=== 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: 992aa927d070b294a3f7bcdbda4f1ad818fbb7c6


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

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

LMAX           := 5
MAX_CONTR      := 4

GPUVER         := P100
OFFLOAD_TARGET := cuda

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

CFLAGS         += $(DFLAGS)

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

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

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

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

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

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


===== TESTS (description) =====
 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-32 RI-RPA/RI-MP2 correlation energy
 input file: benchmarks/QS_mp2_rpa/32-H2O/RI-RPA.inp
 required files: ['benchmarks/QS_mp2_rpa/32-H2O/BASIS_H2O', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32.xyz', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32-PBE-TZ.inp', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32-RI-dRPA-TZ.inp']
 output file: result.log
 # nodes = 8
 # ranks/node = 2
 # threads/rank = 6
 nrepeat = 1
 time[min] = 15
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/01
 job id: 48522974
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/02
 job id: 48522975
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/03
 job id: 48522976
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/04
 job id: 48522977
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/05
 job id: 48522978
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/06
 job id: 48522981
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/07
 job id: 48522982
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/08
 job id: 48522983
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/09
 job id: 48522984
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/10
 job id: 48522986
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/11
 job id: 48522987
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/12
 job id: 48522988
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/13
 job id: 48522990
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/14
 job id: 48522991
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/15
 job id: 48522992
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/16
 job id: 48522993
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/17
 job id: 48522994
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/18
 job id: 48522995
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/19
 job id: 48522996
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/20
 job id: 48522998
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/21
 job id: 48522999
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/22
 job id: 48523000
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/23
 job id: 48523001
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/24
 job id: 48523002
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/25
 job id: 48523003
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/26
 job id: 48523004
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/27
 job id: 48523005
 --- 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/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/01/result.log


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

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

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               15                 177869.
 MP_Allreduce          424                      8.
 MP_Sync                 3
 MP_comm_split           1
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.036    0.045  133.784  133.785
 farming_run                          1  2.0  133.159  133.161  133.732  133.734
 -------------------------------------------------------------------------------


 @@@@@@@@@@ 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               1.498718E+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    0.027  115.057  115.058
 qs_energies                          1  2.0    0.000    0.000  114.728  114.732
 mp2_main                             1  3.0    0.000    0.000  112.690  112.694
 mp2_gpw_main                         1  4.0    0.045    0.314  111.709  111.713
 mp2_ri_gpw_compute_in                1  5.0    0.171    0.174   92.654   93.078
 mp2_ri_gpw_compute_in_loop           1  6.0    0.004    0.004   54.669   55.093
 mp2_eri_3c_integrate_gpw           272  7.0    0.152    0.164   41.045   46.177
 get_2c_integrals                     1  6.0    0.008    0.009   37.066   37.813
 integrate_v_rspace                 273  8.0    0.439    0.454   24.620   29.525
 pw_transfer                       6555 10.6    0.378    0.406   26.828   27.260
 fft_wrap_pw1pw2                   5465 11.4    0.044    0.045   25.440   25.974
 grid_integrate_task_list           273  9.0   20.532   25.896   20.532   25.896
 fft_wrap_pw1pw2_100               2178 12.4    1.119    1.293   22.995   23.510
 compute_2c_integrals                 1  7.0    0.002    0.003   19.406   19.408
 compute_2c_integrals_loop_lm         1  8.0    0.003    0.004   18.625   19.142
 mp2_eri_2c_integrate_gpw             1  9.0    2.363    2.411   18.622   19.138
 rpa_ri_compute_en                    1  5.0    0.020    0.024   18.649   18.823
 cp_fm_cholesky_decompose            12  8.2   17.579   18.346   17.579   18.346
 cholesky_decomp                      1  7.0    0.000    0.000   16.504   17.272
 fft3d_s                           5443 13.4   16.126   16.458   16.148   16.480
 ao_to_mo_and_store_B_mult_1        272  7.0   10.781   15.317   10.781   15.317
 calculate_wavefunction             272  8.0    5.411    5.557   12.325   13.032
 rpa_num_int                          1  6.0    0.000    0.004   10.590   10.591
 rpa_num_int_RPA_matrix_operati       8  7.0    0.000    0.000   10.577   10.589
 calc_mat_Q                           8  8.0    0.000    0.000    9.452    9.539
 contract_S_to_Q                      8  9.0    0.000    0.000    8.873    8.962
 calc_potential_gpw                 544  9.5    0.005    0.005    8.257    8.748
 parallel_gemm_fm                    14  9.1    0.000    0.000    8.463    8.565
 parallel_gemm_fm_cosma              14 10.1    8.463    8.565    8.463    8.565
 mp2_eri_2c_integrate_gpw_pot_l     272 10.0    0.001    0.002    8.100    8.445
 potential_pw2rs                    545 10.0    0.107    0.108    7.487    8.085
 collocate_single_gaussian          272 10.0    0.039    0.042    7.354    7.650
 create_integ_mat                     1  6.0    0.022    0.028    7.541    7.541
 array2fm                             1  7.0    0.000    0.000    6.591    6.948
 pw_scatter_s                      2720 13.7    4.348    4.494    4.348    4.494
 pw_gather_s                       2722 13.2    3.452    3.771    3.452    3.771
 array2fm_buffer_send                 1  8.0    2.965    3.138    2.965    3.138
 pw_poisson_solve                   545 10.5    1.124    1.208    2.216    2.491
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="10", plot="h2o_32_ri_rpa_mp2", label="RI-RPA (8n/2r/6t)", y=111.708500, yerr=0.000000
PlotPoint: name="11", plot="h2o_32_ri_rpa_mp2_mem", label="RI-RPA (8n/2r/6t)", y=2803.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/02/result.log


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

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

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               22                 205321.
 MP_Allreduce          424                      9.
 MP_Sync                 4
 MP_comm_split           1
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.029    0.039  421.626  421.639
 farming_run                          1  2.0  420.999  421.016  421.578  421.591
 -------------------------------------------------------------------------------


