mem", label="(8n/4r/3t)", y=496.545455, yerr=0.497930
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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             557.355008E+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    0.036    0.072   37.539   37.539
 qs_mol_dyn_low                       1  2.0    0.003    0.003   37.266   37.275
 qs_forces                           11  3.9    0.002    0.003   37.156   37.156
 qs_energies                         11  4.9    0.009    0.022   35.440   35.446
 scf_env_do_scf                      11  5.9    0.000    0.001   30.150   30.152
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.006   26.656   26.656
 dbcsr_multiply_generic            2286 12.5    0.114    0.132   20.302   20.441
 velocity_verlet                     10  3.0    0.014    0.018   18.808   18.812
 qs_scf_new_mos                     108  7.5    0.001    0.001   18.350   18.408
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   18.350   18.407
 ot_scf_mini                        108  9.5    0.002    0.003   17.312   17.379
 multiply_cannon                   2286 13.5    0.219    0.227   16.394   16.743
 multiply_cannon_loop              2286 14.5    1.530    1.620   15.375   15.802
 ot_mini                            108 10.5    0.001    0.001   10.611   10.676
 multiply_cannon_multrec          27432 15.5    2.470    3.152    9.164    9.458
 qs_ot_get_derivative               108 11.5    0.001    0.001    8.722    8.793
 dbcsr_mm_accdrv_process          47916 15.9    5.935    7.647    6.591    7.922
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.414    6.459
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    6.414    6.458
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.684    5.723
 init_scf_run                        11  5.9    0.000    0.001    3.925    3.925
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.925    3.925
 qs_ot_get_p                        119 10.4    0.001    0.002    3.820    3.902
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    3.231    3.626
 sum_up_and_integrate               119 10.3    0.001    0.001    3.572    3.581
 integrate_v_rspace                 119 11.3    0.003    0.003    3.561    3.569
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.505    3.543
 calculate_rho_elec                 119  8.7    0.040    0.046    3.504    3.543
 init_scf_loop                       11  6.9    0.000    0.000    3.470    3.471
 prepare_preconditioner              11  7.9    0.000    0.000    2.635    2.643
 make_preconditioner                 11  8.9    0.000    0.000    2.635    2.643
 make_full_inverse_cholesky          11  9.9    0.000    0.000    2.229    2.569
 acc_transpose_blocks             27432 15.5    0.120    0.123    2.407    2.551
 make_m2s                          4572 13.5    0.054    0.056    2.410    2.520
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.489    2.490
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    2.455    2.489
 mp_waitall_1                    137007 16.6    1.940    2.432    1.940    2.432
 make_images                       4572 14.5    0.274    0.335    2.302    2.411
 qs_ot_p2m_diag                      50 11.0    0.016    0.023    2.352    2.362
 calculate_dm_sparse                119  9.5    0.000    0.000    2.266    2.330
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.122    2.248
 apply_single                       119 13.6    0.000    0.000    2.122    2.248
 pw_transfer                       1439 11.6    0.065    0.069    2.043    2.080
 density_rs2pw                      119  9.7    0.004    0.004    1.943    2.068
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.951    1.991
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.926    1.927
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.912    1.913
 grid_integrate_task_list           119 12.3    1.829    1.891    1.829    1.891
 ot_diis_step                       108 11.5    0.012    0.012    1.845    1.846
 jit_kernel_multiply                  9 16.1    0.590    1.725    0.590    1.725
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.689    1.702
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.659    1.669
 cp_fm_diag_elpa_base                50 14.0    1.623    1.641    1.657    1.667
 fft_wrap_pw1pw2_140                487 13.2    0.227    0.235    1.598    1.641
 acc_transpose_blocks_sync        82296 16.5    1.426    1.563    1.426    1.563
 fft3d_ps                          1201 14.6    0.592    0.651    1.440    1.463
 wfi_extrapolate                     11  7.9    0.001    0.001    1.381    1.381
 potential_pw2rs                    119 12.3    0.008    0.009    1.371    1.375
 multiply_cannon_metrocomm3       27432 15.5    0.040    0.041    0.803    1.371
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.358    1.371
 grid_collocate_task_list           119  9.7    1.249    1.341    1.249    1.341
 mp_sum_l                          7287 12.8    1.055    1.336    1.055    1.336
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.313    1.331
 cp_fm_upper_to_full                 72 14.2    0.832    1.191    0.832    1.191
 dbcsr_complete_redistribute        329 12.2    0.138    0.187    0.843    1.126
 transfer_rs2pw                     487 10.6    0.004    0.005    0.988    1.117
 qs_energies_init_hamiltonians       11  5.9    0.000    0.001    1.070    1.071
 make_images_data                  4572 15.5    0.048    0.052    0.910    1.021
 hybrid_alltoall_any               4725 16.4    0.066    0.156    0.783    0.930
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    0.626    0.901
 mp_alltoall_d11v                  2130 13.8    0.789    0.878    0.789    0.878
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.800    0.877
 acc_transpose_blocks_kernels     27432 16.5    0.270    0.277    0.833    0.847
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.819    0.824
 cp_fm_cholesky_invert               11 10.9    0.788    0.791    0.788    0.791
 transfer_pw2rs                     487 13.2    0.004    0.004    0.785    0.789
 mp_alltoall_z22v                  1201 16.6    0.730    0.760    0.730    0.760
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="106", plot="h2o_64_md", label="(8n/3r/4t)", y=37.539000, yerr=0.000000
PlotPoint: name="107", plot="h2o_64_md_mem", label="(8n/3r/4t)", y=529.454545, yerr=2.807899
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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             630.525952E+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    0.010    0.029   30.400   30.402
 qs_mol_dyn_low                       1  2.0    0.003    0.003   30.024   30.042
 qs_forces                           11  3.9    0.003    0.003   29.936   29.937
 qs_energies                         11  4.9    0.001    0.002   28.215   28.218
 scf_env_do_scf                      11  5.9    0.000    0.001   23.158   23.158
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.006   20.586   20.587
 velocity_verlet                     10  3.0    0.028    0.029   15.163   15.166
 dbcsr_multiply_generic            2286 12.5    0.093    0.096   13.505   13.628
 qs_scf_new_mos                     108  7.5    0.001    0.001   12.634   12.661
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   12.634   12.660
 ot_scf_mini                        108  9.5    0.002    0.002   11.907   11.930
 multiply_cannon                   2286 13.5    0.224    0.229   10.709   11.123
 multiply_cannon_loop              2286 14.5    0.645    0.673    9.745    9.979
 ot_mini                            108 10.5    0.001    0.001    6.749    6.777
 multiply_cannon_multrec           9144 15.5    1.760    1.946    6.052    6.281
 rebuild_ks_matrix                  119  8.3    0.000    0.000    5.951    5.972
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    5.950    5.972
 qs_ot_get_derivative               108 11.5    0.001    0.001    5.421    5.443
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.303    5.323
 dbcsr_mm_accdrv_process          12550 15.8    3.618    4.183    4.179    4.261
 sum_up_and_integrate               119 10.3    0.001    0.001    3.562    3.566
 integrate_v_rspace                 119 11.3    0.003    0.003    3.552    3.556
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.499    3.505
 calculate_rho_elec                 119  8.7    0.060    0.061    3.499    3.504
 init_scf_run                        11  5.9    0.000    0.001    3.425    3.425
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.425    3.425
 qs_ot_get_p                        119 10.4    0.001    0.002    3.206    3.239
 init_scf_loop                       11  6.9    0.000    0.000    2.552    2.553
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.257    2.258
 pw_transfer                       1439 11.6    0.065    0.068    2.195    2.205
 mp_waitall_1                    115863 16.7    1.676    2.183    1.676    2.183
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    2.102    2.113
 qs_ot_p2m_diag                      50 11.0    0.022    0.023    2.108    2.111
 make_m2s                          4572 13.5    0.034    0.034    1.937    2.079
 make_images                       4572 14.5    0.269    0.300    1.847    1.988
 density_rs2pw                      119  9.7    0.003    0.003    1.876    1.973
 grid_integrate_task_list           119 12.3    1.872    1.949    1.872    1.949
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.854    1.855
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    1.799    1.819
 prepare_preconditioner              11  7.9    0.000    0.000    1.809    1.811
 make_preconditioner                 11  8.9    0.000    0.000    1.808    1.811
 calculate_dm_sparse                119  9.5    0.000    0.000    1.761    1.781
 fft_wrap_pw1pw2_140                487 13.2    0.324    0.331    1.721    1.732
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.698    1.723
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.587    1.588
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.526    1.535
 cp_fm_diag_elpa_base                50 14.0    1.498    1.516    1.524    1.533
 acc_transpose_blocks              9144 15.5    0.043    0.044    1.423    1.467
 fft3d_ps                          1201 14.6    0.652    0.665    1.455    1.465
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.441    1.454
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.380    1.386
 grid_collocate_task_list           119  9.7    1.298    1.375    1.298    1.375
 qs_energies_init_hamiltonians       11  5.9    0.024    0.024    1.371    1.373
 potential_pw2rs                    119 12.3    0.010    0.011    1.360    1.364
 ot_diis_step                       108 11.5    0.013    0.013    1.313    1.313
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    1.246    1.273
 apply_single                       119 13.6    0.000    0.000    1.246    1.273
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.132    1.138
 wfi_extrapolate                     11  7.9    0.001    0.001    1.114    1.114
 hybrid_alltoall_any               4725 16.4    0.065    0.177    0.859    1.070
 jit_kernel_multiply                  6 15.6    0.521    1.059    0.521    1.059
 make_images_data                  4572 15.5    0.042    0.046    0.863    1.021
 transfer_rs2pw                     487 10.6    0.004    0.004    0.847    0.942
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.874    0.927
 cp_fm_cholesky_invert               11 10.9    0.906    0.909    0.906    0.909
 mp_alltoall_d11v                  2130 13.8    0.842    0.894    0.842    0.894
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.857    0.864
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    0.797    0.847
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.770    0.772
 multiply_cannon_metrocomm3        9144 15.5    0.020    0.020    0.416    0.768
 acc_transpose_blocks_sync        27432 16.5    0.717    0.759    0.717    0.759
 mp_allgather_i34                  2286 14.5    0.277    0.752    0.277    0.752
 transfer_pw2rs                     487 13.2    0.003    0.004    0.723    0.725
 mp_alltoall_z22v                  1201 16.6    0.677    0.710    0.677    0.710
 acc_transpose_blocks_kernels      9144 16.5    0.118    0.120    0.647    0.651
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="108", plot="h2o_64_md", label="(8n/2r/6t)", y=30.402000, yerr=0.000000
PlotPoint: name="109", plot="h2o_64_md_mem", label="(8n/2r/6t)", y=600.090909, yerr=4.032922
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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             773.513216E+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    0.021    0.096   44.386   44.386
 qs_mol_dyn_low                       1  2.0    0.003    0.003   44.026   44.035
 qs_forces                           11  3.9    0.002    0.003   43.961   43.962
 qs_energies                         11  4.9    0.002    0.003   41.949   41.952
 scf_env_do_scf                      11  5.9    0.001    0.001   35.993   35.993
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.007   28.004   28.006
 velocity_verlet                     10  3.0    0.002    0.003   24.605   24.611
 dbcsr_multiply_generic            2286 12.5    0.102    0.103   19.437   19.496
 qs_scf_new_mos                     108  7.5    0.001    0.001   18.042   18.138
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   18.041   18.138
 ot_scf_mini                        108  9.5    0.002    0.002   16.866   16.966
 multiply_cannon                   2286 13.5    0.302    0.311   15.352   16.149
 multiply_cannon_loop              2286 14.5    0.876    0.898   14.075   14.906
 ot_mini                            108 10.5    0.001    0.001   10.292   10.407
 multiply_cannon_multrec           9144 15.5    3.466    4.954    8.968    9.128
 qs_ot_get_derivative               108 11.5    0.001    0.001    8.228    8.327
 init_scf_loop                       11  6.9    0.000    0.000    7.960    7.963
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.417    7.560
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.013    7.416    7.560
 prepare_preconditioner              11  7.9    0.000    0.000    6.971    6.985
 make_preconditioner                 11  8.9    0.000    0.000    6.971    6.985
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.507    6.862
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.686    6.816
 dbcsr_mm_accdrv_process          12550 15.8    4.654    6.423    5.362    6.659
 cp_fm_upper_to_full                 72 14.2    3.233    4.640    3.233    4.640
 qs_rho_update_rho_low              119  7.7    0.001    0.001    4.375    4.390
 calculate_rho_elec                 119  8.7    0.117    0.120    4.374    4.390
 sum_up_and_integrate               119 10.3    0.001    0.001    3.970    3.975
 integrate_v_rspace                 119 11.3    0.004    0.004    3.959    3.965
 init_scf_run                        11  5.9    0.000    0.001    3.790    3.790
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.789    3.789
 qs_ot_get_p                        119 10.4    0.003    0.003    3.614    3.753
 mp_waitall_1                     94719 16.7    2.459    3.326    2.459    3.326
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.846    3.261
 pw_transfer                       1439 11.6    0.069    0.069    3.169    3.175
 fft_wrap_pw1pw2                   1201 12.6    0.009    0.009    3.071    3.076
 dbcsr_complete_redistribute        329 12.2    0.281    0.284    2.031    2.900
 make_m2s                          4572 13.5    0.037    0.038    2.499    2.652
 fft_wrap_pw1pw2_140                487 13.2    0.649    0.655    2.592    2.600
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    1.714    2.575
 make_images                       4572 14.5    0.357    0.392    2.376    2.528
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.218    2.497
 apply_single                       119 13.6    0.000    0.000    2.218    2.497
 calculate_dm_sparse                119  9.5    0.000    0.000    2.385    2.395
 density_rs2pw                      119  9.7    0.003    0.004    2.369    2.383
 mp_alltoall_i22                    627 13.8    1.440    2.341    1.440    2.341
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.458    2.310
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.261    2.276
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    2.133    2.182
 multiply_cannon_metrocomm3        9144 15.5    0.021    0.021    1.405    2.173
 qs_ot_p2m_diag                      50 11.0    0.044    0.044    2.142    2.143
 grid_integrate_task_list           119 12.3    2.075    2.113    2.075    2.113
 ot_diis_step                       108 11.5    0.014    0.014    2.039    2.040
 fft3d_ps                          1201 14.6    0.870    0.889    1.990    1.996
 acc_transpose_blocks              9144 15.5    0.046    0.047    1.850    1.884
 qs_energies_init_hamiltonians       11  5.9    0.011    0.018    1.843    1.844
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.830    1.831
 mp_sum_l                          7287 12.8    1.040    1.780    1.040    1.780
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.777    1.778
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.571    1.612
 grid_collocate_task_list           119  9.7    1.519    1.539    1.519    1.539
 cp_fm_cholesky_invert               11 10.9    1.491    1.495    1.491    1.495
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.462    1.462
 potential_pw2rs                    119 12.3    0.014    0.014    1.459    1.461
 cp_fm_diag_elpa_base                50 14.0    1.309    1.367    1.459    1.459
 wfi_extrapolate                     11  7.9    0.001    0.001    1.443    1.444
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.377    1.390
 hybrid_alltoall_any               4725 16.4    0.091    0.150    1.127    1.368
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.332    1.350
 mp_alltoall_d11v                  2130 13.8    1.257    1.291    1.257    1.291
 make_images_data                  4572 15.5    0.047    0.050    1.067    1.282
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    1.143    1.161
 acc_transpose_blocks_sync        27432 16.5    1.119    1.153    1.119    1.153
 jit_kernel_multiply                  6 15.7    0.679    1.016    0.679    1.016
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.001    0.989    1.015
 mp_alltoall_z22v                  1201 16.6    0.983    1.009    0.983    1.009
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.941    0.955
 qs_create_task_list                 11  7.9    0.001    0.001    0.934    0.946
 generate_qs_task_list               11  8.9    0.368    0.388    0.934    0.946
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="110", plot="h2o_64_md", label="(8n/1r/12t)", y=44.386000, yerr=0.000000
PlotPoint: name="111", plot="h2o_64_md_mem", label="(8n/1r/12t)", y=728.727273, yerr=13.328649
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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             502.390784E+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                 716768.