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32             16777216       0.0%      0.0%    100.0%
 flops    14 x    32 x    32            565182464       0.0%      0.0%    100.0%
 flops    29 x    32 x    32            585367552       0.0%      0.0%    100.0%
 flops    14 x    14 x    32            626196480       0.0%      0.0%    100.0%
 flops    29 x    14 x    32            638582784       0.0%      0.0%    100.0%
 flops    14 x    29 x    32            638582784       0.0%      0.0%    100.0%
 flops    29 x    29 x    32            682057728       0.0%      0.0%    100.0%
 flops    14 x    32 x    14         897827141120       0.0%      0.0%    100.0%
 flops    29 x    32 x    14         929989394432       0.0%      0.0%    100.0%
 flops    14 x    32 x    29         929989394432       0.0%      0.0%    100.0%
 flops    29 x    32 x    29         963203301376       0.0%      0.0%    100.0%
 flops    32 x    32 x    14        1693481172992       0.0%      0.0%    100.0%
 flops    32 x    32 x    29        1753962643456       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         7.172206E+12       0.0%      0.0%    100.0%
 flops max/rank                    150.696064E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          249788822       0.0%      0.0%    100.0%
 number of processed stacks                 98736       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    2529.9
 marketing flops                     7.174951E+12
 -------------------------------------------------------------------------------
 # multiplications                           1140
 max memory usage/rank               1.235599E+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               19427498.
 MP_SendRecv          2876                2171486.
 MP_ISendRecv         1034                 172620.
 MP_Wait              1346
 MP_comm_split           7
 MP_ISend              264                 362227.
 MP_IRecv              264                 362718.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.012    0.034  218.216  218.223
 qs_energies                          1  2.0    0.000    0.000  217.973  217.989
 scf_env_do_scf                       1  3.0    0.000    0.000  115.348  115.352
 qs_ks_update_qs_env                  5  5.0    0.000    0.000  114.412  114.422
 rebuild_ks_matrix                    4  6.0    0.000    0.000  114.411  114.421
 qs_ks_build_kohn_sham_matrix         4  7.0    0.055    0.061  114.411  114.421
 hfx_ks_matrix                        4  8.0    0.001    0.001  114.060  114.068
 integrate_four_center                4  9.0    0.154    0.470  114.060  114.068
 integrate_four_center_main           4 10.0    0.127    0.649  102.188  105.727
 integrate_four_center_bin          264 11.0  102.061  105.284  102.061  105.284
 mp2_main                             1  3.0    0.000    0.000  102.329  102.345
 mp2_gpw_main                         1  4.0    0.048    0.066  101.237  101.254
 init_scf_loop                        1  4.0    0.000    0.000   97.391   97.394
 mp2_ri_gpw_compute_in                1  5.0    0.064    0.065   74.029   75.183
 mp2_ri_gpw_compute_in_loop           1  6.0    0.002    0.002   53.819   54.973
 mp2_eri_3c_integrate_gpw            91  7.0    0.144    0.154   41.347   46.300
 integrate_v_rspace                  95  8.0    0.396    0.564   27.818   32.636
 pw_transfer                       2240 10.6    0.145    0.163   29.528   29.900
 fft_wrap_pw1pw2                   1868 11.4    0.017    0.020   28.530   28.921
 mp2_ri_gpw_compute_en                1  5.0    0.061    0.078   27.043   28.737
 ao_to_mo_and_store_B_mult_1         91  7.0   10.792   28.678   10.792   28.678
 grid_integrate_task_list            95  9.0   23.236   28.287   23.236   28.287
 fft_wrap_pw1pw2_100                730 12.4    1.281    1.458   26.271   26.688
 mp2_ri_gpw_compute_en_RI_loop        1  6.0    1.842    1.888   25.221   25.231
 get_2c_integrals                     1  6.0    0.000    0.000   20.111   20.147
 compute_2c_integrals                 1  7.0    0.003    0.006   19.096   19.099
 compute_2c_integrals_loop_lm         1  8.0    0.001    0.002   18.625   18.965
 mp2_eri_2c_integrate_gpw             1  9.0    1.724    1.862   18.624   18.965
 fft3d_s                           1823 13.4   18.513   18.869   18.527   18.882
 scf_env_do_scf_inner_loop            4  4.0    0.000    0.000   17.955   17.956
 calculate_wavefunction              91  8.0    2.008    2.036    9.620    9.806
 mp2_ri_gpw_compute_en_expansio     172  7.0    0.559    0.590    8.805    9.419
 potential_pw2rs                    186 10.0    0.033    0.036    8.415    9.035
 local_gemm                         172  8.0    8.246    8.854    8.246    8.854
 mp2_ri_gpw_compute_en_comm          22  7.0    0.495    0.508    8.191    8.758
 mp2_eri_2c_integrate_gpw_pot_l      91 10.0    0.001    0.001    8.155    8.498
 calc_potential_gpw                 182  9.5    0.002    0.002    7.913    8.202
 collocate_single_gaussian           91 10.0    0.016    0.020    7.759    7.970
 mp_sync                             37 10.5    3.815    7.606    3.815    7.606
 mp_sendrecv_dm3                   2068  8.0    6.234    6.800    6.234    6.800
 integrate_four_center_load           4 10.0    0.000    0.000    6.768    6.772
 hfx_load_balance                     1 11.0    0.000    0.000    6.768    6.772
 mp2_ri_gpw_compute_en_ener         172  7.0    6.339    6.439    6.339    6.439
 pw_gather_s                        912 13.2    4.476    4.956    4.476    4.956
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="20", plot="h2o_32_ri_rpa_mp2", label="RI-MP2 (8n/6r/2t)", y=101.233350, yerr=0.000000
PlotPoint: name="21", plot="h2o_32_ri_rpa_mp2_mem", label="RI-MP2 (8n/6r/2t)", y=1492.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/03/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                     29.277748E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               5055360       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      29.1
 marketing flops                     2.107592E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             452.911104E+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    0.018    0.036   54.246   54.253
 qs_mol_dyn_low                       1  2.0    0.004    0.008   53.939   53.952
 qs_forces                           11  3.9    0.003    0.005   53.877   53.884
 qs_energies                         11  4.9    0.001    0.002   52.382   52.407
 scf_env_do_scf                      11  5.9    0.000    0.001   46.406   46.411
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   44.362   44.366
 qs_scf_new_mos                     108  7.5    0.000    0.001   34.442   34.758
 qs_scf_loop_do_ot                  108  8.5    0.000    0.001   34.441   34.758
 dbcsr_multiply_generic            2286 12.5    0.094    0.099   33.994   34.528
 ot_scf_mini                        108  9.5    0.002    0.002   32.678   32.852
 multiply_cannon                   2286 13.5    0.187    0.193   26.386   28.232
 multiply_cannon_loop              2286 14.5    1.843    1.943   25.752   27.627
 velocity_verlet                     10  3.0    0.001    0.002   27.085   27.088
 ot_mini                            108 10.5    0.001    0.001   19.700   19.935
 qs_ot_get_derivative               108 11.5    0.001    0.004   16.641   16.816
 mp_waitall_1                    245248 16.5    8.661   14.794    8.661   14.794
 multiply_cannon_metrocomm3       54864 15.5    0.074    0.080    6.235   12.917
 multiply_cannon_multrec          54864 15.5    3.618    5.664    7.555   10.947
 qs_ot_get_p                        119 10.4    0.001    0.001    8.168    8.467
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.752    7.912
 qs_ks_build_kohn_sham_matrix       119  9.3    0.010    0.011    7.752    7.911
 mp_sum_l                          7287 12.8    5.748    7.541    5.748    7.541
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.823    6.974
 multiply_cannon_sync_h2d         54864 15.5    5.123    6.592    5.123    6.592
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    5.866    6.284
 dbcsr_mm_accdrv_process          76910 16.1    1.838    2.886    3.851    5.512
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    5.164    5.278
 qs_ot_p2m_diag                      50 11.0    0.004    0.006    5.245    5.277
 init_scf_run                        11  5.9    0.000    0.001    4.672    4.673
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    4.672    4.672
 cp_dbcsr_syevd                      50 12.0    0.002    0.003    4.447    4.448
 sum_up_and_integrate               119 10.3    0.012    0.014    4.362    4.369
 integrate_v_rspace                 119 11.3    0.002    0.003    4.350    4.358
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    4.264    4.264
 cp_fm_redistribute_end              50 14.0    2.175    4.241    2.181    4.244
 qs_rho_update_rho_low              119  7.7    0.000    0.001    4.093    4.233
 calculate_rho_elec                 119  8.7    0.011    0.017    4.093    4.232
 cp_fm_diag_elpa_base                50 14.0    2.058    4.141    2.062    4.148
 calculate_dm_sparse                119  9.5    0.000    0.001    2.977    3.144
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.925    3.138
 apply_single                       119 13.6    0.000    0.000    2.925    3.138
 multiply_cannon_metrocomm1       54864 15.5    0.058    0.064    1.844    3.084
 ot_diis_step                       108 11.5    0.006    0.006    2.777    2.778
 acc_transpose_blocks             54864 15.5    0.232    0.257    2.224    2.741
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    2.584    2.670
 jit_kernel_multiply                 13 15.8    1.949    2.537    1.949    2.537
 calculate_first_density_matrix       1  7.0    0.000    0.001    2.410    2.414
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.002    2.225    2.227
 wfi_extrapolate                     11  7.9    0.001    0.001    2.193    2.194
 density_rs2pw                      119  9.7    0.004    0.004    2.055    2.184
 grid_integrate_task_list           119 12.3    2.017    2.117    2.017    2.117
 mp_sum_d                          4135 12.0    1.474    2.061    1.474    2.061
 init_scf_loop                       11  6.9    0.000    0.001    2.029    2.029
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.897    1.971
 potential_pw2rs                    119 12.3    0.004    0.004    1.741    1.751
 pw_transfer                       1439 11.6    0.052    0.058    1.578    1.650
 make_m2s                          4572 13.5    0.054    0.057    1.555    1.610
 fft_wrap_pw1pw2                   1201 12.6    0.007    0.007    1.503    1.574
 mp_alltoall_d11v                  2130 13.8    1.339    1.540    1.339    1.540
 make_images                       4572 14.5    0.133    0.139    1.473    1.527
 acc_transpose_blocks_sync       164592 16.5    1.216    1.450    1.216    1.450
 transfer_rs2pw                     487 10.6    0.005    0.006    1.336    1.444
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.001    1.382    1.418
 grid_collocate_task_list           119  9.7    1.347    1.411    1.347    1.411
 mp_waitany                       12084 13.8    1.278    1.376    1.278    1.376
 fft3d_ps                          1201 14.6    0.367    0.475    1.217    1.286
 transfer_pw2rs                     487 13.2    0.006    0.006    1.279    1.286
 dbcsr_dot_sd                      1205 11.9    0.049    0.058    0.850    1.275
 fft_wrap_pw1pw2_140                487 13.2    0.141    0.154    1.168    1.240
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="100", plot="h2o_64_md", label="(8n/12r/1t)", y=54.253000, yerr=0.000000
PlotPoint: name="101", plot="h2o_64_md_mem", label="(8n/12r/1t)", y=431.181818, yerr=1.113404
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_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             488.423424E+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                 844732.
 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    0.207    0.384   39.594   39.598
 qs_mol_dyn_low                       1  2.0    0.003    0.003   38.436   38.444
 qs_forces                           11  3.9    0.002    0.003   38.380   38.380
 qs_energies                         11  4.9    0.004    0.009   36.689   36.692
 scf_env_do_scf                      11  5.9    0.001    0.002   31.601   31.602
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.009   29.188   29.190
 dbcsr_multiply_generic            2286 12.5    0.101    0.105   21.974   22.322
 qs_scf_new_mos                     108  7.5    0.001    0.001   20.599   20.826
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   20.598   20.826
 ot_scf_mini                        108  9.5    0.003    0.003   19.687   19.854
 multiply_cannon                   2286 13.5    0.210    0.218   16.882   18.382
 velocity_verlet                     10  3.0    0.001    0.002   18.263   18.264
 multiply_cannon_loop              2286 14.5    1.198    1.259   15.719   17.130
 ot_mini                            108 10.5    0.001    0.001   12.129   12.360
 mp_waitall_1                    200699 16.5    5.546   10.706    5.546   10.706
 qs_ot_get_derivative               108 11.5    0.001    0.002    9.759    9.928
 multiply_cannon_metrocomm3       27432 15.5    0.071    0.074    4.060    9.463
 multiply_cannon_multrec          27432 15.5    1.807    4.129    6.119    8.995
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.786    6.927
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.014    6.785    6.926
 dbcsr_mm_accdrv_process          47894 16.0    3.573    5.750    4.231    6.305
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.949    6.078
 qs_ot_get_p                        119 10.4    0.001    0.001    4.642    4.873
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    3.708    4.562
 mp_sum_l                          7287 12.8    2.045    4.077    2.045    4.077
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    3.015    4.065
 apply_single                       119 13.6    0.000    0.000    3.014    4.065
 init_scf_run                        11  5.9    0.000    0.001    3.845    3.846
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.845    3.846
 sum_up_and_integrate               119 10.3    0.025    0.028    3.694    3.703
 integrate_v_rspace                 119 11.3    0.003    0.012    3.669    3.682
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.580    3.606
 calculate_rho_elec                 119  8.7    0.021    0.024    3.579    3.605
 qs_ot_p2m_diag                      50 11.0    0.009    0.013    3.000    3.018
 make_m2s                          4572 13.5    0.052    0.054    2.602    2.936
 make_images                       4572 14.5    0.209    0.251    2.514    2.852
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    2.597    2.598
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    2.314    2.400
 init_scf_loop                       11  6.9    0.001    0.003    2.392    2.394
 calculate_first_density_matrix       1  7.0    0.001    0.004    2.336    2.338
 ot_diis_step                       108 11.5    0.010    0.011    2.322    2.322
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    2.280    2.280
 cp_fm_redistribute_end              50 14.0    1.157    2.255    1.160    2.258
 cp_fm_diag_elpa_base                50 14.0    1.066    2.166    1.094    2.199
 multiply_cannon_sync_h2d         27432 15.5    1.691    2.179    1.691    2.179
 calculate_dm_sparse                119  9.5    0.000    0.001    2.051    2.132
 density_rs2pw                      119  9.7    0.004    0.004    1.883    1.965
 grid_integrate_task_list           119 12.3    1.846    1.954    1.846    1.954
 acc_transpose_blocks             27432 15.5    0.113    0.120    1.618    1.946
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.890    1.893
 pw_transfer                       1439 11.6    0.065    0.069    1.827    1.857
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.736    1.768
 jit_kernel_multiply                  9 16.6    0.601    1.728    0.601    1.728
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.666    1.703
 make_images_data                  4572 15.5    0.048    0.055    1.238    1.569
 prepare_preconditioner              11  7.9    0.000    0.000    1.499    1.526
 make_preconditioner                 11  8.9    0.001    0.001    1.498    1.526