 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    0.013    0.029   84.846   84.847
 qs_mol_dyn_low                       1  2.0    0.003    0.003   84.519   84.558
 qs_forces                           11  3.9    0.003    0.004   84.445   84.446
 qs_energies                         11  4.9    0.002    0.003   81.576   81.589
 scf_env_do_scf                      11  5.9    0.000    0.001   71.942   71.944
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.006   66.004   66.004
 dbcsr_multiply_generic            2055 12.4    0.129    0.137   52.020   52.246
 qs_scf_new_mos                      99  7.5    0.000    0.001   48.182   48.313
 qs_scf_loop_do_ot                   99  8.5    0.000    0.001   48.182   48.313
 ot_scf_mini                         99  9.5    0.002    0.002   45.748   45.873
 velocity_verlet                     10  3.0    0.001    0.002   44.219   44.220
 multiply_cannon                   2055 13.4    0.182    0.187   43.092   43.821
 multiply_cannon_loop              2055 14.4    1.808    1.846   42.044   42.637
 ot_mini                             99 10.5    0.001    0.001   26.809   26.941
 qs_ot_get_derivative                99 11.5    0.001    0.001   19.986   20.126
 multiply_cannon_multrec          49320 15.4   11.377   12.114   17.767   18.663
 rebuild_ks_matrix                  110  8.3    0.000    0.001   14.902   15.006
 qs_ks_build_kohn_sham_matrix       110  9.3    0.011    0.012   14.901   15.006
 qs_ks_update_qs_env                110  7.6    0.001    0.001   13.104   13.188
 mp_waitall_1                    220248 16.4   11.089   11.861   11.089   11.861
 qs_ot_get_p                        110 10.4    0.001    0.001   10.332   10.428
 multiply_cannon_sync_h2d         49320 15.4    9.625   10.292    9.625   10.292
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    7.647    8.259
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    7.298    7.874
 apply_single                       110 13.6    0.000    0.000    7.298    7.874
 init_scf_run                        11  5.9    0.000    0.001    7.540    7.540
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    7.539    7.540
 sum_up_and_integrate               110 10.3    0.002    0.003    7.299    7.313
 integrate_v_rspace                 110 11.3    0.003    0.003    7.274    7.293
 multiply_cannon_metrocomm3       49320 15.4    0.084    0.087    6.442    7.181
 qs_ot_p2m_diag                      48 11.0    0.013    0.019    7.059    7.094
 qs_rho_update_rho_low              110  7.6    0.000    0.001    6.795    6.946
 calculate_rho_elec                 110  8.6    0.021    0.024    6.794    6.945
 dbcsr_mm_accdrv_process          87628 16.1    3.067    3.158    6.258    6.617
 ot_diis_step                        99 11.5    0.005    0.006    6.612    6.612
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    6.190    6.190
 init_scf_loop                       11  6.9    0.000    0.000    5.908    5.909
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    5.576    5.604
 cp_fm_diag_elpa_base                48 14.0    5.560    5.587    5.573    5.602
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    5.494    5.564
 mp_sum_l                          6594 12.7    4.106    5.028    4.106    5.028
 make_m2s                          4110 13.4    0.060    0.064    4.339    4.454
 make_images                       4110 14.4    0.178    0.190    4.243    4.362
 wfi_extrapolate                     11  7.9    0.001    0.001    4.211    4.212
 calculate_dm_sparse                110  9.5    0.001    0.001    4.069    4.164
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.002    3.903    3.908
 density_rs2pw                      110  9.6    0.004    0.005    3.723    3.901
 prepare_preconditioner              11  7.9    0.000    0.000    3.691    3.707
 make_preconditioner                 11  8.9    0.000    0.000    3.691    3.707
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    3.540    3.601
 make_full_inverse_cholesky          11  9.9    0.000    0.000    3.469    3.517
 multiply_cannon_metrocomm1       49320 15.4    0.065    0.068    2.467    3.512
 pw_transfer                       1331 11.6    0.055    0.067    3.405    3.502
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.316    3.416
 grid_integrate_task_list           110 12.3    3.242    3.405    3.242    3.405
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    3.265    3.314
 calculate_first_density_matrix       1  7.0    0.000    0.000    3.225    3.229
 jit_kernel_multiply                 13 15.9    2.909    3.018    2.909    3.018
 fft_wrap_pw1pw2_140                451 13.1    0.310    0.331    2.768    2.891
 potential_pw2rs                    110 12.3    0.005    0.006    2.838    2.867
 mp_alltoall_d11v                  2046 13.8    2.335    2.799    2.335    2.799
 acc_transpose_blocks             49320 15.4    0.213    0.221    2.621    2.690
 fft3d_ps                          1111 14.6    0.793    0.884    2.608    2.678
 grid_collocate_task_list           110  9.6    2.160    2.298    2.160    2.298
 transfer_rs2pw                     451 10.6    0.005    0.006    2.101    2.276
 make_images_data                  4110 15.4    0.044    0.048    1.988    2.145
 mp_waitany                       14300 13.8    1.869    2.039    1.869    2.039
 hybrid_alltoall_any               4261 16.3    0.085    0.485    1.707    2.023
 cp_fm_cholesky_invert               11 10.9    1.994    1.998    1.994    1.998
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.929    1.951
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.920    1.949
 transfer_pw2rs                     451 13.1    0.006    0.007    1.907    1.932
 mp_sum_d                          3891 11.9    1.320    1.914    1.320    1.914
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="200", plot="h2o_128_md", label="(8n/12r/1t)", y=84.847000, yerr=0.000000
PlotPoint: name="201", plot="h2o_128_md_mem", label="(8n/12r/1t)", y=477.090909, yerr=2.609582
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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             592.228352E+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                1623421.
 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    0.008    0.026   69.330   69.331
 qs_mol_dyn_low                       1  2.0    0.003    0.003   69.099   69.111
 qs_forces                           11  3.9    0.008    0.010   69.028   69.029
 qs_energies                         11  4.9    0.002    0.004   65.690   65.697
 scf_env_do_scf                      11  5.9    0.000    0.001   56.954   56.957
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.007   49.380   49.381
 dbcsr_multiply_generic            2055 12.4    0.112    0.116   38.086   38.236
 velocity_verlet                     10  3.0    0.001    0.002   36.098   36.099
 qs_scf_new_mos                      99  7.5    0.001    0.001   33.376   33.495
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   33.376   33.495
 multiply_cannon                   2055 13.4    0.225    0.247   31.365   32.538
 ot_scf_mini                         99  9.5    0.003    0.003   31.699   31.810
 multiply_cannon_loop              2055 14.4    1.166    1.201   30.073   30.851
 ot_mini                             99 10.5    0.001    0.001   18.453   18.571
 multiply_cannon_multrec          24660 15.4    6.986    9.198   14.089   16.163
 rebuild_ks_matrix                  110  8.3    0.000    0.000   13.608   13.701
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.014   13.607   13.701
 qs_ot_get_derivative                99 11.5    0.001    0.001   12.688   12.804
 qs_ks_update_qs_env                110  7.6    0.001    0.001   11.971   12.061
 mp_waitall_1                    176588 16.5    7.545   10.129    7.545   10.129
 multiply_cannon_metrocomm3       24660 15.4    0.074    0.076    5.114    8.321
 multiply_cannon_sync_h2d         24660 15.4    6.369    7.917    6.369    7.917
 init_scf_loop                       11  6.9    0.000    0.000    7.539    7.540
 dbcsr_mm_accdrv_process          52282 16.1    5.540    6.138    6.932    7.233
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    6.462    7.076
 apply_single                       110 13.6    0.000    0.001    6.461    7.076
 qs_ot_get_p                        110 10.4    0.001    0.003    6.583    6.743
 sum_up_and_integrate               110 10.3    0.001    0.002    6.424    6.436
 integrate_v_rspace                 110 11.3    0.003    0.003    6.397    6.409
 init_scf_run                        11  5.9    0.000    0.001    6.354    6.355
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    6.354    6.355
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.979    5.985
 calculate_rho_elec                 110  8.6    0.039    0.047    5.978    5.985
 ot_diis_step                        99 11.5    0.010    0.010    5.719    5.719
 prepare_preconditioner              11  7.9    0.000    0.000    5.539    5.562
 make_preconditioner                 11  8.9    0.000    0.000    5.539    5.562
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    4.750    5.490
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.109    5.269
 make_m2s                          4110 13.4    0.057    0.059    4.319    4.790
 qs_ot_p2m_diag                      48 11.0    0.029    0.044    4.663    4.684
 make_images                       4110 14.4    0.408    0.467    4.207    4.674
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    4.173    4.173
 pw_transfer                       1331 11.6    0.066    0.072    3.632    3.786
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.009    3.525    3.681
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.587    3.601
 cp_fm_diag_elpa_base                48 14.0    3.538    3.552    3.584    3.598
 wfi_extrapolate                     11  7.9    0.001    0.001    3.509    3.509
 density_rs2pw                      110  9.6    0.004    0.004    3.203    3.407
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.320    3.389
 grid_integrate_task_list           110 12.3    3.159    3.324    3.159    3.324
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.002    3.291    3.292
 fft_wrap_pw1pw2_140                451 13.1    0.357    0.376    2.992    3.147
 calculate_dm_sparse                110  9.5    0.001    0.001    3.004    3.030
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.935    2.970
 make_images_data                  4110 15.4    0.049    0.053    2.317    2.813
 hybrid_alltoall_any               4261 16.3    0.105    0.452    2.028    2.795
 fft3d_ps                          1111 14.6    1.115    1.351    2.618    2.789
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.739    2.741
 cp_fm_cholesky_invert               11 10.9    2.610    2.617    2.610    2.617
 mp_sum_l                          6594 12.7    1.772    2.441    1.772    2.441
 grid_collocate_task_list           110  9.6    2.169    2.364    2.169    2.364
 potential_pw2rs                    110 12.3    0.008    0.009    2.287    2.297
 mp_alltoall_d11v                  2046 13.8    1.803    2.087    1.803    2.087
 acc_transpose_blocks             24660 15.4    0.116    0.120    1.970    2.008
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.982    2.004
 jit_kernel_multiply                 10 16.2    1.024    1.967    1.024    1.967
 qs_energies_init_hamiltonians       11  5.9    0.000    0.001    1.864    1.869
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.792    1.805
 multiply_cannon_metrocomm4       22605 15.4    0.074    0.078    0.764    1.720
 transfer_rs2pw                     451 10.6    0.006    0.007    1.472    1.692
 mp_allgather_i34                  2055 14.4    0.592    1.617    0.592    1.617
 mp_irecv_dv                      57340 16.2    0.639    1.602    0.639    1.602
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.564    1.574
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.390    1.494
 dbcsr_complete_redistribute        325 12.2    0.250    0.306    1.156    1.418
 mp_waitany                       10164 13.8    1.169    1.392    1.169    1.392
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="202", plot="h2o_128_md", label="(8n/6r/2t)", y=69.331000, yerr=0.000000
PlotPoint: name="203", plot="h2o_128_md_mem", label="(8n/6r/2t)", y=560.636364, yerr=6.256237
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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             668.192768E+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    0.010    0.033   61.082   61.083
 qs_mol_dyn_low                       1  2.0    0.003    0.003   60.699   60.735
 qs_forces                           11  3.9    0.027    0.042   60.626   60.627
 qs_energies                         11  4.9    0.010    0.023   57.401   57.428
 scf_env_do_scf                      11  5.9    0.001    0.001   49.314   49.314
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.007   40.625   40.626
 velocity_verlet                     10  3.0    0.001    0.002   32.854   32.856
 dbcsr_multiply_generic            2055 12.4    0.116    0.126   29.009   29.290
 qs_scf_new_mos                      99  7.5    0.001    0.001   25.811   25.907
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   25.810   25.907
 ot_scf_mini                         99  9.5    0.002    0.003   24.543   24.673
 multiply_cannon                   2055 13.4    0.212    0.227   22.582   23.740
 multiply_cannon_loop              2055 14.4    0.822    0.848   21.473   22.625
 ot_mini                             99 10.5    0.001    0.001   13.989   14.118
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.244   12.388
 qs_ks_build_kohn_sham_matrix       110  9.3    0.014    0.025   12.243   12.388
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.775   10.906
 multiply_cannon_multrec          16440 15.4    3.591    4.672    9.787   10.757
 mp_waitall_1                    139946 16.5    7.256   10.531    7.256   10.531
 qs_ot_get_derivative                99 11.5    0.001    0.001    9.519    9.652
 init_scf_loop                       11  6.9    0.000    0.000    8.654    8.655
 multiply_cannon_metrocomm3       16440 15.4    0.046    0.048    4.571    7.779
 prepare_preconditioner              11  7.9    0.000    0.000    6.877    6.896
 make_preconditioner                 11  8.9    0.000    0.000    6.877    6.896
 make_full_inverse_cholesky          11  9.9    0.000    0.000    6.213    6.579
 sum_up_and_integrate               110 10.3    0.002    0.002    6.356    6.372
 integrate_v_rspace                 110 11.3    0.003    0.003    6.330    6.346
 dbcsr_mm_accdrv_process          34862 16.1    5.367    5.656    6.041    6.205
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.844    5.852
 calculate_rho_elec                 110  8.6    0.059    0.059    5.843    5.852
 qs_ot_get_p                        110 10.4    0.001    0.001    5.682    5.819
 init_scf_run                        11  5.9    0.000    0.001    5.665    5.665
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    5.665    5.665
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.935    5.409
 apply_single                       110 13.6    0.000    0.000    4.935    5.409
 make_m2s                          4110 13.4    0.050    0.051    4.250    4.537
 ot_diis_step                        99 11.5    0.011    0.011    4.431    4.431
 make_images                       4110 14.4    0.401    0.524    4.133    4.421