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.400    1.458
 mp_alltoall_d11v                  2130 13.8    1.210    1.451    1.210    1.451
 wfi_extrapolate                     11  7.9    0.001    0.001    1.450    1.450
 hybrid_alltoall_any               4725 16.4    0.054    0.116    1.109    1.449
 potential_pw2rs                    119 12.3    0.006    0.006    1.414    1.424
 fft_wrap_pw1pw2_140                487 13.2    0.159    0.167    1.384    1.416
 fft3d_ps                          1201 14.6    0.517    0.573    1.372    1.398
 grid_collocate_task_list           119  9.7    1.288    1.343    1.288    1.343
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.001    1.247    1.255
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.197    1.247
 transfer_rs2pw                     487 10.6    0.005    0.005    1.071    1.147
 mp_sum_d                          4135 12.0    0.560    1.070    0.560    1.070
 mp_allgather_i34                  2286 14.5    0.585    0.987    0.585    0.987
 qs_energies_init_hamiltonians       11  5.9    0.005    0.010    0.968    0.969
 acc_transpose_blocks_sync        82296 16.5    0.822    0.944    0.822    0.944
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.894    0.907
 transfer_pw2rs                     487 13.2    0.005    0.005    0.881    0.885
 acc_transpose_blocks_kernels     27432 16.5    0.189    0.276    0.657    0.867
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="102", plot="h2o_64_md", label="(8n/6r/2t)", y=39.598000, yerr=0.000000
PlotPoint: name="103", plot="h2o_64_md_mem", label="(8n/6r/2t)", y=465.000000, yerr=1.705606
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/05/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                     59.051995E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               3143552       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      46.8
 marketing flops                     2.107587E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             522.461184E+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    0.017    0.038   31.844   31.848
 qs_mol_dyn_low                       1  2.0    0.003    0.004   31.536   31.544
 qs_forces                           11  3.9    0.002    0.003   31.481   31.482
 qs_energies                         11  4.9    0.002    0.008   29.928   29.932
 scf_env_do_scf                      11  5.9    0.001    0.001   25.291   25.292
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.007   22.910   22.911
 dbcsr_multiply_generic            2286 12.5    0.096    0.101   16.779   16.853
 qs_scf_new_mos                     108  7.5    0.001    0.001   15.256   15.273
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   15.255   15.273
 velocity_verlet                     10  3.0    0.002    0.002   14.992   14.993
 ot_scf_mini                        108  9.5    0.002    0.003   14.501   14.511
 multiply_cannon                   2286 13.5    0.193    0.196   13.571   14.264
 multiply_cannon_loop              2286 14.5    0.861    0.925   12.798   13.523
 ot_mini                            108 10.5    0.001    0.001    8.969    8.984
 qs_ot_get_derivative               108 11.5    0.001    0.001    7.486    7.496
 multiply_cannon_multrec          18288 15.5    1.883    2.898    6.949    7.268
 rebuild_ks_matrix                  119  8.3    0.000    0.000    5.975    5.993
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    5.975    5.993
 dbcsr_mm_accdrv_process          38222 16.0    4.915    5.723    4.973    5.788
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.260    5.277
 mp_waitall_1                    158411 16.6    2.536    3.630    2.536    3.630
 sum_up_and_integrate               119 10.3    0.030    0.031    3.553    3.560
 integrate_v_rspace                 119 11.3    0.002    0.003    3.523    3.533
 init_scf_run                        11  5.9    0.000    0.001    3.433    3.433
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    3.433    3.433
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.823    3.416
 qs_ot_get_p                        119 10.4    0.001    0.001    3.313    3.334
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.239    3.243
 calculate_rho_elec                 119  8.7    0.031    0.032    3.239    3.242
 init_scf_loop                       11  6.9    0.001    0.003    2.364    2.365
 multiply_cannon_metrocomm3       18288 15.5    0.047    0.049    1.432    2.355
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    1.995    2.343
 apply_single                       119 13.6    0.000    0.000    1.995    2.343
 calculate_first_density_matrix       1  7.0    0.000    0.003    2.224    2.225
 qs_ot_p2m_diag                      50 11.0    0.012    0.013    2.218    2.223
 make_m2s                          4572 13.5    0.044    0.046    1.790    1.951
 density_rs2pw                      119  9.7    0.004    0.004    1.804    1.936
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.922    1.922
 grid_integrate_task_list           119 12.3    1.803    1.884    1.803    1.884
 make_images                       4572 14.5    0.195    0.207    1.706    1.865
 calculate_dm_sparse                119  9.5    0.000    0.000    1.837    1.852
 pw_transfer                       1439 11.6    0.065    0.069    1.805    1.814
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.713    1.724
 acc_transpose_blocks             18288 15.5    0.080    0.082    1.618    1.710
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.688    1.692
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.670    1.687
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.684    1.686
 cp_fm_diag_elpa_base                50 14.0    1.648    1.664    1.669    1.686
 prepare_preconditioner              11  7.9    0.000    0.000    1.597    1.599
 make_preconditioner                 11  8.9    0.000    0.001    1.597    1.599
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.459    1.540
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.528    1.535
 ot_diis_step                       108 11.5    0.011    0.011    1.465    1.466
 mp_sum_l                          7287 12.8    1.052    1.406    1.052    1.406
 fft_wrap_pw1pw2_140                487 13.2    0.212    0.217    1.385    1.396
 potential_pw2rs                    119 12.3    0.007    0.008    1.329    1.334
 grid_collocate_task_list           119  9.7    1.233    1.311    1.233    1.311
 fft3d_ps                          1201 14.6    0.525    0.543    1.282    1.292
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.001    1.179    1.185
 multiply_cannon_sync_h2d         18288 15.5    1.039    1.169    1.039    1.169
 wfi_extrapolate                     11  7.9    0.001    0.001    1.156    1.156
 transfer_rs2pw                     487 10.6    0.005    0.005    0.998    1.143
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    0.976    0.977
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.937    0.955
 make_images_data                  4572 15.5    0.047    0.051    0.765    0.926
 hybrid_alltoall_any               4725 16.4    0.058    0.115    0.662    0.853
 acc_transpose_blocks_sync        54864 16.5    0.735    0.821    0.735    0.821
 transfer_pw2rs                     487 13.2    0.004    0.004    0.813    0.816
 mp_alltoall_d11v                  2130 13.8    0.662    0.796    0.662    0.796
 acc_transpose_blocks_kernels     18288 16.5    0.216    0.222    0.784    0.791
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.787    0.788
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.001    0.676    0.747
 transfer_rs2pw_140                 130 11.5    0.117    0.120    0.542    0.681
 cp_fm_cholesky_invert               11 10.9    0.674    0.678    0.674    0.678
 mp_waitany                        9880 13.7    0.558    0.676    0.558    0.676
 mp_alltoall_z22v                  1201 16.6    0.608    0.673    0.608    0.673
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="104", plot="h2o_64_md", label="(8n/4r/3t)", y=31.848000, yerr=0.000000
PlotPoint: name="105", plot="h2o_64_md_mem", label="(8n/4r/3t)", y=497.272727, yerr=2.004128
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/06/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                    114.044384E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               3805952       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      38.6
 marketing flops                     2.107592E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             556.822528E+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    0.029    0.046   36.963   36.965
 qs_mol_dyn_low                       1  2.0    0.004    0.040   36.712   36.721
 qs_forces                           11  3.9    0.035    0.041   36.628   36.655
 qs_energies                         11  4.9    0.008    0.046   34.888   34.947
 scf_env_do_scf                      11  5.9    0.001    0.001   29.320   29.321
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.007   25.954   25.954
 dbcsr_multiply_generic            2286 12.5    0.110    0.112   19.893   20.045
 velocity_verlet                     10  3.0    0.002    0.002   18.397   18.399
 qs_scf_new_mos                     108  7.5    0.001    0.001   17.896   17.955
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   17.895   17.954
 ot_scf_mini                        108  9.5    0.002    0.003   16.866   16.924
 multiply_cannon                   2286 13.5    0.218    0.225   16.170   16.689
 multiply_cannon_loop              2286 14.5    1.534    1.639   15.216   15.548
 ot_mini                            108 10.5    0.001    0.001   10.402   10.473
 multiply_cannon_multrec          27432 15.5    2.452    3.102    9.007    9.295
 qs_ot_get_derivative               108 11.5    0.001    0.001    8.533    8.591
 dbcsr_mm_accdrv_process          47916 15.9    6.125    7.730    6.454    7.792
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.336    6.391
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    6.336    6.390
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.616    5.666
 init_scf_run                        11  5.9    0.000    0.001    3.712    3.714
 scf_env_initial_rho_setup           11  6.9    0.011    0.015    3.712    3.714
 qs_ot_get_p                        119 10.4    0.001    0.001    3.609    3.683
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    3.142    3.543
 sum_up_and_integrate               119 10.3    0.035    0.038    3.515    3.523
 integrate_v_rspace                 119 11.3    0.003    0.003    3.480    3.488
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.324    3.363
 calculate_rho_elec                 119  8.7    0.040    0.046    3.324    3.362
 init_scf_loop                       11  6.9    0.001    0.002    3.346    3.346
 acc_transpose_blocks             27432 15.5    0.121    0.125    2.409    2.601
 prepare_preconditioner              11  7.9    0.000    0.000    2.516    2.524
 make_preconditioner                 11  8.9    0.000    0.001    2.515    2.524
 mp_waitall_1                    137007 16.6    1.833    2.458    1.833    2.458
 make_full_inverse_cholesky          11  9.9    0.000    0.000    2.127    2.453
 make_m2s                          4572 13.5    0.054    0.056    2.274    2.392
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    2.329    2.358
 calculate_first_density_matrix       1  7.0    0.001    0.011    2.305    2.318
 make_images                       4572 14.5    0.277    0.341    2.165    2.282
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.100    2.242
 apply_single                       119 13.6    0.000    0.000    2.100    2.242
 qs_ot_p2m_diag                      50 11.0    0.016    0.023    2.195    2.207
 calculate_dm_sparse                119  9.5    0.000    0.000    2.128    2.183
 pw_transfer                       1439 11.6    0.065    0.069    1.901    1.937
 grid_integrate_task_list           119 12.3    1.821    1.931    1.821    1.931
 density_rs2pw                      119  9.7    0.004    0.004    1.785    1.928
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.809    1.849
 ot_diis_step                       108 11.5    0.012    0.012    1.828    1.829
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.813    1.815
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.794    1.794
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.651    1.666
 acc_transpose_blocks_sync        82296 16.5    1.425    1.612    1.425    1.612
 qs_energies_init_hamiltonians       11  5.9    0.037    0.052    1.524    1.584
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.557    1.564
 cp_fm_diag_elpa_base                50 14.0    1.523    1.538    1.554    1.562
 fft_wrap_pw1pw2_140                487 13.2    0.246    0.258    1.496    1.536
 mp_sum_l                          7287 12.8    1.021    1.375    1.021    1.375
 fft3d_ps                          1201 14.6    0.554    0.605    1.329    1.354
 grid_collocate_task_list           119  9.7    1.249    1.344    1.249    1.344
 wfi_extrapolate                     11  7.9    0.001    0.001    1.343    1.343
 multiply_cannon_metrocomm3       27432 15.5    0.040    0.041    0.798    1.332
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.287    1.304
 potential_pw2rs                    119 12.3    0.008    0.010    1.296    1.300
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.227    1.237
 transfer_rs2pw                     487 10.6    0.004    0.005    0.968    1.228
 cp_fm_upper_to_full                 72 14.2    0.807    1.149    0.807    1.149
 jit_kernel_multiply                  6 16.2    0.263    1.087    0.263    1.087
 dbcsr_complete_redistribute        329 12.2    0.117    0.146    0.752    1.021
 make_images_data                  4572 15.5    0.047    0.051    0.847    0.970
 hybrid_alltoall_any               4725 16.4    0.066    0.154    0.730    0.927
 qs_env_update_s_mstruct             11  6.9    0.056    0.086    0.855    0.908
 mp_alltoall_d11v                  2130 13.8    0.745    0.887    0.745    0.887
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.801    0.878
 mp_sum_d                          4133 12.0    0.614    0.873    0.614    0.873
 acc_transpose_blocks_kernels     27432 16.5    0.269    0.276    0.834    0.860
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.810    0.814
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    0.546    0.810
 transfer_rs2pw_140                 130 11.5    0.106    0.111    0.529    0.794
 mp_waitany                        7280 13.7    0.523    0.782    0.523    0.782
 transfer_pw2rs                     487 13.2    0.004    0.004    0.748    0.750
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="106", plot="h2o_64_md", label="(8n/3r/4t)", y=36.965000, yerr=0.000000
PlotPoint: name="107", plot="h2o_64_md_mem", label="(8n/3r/4t)", y=528.545455, yerr=3.285329
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_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             625.147904E+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    0.028    0.033   30.117   30.117
 qs_mol_dyn_low                       1  2.0    0.003    0.003   29.876   29.883
 qs_forces                           11  3.9    0.002    0.002   29.624   29.625
 qs_energies                         11  4.9    0.003    0.014   27.905   27.907
 scf_env_do_scf                      11  5.9    0.000    0.001   22.691   22.691
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.006   20.127   20.127
 velocity_verlet                     10  3.0    0.002    0.002   15.146   15.161
 dbcsr_multiply_generic            2286 12.5    0.130    0.135   13.621   13.741
 qs_scf_new_mos                     108  7.5    0.001    0.001   12.396   12.431
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   12.395   12.430
 ot_scf_mini                        108  9.5    0.002    0.002   11.678   11.710
 multiply_cannon                   2286 13.5    0.222    0.227   10.884   11.261
 multiply_cannon_loop              2286 14.5    0.644    0.667    9.963   10.175
 ot_mini                            108 10.5    0.001    0.001    6.696    6.734
 multiply_cannon_multrec           9144 15.5    1.741    2.032    6.084    6.383
 rebuild_ks_matrix                  119  8.3    0.000    0.000    5.822    5.843
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    5.822    5.843