 qs_ot_p2m_diag                      48 11.0    0.042    0.044    3.973    3.980
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.217    3.876
 multiply_cannon_sync_h2d         16440 15.4    3.186    3.871    3.186    3.871
 pw_transfer                       1331 11.6    0.065    0.071    3.663    3.674
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.587    3.587
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.556    3.570
 grid_integrate_task_list           110 12.3    3.194    3.399    3.194    3.399
 density_rs2pw                      110  9.6    0.004    0.004    3.077    3.348
 fft_wrap_pw1pw2_140                451 13.1    0.461    0.472    3.062    3.076
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.013    3.021
 cp_fm_diag_elpa_base                48 14.0    2.942    2.975    3.012    3.019
 wfi_extrapolate                     11  7.9    0.001    0.001    2.982    2.982
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.907    2.908
 make_images_data                  4110 15.4    0.047    0.051    2.400    2.747
 cp_fm_cholesky_invert               11 10.9    2.707    2.714    2.707    2.714
 hybrid_alltoall_any               4261 16.3    0.108    0.385    2.101    2.663
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.585    2.653
 calculate_first_density_matrix       1  7.0    0.000    0.001    2.590    2.593
 calculate_dm_sparse                110  9.5    0.001    0.001    2.558    2.588
 multiply_cannon_metrocomm4       14385 15.4    0.047    0.051    0.904    2.528
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.450    2.499
 fft3d_ps                          1111 14.6    1.121    1.130    2.472    2.484
 grid_collocate_task_list           110  9.6    2.212    2.403    2.212    2.403
 mp_irecv_dv                      48980 15.7    0.829    2.389    0.829    2.389
 mp_sum_l                          6594 12.7    1.552    2.240    1.552    2.240
 potential_pw2rs                    110 12.3    0.010    0.011    2.206    2.211
 dbcsr_complete_redistribute        325 12.2    0.376    0.447    1.563    2.037
 mp_alltoall_d11v                  2046 13.8    1.779    2.020    1.779    2.020
 qs_energies_init_hamiltonians       11  5.9    0.000    0.002    1.961    1.985
 cp_fm_upper_to_full                 70 14.2    1.456    1.855    1.456    1.855
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.661    1.675
 cp_fm_cholesky_decompose            22 10.9    1.623    1.646    1.623    1.646
 acc_transpose_blocks             16440 15.4    0.079    0.082    1.584    1.620
 transfer_rs2pw                     451 10.6    0.005    0.006    1.338    1.582
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    1.082    1.541
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.476    1.491
 mp_waitany                       17072 13.8    1.198    1.479    1.198    1.479
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.365    1.477
 mp_allgather_i34                  2055 14.4    0.420    1.466    0.420    1.466
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.310    1.319
 transfer_pw2rs                     451 13.1    0.005    0.005    1.248    1.256
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="204", plot="h2o_128_md", label="(8n/4r/3t)", y=61.083000, yerr=0.000000
PlotPoint: name="205", plot="h2o_128_md_mem", label="(8n/4r/3t)", y=632.545455, yerr=9.218200
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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             743.448576E+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    0.027    0.060   66.767   66.768
 qs_mol_dyn_low                       1  2.0    0.003    0.004   66.473   66.482
 qs_forces                           11  3.9    0.016    0.032   66.405   66.406
 qs_energies                         11  4.9    0.020    0.034   62.908   62.924
 scf_env_do_scf                      11  5.9    0.001    0.002   54.211   54.214
 scf_env_do_scf_inner_loop           99  6.5    0.009    0.029   42.391   42.393
 velocity_verlet                     10  3.0    0.002    0.002   37.489   37.491
 dbcsr_multiply_generic            2055 12.4    0.116    0.121   30.878   31.083
 qs_scf_new_mos                      99  7.5    0.001    0.001   27.658   27.787
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   27.657   27.787
 ot_scf_mini                         99  9.5    0.003    0.004   25.957   26.052
 multiply_cannon                   2055 13.4    0.238    0.251   23.708   24.984
 multiply_cannon_loop              2055 14.4    1.400    1.487   22.264   22.890
 ot_mini                             99 10.5    0.001    0.001   14.914   15.032
 multiply_cannon_multrec          24660 15.4    4.115    6.730   13.160   14.262
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.100   12.202
 qs_ks_build_kohn_sham_matrix       110  9.3    0.015    0.030   12.099   12.202
 init_scf_loop                       11  6.9    0.001    0.004   11.778   11.780
 qs_ot_get_derivative                99 11.5    0.001    0.001   10.721   10.824
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.620   10.707
 prepare_preconditioner              11  7.9    0.000    0.000   10.024   10.040
 make_preconditioner                 11  8.9    0.000    0.001   10.024   10.040
 dbcsr_mm_accdrv_process          52304 16.0    7.800    9.305    8.887    9.835
 make_full_inverse_cholesky          11  9.9    0.000    0.002    8.207    9.706
 sum_up_and_integrate               110 10.3    0.002    0.003    6.325    6.342
 integrate_v_rspace                 110 11.3    0.003    0.003    6.299    6.316
 mp_waitall_1                    121746 16.5    4.254    6.149    4.254    6.149
 qs_ot_get_p                        110 10.4    0.002    0.002    5.923    6.085
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.922    5.934
 calculate_rho_elec                 110  8.6    0.078    0.081    5.922    5.934
 make_m2s                          4110 13.4    0.060    0.062    5.486    5.839
 init_scf_run                        11  5.9    0.000    0.001    5.816    5.817
 scf_env_initial_rho_setup           11  6.9    0.002    0.003    5.816    5.816
 make_images                       4110 14.4    0.576    0.698    5.344    5.695
 cp_fm_upper_to_full                 70 14.2    3.414    4.960    3.414    4.960
 ot_diis_step                        99 11.5    0.011    0.011    4.153    4.153
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.055    4.134
 apply_single                       110 13.6    0.000    0.000    4.055    4.134
 qs_ot_p2m_diag                      48 11.0    0.055    0.064    4.036    4.055
 dbcsr_complete_redistribute        325 12.2    0.486    0.577    2.792    3.957
 pw_transfer                       1331 11.6    0.065    0.073    3.834    3.873
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.728    3.769
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.528    3.578
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.432    3.488
 cp_dbcsr_syevd                      48 12.0    0.003    0.004    3.465    3.466
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    2.278    3.435
 grid_integrate_task_list           110 12.3    3.282    3.423    3.282    3.423
 fft_wrap_pw1pw2_140                451 13.1    0.532    0.543    3.204    3.247
 density_rs2pw                      110  9.6    0.004    0.004    3.031    3.140
 calculate_dm_sparse                110  9.5    0.001    0.001    3.088    3.127
 hybrid_alltoall_any               4261 16.3    0.123    0.459    2.332    3.049
 make_images_data                  4110 15.4    0.049    0.053    2.726    3.030
 multiply_cannon_metrocomm3       24660 15.4    0.037    0.039    1.352    3.007
 wfi_extrapolate                     11  7.9    0.001    0.001    2.998    2.998
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.982    2.984
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.808    2.951
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    2.919    2.930
 cp_fm_diag_elpa_base                48 14.0    2.768    2.828    2.916    2.927
 mp_alltoall_i22                    605 13.7    1.680    2.875    1.680    2.875
 cp_fm_cholesky_invert               11 10.9    2.715    2.724    2.715    2.724
 calculate_first_density_matrix       1  7.0    0.001    0.008    2.719    2.723
 acc_transpose_blocks             24660 15.4    0.113    0.116    2.432    2.579
 fft3d_ps                          1111 14.6    1.153    1.192    2.553    2.573
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.521    2.554
 multiply_cannon_sync_h2d         24660 15.4    2.361    2.529    2.361    2.529
 grid_collocate_task_list           110  9.6    2.267    2.405    2.267    2.405
 qs_energies_init_hamiltonians       11  5.9    0.006    0.008    2.268    2.282
 potential_pw2rs                    110 12.3    0.012    0.013    2.133    2.145
 mp_alltoall_d11v                  2046 13.8    1.795    1.992    1.795    1.992
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.799    1.840
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.720    1.735
 cp_fm_cholesky_decompose            22 10.9    1.675    1.715    1.675    1.715
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.615    1.713
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.630    1.650
 mp_sum_l                          6594 12.7    1.025    1.630    1.025    1.630
 mp_allgather_i34                  2055 14.4    0.528    1.596    0.528    1.596
 acc_transpose_blocks_sync        73980 16.4    1.378    1.516    1.378    1.516
 jit_kernel_multiply                  8 15.7    0.737    1.484    0.737    1.484
 transfer_rs2pw                     451 10.6    0.005    0.005    1.238    1.426
 multiply_cannon_metrocomm4       20550 15.4    0.060    0.062    0.851    1.412
 mp_waitany                       13376 13.8    1.078    1.347    1.078    1.347
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="206", plot="h2o_128_md", label="(8n/3r/4t)", y=66.768000, yerr=0.000000
PlotPoint: name="207", plot="h2o_128_md_mem", label="(8n/3r/4t)", y=703.727273, yerr=11.600085
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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             853.671936E+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    0.021    0.038   57.084   57.086
 qs_mol_dyn_low                       1  2.0    0.003    0.003   56.779   56.799
 qs_forces                           11  3.9    0.003    0.003   56.675   56.675
 qs_energies                         11  4.9    0.016    0.019   53.008   53.013
 scf_env_do_scf                      11  5.9    0.000    0.001   44.341   44.341
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.007   36.393   36.393
 velocity_verlet                     10  3.0    0.029    0.044   31.632   31.636
 dbcsr_multiply_generic            2055 12.4    0.108    0.110   24.000   24.187
 qs_scf_new_mos                      99  7.5    0.001    0.001   21.585   21.657
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   21.584   21.657
 ot_scf_mini                         99  9.5    0.002    0.002   20.313   20.364
 multiply_cannon                   2055 13.4    0.239    0.253   18.416   19.388
 multiply_cannon_loop              2055 14.4    0.606    0.629   17.160   17.553
 rebuild_ks_matrix                  110  8.3    0.000    0.000   11.745   11.798
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.013   11.745   11.797
 ot_mini                             99 10.5    0.001    0.001   11.268   11.319
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.454   10.496
 multiply_cannon_multrec           8220 15.4    3.338    5.027    8.043    9.286
 init_scf_loop                       11  6.9    0.000    0.000    7.900    7.900
 mp_waitall_1                    103326 16.6    6.069    7.689    6.069    7.689
 qs_ot_get_derivative                99 11.5    0.001    0.001    7.469    7.520
 sum_up_and_integrate               110 10.3    0.001    0.002    6.302    6.315
 integrate_v_rspace                 110 11.3    0.003    0.003    6.276    6.289
 prepare_preconditioner              11  7.9    0.000    0.000    6.242    6.248
 make_preconditioner                 11  8.9    0.000    0.000    6.242    6.248
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.144    6.159
 calculate_rho_elec                 110  8.6    0.113    0.113    6.143    6.158
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.813    5.887
 dbcsr_mm_accdrv_process          17442 15.9    3.275    4.553    4.564    5.749
 init_scf_run                        11  5.9    0.000    0.001    5.513    5.513
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    5.513    5.513
 qs_ot_get_p                        110 10.4    0.002    0.002    5.084    5.144
 multiply_cannon_metrocomm3        8220 15.4    0.018    0.019    3.172    4.613
 make_m2s                          4110 13.4    0.038    0.039    4.218    4.411
 make_images                       4110 14.4    0.648    0.708    4.089    4.277
 pw_transfer                       1331 11.6    0.066    0.070    4.175    4.184
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    4.067    4.081
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    3.814    3.863
 apply_single                       110 13.6    0.000    0.000    3.814    3.863
 ot_diis_step                        99 11.5    0.012    0.012    3.775    3.776
 qs_ot_p2m_diag                      48 11.0    0.081    0.084    3.653    3.657
 fft_wrap_pw1pw2_140                451 13.1    0.719    0.732    3.517    3.532
 grid_integrate_task_list           110 12.3    3.370    3.523    3.370    3.523
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.305    3.305
 density_rs2pw                      110  9.6    0.004    0.004    3.095    3.233
 cp_fm_cholesky_invert               11 10.9    3.075    3.079    3.075    3.079
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.793    2.794
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    2.716    2.723
 cp_fm_diag_elpa_base                48 14.0    2.659    2.681    2.714    2.722
 wfi_extrapolate                     11  7.9    0.001    0.001    2.721    2.722
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.694    2.696
 qs_energies_init_hamiltonians       11  5.9    0.006    0.008    2.676    2.677
 calculate_dm_sparse                110  9.5    0.001    0.001    2.615    2.658
 hybrid_alltoall_any               4261 16.3    0.199    0.840    2.248    2.642
 fft3d_ps                          1111 14.6    1.294    1.304    2.609    2.626
 make_images_data                  4110 15.4    0.041    0.047    2.231    2.535
 grid_collocate_task_list           110  9.6    2.374    2.497    2.374    2.497
 multiply_cannon_sync_h2d          8220 15.4    2.345    2.475    2.345    2.475
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.300    2.322
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    2.109    2.146
 potential_pw2rs                    110 12.3    0.015    0.015    2.081    2.086
 mp_alltoall_d11v                  2046 13.8    1.824    2.012    1.824    2.012
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.785    1.994
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    1.960    1.985
 cp_fm_cholesky_decompose            22 10.9    1.698    1.717    1.698    1.717
 dbcsr_complete_redistribute        325 12.2    0.619    0.685    1.587    1.672
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.620    1.631
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    1.494    1.610
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.548    1.560