 qs_ot_get_derivative               108 11.5    0.001    0.001    5.390    5.421
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.180    5.199
 dbcsr_mm_accdrv_process          12550 15.8    3.547    4.278    4.232    4.320
 init_scf_run                        11  5.9    0.000    0.001    3.614    3.614
 scf_env_initial_rho_setup           11  6.9    0.005    0.005    3.614    3.614
 sum_up_and_integrate               119 10.3    0.037    0.041    3.496    3.501
 integrate_v_rspace                 119 11.3    0.003    0.003    3.459    3.464
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.399    3.406
 calculate_rho_elec                 119  8.7    0.060    0.061    3.398    3.406
 qs_ot_get_p                        119 10.4    0.001    0.001    3.077    3.108
 init_scf_loop                       11  6.9    0.000    0.001    2.539    2.540
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.447    2.451
 mp_waitall_1                    115863 16.7    1.573    2.083    1.573    2.083
 pw_transfer                       1439 11.6    0.065    0.068    2.023    2.034
 qs_ot_p2m_diag                      50 11.0    0.022    0.023    2.028    2.030
 make_m2s                          4572 13.5    0.034    0.035    1.848    1.990
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.930    1.942
 grid_integrate_task_list           119 12.3    1.866    1.936    1.866    1.936
 calculate_dm_sparse                119  9.5    0.000    0.000    1.891    1.911
 make_images                       4572 14.5    0.272    0.304    1.759    1.901
 density_rs2pw                      119  9.7    0.003    0.004    1.777    1.855
 jit_kernel_multiply                 10 15.6    0.645    1.843    0.645    1.843
 prepare_preconditioner              11  7.9    0.000    0.000    1.802    1.806
 make_preconditioner                 11  8.9    0.000    0.000    1.802    1.806
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    1.782    1.803
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.776    1.777
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.689    1.716
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.694    1.696
 acc_transpose_blocks              9144 15.5    0.042    0.043    1.595    1.649
 fft_wrap_pw1pw2_140                487 13.2    0.322    0.331    1.573    1.588
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.509    1.517
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.472    1.480
 cp_fm_diag_elpa_base                50 14.0    1.444    1.462    1.470    1.479
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.390    1.406
 grid_collocate_task_list           119  9.7    1.300    1.389    1.300    1.389
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    1.355    1.356
 fft3d_ps                          1201 14.6    0.558    0.570    1.345    1.353
 ot_diis_step                       108 11.5    0.013    0.013    1.293    1.294
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.274    1.278
 potential_pw2rs                    119 12.3    0.010    0.011    1.265    1.268
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    1.227    1.266
 apply_single                       119 13.6    0.000    0.000    1.227    1.266
 wfi_extrapolate                     11  7.9    0.001    0.001    1.109    1.109
 hybrid_alltoall_any               4725 16.4    0.065    0.175    0.803    1.006
 transfer_rs2pw                     487 10.6    0.004    0.004    0.837    0.966
 make_images_data                  4572 15.5    0.042    0.046    0.787    0.957
 multiply_cannon_metrocomm3        9144 15.5    0.020    0.021    0.472    0.954
 mp_alltoall_d11v                  2130 13.8    0.842    0.934    0.842    0.934
 cp_fm_cholesky_invert               11 10.9    0.923    0.925    0.923    0.925
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.876    0.925
 qs_env_update_s_mstruct             11  6.9    0.045    0.053    0.798    0.855
 acc_transpose_blocks_kernels      9144 16.5    0.118    0.120    0.816    0.846
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.837    0.844
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.766    0.769
 acc_transpose_blocks_sync        27432 16.5    0.722    0.753    0.722    0.753
 jit_kernel_transpose                 5 15.6    0.698    0.727    0.698    0.727
 mp_alltoall_z22v                  1201 16.6    0.659    0.687    0.659    0.687
 transfer_pw2rs                     487 13.2    0.003    0.004    0.675    0.676
 mp_allgather_i34                  2286 14.5    0.234    0.663    0.234    0.663
 mp_sum_l                          7287 12.8    0.403    0.614    0.403    0.614
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="108", plot="h2o_64_md", label="(8n/2r/6t)", y=30.117000, yerr=0.000000
PlotPoint: name="109", plot="h2o_64_md_mem", label="(8n/2r/6t)", y=591.090909, yerr=7.982419
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_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             776.769536E+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    0.024    0.057   43.852   43.853
 qs_mol_dyn_low                       1  2.0    0.003    0.003   43.606   43.614
 qs_forces                           11  3.9    0.002    0.002   43.106   43.107
 qs_energies                         11  4.9    0.004    0.004   41.091   41.094
 scf_env_do_scf                      11  5.9    0.001    0.001   34.885   34.885
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.007   27.018   27.020
 velocity_verlet                     10  3.0    0.002    0.004   24.597   24.657
 dbcsr_multiply_generic            2286 12.5    0.139    0.142   19.303   19.458
 qs_scf_new_mos                     108  7.5    0.001    0.001   17.498   17.598
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   17.498   17.598
 ot_scf_mini                        108  9.5    0.002    0.002   16.330   16.435
 multiply_cannon                   2286 13.5    0.295    0.299   15.198   16.086
 multiply_cannon_loop              2286 14.5    0.854    0.884   13.916   14.856
 ot_mini                            108 10.5    0.001    0.001    9.823    9.942
 multiply_cannon_multrec           9144 15.5    3.393    5.069    8.830    8.924
 qs_ot_get_derivative               108 11.5    0.001    0.001    7.758    7.863
 init_scf_loop                       11  6.9    0.001    0.001    7.838    7.839
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.194    7.338
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.013    7.193    7.338
 prepare_preconditioner              11  7.9    0.000    0.000    6.877    6.892
 make_preconditioner                 11  8.9    0.000    0.000    6.877    6.892
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.442    6.766
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.478    6.609
 dbcsr_mm_accdrv_process          12550 15.8    4.638    6.543    5.300    6.575
 cp_fm_upper_to_full                 72 14.2    3.188    4.562    3.188    4.562
 qs_rho_update_rho_low              119  7.7    0.001    0.001    4.130    4.185
 calculate_rho_elec                 119  8.7    0.118    0.121    4.129    4.185
 init_scf_run                        11  5.9    0.000    0.001    4.032    4.032
 scf_env_initial_rho_setup           11  6.9    0.004    0.005    4.032    4.032
 sum_up_and_integrate               119 10.3    0.065    0.066    3.854    3.860
 integrate_v_rspace                 119 11.3    0.004    0.004    3.789    3.796
 qs_ot_get_p                        119 10.4    0.001    0.001    3.544    3.690
 mp_waitall_1                     94719 16.7    2.349    3.371    2.349    3.371
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.792    3.230
 dbcsr_complete_redistribute        329 12.2    0.314    0.320    2.021    2.859
 pw_transfer                       1439 11.6    0.068    0.069    2.630    2.635
 make_m2s                          4572 13.5    0.038    0.038    2.441    2.604
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.485    2.542
 fft_wrap_pw1pw2                   1201 12.6    0.009    0.009    2.532    2.537
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    1.700    2.535
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.239    2.506
 apply_single                       119 13.6    0.000    0.000    2.239    2.506