 acc_transpose_blocks              8220 15.4    0.041    0.042    1.488    1.521
 mp_allgather_i34                  2055 14.4    0.426    1.480    0.426    1.480
 multiply_cannon_metrocomm1        8220 15.4    0.022    0.023    0.814    1.359
 multiply_cannon_metrocomm4        6165 15.4    0.018    0.020    0.479    1.354
 mp_irecv_dv                      24056 15.7    0.454    1.311    0.454    1.311
 qs_create_task_list                 11  7.9    0.000    0.001    1.207    1.305
 generate_qs_task_list               11  8.9    0.373    0.440    1.207    1.305
 jit_kernel_multiply                  6 15.5    0.968    1.294    0.968    1.294
 transfer_rs2pw                     451 10.6    0.005    0.005    1.129    1.291
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.228    1.255
 mp_waitany                        9240 13.8    1.056    1.213    1.056    1.213
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="208", plot="h2o_128_md", label="(8n/2r/6t)", y=57.086000, yerr=0.000000
PlotPoint: name="209", plot="h2o_128_md_mem", label="(8n/2r/6t)", y=807.818182, yerr=11.223500
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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               1.365086E+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    0.035    0.071   89.504   89.511
 qs_mol_dyn_low                       1  2.0    0.003    0.003   89.110   89.124
 qs_forces                           11  3.9    0.003    0.004   88.993   89.000
 qs_energies                         11  4.9    0.002    0.002   84.808   84.815
 scf_env_do_scf                      11  5.9    0.000    0.001   74.761   74.767
 velocity_verlet                     10  3.0    0.002    0.002   57.178   57.196
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.007   45.926   45.932
 dbcsr_multiply_generic            2055 12.4    0.121    0.125   30.071   30.237
 init_scf_loop                       11  6.9    0.000    0.000   28.761   28.763
 qs_scf_new_mos                      99  7.5    0.001    0.001   27.693   27.783
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   27.692   27.782
 prepare_preconditioner              11  7.9    0.000    0.000   26.717   26.734
 make_preconditioner                 11  8.9    0.000    0.000   26.717   26.734
 make_full_inverse_cholesky          11  9.9    0.000    0.000   20.822   26.188
 ot_scf_mini                         99  9.5    0.002    0.002   25.895   25.975
 multiply_cannon                   2055 13.4    0.335    0.358   22.713   23.384
 multiply_cannon_loop              2055 14.4    0.828    0.851   20.841   21.249
 cp_fm_upper_to_full                 70 14.2   12.859   18.481   12.859   18.481
 ot_mini                             99 10.5    0.001    0.001   14.623   14.703
 rebuild_ks_matrix                  110  8.3    0.001    0.001   14.180   14.284
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.013   14.179   14.283
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.869   12.962
 dbcsr_complete_redistribute        325 12.2    1.003    1.024    7.471   10.783
 multiply_cannon_multrec           8220 15.4    4.057    4.218    9.748    9.855
 qs_ot_get_derivative                99 11.5    0.001    0.001    9.762    9.840
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    6.445    9.752
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    5.880    9.160
 mp_waitall_1                     84994 16.7    7.819    8.960    7.819    8.960
 mp_alltoall_i22                    605 13.7    5.530    8.799    5.530    8.799
 qs_rho_update_rho_low              110  7.6    0.001    0.001    7.588    7.624
 calculate_rho_elec                 110  8.6    0.222    0.222    7.588    7.624
 sum_up_and_integrate               110 10.3    0.002    0.002    7.060    7.073
 integrate_v_rspace                 110 11.3    0.004    0.004    7.032    7.045
 make_m2s                          4110 13.4    0.043    0.044    5.492    6.036
 qs_ot_get_p                        110 10.4    0.002    0.002    5.901    5.998
 pw_transfer                       1331 11.6    0.074    0.075    5.921    5.926
 make_images                       4110 14.4    0.884    0.935    5.303    5.846
 fft_wrap_pw1pw2                   1111 12.6    0.009    0.009    5.804    5.809
 init_scf_run                        11  5.9    0.000    0.001    5.753    5.754
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.753    5.753
 dbcsr_mm_accdrv_process          11614 15.7    3.858    4.133    5.543    5.744
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.944    5.475
 apply_single                       110 13.6    0.000    0.000    4.944    5.475
 cp_fm_cholesky_invert               11 10.9    5.466    5.471    5.466    5.471
 multiply_cannon_metrocomm3        8220 15.4    0.019    0.019    5.034    5.382
 fft_wrap_pw1pw2_140                451 13.1    1.366    1.369    5.083    5.089
 ot_diis_step                        99 11.5    0.016    0.018    4.839    4.839
 qs_ot_p2m_diag                      48 11.0    0.151    0.156    4.205    4.214
 density_rs2pw                      110  9.6    0.004    0.004    4.020    4.053
 grid_integrate_task_list           110 12.3    3.710    3.769    3.710    3.769
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.673    3.674
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    3.672    3.673
 hybrid_alltoall_any               4261 16.3    0.266    0.567    2.896    3.663
 make_images_data                  4110 15.4    0.046    0.049    2.924    3.608
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.101    3.566
 fft3d_ps                          1111 14.6    1.890    1.893    3.509    3.517
 wfi_extrapolate                     11  7.9    0.001    0.001    3.366    3.367
 calculate_dm_sparse                110  9.5    0.001    0.001    3.162    3.188
 multiply_cannon_sync_h2d          8220 15.4    3.124    3.162    3.124    3.162
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.062    3.062
 cp_fm_diag_elpa_base                48 14.0    2.520    2.717    3.060    3.060
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.920    2.922
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.727    2.771
 grid_collocate_task_list           110  9.6    2.694    2.719    2.694    2.719
 potential_pw2rs                    110 12.3    0.021    0.021    2.527    2.537
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.403    2.437
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.267    2.268
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    2.182    2.226
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    2.123    2.224
 mp_alltoall_d11v                  2046 13.8    2.081    2.171    2.081    2.171
 cp_fm_cholesky_decompose            22 10.9    1.986    2.011    1.986    2.011
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.911    1.921
 qs_create_task_list                 11  7.9    0.001    0.001    1.878    1.919
 generate_qs_task_list               11  8.9    0.731    0.787    1.877    1.919
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.769    1.819
 acc_transpose_blocks              8220 15.4    0.042    0.043    1.747    1.795
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="210", plot="h2o_128_md", label="(8n/1r/12t)", y=89.511000, yerr=0.000000
PlotPoint: name="211", plot="h2o_128_md_mem", label="(8n/1r/12t)", y=1232.454545, yerr=57.477843
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/15/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420242647040       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528903135232       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514766E+12       0.0%      0.0%    100.0%
 flops max/rank                      1.094965E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755941440       0.0%      0.0%    100.0%
 number of processed stacks              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             632.410112E+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            3175955383376
   4194304 < size <= 16777216              261888            1145794321408
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4020                  57505.
 MP_Allreduce        11129                    795.
 MP_Sync                87
 MP_Alltoall          2226                2529087.
 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    0.011    0.029  210.153  210.159
 qs_mol_dyn_low                       1  2.0    0.003    0.003  209.705  209.719
 qs_forces                           11  3.9    0.005    0.007  209.616  209.622
 qs_energies                         11  4.9    0.001    0.002  203.994  204.013
 scf_env_do_scf                      11  5.9    0.001    0.002  187.246  187.255
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.008  166.426  166.432
 dbcsr_multiply_generic            2507 12.6    0.175    0.178  125.806  126.755
 qs_scf_new_mos                     117  7.6    0.001    0.001  126.368  126.639
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001  126.367  126.638
 velocity_verlet                     10  3.0    0.002    0.005  125.238  125.243
 ot_scf_mini                        117  9.6    0.003    0.003  119.616  119.856
 multiply_cannon                   2507 13.6    0.236    0.245  101.572  103.566
 multiply_cannon_loop              2507 14.6    2.417    2.469   99.323  101.308
 ot_mini                            117 10.6    0.001    0.001   66.343   66.606
 multiply_cannon_multrec          60168 15.6   31.908   33.872   41.694   43.472
 qs_ot_get_derivative               117 11.6    0.001    0.001   41.387   41.652
 rebuild_ks_matrix                  128  8.3    0.001    0.001   33.957   34.285
 qs_ks_build_kohn_sham_matrix       128  9.3    0.016    0.025   33.957   34.285
 mp_waitall_1                    267128 16.5   28.952   32.272   28.952   32.272
 qs_ot_get_p                        128 10.4    0.001    0.002   31.034   31.321
 qs_ks_update_qs_env                128  7.6    0.001    0.001   30.506   30.836
 multiply_cannon_sync_h2d         60168 15.6   26.440   28.244   26.440   28.244
 apply_preconditioner_dbcsr         128 12.6    0.000    0.001   24.429   25.195
 apply_single                       128 13.6    0.001    0.001   24.428   25.194
 ot_diis_step                       117 11.6    0.007    0.008   24.678   24.680
 qs_ot_p2m_diag                      83 11.4    0.079    0.092   24.342   24.423
 cp_dbcsr_syevd                      83 12.4    0.005    0.005   21.634   21.635
 init_scf_loop                       11  6.9    0.000    0.000   20.744   20.745
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002   19.774   19.989
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   18.537   18.567
 cp_fm_diag_elpa_base                83 14.4   18.461   18.490   18.532   18.564
 multiply_cannon_metrocomm3       60168 15.6    0.123    0.127   16.009   18.119
 prepare_preconditioner              11  7.9    0.000    0.000   16.116   16.178
 make_preconditioner                 11  8.9    0.000    0.000   16.116   16.178
 make_full_inverse_cholesky          11  9.9    0.000    0.000   15.347   15.534
 make_m2s                          5014 13.6    0.104    0.113   14.191   14.553
 make_images                       5014 14.6    0.403    0.422   14.012   14.388
 sum_up_and_integrate               128 10.3    0.002    0.004   14.288   14.307
 integrate_v_rspace                 128 11.3    0.003    0.004   14.230   14.249
 qs_rho_update_rho_low              128  7.7    0.001    0.001   13.465   13.648
 calculate_rho_elec                 128  8.7    0.045    0.064   13.465   13.647
 init_scf_run                        11  5.9    0.000    0.001   12.598   12.599
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   12.597   12.598
 mp_sum_l                          7950 12.9    8.789   10.244    8.789   10.244
 dbcsr_mm_accdrv_process         124484 16.2    4.715    4.852    9.352    9.870
 wfi_extrapolate                     11  7.9    0.001    0.001    9.258    9.258
 cp_fm_cholesky_invert               11 10.9    9.185    9.193    9.185    9.193
 calculate_dm_sparse                128  9.5    0.001    0.001    8.562    8.687
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    8.145    8.310
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    8.065    8.156
 pw_transfer                       1547 11.6    0.074    0.086    7.822    8.029
 make_images_data                  5014 15.6    0.068    0.073    6.980    7.856
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.012    7.620    7.823
 density_rs2pw                      128  9.7    0.006    0.006    7.110    7.790
 multiply_cannon_metrocomm1       60168 15.6    0.094    0.099    6.071    7.783
 grid_integrate_task_list           128 12.3    7.038    7.413    7.038    7.413
 hybrid_alltoall_any               5200 16.5    0.299    2.286    6.104    7.295
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.003    6.847    6.858
 fft_wrap_pw1pw2_140                523 13.2    0.861    0.906    6.589    6.779
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.853    5.978
 fft3d_ps                          1291 14.7    2.194    2.841    5.620    5.976
 mp_alltoall_d11v                  2415 14.1    4.411    5.584    4.411    5.584
 grid_collocate_task_list           128  9.7    4.842    5.239    4.842    5.239
 potential_pw2rs                    128 12.3    0.009    0.010    4.781    4.810
 cp_fm_cholesky_decompose            22 10.9    4.730    4.742    4.730    4.742
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="400", plot="h2o_256_md", label="(8n/12r/1t)", y=210.159000, yerr=0.000000
PlotPoint: name="401", plot="h2o_256_md_mem", label="(8n/12r/1t)", y=599.363636, yerr=6.785985
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/16/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420242647040       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528903135232       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514766E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.183246E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755941440       0.0%      0.0%    100.0%
 number of processed stacks               5975232       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1130.7
 marketing flops                   144.580175E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank             840.671232E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 2406720
 MPI messages size (bytes):
  total size                         4.100943E+12
  min size                           0.000000E+00
  max size                          17.653760E+06
  average size                       1.703955E+06
 MPI breakdown and total messages size (bytes):
             size <=      128               14916                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768               70860               2317615104
     32768 < size <=   131072              722992              55511613440
    131072 < size <=  4194304             1375664            1398181724160
   4194304 < size <= 16777216              154704            1463834845264
  16777216 < size                           67584            1181116006400
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4002                  58214.
 MP_Allreduce        11083                    960.
 MP_Sync                87
 MP_Alltoall          1969                6646599.
 MP_SendRecv         12032                  47072.
 MP_ISendRecv        12032                  47072.
 MP_Wait             25916
 MP_ISend            11748                 212467.
 MP_IRecv            11748                 212467.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.057    0.121  192.395  192.397
 qs_mol_dyn_low                       1  2.0    0.005    0.012  191.883  191.896
 qs_forces                           11  3.9    0.004    0.005  191.784  191.789
 qs_energies                         11  4.9    0.009    0.024  184.934  184.957
 scf_env_do_scf                      11  5.9    0.003    0.013  168.106  168.116
 scf_env_do_scf_inner_loop          117  6.6    0.007    0.029  134.857  134.860
 velocity_verlet                     10  3.0    0.009    0.015  120.523  120.525
 dbcsr_multiply_generic            2507 12.6    0.187    0.195   97.914   99.087
 qs_scf_new_mos                     117  7.6    0.001    0.001   95.636   96.173
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   95.636   96.172
 ot_scf_mini                        117  9.6    0.004    0.005   90.819   91.347
 multiply_cannon                   2507 13.6    0.503    0.558   77.573   82.491
 multiply_cannon_loop              2507 14.6    1.572    1.637   74.105   76.546
 ot_mini                            117 10.6    0.001    0.003   50.824   51.372
 mp_waitall_1                    214728 16.6   24.219   39.859   24.219   39.859
 multiply_cannon_multrec          30084 15.6   21.023   25.860   31.782   36.958
 rebuild_ks_matrix                  128  8.3    0.001    0.001   32.649   33.306
 qs_ks_build_kohn_sham_matrix       128  9.3    0.026    0.039   32.648   33.306
 init_scf_loop                       11  6.9    0.001    0.004   33.148   33.151
 qs_ks_update_qs_env                128  7.6    0.001    0.001   29.314   29.914
 multiply_cannon_metrocomm3       30084 15.6    0.100    0.108   15.593   29.444
 qs_ot_get_derivative               117 11.6    0.001    0.002   28.813   29.337
 prepare_preconditioner              11  7.9    0.000    0.000   28.736   28.796
 make_preconditioner                 11  8.9    0.000    0.002   28.736   28.796
 make_full_inverse_cholesky          11  9.9    0.000    0.002   27.341   27.883
 apply_preconditioner_dbcsr         128 12.6    0.000    0.000   22.116   23.191
 apply_single                       128 13.6    0.001    0.001   22.116   23.190
 qs_ot_get_p                        128 10.4    0.002    0.003   22.035   22.590
 ot_diis_step                       117 11.6    0.014    0.015   21.829   21.832
 multiply_cannon_sync_h2d         30084 15.6   18.027   20.471   18.027   20.471
 qs_ot_p2m_diag                      83 11.4    0.189    0.217   16.913   16.947
 cp_fm_cholesky_invert               11 10.9   16.723   16.736   16.723   16.736
 make_m2s                          5014 13.6    0.087    0.092   14.334   16.077
 make_images                       5014 14.6    1.175    1.368   14.119   15.858
 cp_dbcsr_syevd                      83 12.4    0.006    0.007   15.697   15.698
 sum_up_and_integrate               128 10.3    0.003    0.005   14.262   14.295
 integrate_v_rspace                 128 11.3    0.003    0.004   14.202   14.237
 qs_rho_update_rho_low              128  7.7    0.001    0.001   13.816   13.843
 calculate_rho_elec                 128  8.7    0.088    0.105   13.815   13.842
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   12.418   12.452
 cp_fm_diag_elpa_base                83 14.4   12.153   12.261   12.411   12.441
 qs_ot_get_derivative_diag           77 12.4    0.002    0.003   11.375   11.753
 init_scf_run                        11  5.9    0.000    0.001   11.702   11.703
 scf_env_initial_rho_setup           11  6.9    0.001    0.002   11.701   11.703
 dbcsr_mm_accdrv_process          62242 16.2    5.498    6.480   10.207   10.891
 multiply_cannon_metrocomm4       27577 15.6    0.100    0.114    3.858   10.838
 make_images_data                  5014 15.6    0.067    0.077    8.419   10.479
 mp_irecv_dv                      69486 16.3    3.658   10.433    3.658   10.433
 hybrid_alltoall_any               5200 16.5    0.349    1.513    7.245    9.956
 pw_transfer                       1547 11.6    0.085    0.101    8.785    8.845
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.011    8.562    8.627
 wfi_extrapolate                     11  7.9    0.001    0.001    8.479    8.480
 density_rs2pw                      128  9.7    0.006    0.006    7.380    7.800
 fft_wrap_pw1pw2_140                523 13.2    0.933    0.959    7.536    7.609
 grid_integrate_task_list           128 12.3    7.181    7.581    7.181    7.581
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    6.357    7.149
 cp_fm_cholesky_decompose            22 10.9    7.037    7.120    7.037    7.120
 calculate_dm_sparse                128  9.5    0.001    0.001    6.474    6.648
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.177    6.188
 fft3d_ps                          1291 14.7    2.828    3.015    6.118    6.171
 mp_sum_l                          7950 12.9    4.234    6.106    4.234    6.106
 grid_collocate_task_list           128  9.7    5.000    5.464    5.000    5.464
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    5.384    5.448
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.212    5.392
 mp_alltoall_d11v                  2415 14.1    4.704    5.146    4.704    5.146
 mp_allgather_i34                  2507 14.6    1.989    5.027    1.989    5.027
 potential_pw2rs                    128 12.3    0.015    0.017    4.681    4.696
 dbcsr_complete_redistribute        395 12.7    0.762    0.870    3.316    4.159
 mp_sum_d                          4472 12.1    2.668    3.905    2.668    3.905
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="402", plot="h2o_256_md", label="(8n/6r/2t)", y=192.397000, yerr=0.000000
PlotPoint: name="403", plot="h2o_256_md_mem", label="(8n/6r/2t)", y=798.454545, yerr=1.724879
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/17/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420242647040       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528903135232       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514766E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.928533E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755941440       0.0%      0.0%    100.0%
 number of processed stacks               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             938.315776E+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             931531265168
  16777216 < size                           28672             751619276800
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4002                  58208.
 MP_Allreduce        11082                    999.
 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    0.013    0.029  179.977  179.980
 qs_mol_dyn_low                       1  2.0    0.003    0.003  179.569  179.571
 qs_forces                           11  3.9    0.004    0.004  179.472  179.476
 qs_energies                         11  4.9    0.001    0.002  172.808  172.819
 scf_env_do_scf                      11  5.9    0.001    0.001  156.928  156.936
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.008  120.839  120.841
 velocity_verlet                     10  3.0    0.002    0.002  115.424  115.428
 dbcsr_multiply_generic            2507 12.6    0.183    0.186   83.047   84.230
 qs_scf_new_mos                     117  7.6    0.001    0.001   82.754   83.161
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   82.753   83.161
 ot_scf_mini                        117  9.6    0.003    0.004   78.471   78.906
 multiply_cannon                   2507 13.6    0.505    0.529   62.683   67.856
 multiply_cannon_loop              2507 14.6    1.140    1.209   59.524   62.316
 ot_mini                            117 10.6    0.001    0.001   43.245   43.663
 init_scf_loop                       11  6.9    0.000    0.000   35.984   35.985
 mp_waitall_1                    170520 16.6   25.492   35.037   25.492   35.037
 prepare_preconditioner              11  7.9    0.000    0.000   31.909   31.960
 make_preconditioner                 11  8.9    0.000    0.000   31.909   31.960
 rebuild_ks_matrix                  128  8.3    0.001    0.001   30.880   31.369
 qs_ks_build_kohn_sham_matrix       128  9.3    0.016    0.018   30.879   31.368
 make_full_inverse_cholesky          11  9.9    0.000    0.000   29.432   30.928
 qs_ks_update_qs_env                128  7.6    0.001    0.001   27.792   28.236
 multiply_cannon_multrec          20056 15.6   13.113   15.727   22.463   25.204
 multiply_cannon_metrocomm3       20056 15.6    0.063    0.068   15.477   24.436
 qs_ot_get_derivative               117 11.6    0.001    0.002   23.641   24.070
 qs_ot_get_p                        128 10.4    0.002    0.002   20.371   20.824
 apply_preconditioner_dbcsr         128 12.6    0.000    0.000   19.619   20.707
 apply_single                       128 13.6    0.001    0.001   19.619   20.707
 ot_diis_step                       117 11.6    0.018    0.018   19.494   19.495
 make_m2s                          5014 13.6    0.078    0.082   15.232   16.625
 make_images                       5014 14.6    1.160    1.249   14.997   16.382
 qs_ot_p2m_diag                      83 11.4    0.265    0.272   15.908   15.915
 multiply_cannon_sync_h2d         20056 15.6   13.607   14.985   13.607   14.985
 cp_fm_cholesky_invert               11 10.9   14.854   14.864   14.854   14.864
 cp_dbcsr_syevd                      83 12.4    0.005    0.006   14.814   14.815
 sum_up_and_integrate               128 10.3    0.002    0.003   14.357   14.380
 integrate_v_rspace                 128 11.3    0.003    0.004   14.297   14.320
 qs_rho_update_rho_low              128  7.7    0.001    0.001   14.059   14.096
 calculate_rho_elec                 128  8.7    0.130    0.144   14.058   14.096
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   11.514   11.531
 cp_fm_diag_elpa_base                83 14.4   11.074   11.248   11.510   11.527
 make_images_data                  5014 15.6    0.065    0.075    9.153   11.020
 init_scf_run                        11  5.9    0.000    0.001   10.737   10.738
 scf_env_initial_rho_setup           11  6.9    0.001    0.002   10.737   10.737
 hybrid_alltoall_any               5200 16.5    0.449    2.042    7.894   10.586
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002    9.396    9.698
 pw_transfer                       1547 11.6    0.085    0.104    9.184    9.293
 multiply_cannon_metrocomm4       17549 15.6    0.065    0.076    3.455    9.120
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.012    8.961    9.077
 dbcsr_mm_accdrv_process          41502 16.2    5.629    5.924    8.807    8.930
 mp_irecv_dv                      50230 16.2    3.327    8.865    3.327    8.865
 fft_wrap_pw1pw2_140                523 13.2    1.058    1.098    7.851    7.974
 grid_integrate_task_list           128 12.3    7.262    7.875    7.262    7.875
 density_rs2pw                      128  9.7    0.006    0.006    7.309    7.688
 cp_fm_upper_to_full                105 14.8    6.029    7.673    6.029    7.673
 wfi_extrapolate                     11  7.9    0.001    0.001    7.586    7.586
 cp_fm_cholesky_decompose            22 10.9    7.483    7.520    7.483    7.520
 dbcsr_complete_redistribute        395 12.7    1.163    1.193    4.905    6.762
 fft3d_ps                          1291 14.7    2.817    3.057    6.278    6.374
 calculate_dm_sparse                128  9.5    0.001    0.001    5.878    5.964
 grid_collocate_task_list           128  9.7    5.150    5.610    5.150    5.610
 copy_fm_to_dbcsr                   209 11.7    0.002    0.002    3.680    5.536
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.513    5.519
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    4.786    5.408
 mp_alltoall_d11v                  2415 14.1    4.697    5.346    4.697    5.346
 mp_sum_l                          7950 12.9    3.302    4.930    3.302    4.930
 mp_allgather_i34                  2507 14.6    1.654    4.915    1.654    4.915
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.599    4.741
 potential_pw2rs                    128 12.3    0.020    0.021    4.676    4.695
 transfer_fm_to_dbcsr                11  9.9    0.020    0.025    2.458    4.310
 mp_alltoall_i22                    716 14.1    2.166    4.121    2.166    4.121
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    3.959    3.994
 qs_energies_init_hamiltonians       11  5.9    0.006    0.009    3.780    3.781
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    3.587    3.632
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="404", plot="h2o_256_md", label="(8n/4r/3t)", y=179.980000, yerr=0.000000
PlotPoint: name="405", plot="h2o_256_md_mem", label="(8n/4r/3t)", y=890.090909, yerr=9.404588
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/18/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                      4.353788E+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               5977344       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1130.3
 marketing flops                   144.580175E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank               1.143607E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1143192
 MPI messages size (bytes):
  total size                         2.023815E+12
  min size                           0.000000E+00
  max size                          17.653760E+06
  average size                       1.770319E+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              319024              36042702848
    131072 < size <=  4194304              715736             785529176064
   4194304 < size <= 16777216               70320             665379241840
  16777216 < size                           30720             536870912000
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3992                  58348.
 MP_Allreduce        11057                   1083.
 MP_Sync                87
 MP_Alltoall          1712               12503107.
 MP_SendRecv          5888                  75008.
 MP_ISendRecv         5888                  75008.
 MP_Wait             22442
 MP_ISend            14952                 244818.
 MP_IRecv            14952                 244818.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.042    0.102  189.539  189.542
 qs_mol_dyn_low                       1  2.0    0.003    0.003  188.972  189.021
 qs_forces                           11  3.9    0.004    0.004  188.850  188.859
 qs_energies                         11  4.9    0.003    0.017  181.677  181.693
 scf_env_do_scf                      11  5.9    0.001    0.002  164.558  164.569
 velocity_verlet                     10  3.0    0.002    0.002  125.478  125.483
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.008  117.714  117.716
 dbcsr_multiply_generic            2507 12.6    0.191    0.197   80.776   81.447
 qs_scf_new_mos                     117  7.6    0.001    0.001   81.068   81.369
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   81.068   81.368
 ot_scf_mini                        117  9.6    0.003    0.004   76.504   76.786
 multiply_cannon                   2507 13.6    0.551    0.601   55.852   58.844
 multiply_cannon_loop              2507 14.6    1.801    1.916   52.093   53.454
 init_scf_loop                       11  6.9    0.001    0.005   46.718   46.719
 ot_mini                            117 10.6    0.001    0.001   43.126   43.404
 prepare_preconditioner              11  7.9    0.000    0.000   42.582   42.611
 make_preconditioner                 11  8.9    0.000    0.002   42.582   42.611
 make_full_inverse_cholesky          11  9.9    0.012    0.023   36.100   41.206
 multiply_cannon_multrec          30084 15.6   13.808   18.863   26.724   31.424
 rebuild_ks_matrix                  128  8.3    0.001    0.001   29.531   29.754
 qs_ks_build_kohn_sham_matrix       128  9.3    0.024    0.081   29.530   29.753
 qs_ks_update_qs_env                128  7.6    0.001    0.001   26.593   26.800
 mp_waitall_1                    147882 16.7   17.194   26.292   17.194   26.292
 qs_ot_get_derivative               117 11.6    0.001    0.002   23.470   23.751
 make_m2s                          5014 13.6    0.093    0.097   20.489   21.540
 make_images                       5014 14.6    1.957    2.293   20.179   21.228
 qs_ot_get_p                        128 10.4    0.002    0.002   19.487   19.802
 apply_preconditioner_dbcsr         128 12.6    0.000    0.001   19.075   19.567
 apply_single                       128 13.6    0.001    0.001   19.075   19.566
 ot_diis_step                       117 11.6    0.017    0.019   19.522   19.524
 cp_fm_upper_to_full                105 14.8   11.662   17.153   11.662   17.153
 cp_fm_cholesky_invert               11 10.9   16.207   16.216   16.207   16.216
 qs_ot_p2m_diag                      83 11.4    0.343    0.390   15.249   15.300
 multiply_cannon_metrocomm3       30084 15.6    0.049    0.051    6.171   15.283
 sum_up_and_integrate               128 10.3    0.002    0.005   14.135   14.164
 integrate_v_rspace                 128 11.3    0.003    0.004   14.074   14.106
 qs_rho_update_rho_low              128  7.7    0.001    0.001   13.992   14.027
 calculate_rho_elec                 128  8.7    0.171    0.186   13.991   14.026
 cp_dbcsr_syevd                      83 12.4    0.006    0.014   13.820   13.821
 dbcsr_complete_redistribute        395 12.7    1.504    1.638    9.163   13.010
 dbcsr_mm_accdrv_process          62264 16.2    8.463    9.227   12.489   12.937
 make_images_data                  5014 15.6    0.066    0.074   10.996   12.755
 hybrid_alltoall_any               5200 16.5    0.529    2.222    9.774   11.955
 copy_fm_to_dbcsr                   209 11.7    0.001    0.002    7.789   11.638
 multiply_cannon_sync_h2d         30084 15.6   10.476   11.460   10.476   11.460
 init_scf_run                        11  5.9    0.000    0.001   11.049   11.051
 scf_env_initial_rho_setup           11  6.9    0.001    0.002   11.049   11.050
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   10.699   10.708
 cp_fm_diag_elpa_base                83 14.4    9.710   10.032   10.692   10.701
 transfer_fm_to_dbcsr                11  9.9    0.001    0.005    6.459   10.230
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002    9.856   10.068
 mp_alltoall_i22                    716 14.1    5.674    9.704    5.674    9.704
 pw_transfer                       1547 11.6    0.086    0.102    9.358    9.420
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.011    9.132    9.201
 fft_wrap_pw1pw2_140                523 13.2    1.250    1.297    8.096    8.171
 grid_integrate_task_list           128 12.3    7.476    7.968    7.476    7.968
 wfi_extrapolate                     11  7.9    0.001    0.001    7.787    7.787
 cp_fm_cholesky_decompose            22 10.9    7.536    7.654    7.536    7.654
 multiply_cannon_metrocomm4       25070 15.6    0.079    0.090    2.742    7.321
 density_rs2pw                      128  9.7    0.006    0.006    7.016    7.302
 mp_irecv_dv                      76098 16.2    2.592    7.046    2.592    7.046
 calculate_dm_sparse                128  9.5    0.001    0.001    6.312    6.401
 fft3d_ps                          1291 14.7    2.991    3.036    6.174    6.238
 mp_alltoall_d11v                  2415 14.1    5.033    5.679    5.033    5.679
 grid_collocate_task_list           128  9.7    5.285    5.671    5.285    5.671
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.562    5.628
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    4.520    4.605
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.421    4.505
 qs_energies_init_hamiltonians       11  5.9    0.020    0.023    4.477    4.478
 potential_pw2rs                    128 12.3    0.023    0.024    4.358    4.368
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    4.267    4.332
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="406", plot="h2o_256_md", label="(8n/3r/4t)", y=189.542000, yerr=0.000000
PlotPoint: name="407", plot="h2o_256_md_mem", label="(8n/3r/4t)", y=1084.636364, yerr=14.717168
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/19/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1410023282688       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1924145348608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1957871443968       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1963544850432       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2714615709696       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4377645416448       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5350455508992       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5395653328896       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6594687401984       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11444707676160       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15019188129792       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15019188129792       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19624853225472       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        92.796579E+12       0.0%      0.0%    100.0%
 flops max/rank                      5.820059E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6705500928       0.0%      0.0%    100.0%
 number of processed stacks               1944496       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    3448.5
 marketing flops                   143.507742E+12
 -------------------------------------------------------------------------------
 # multiplications                           2485
 max memory usage/rank               1.533207E+09
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  238560
 MPI messages size (bytes):
  total size                         1.321104E+12
  min size                           0.000000E+00
  max size                          52.428800E+06
  average size                       5.537828E+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              112800              59139686400
   4194304 < size <= 16777216              104112             545846722560
  16777216 < size                           20064             716108638608
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         8852                     52.