 make_images                       4572 14.5    0.359    0.391    2.321    2.484
 calculate_dm_sparse                119  9.5    0.000    0.000    2.374    2.427
 mp_alltoall_i22                    627 13.8    1.439    2.279    1.439    2.279
 multiply_cannon_metrocomm3        9144 15.5    0.021    0.021    1.344    2.275
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.430    2.259
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    2.105    2.158
 fft_wrap_pw1pw2_140                487 13.2    0.576    0.580    2.134    2.144
 grid_integrate_task_list           119 12.3    2.080    2.116    2.080    2.116
 density_rs2pw                      119  9.7    0.003    0.004    2.087    2.106
 qs_ot_p2m_diag                      50 11.0    0.043    0.044    2.093    2.095
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.056    2.057
 ot_diis_step                       108 11.5    0.014    0.015    2.039    2.040
 acc_transpose_blocks              9144 15.5    0.044    0.045    1.912    1.958
 qs_energies_init_hamiltonians       11  5.9    0.002    0.002    1.876    1.876
 mp_sum_l                          7287 12.8    1.099    1.820    1.099    1.820
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.730    1.737
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.732    1.734
 fft3d_ps                          1201 14.6    0.594    0.606    1.627    1.631
 grid_collocate_task_list           119  9.7    1.521    1.541    1.521    1.541
 cp_fm_cholesky_invert               11 10.9    1.474    1.478    1.474    1.478
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.434    1.434
 cp_fm_diag_elpa_base                50 14.0    1.285    1.338    1.432    1.433
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.370    1.424
 wfi_extrapolate                     11  7.9    0.001    0.001    1.423    1.423
 mp_alltoall_d11v                  2130 13.8    1.261    1.347    1.261    1.347
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.325    1.347
 potential_pw2rs                    119 12.3    0.014    0.014    1.305    1.308
 hybrid_alltoall_any               4725 16.4    0.090    0.149    1.102    1.307
 make_images_data                  4572 15.5    0.046    0.048    1.046    1.258
 qs_env_update_s_mstruct             11  6.9    0.025    0.049    1.183    1.213
 acc_transpose_blocks_sync        27432 16.5    1.082    1.123    1.082    1.123
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.001    1.048
 jit_kernel_multiply                  6 15.6    0.633    1.013    0.633    1.013
 qs_create_task_list                 11  7.9    0.008    0.008    0.937    0.950
 generate_qs_task_list               11  8.9    0.366    0.386    0.929    0.942
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.926    0.940
 mp_alltoall_z22v                  1201 16.6    0.896    0.915    0.896    0.915
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="110", plot="h2o_64_md", label="(8n/1r/12t)", y=43.853000, yerr=0.000000
PlotPoint: name="111", plot="h2o_64_md_mem", label="(8n/1r/12t)", y=725.818182, yerr=19.139764
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_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             500.178944E+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                1383689.
 MP_SendRecv         20900                   9096.
 MP_ISendRecv        20900                   9096.
 MP_Wait             37268
 MP_ISend            14300                  82312.
 MP_IRecv            14300                  82312.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.016    0.039   81.141   81.152
 qs_mol_dyn_low                       1  2.0    0.004    0.007   80.840   80.862
 qs_forces                           11  3.9    0.003    0.003   80.768   80.779
 qs_energies                         11  4.9    0.001    0.002   77.936   77.956
 scf_env_do_scf                      11  5.9    0.000    0.001   69.225   69.239
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.007   63.879   63.889
 dbcsr_multiply_generic            2055 12.4    0.105    0.108   50.921   51.181
 qs_scf_new_mos                      99  7.5    0.000    0.001   46.999   47.119
 qs_scf_loop_do_ot                   99  8.5    0.000    0.001   46.999   47.119
 ot_scf_mini                         99  9.5    0.002    0.002   44.621   44.741
 multiply_cannon                   2055 13.4    0.183    0.189   42.645   43.530
 velocity_verlet                     10  3.0    0.001    0.002   42.988   42.996
 multiply_cannon_loop              2055 14.4    1.800    1.863   41.726   42.645
 ot_mini                             99 10.5    0.001    0.001   26.681   26.770
 qs_ot_get_derivative                99 11.5    0.001    0.001   19.884   19.988
 multiply_cannon_multrec          49320 15.4   11.399   12.155   17.353   18.027
 rebuild_ks_matrix                  110  8.3    0.000    0.001   14.368   14.508
 qs_ks_build_kohn_sham_matrix       110  9.3    0.011    0.012   14.368   14.508
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.598   12.726
 mp_waitall_1                    220248 16.4   10.831   11.602   10.831   11.602
 multiply_cannon_sync_h2d         49320 15.4    9.618   10.293    9.618   10.293
 qs_ot_get_p                        110 10.4    0.001    0.001    9.499    9.660
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    7.818    8.363
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    7.202    7.721
 apply_single                       110 13.6    0.000    0.000    7.202    7.721
 multiply_cannon_metrocomm3       49320 15.4    0.085    0.088    6.664    7.718
 sum_up_and_integrate               110 10.3    0.036    0.042    6.899    6.916
 integrate_v_rspace                 110 11.3    0.003    0.004    6.863    6.889
 init_scf_run                        11  5.9    0.000    0.001    6.705    6.706
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    6.705    6.706
 ot_diis_step                        99 11.5    0.006    0.006    6.579    6.580
 qs_ot_p2m_diag                      48 11.0    0.012    0.019    6.348    6.365
 qs_rho_update_rho_low              110  7.6    0.000    0.001    6.176    6.306
 calculate_rho_elec                 110  8.6    0.021    0.024    6.175    6.306
 dbcsr_mm_accdrv_process          87628 16.1    3.017    3.119    5.824    6.101
 cp_dbcsr_syevd                      48 12.0    0.002    0.003    5.527    5.528
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    5.349    5.405
 init_scf_loop                       11  6.9    0.000    0.001    5.321    5.323
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    4.984    5.007
 cp_fm_diag_elpa_base                48 14.0    4.971    4.994    4.982    5.006
 mp_sum_l                          6594 12.7    4.004    4.683    4.004    4.683
 wfi_extrapolate                     11  7.9    0.001    0.001    3.976    3.976
 make_m2s                          4110 13.4    0.061    0.066    3.821    3.932
 calculate_dm_sparse                110  9.5    0.001    0.001    3.735    3.877
 make_images                       4110 14.4    0.177    0.189    3.725    3.841
 multiply_cannon_metrocomm1       49320 15.4    0.067    0.069    2.412    3.519
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.005    3.492    3.497
 grid_integrate_task_list           110 12.3    3.261    3.431    3.261    3.431
 density_rs2pw                      110  9.6    0.004    0.005    3.220    3.398
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    3.177    3.233
 prepare_preconditioner              11  7.9    0.000    0.000    3.193    3.211
 make_preconditioner                 11  8.9    0.000    0.000    3.193    3.210
 qs_ot_get_orbitals                  99 10.5    0.000    0.001    3.135    3.189
 pw_transfer                       1331 11.6    0.055    0.065    2.967    3.041
 make_full_inverse_cholesky          11  9.9    0.000    0.000    2.982    3.023
 fft_wrap_pw1pw2                   1111 12.6    0.007    0.008    2.878    2.956
 calculate_first_density_matrix       1  7.0    0.001    0.005    2.631    2.636
 acc_transpose_blocks             49320 15.4    0.215    0.223    2.554    2.631
 fft_wrap_pw1pw2_140                451 13.1    0.390    0.435    2.480    2.564