 MP_Alltoall          9584                 804353.
 MP_ISend            39716                2104723.
 MP_IRecv            39716                2103824.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3997                  58273.
 MP_Allreduce        11070                   1167.
 MP_Sync                86
 MP_Alltoall          1700               18828160.
 MP_SendRecv          3810                 122880.
 MP_ISendRecv         3810                 122880.
 MP_Wait             16000
 MP_ISend            10600                 423612.
 MP_IRecv            10600                 423612.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.038    0.053  169.541  169.542
 qs_mol_dyn_low                       1  2.0    0.003    0.003  169.020  169.047
 qs_forces                           11  3.9    0.004    0.004  168.913  168.916
 qs_energies                         11  4.9    0.002    0.004  161.448  161.457
 scf_env_do_scf                      11  5.9    0.001    0.001  143.990  144.005
 velocity_verlet                     10  3.0    0.019    0.023  110.665  110.669
 scf_env_do_scf_inner_loop          116  6.6    0.003    0.009  108.425  108.426
 dbcsr_multiply_generic            2485 12.5    0.181    0.187   71.436   71.785
 qs_scf_new_mos                     116  7.6    0.001    0.001   71.353   71.448
 qs_scf_loop_do_ot                  116  8.6    0.001    0.001   71.353   71.448
 ot_scf_mini                        116  9.6    0.003    0.004   66.980   67.064
 multiply_cannon                   2485 13.5    0.556    0.584   52.840   56.379
 multiply_cannon_loop              2485 14.5    0.807    0.835   49.914   50.673
 ot_mini                            116 10.6    0.001    0.001   37.232   37.307
 init_scf_loop                       11  6.9    0.000    0.000   35.406   35.407
 prepare_preconditioner              11  7.9    0.000    0.000   31.504   31.529
 make_preconditioner                 11  8.9    0.000    0.000   31.504   31.529
 mp_waitall_1                    124680 16.7   24.520   30.499   24.520   30.499
 make_full_inverse_cholesky          11  9.9    0.016    0.027   29.360   29.670
 rebuild_ks_matrix                  127  8.3    0.001    0.001   29.217   29.318
 qs_ks_build_kohn_sham_matrix       127  9.3    0.017    0.017   29.216   29.317
 qs_ks_update_qs_env                127  7.6    0.001    0.001   26.608   26.699
 multiply_cannon_multrec           9940 15.5   10.330   14.305   17.874   20.896
 qs_ot_get_derivative               116 11.6    0.002    0.002   20.429   20.509
 multiply_cannon_metrocomm3        9940 15.5    0.024    0.025   12.369   19.612
 cp_fm_cholesky_invert               11 10.9   17.847   17.852   17.847   17.852
 qs_ot_get_p                        127 10.4    0.002    0.002   17.134   17.220
 apply_preconditioner_dbcsr         127 12.6    0.000    0.000   16.863   17.027
 apply_single                       127 13.6    0.001    0.001   16.863   17.027
 ot_diis_step                       116 11.6    0.019    0.020   16.734   16.734
 make_m2s                          4970 13.5    0.064    0.069   14.743   15.543
 make_images                       4970 14.5    2.154    2.580   14.439   15.238
 qs_rho_update_rho_low              127  7.7    0.001    0.001   14.284   14.317
 calculate_rho_elec                 127  8.7    0.252    0.262   14.283   14.316
 sum_up_and_integrate               127 10.3    0.002    0.002   14.233   14.281
 integrate_v_rspace                 127 11.3    0.004    0.004   14.173   14.223
 qs_ot_p2m_diag                      82 11.4    0.490    0.495   13.370   13.388
 cp_dbcsr_syevd                      82 12.4    0.005    0.006   12.207   12.208
 multiply_cannon_sync_h2d          9940 15.5   10.802   11.254   10.802   11.254
 init_scf_run                        11  5.9    0.000    0.001   10.605   10.606
 scf_env_initial_rho_setup           11  6.9    0.002    0.002   10.605   10.606
 pw_transfer                       1535 11.6    0.084    0.092    9.946    9.984
 fft_wrap_pw1pw2                   1281 12.7    0.010    0.010    9.726    9.769
 hybrid_alltoall_any               5155 16.4    0.835    3.754    8.358    9.762
 make_images_data                  4970 15.5    0.055    0.065    8.496    9.758
 cp_fm_diag_elpa                     82 13.4    0.000    0.000    9.343    9.354
 cp_fm_diag_elpa_base                82 14.4    9.099    9.187    9.338    9.349
 fft_wrap_pw1pw2_140                519 13.2    1.663    1.696    8.592    8.638
 qs_ot_get_derivative_diag           76 12.4    0.002    0.003    8.015    8.073
 grid_integrate_task_list           127 12.3    7.730    8.063    7.730    8.063
 cp_fm_cholesky_decompose            22 10.9    7.910    8.006    7.910    8.006
 dbcsr_mm_accdrv_process          20590 16.1    3.288    4.316    7.195    7.906
 wfi_extrapolate                     11  7.9    0.001    0.001    7.472    7.472
 density_rs2pw                      127  9.7    0.005    0.005    7.014    7.250
 multiply_cannon_metrocomm1        9940 15.5    0.030    0.031    4.379    7.079
 fft3d_ps                          1281 14.7    3.117    3.221    6.204    6.233
 calculate_dm_sparse                127  9.5    0.001    0.001    6.029    6.109
 dbcsr_complete_redistribute        393 12.7    2.113    2.203    5.345    5.744
 grid_collocate_task_list           127  9.7    5.537    5.688    5.537    5.688
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.246    5.272
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    5.251    5.254
 mp_alltoall_d11v                  2401 14.1    4.682    4.977    4.682    4.977
 mp_allgather_i34                  2485 14.5    1.127    4.589    1.127    4.589
 potential_pw2rs                    127 12.3    0.026    0.026    4.439    4.443
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.056    4.114
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    3.574    3.912
 copy_fm_to_dbcsr                   208 11.6    0.002    0.002    3.507    3.841
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    3.620    3.697
 multiply_cannon_metrocomm4        7455 15.5    0.025    0.028    1.721    3.675
 copy_dbcsr_to_fm                   185 11.7    0.004    0.004    3.480    3.618
 mp_irecv_dv                      28618 15.9    1.683    3.605    1.683    3.605
 qs_ot_get_orbitals                 116 10.6    0.001    0.001    3.548    3.585
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    3.508    3.519
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="408", plot="h2o_256_md", label="(8n/2r/6t)", y=169.542000, yerr=0.000000
PlotPoint: name="409", plot="h2o_256_md_mem", label="(8n/2r/6t)", y=1450.000000, yerr=16.011360
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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               3.116315E+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    0.031    0.060  296.792  296.801
 qs_mol_dyn_low                       1  2.0    0.003    0.003  296.204  296.240
 qs_forces                           11  3.9    0.005    0.005  296.098  296.100
 qs_energies                         11  4.9    0.002    0.002  287.155  287.161
 scf_env_do_scf                      11  5.9    0.001    0.001  264.489  264.495
 velocity_verlet                     10  3.0    0.018    0.019  214.738  214.745
 scf_env_do_scf_inner_loop          118  6.6    0.004    0.008  138.413  138.415
 init_scf_loop                       11  6.9    0.000    0.000  125.803  125.807
 prepare_preconditioner              11  7.9    0.000    0.000  120.843  120.860
 make_preconditioner                 11  8.9    0.000    0.000  120.843  120.860
 make_full_inverse_cholesky          11  9.9    0.038    0.039   96.831  118.002
 qs_scf_new_mos                     118  7.6    0.001    0.001   92.682   92.764
 qs_scf_loop_do_ot                  118  8.6    0.001    0.001   92.682   92.763
 ot_scf_mini                        118  9.6    0.004    0.004   87.696   87.730
 dbcsr_multiply_generic            2535 12.6    0.218    0.229   83.286   83.777
 cp_fm_upper_to_full                106 14.8   53.985   77.082   53.985   77.082
 multiply_cannon                   2535 13.6    0.685    0.731   59.985   61.007
 multiply_cannon_loop              2535 14.6    1.057    1.087   55.905   57.171
 ot_mini                            118 10.6    0.001    0.001   45.171   45.209
 dbcsr_complete_redistribute        397 12.7    3.971    4.049   30.017   42.810
 copy_fm_to_dbcsr                   210 11.7    0.001    0.002   26.487   39.255
 transfer_fm_to_dbcsr                11  9.9    0.030    0.030   23.970   36.529
 rebuild_ks_matrix                  129  8.3    0.001    0.001   35.329   35.375
 qs_ks_build_kohn_sham_matrix       129  9.3    0.017    0.017   35.328   35.374
 mp_alltoall_i22                    720 14.1   21.753   34.656   21.753   34.656
 cp_fm_cholesky_invert               11 10.9   33.772   33.778   33.772   33.778
 mp_waitall_1                    104820 16.8   28.703   33.243   28.703   33.243
 qs_ks_update_qs_env                129  7.6    0.001    0.001   32.817   32.850
 qs_ot_get_p                        129 10.4    0.020    0.038   27.284   27.348
 qs_ot_get_derivative               118 11.6    0.002    0.002   25.235   25.267
 qs_ot_p2m_diag                      84 11.4    0.891    0.895   23.027   23.063
 cp_dbcsr_syevd                      84 12.4    0.006    0.006   21.156   21.159
 multiply_cannon_metrocomm3       10140 15.6    0.025    0.026   19.599   20.782
 make_m2s                          5070 13.6    0.076    0.079   18.574   20.057
 ot_diis_step                       118 11.6    0.022    0.022   19.903   19.903
 make_images                       5070 14.6    3.091    3.287   18.087   19.570
 apply_preconditioner_dbcsr         129 12.6    0.000    0.000   19.167   19.276
 apply_single                       129 13.6    0.001    0.001   19.166   19.276
 multiply_cannon_multrec          10140 15.6   10.382   12.239   18.242   18.346
 cp_fm_diag_elpa                     84 13.4    0.000    0.000   17.849   17.849
 cp_fm_diag_elpa_base                84 14.4   13.286   14.999   17.844   17.844
 qs_rho_update_rho_low              129  7.7    0.001    0.001   17.681   17.704
 calculate_rho_elec                 129  8.7    0.482    0.482   17.680   17.704
 sum_up_and_integrate               129 10.3    0.002    0.002   16.752   16.839
 integrate_v_rspace                 129 11.3    0.005    0.005   16.689   16.776
 multiply_cannon_sync_h2d         10140 15.6   14.426   14.455   14.426   14.455
 pw_transfer                       1559 11.6    0.096    0.096   13.555   13.562
 fft_wrap_pw1pw2                   1301 12.7    0.012    0.012   13.315   13.323
 hybrid_alltoall_any               5257 16.5    1.327    3.088   10.472   12.667
 make_images_data                  5070 15.6    0.065    0.071   10.358   12.582
 init_scf_run                        11  5.9    0.000    0.001   12.293   12.295
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   12.292   12.294
 fft_wrap_pw1pw2_140                527 13.2    3.245    3.302   11.810   11.819
 qs_ot_get_derivative_diag           78 12.4    0.002    0.003   10.083   10.121
 dbcsr_mm_accdrv_process          20958 16.1    4.324    6.119    7.608    9.527
 wfi_extrapolate                     11  7.9    0.001    0.001    9.148    9.148
 cp_fm_cholesky_decompose            22 10.9    9.039    9.058    9.039    9.058
 grid_integrate_task_list           129 12.3    8.619    8.812    8.619    8.812
 density_rs2pw                      129  9.7    0.005    0.005    8.629    8.677
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    8.204    8.204
 fft3d_ps                          1301 14.7    4.010    4.028    7.735    7.777
 mp_alltoall_d11v                  2429 14.1    7.054    7.188    7.054    7.188
 calculate_dm_sparse                129  9.5    0.001    0.001    6.879    6.973
 grid_collocate_task_list           129  9.7    6.465    6.542    6.465    6.542
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.379    6.417
 copy_dbcsr_to_fm                   187 11.8    0.004    0.004    6.197    6.292
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="410", plot="h2o_256_md", label="(8n/1r/12t)", y=296.801000, yerr=0.000000
PlotPoint: name="411", plot="h2o_256_md_mem", label="(8n/1r/12t)", y=2849.545455, yerr=137.786636
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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               1.260798E+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               21516551.
 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    0.014    0.033   85.858   85.883
 qs_energies                          1  2.0    0.000    0.000   85.006   85.032
 ls_scf                               1  3.0    0.000    0.000   84.044   84.072
 dbcsr_multiply_generic             111  6.7    0.015    0.016   72.766   72.983
 multiply_cannon                    111  7.7    0.017    0.020   56.050   57.362
 multiply_cannon_loop               111  8.7    0.230    0.245   52.570   53.855
 ls_scf_main                          1  4.0    0.000    0.000   52.317   52.332
 density_matrix_trs4                  2  5.0    0.002    0.003   46.744   46.866
 ls_scf_init_scf                      1  4.0    0.000    0.000   28.674   28.683
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   27.531   27.586
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.003   25.199   25.223
 mp_waitall_1                     11031 10.9   22.612   25.174   22.612   25.174
 multiply_cannon_multrec           2664  9.7    8.139    8.816   15.640   17.353
 multiply_cannon_sync_h2d          2664  9.7   13.402   15.806   13.402   15.806
 make_m2s                           222  7.7    0.010    0.012   13.103   13.718
 make_images                        222  8.7    0.100    0.110   13.080   13.697
 multiply_cannon_metrocomm1        2664  9.7    0.011    0.012    9.766   12.293
 multiply_cannon_metrocomm3        2664  9.7    0.010    0.012    5.530    8.927
 make_images_data                   222  9.7    0.005    0.006    7.657    8.148
 dbcsr_mm_accdrv_process           4760 10.4    0.596    0.714    7.122    8.140
 hybrid_alltoall_any                227 10.6    0.219    1.840    6.642    7.909
 dbcsr_mm_accdrv_process_sort      4760 11.4    6.321    7.238    6.321    7.238
 calculate_norms                   4752  9.8    5.511    6.090    5.511    6.090
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.064    5.171
 mp_sum_l                           887  5.1    3.074    4.528    3.074    4.528
 multiply_cannon_metrocomm4        2442  9.7    0.012    0.015    2.052    3.544
 mp_irecv_dv                       6231 10.9    2.036    3.532    2.036    3.532
 make_images_sizes                  222  9.7    0.000    0.000    0.690    3.475
 mp_alltoall_i44                    222 10.7    0.690    3.475    0.690    3.475
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    2.312    3.408
 arnoldi_extremal                     4  6.8    0.000    0.000    3.219    3.243
 arnoldi_normal_ev                    4  7.8    0.001    0.004    3.219    3.243
 build_subspace                      16  8.4    0.009    0.012    3.122    3.123
 ls_scf_post                          1  4.0    0.000    0.000    3.054    3.065
 ls_scf_store_result                  1  5.0    0.000    0.000    2.870    2.913
 dbcsr_special_finalize             555  9.7    0.006    0.007    2.393    2.870
 dbcsr_merge_single_wm              555 10.7    0.468    0.601    2.384    2.861
 make_images_pack                   222  9.7    2.213    2.633    2.215    2.635
 dbcsr_sort_data                    658 11.4    2.172    2.589    2.172    2.589
 dbcsr_matrix_vector_mult           304  9.0    0.006    0.013    2.312    2.559
 dbcsr_matrix_vector_mult_local     304 10.0    2.062    2.458    2.065    2.460
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.315    2.380
 buffer_matrices_ensure_size        222  8.7    1.767    2.103    1.767    2.103
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.808    1.809
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.799    1.800
 qs_ks_build_kohn_sham_matrix         3  8.3    0.000    0.001    1.798    1.800
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="500", plot="h2o_32_nrep3_ls", label="(8n/12r/1t)", y=85.883000, yerr=0.000000
PlotPoint: name="501", plot="h2o_32_nrep3_ls_mem", label="(8n/12r/1t)", y=1132.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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               2.172830E+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    0.060    0.109   90.533   90.550
 qs_energies                          1  2.0    0.000    0.000   89.349   89.368
 ls_scf                               1  3.0    0.000    0.001   87.994   88.013
 dbcsr_multiply_generic             111  6.7    0.015    0.016   73.845   74.196
 multiply_cannon                    111  7.7    0.028    0.040   52.618   56.540
 ls_scf_main                          1  4.0    0.005    0.054   54.378   54.381
 multiply_cannon_loop               111  8.7    0.137    0.148   49.899   53.551
 density_matrix_trs4                  2  5.0    0.002    0.003   48.668   48.868
 mp_waitall_1                      9105 10.9   20.520   29.963   20.520   29.963
 ls_scf_init_scf                      1  4.0    0.000    0.001   29.893   29.894
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   28.514   28.632
 multiply_cannon_multrec           1332  9.7   13.322   17.180   22.703   27.725
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   26.145   26.155
 multiply_cannon_metrocomm3        1332  9.7    0.007    0.009   11.339   20.997
 make_m2s                           222  7.7    0.007    0.007   15.007   15.564
 make_images                        222  8.7    1.377    1.706   14.977   15.535
 dbcsr_mm_accdrv_process           4041 10.4    0.338    0.538    8.976   10.591
 dbcsr_mm_accdrv_process_sort      4041 11.4    8.494   10.053    8.494   10.053
 make_images_data                   222  9.7    0.004    0.005    8.668    9.510
 hybrid_alltoall_any                227 10.6    0.545    2.569    8.093    9.413
 mp_sum_l                           887  5.1    4.878    8.214    4.878    8.214
 multiply_cannon_metrocomm4        1221  9.7    0.007    0.009    3.196    7.721
 mp_irecv_dv                       3311 11.0    3.176    7.666    3.176    7.666
 calculate_norms                   2376  9.8    6.089    6.801    6.089    6.801
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.538    6.418
 multiply_cannon_sync_h2d          1332  9.7    4.916    6.275    4.916    6.275
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.928    5.138
 arnoldi_extremal                     4  6.8    0.000    0.000    4.689    4.704
 arnoldi_normal_ev                    4  7.8    0.001    0.005    4.689    4.704
 build_subspace                      16  8.4    0.014    0.021    4.442    4.445
 ls_scf_post                          1  4.0    0.003    0.027    3.724    3.743
 ls_scf_store_result                  1  5.0    0.000    0.000    3.434    3.538
 dbcsr_matrix_vector_mult           304  9.0    0.010    0.022    3.181    3.426
 dbcsr_matrix_vector_mult_local     304 10.0    2.779    3.274    2.781    3.276
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.004    1.162    2.993
 mp_allgather_i34                   111  8.7    0.708    2.865    0.708    2.865
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.626    2.746
 dbcsr_data_new                    4174 10.1    2.111    2.402    2.111    2.402
 make_images_pack                   222  9.7    1.819    2.134    1.822    2.136
 dbcsr_sort_data                    436 11.2    1.848    2.112    1.848    2.112
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.971    1.973
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.958    1.960
 qs_ks_build_kohn_sham_matrix         3  8.3    0.000    0.001    1.958    1.960
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="502", plot="h2o_32_nrep3_ls", label="(8n/6r/2t)", y=90.550000, yerr=0.000000
PlotPoint: name="503", plot="h2o_32_nrep3_ls_mem", label="(8n/6r/2t)", y=1779.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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               2.831229E+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    0.027    0.043   91.956   91.958
 qs_energies                          1  2.0    0.000    0.000   91.160   91.164
 ls_scf                               1  3.0    0.000    0.000   89.712   89.715
 dbcsr_multiply_generic             111  6.7    0.016    0.017   74.346   74.625
 multiply_cannon                    111  7.7    0.030    0.045   51.555   56.308
 ls_scf_main                          1  4.0    0.000    0.000   55.949   55.956
 multiply_cannon_loop               111  8.7    0.117    0.132   48.810   52.657
 density_matrix_trs4                  2  5.0    0.002    0.003   50.069   50.221
 mp_waitall_1                      7281 11.0   22.783   32.432   22.783   32.432
 ls_scf_init_scf                      1  4.0    0.000    0.000   30.104   30.107
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   28.911   28.993
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   26.524   26.532
 multiply_cannon_multrec            888  9.7   12.750   15.199   21.444   24.215
 multiply_cannon_metrocomm3         888  9.7    0.004    0.005   10.389   22.200
 make_m2s                           222  7.7    0.006    0.007   16.384   17.075
 make_images                        222  8.7    1.589    1.853   16.346   17.038
 make_images_data                   222  9.7    0.004    0.005    9.470   10.590
 hybrid_alltoall_any                227 10.6    0.641    2.957    9.003   10.212
 dbcsr_mm_accdrv_process           3754 10.4    0.311    0.490    8.212    9.453
 dbcsr_mm_accdrv_process_sort      3754 11.4    7.777    8.963    7.777    8.963
 mp_sum_l                           887  5.1    4.690    7.892    4.690    7.892
 multiply_cannon_metrocomm4         777  9.7    0.004    0.005    2.485    7.423
 multiply_cannon_sync_h2d           888  9.7    6.018    7.371    6.018    7.371
 mp_irecv_dv                       2335 11.1    2.468    7.358    2.468    7.358
 multiply_cannon_metrocomm1         888  9.7    0.003    0.003    3.569    6.750
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.517    6.022
 arnoldi_extremal                     4  6.8    0.000    0.000    5.137    5.151
 arnoldi_normal_ev                    4  7.8    0.001    0.005    5.137    5.151
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.727    4.949
 calculate_norms                   1584  9.8    4.363    4.847    4.363    4.847
 build_subspace                      16  8.4    0.014    0.020    4.832    4.839
 dbcsr_matrix_vector_mult           304  9.0    0.010    0.021    3.478    3.809
 mp_allgather_i34                   111  8.7    0.853    3.750    0.853    3.750
 ls_scf_post                          1  4.0    0.000    0.000    3.659    3.663
 dbcsr_matrix_vector_mult_local     304 10.0    3.055    3.627    3.057    3.629
 ls_scf_store_result                  1  5.0    0.000    0.000    3.435    3.487
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.846    2.941
 dbcsr_data_new                    4116  9.9    2.113    2.443    2.113    2.443
 dbcsr_sort_data                    325 11.1    1.901    2.168    1.901    2.168
 make_images_sizes                  222  9.7    0.000    0.000    1.059    2.117
 mp_alltoall_i44                    222 10.7    1.059    2.116    1.059    2.116
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.886    1.888
 make_images_pack                   222  9.7    1.623    1.876    1.626    1.879
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.867    1.869
 qs_ks_build_kohn_sham_matrix         3  8.3    0.000    0.001    1.867    1.869
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="504", plot="h2o_32_nrep3_ls", label="(8n/4r/3t)", y=91.958000, yerr=0.000000
PlotPoint: name="505", plot="h2o_32_nrep3_ls_mem", label="(8n/4r/3t)", y=2198.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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               3.384963E+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    0.029    0.044   97.018   97.019
 qs_energies                          1  2.0    0.000    0.000   96.192   96.198
 ls_scf                               1  3.0    0.000    0.000   94.527   94.533
 dbcsr_multiply_generic             111  6.7    0.016    0.017   78.170   78.427
 ls_scf_main                          1  4.0    0.000    0.000   58.614   58.615
 multiply_cannon                    111  7.7    0.043    0.109   51.461   55.963
 density_matrix_trs4                  2  5.0    0.002    0.003   52.463   52.612
 multiply_cannon_loop               111  8.7    0.152    0.168   46.334   48.682
 ls_scf_init_scf                      1  4.0    0.000    0.000   32.691   32.694
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   31.455   31.540
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.002   28.988   29.003
 mp_waitall_1                      6369 11.0   22.273   28.683   22.273   28.683
 multiply_cannon_multrec           1332  9.7   14.216   17.545   22.233   25.085
 make_m2s                           222  7.7    0.008    0.009   21.066   22.460
 make_images                        222  8.7    3.147    3.606   21.014   22.412
 multiply_cannon_metrocomm3        1332  9.7    0.004    0.004    8.918   16.544
 make_images_data                   222  9.7    0.004    0.005   11.760   13.422
 hybrid_alltoall_any                227 10.6    0.798    3.782   11.091   12.788
 dbcsr_mm_accdrv_process           3641 10.4    0.311    0.482    7.654    9.218
 dbcsr_mm_accdrv_process_sort      3641 11.4    7.213    8.722    7.213    8.722
 mp_sum_l                           887  5.1    4.060    7.661    4.060    7.661
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.144    6.138
 multiply_cannon_metrocomm4        1110  9.7    0.005    0.007    2.087    6.068
 mp_irecv_dv                       3229 10.9    2.062    6.006    2.062    6.006
 multiply_cannon_sync_h2d          1332  9.7    5.384    5.937    5.384    5.937
 arnoldi_extremal                     4  6.8    0.000    0.000    5.303    5.318
 arnoldi_normal_ev                    4  7.8    0.001    0.005    5.303    5.317
 build_subspace                      16  8.4    0.014    0.021    4.967    4.975
 mp_allgather_i34                   111  8.7    2.239    4.782    2.239    4.782
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.553    4.721
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.003    2.427    4.659
 calculate_norms                   2376  9.8    4.191    4.528    4.191    4.528
 dbcsr_matrix_vector_mult           304  9.0    0.010    0.022    3.650    3.978
 dbcsr_matrix_vector_mult_local     304 10.0    3.236    3.761    3.238    3.764
 dbcsr_sort_data                    658 11.4    3.074    3.452    3.074    3.452
 ls_scf_post                          1  4.0    0.000    0.000    3.222    3.228
 dbcsr_special_finalize             555  9.7    0.006    0.007    2.825    3.205
 dbcsr_merge_single_wm              555 10.7    0.539    0.661    2.816    3.197
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    3.019    3.071
 ls_scf_store_result                  1  5.0    0.000    0.000    2.961    3.025
 dbcsr_data_release               10477 10.7    1.587    2.428    1.587    2.428
 dbcsr_finalize                     304  7.8    0.049    0.061    1.803    1.991
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="506", plot="h2o_32_nrep3_ls", label="(8n/3r/4t)", y=97.019000, yerr=0.000000
PlotPoint: name="507", plot="h2o_32_nrep3_ls_mem", label="(8n/3r/4t)", y=2726.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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               4.757144E+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    0.056    0.065   91.993   91.995
 qs_energies                          1  2.0    0.000    0.000   91.079   91.086
 ls_scf                               1  3.0    0.000    0.000   89.115   89.122
 dbcsr_multiply_generic             111  6.7    0.017    0.019   70.581   70.779
 ls_scf_main                          1  4.0    0.000    0.000   56.409   56.409
 multiply_cannon                    111  7.7    0.089    0.176   52.237   55.933
 multiply_cannon_loop               111  8.7    0.088    0.095   49.686   51.070
 density_matrix_trs4                  2  5.0    0.002    0.003   49.380   49.468
 ls_scf_init_scf                      1  4.0    0.000    0.000   29.330   29.331
 mp_waitall_1                      5436 11.0   24.111   28.651   24.111   28.651
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   28.081   28.109
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.002   25.960   25.970
 multiply_cannon_multrec            444  9.7   13.752   16.356   20.918   23.071
 multiply_cannon_metrocomm1         444  9.7    0.002    0.002   10.743   15.299
 make_m2s                           222  7.7    0.005    0.005   13.655   14.578
 make_images                        222  8.7    2.043    2.480   13.587   14.509
 multiply_cannon_metrocomm3         444  9.7    0.001    0.002    5.827   13.579
 hybrid_alltoall_any                227 10.6    0.803    3.854    8.154    9.822
 make_images_data                   222  9.7    0.003    0.004    8.360    9.627
 multiply_cannon_sync_h2d           444  9.7    6.731    8.164    6.731    8.164
 dbcsr_mm_accdrv_process           3003 10.4    0.352    0.400    6.852    7.988
 dbcsr_mm_accdrv_process_sort      3003 11.4    6.489    7.589    6.489    7.589
 arnoldi_extremal                     4  6.8    0.000    0.000    5.870    5.881
 arnoldi_normal_ev                    4  7.8    0.002    0.005    5.870    5.881
 build_subspace                      16  8.4    0.015    0.020    5.481    5.492
 mp_sum_l                           887  5.1    2.688    4.739    2.688    4.739
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.436    4.605
 dbcsr_matrix_vector_mult           304  9.0    0.011    0.022    4.209    4.404
 dbcsr_matrix_vector_mult_local     304 10.0    3.729    4.168    3.732    4.171
 multiply_cannon_metrocomm4         333  9.7    0.001    0.002    1.522    4.034
 mp_irecv_dv                       1241 11.2    1.510    4.014    1.510    4.014
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    1.898    3.877
 calculate_norms                    792  9.8    3.611    3.750    3.611    3.750
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    3.565    3.638
 mp_allgather_i34                   111  8.7    1.125    3.629    1.125    3.629
 ls_scf_post                          1  4.0    0.000    0.000    3.377    3.383
 make_images_sizes                  222  9.7    0.000    0.000    0.889    3.350
 mp_alltoall_i44                    222 10.7    0.889    3.350    0.889    3.350
 ls_scf_store_result                  1  5.0    0.000    0.000    3.166    3.198
 dbcsr_finalize                     304  7.8    0.062    0.077    2.197    2.315
 dbcsr_data_new                    4608  9.7    1.782    2.297    1.782    2.297
 dbcsr_merge_all                    275  8.9    0.481    0.529    2.054    2.150
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.040    2.041
 rebuild_ks_matrix                    3  7.3    0.000    0.000    2.008    2.009
 qs_ks_build_kohn_sham_matrix         3  8.3    0.000    0.001    2.008    2.009
 qs_energies_init_hamiltonians        1  3.0    0.000    0.001    1.947    1.947
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="508", plot="h2o_32_nrep3_ls", label="(8n/2r/6t)", y=91.995000, yerr=0.000000
PlotPoint: name="509", plot="h2o_32_nrep3_ls_mem", label="(8n/2r/6t)", y=3782.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_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               8.794059E+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    0.073    0.103  109.191  109.193
 qs_energies                          1  2.0    0.000    0.000  107.816  107.823
 ls_scf                               1  3.0    0.000    0.000  104.820  104.826
 dbcsr_multiply_generic             111  6.7    0.023    0.026   78.242   78.395
 ls_scf_main                          1  4.0    0.000    0.000   64.176   64.177
 density_matrix_trs4                  2  5.0    0.002    0.003   55.086   55.158
 multiply_cannon                    111  7.7    0.174    0.271   49.092   51.177
 multiply_cannon_loop               111  8.7    0.099    0.100   46.076   49.254
 ls_scf_init_scf                      1  4.0    0.000    0.000   36.828   36.829
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   35.279   35.290
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.002   32.582   32.591
 mp_waitall_1                      4527 11.1   22.108   25.866   22.108   25.866
 make_m2s                           222  7.7    0.005    0.005   22.741   23.843
 make_images                        222  8.7    3.579    3.868   22.631   23.732
 multiply_cannon_multrec            444  9.7   17.839   18.612   22.530   23.229
 hybrid_alltoall_any                227 10.6    1.657    3.633   12.818   15.816
 make_images_data                   222  9.7    0.004    0.004   13.088   15.252
 multiply_cannon_metrocomm3         444  9.7    0.001    0.002   10.430   10.937
 multiply_cannon_sync_h2d           444  9.7    8.791    8.825    8.791    8.825
 arnoldi_extremal                     4  6.8    0.000    0.000    7.500    7.512
 arnoldi_normal_ev                    4  7.8    0.003    0.009    7.500    7.512
 build_subspace                      16  8.4    0.026    0.036    6.949    6.964
 dbcsr_matrix_vector_mult           304  9.0    0.017    0.035    5.566    5.705
 dbcsr_matrix_vector_mult_local     304 10.0    5.114    5.410    5.116    5.413
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    5.194    5.289
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.886    5.144
 mp_sum_l                           887  5.1    4.002    5.051    4.002    5.051
 dbcsr_mm_accdrv_process           1814 10.4    0.291    0.353    4.514    4.644
 dbcsr_mm_accdrv_process_sort      1814 11.4    4.177    4.312    4.177    4.312
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.411    4.077
 compute_matrix_preconditioner        1  6.0    0.002    0.002    3.821    3.828
 ls_scf_post                          1  4.0    0.000    0.000    3.816    3.823
 make_images_sizes                  222  9.7    0.000    0.000    1.498    3.721
 mp_alltoall_i44                    222 10.7    1.498    3.721    1.498    3.721
 mp_allgather_i34                   111  8.7    1.124    3.657    1.124    3.657
 ls_scf_store_result                  1  5.0    0.000    0.000    3.531    3.571
 acc_transpose_blocks               444  9.7    0.003    0.003    0.606    3.347
 calculate_norms                    792  9.8    3.229    3.265    3.229    3.265
 acc_transpose_blocks_kernels       444 10.7    0.006    0.006    0.522    3.264
 jit_kernel_transpose                 1 13.0    0.516    3.259    0.516    3.259
 dbcsr_finalize                     304  7.8    0.082    0.090    3.077    3.171
 qs_energies_init_hamiltonians        1  3.0    0.001    0.001    2.966    2.966
 dbcsr_merge_all                    275  8.9    0.885    0.923    2.862    2.949
 dbcsr_complete_redistribute          5  7.6    1.428    1.470    2.734    2.854
 matrix_ls_to_qs                      2  6.0    0.000    0.000    2.406    2.527
 dbcsr_sort_data                    325 11.1    2.442    2.498    2.442    2.498
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.469    2.470
 rebuild_ks_matrix                    3  7.3    0.000    0.000    2.403    2.404
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.001    2.403    2.404
 dbcsr_new_transposed                 4  7.5    0.242    0.253    2.346    2.359
 dbcsr_data_new                    6591  9.6    1.811    2.310    1.811    2.310
 dbcsr_frobenius_norm                74  6.6    2.056    2.132    2.184    2.220
 dbcsr_add_d                        103  6.2    0.000    0.000    2.127    2.208
 dbcsr_add_anytype                  103  7.2    0.859    0.890    2.126    2.208
 dbcsr_data_release               12724 10.6    1.985    2.191    1.985    2.191
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="510", plot="h2o_32_nrep3_ls", label="(8n/1r/12t)", y=109.193000, yerr=0.000000
PlotPoint: name="511", plot="h2o_32_nrep3_ls_mem", label="(8n/1r/12t)", y=6996.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/fdb0e7a97118f01e42b96d3a441284ab6d74f5d5_performance_tests/27/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32        7009386627072       0.0%      0.0%    100.0%
 flops     9 x     9 x    32        7335108845568       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        9866241589248       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        9884108906496       0.0%      0.0%    100.0%
 flops    22 x    22 x    32       13354440523776       0.0%      0.0%    100.0%
 flops    32 x    32 x     9       20607185977344       0.0%      0.0%    100.0%
 flops    32 x    32 x    22       25186560638976       0.0%      0.0%    100.0%
 flops     9 x    32 x    32       28458319085568       0.0%      0.0%    100.0%
 flops    22 x    32 x    32       34782389993472       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       42881542373376       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       55680402235392       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       55680402235392       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       72328573419520       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                       383.054662E+12       0.0%      0.0%    100.0%
 flops max/rank                    733.641090E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                        26899403712       0.0%      0.0%    100.0%
 number of processed stacks             118860288       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     226.3
 marketing flops                   780.439111E+12
 -------------------------------------------------------------------------------
 # multiplications                           1445
 max memory usage/rank             593.944576E+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
 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    0.237    0.336  267.586  267.696
 qs_mol_dyn_low                       1  2.0    0.004    0.043  265.925  266.040
 qs_forces                            5  3.8    0.010    0.091  265.684  265.792
 qs_energies                          5  4.8    0.005    0.066  262.067  262.185
 scf_env_do_scf                       5  5.8    0.000    0.002  246.971  247.072
 scf_env_do_scf_inner_loop          105  6.6    0.004    0.040  215.915  216.000
 qs_scf_new_mos                     105  7.6    0.000    0.001  169.250  169.413
 qs_scf_loop_do_ot                  105  8.6    0.001    0.001  169.250  169.413
 ot_scf_mini                        105  9.6    0.003    0.004  159.201  159.396
 dbcsr_multiply_generic            1445 12.2    0.127    0.135  136.028  136.695
 multiply_cannon                   1445 13.2    0.275    0.289  115.297  117.604
 velocity_verlet                      4  3.0    0.005    0.023  115.268  115.315
 multiply_cannon_loop              1445 14.2    2.846    3.013  113.084  114.507
 qs_ot_get_p                        112 10.4    0.001    0.002   66.586   66.825
 ot_mini                            105 10.6    0.001    0.008   62.097   62.217
 qs_ot_p2m_diag                      40 11.0    0.022    0.047   54.797   54.904
 cp_dbcsr_syevd                      40 12.0    0.002    0.002   51.314   51.335
 cp_fm_syevd                         40 13.0    0.000    0.001   45.610   45.744
 multiply_cannon_multrec          69360 15.2   29.741   34.866   39.868   45.559
 mp_waitall_1                    488190 16.1   37.805   44.379   37.805   44.379
 qs_ot_get_derivative                55 11.6    0.001    0.014   40.238   40.378
 cp_fm_redistribute_end              40 14.0   20.219   40.360   20.226   40.367
 cp_fm_syevd_base                    40 14.0   20.123   40.262   20.123   40.262
 multiply_cannon_metrocomm3       69360 15.2    0.205    0.216   26.291   33.622
 multiply_cannon_sync_h2d         69360 15.2   28.854   32.690   28.854   32.690
 rebuild_ks_matrix                  110  8.4    0.000    0.000   32.388   32.556
 qs_ks_build_kohn_sham_matrix       110  9.4    0.013    0.046   32.388   32.556
 init_scf_loop                        7  6.6    0.001    0.028   31.010   31.027
 qs_ks_update_qs_env                112  7.6    0.001    0.001   29.561   29.715
 prepare_preconditioner               7  7.6    0.000    0.001   25.413   25.440
 make_preconditioner                  7  8.6    0.000    0.003   25.413   25.440
 apply_preconditioner_dbcsr          62 12.6    0.000    0.000   23.059   23.326
 apply_single                        62 13.6    0.000    0.000   23.059   23.325
 qs_rho_update_rho_low              110  7.6    0.001    0.018   21.356   21.682
 calculate_rho_elec                 110  8.6    0.030    0.040   21.355   21.681
 ot_new_cg_direction                 55 11.6    0.001    0.003   21.074   21.083
 make_full_inverse_cholesky           7  9.6    0.000    0.002   17.331   17.406
 density_rs2pw                      110  9.6    0.005    0.006   15.242   15.733
 qs_ot_get_orbitals                 105 10.6    0.001    0.001   15.122   15.339
 qs_ot_get_derivative_taylor         37 12.8    0.001    0.001   14.632   14.734
 mp_sum_l                          4764 12.2   12.632   13.332   12.632   13.332
 pw_transfer                       1645 12.4    0.081    0.103   12.735   12.994
 fft_wrap_pw1pw2                   1425 13.5    0.012    0.015   12.595   12.855
 transfer_rs2pw                     445 10.6    0.007    0.008   11.569   12.123
 init_scf_run                         5  5.8    0.000    0.001   12.087   12.093
 scf_env_initial_rho_setup            5  6.8    0.002    0.015   12.086   12.092
 calculate_dm_sparse                110  9.5    0.000    0.001   11.747   11.939
 cp_fm_cholesky_invert                7 10.6   11.823   11.836   11.823   11.836
 sum_up_and_integrate                60 10.3    0.005    0.052   11.292   11.322
 integrate_v_rspace                  60 11.3    0.002    0.023   11.271   11.306
 fft_wrap_pw1pw2_240                915 15.0    0.857    0.947   10.943   11.197
 qs_vxc_create                      110 10.4    0.003    0.054   10.949   11.010
 dbcsr_mm_accdrv_process         154766 15.8    6.206    6.391    9.995   10.874
 qs_ot_get_derivative_diag           18 12.0    0.000    0.001   10.735   10.801
 check_diag                          80 13.5    8.686    8.936   10.296   10.437
 fft3d_pb                           915 16.0    2.411    2.733    9.070    9.494
 make_m2s                          2890 13.2    0.078    0.087    7.644    8.202
 make_images                       2890 14.2    0.242    0.263    7.538    8.096
 multiply_cannon_metrocomm1       69360 15.2    0.095    0.101    4.770    7.919
 xc_rho_set_and_dset_create         110 12.4    0.077    0.114    7.492    7.858
 make_full_single_inverse             7  9.6    0.004    0.034    7.730    7.757
 acc_transpose_blocks             69360 15.2    0.360    0.379    7.342    7.684
 xc_vxc_pw_create                    60 11.3    0.040    0.079    7.422    7.484
 potential_pw2rs                     60 12.3    0.002    0.003    7.167    7.220
 cp_dbcsr_sm_fm_multiply             15  9.3    0.001    0.004    7.127    7.144
 calculate_first_density_matrix       1  7.0    0.001    0.006    6.783    6.797
 cp_dbcsr_sm_fm_multiply_core        15 10.3    0.000    0.000    6.645    6.699
 xc_pw_derive                       510 13.4    0.006    0.007    6.602    6.683
 mp_alltoall_z22v                  2340 17.7    6.059    6.577    6.059    6.577
 transfer_rs2pw_30                  110 11.6    1.261    1.328    5.654    5.971
 transfer_pw2rs                     245 13.2    0.003    0.004    5.870    5.913
 mp_sendrecv_dv                  168740 12.6    5.636    5.827    5.636    5.827
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="601", plot="h2o_512_md", label="(64n/12r/1t)", y=267.696000, yerr=0.000000
PlotPoint: name="602", plot="h2o_512_md_mem", label="(64n/12r/1t)", y=563.600000, yerr=3.322650
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


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

CommitSHA: fdb0e7a97118f01e42b96d3a441284ab6d74f5d5
Summary: empty
Status: OK