 jit_kernel_multiply                 13 15.9    2.528    2.541    2.528    2.541
 potential_pw2rs                    110 12.3    0.006    0.006    2.490    2.507
 mp_alltoall_d11v                  2046 13.8    2.013    2.429    2.013    2.429
 grid_collocate_task_list           110  9.6    2.162    2.292    2.162    2.292
 fft3d_ps                          1111 14.6    0.790    0.874    2.173    2.219
 mp_waitany                       14300 13.8    1.813    1.965    1.813    1.965
 transfer_rs2pw                     451 10.6    0.005    0.006    1.823    1.960
 mp_sum_d                          3889 11.9    1.378    1.952    1.378    1.952
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.899    1.913
 make_images_data                  4110 15.4    0.043    0.046    1.751    1.879
 hybrid_alltoall_any               4261 16.3    0.085    0.483    1.514    1.799
 cp_fm_cholesky_invert               11 10.9    1.724    1.728    1.724    1.728
 transfer_pw2rs                     451 13.1    0.006    0.007    1.688    1.695
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.631    1.657
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="200", plot="h2o_128_md", label="(8n/12r/1t)", y=81.152000, yerr=0.000000
PlotPoint: name="201", plot="h2o_128_md_mem", label="(8n/12r/1t)", y=475.818182, yerr=2.208174
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_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             591.654912E+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                1716618.
 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    0.014    0.033   68.296   68.297
 qs_mol_dyn_low                       1  2.0    0.003    0.004   68.050   68.059
 qs_forces                           11  3.9    0.003    0.003   67.952   67.952
 qs_energies                         11  4.9    0.002    0.005   64.622   64.625
 scf_env_do_scf                      11  5.9    0.001    0.001   56.121   56.124
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.007   48.717   48.718
 dbcsr_multiply_generic            2055 12.4    0.115    0.119   37.865   38.038
 velocity_verlet                     10  3.0    0.001    0.002   35.750   35.751
 qs_scf_new_mos                      99  7.5    0.001    0.001   32.955   33.086
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   32.955   33.085
 multiply_cannon                   2055 13.4    0.224    0.248   31.344   32.565
 ot_scf_mini                         99  9.5    0.003    0.004   31.293   31.405
 multiply_cannon_loop              2055 14.4    1.171    1.202   30.073   30.973
 ot_mini                             99 10.5    0.001    0.001   18.301   18.433
 multiply_cannon_multrec          24660 15.4    7.018    8.390   14.033   15.571
 rebuild_ks_matrix                  110  8.3    0.000    0.000   13.524   13.635
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.014   13.524   13.634
 qs_ot_get_derivative                99 11.5    0.001    0.001   12.466   12.586
 qs_ks_update_qs_env                110  7.6    0.001    0.001   11.886   11.986
 mp_waitall_1                    176588 16.5    7.468   10.102    7.468   10.102
 multiply_cannon_metrocomm3       24660 15.4    0.072    0.074    5.118    7.912
 multiply_cannon_sync_h2d         24660 15.4    6.442    7.444    6.442    7.444
 init_scf_loop                       11  6.9    0.001    0.003    7.369    7.370
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    6.515    7.180
 apply_single                       110 13.6    0.000    0.001    6.515    7.180
 dbcsr_mm_accdrv_process          52282 16.1    5.442    6.429    6.845    7.145
 qs_ot_get_p                        110 10.4    0.001    0.001    6.337    6.486
 sum_up_and_integrate               110 10.3    0.053    0.059    6.343    6.359
 integrate_v_rspace                 110 11.3    0.003    0.003    6.290    6.307
 init_scf_run                        11  5.9    0.000    0.001    6.111    6.112
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    6.111    6.112
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.816    5.824
 calculate_rho_elec                 110  8.6    0.039    0.047    5.815    5.824
 ot_diis_step                        99 11.5    0.010    0.010    5.788    5.788
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    4.687    5.385
 prepare_preconditioner              11  7.9    0.000    0.000    5.351    5.369
 make_preconditioner                 11  8.9    0.001    0.003    5.351    5.369
 make_full_inverse_cholesky          11  9.9    0.000    0.000    4.922    5.081
 make_m2s                          4110 13.4    0.058    0.061    4.194    4.669
 make_images                       4110 14.4    0.415    0.477    4.086    4.557
 qs_ot_p2m_diag                      48 11.0    0.029    0.044    4.472    4.492
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    4.010    4.011
 pw_transfer                       1331 11.6    0.066    0.072    3.495    3.626
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.388    3.522
 wfi_extrapolate                     11  7.9    0.001    0.001    3.491    3.491
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.457    3.474
 cp_fm_diag_elpa_base                48 14.0    3.412    3.430    3.455    3.471
 grid_integrate_task_list           110 12.3    3.167    3.327    3.167    3.327
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.251    3.311
 density_rs2pw                      110  9.6    0.004    0.005    3.067    3.287
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    3.260    3.261
 fft_wrap_pw1pw2_140                451 13.1    0.458    0.475    2.922    3.057
 calculate_dm_sparse                110  9.5    0.001    0.001    2.961    2.986
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.928    2.963
 make_images_data                  4110 15.4    0.049    0.052    2.293    2.769
 hybrid_alltoall_any               4261 16.3    0.107    0.449    1.983    2.766
 fft3d_ps                          1111 14.6    1.110    1.337    2.487    2.635
 calculate_first_density_matrix       1  7.0    0.000    0.002    2.522    2.525
 cp_fm_cholesky_invert               11 10.9    2.499    2.505    2.499    2.505
 mp_sum_l                          6594 12.7    1.701    2.325    1.701    2.325
 grid_collocate_task_list           110  9.6    2.164    2.299    2.164    2.299
 potential_pw2rs                    110 12.3    0.008    0.009    2.192    2.210
 acc_transpose_blocks             24660 15.4    0.115    0.118    1.971    1.994
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.963    1.989
 mp_alltoall_d11v                  2046 13.8    1.717    1.941    1.717    1.941
 jit_kernel_multiply                 10 16.4    1.039    1.901    1.039    1.901
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    1.881    1.882
 multiply_cannon_metrocomm4       22605 15.4    0.078    0.084    0.755    1.801
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.794    1.801
 transfer_rs2pw                     451 10.6    0.007    0.007    1.425    1.624
 mp_allgather_i34                  2055 14.4    0.578    1.619    0.578    1.619
 mp_irecv_dv                      57340 16.2    0.628    1.582    0.628    1.582
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.003    1.532    1.541
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.391    1.496
 mp_waitany                       10164 13.8    1.183    1.378    1.183    1.378
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="202", plot="h2o_128_md", label="(8n/6r/2t)", y=68.297000, yerr=0.000000
PlotPoint: name="203", plot="h2o_128_md_mem", label="(8n/6r/2t)", y=559.454545, yerr=6.610785
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/11/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                    404.681598E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               3346752       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     294.1
 marketing flops                    15.646297E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank             667.770880E+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    0.298    0.705   60.245   60.251
 qs_mol_dyn_low                       1  2.0    0.003    0.003   59.233   59.469
 qs_forces                           11  3.9    0.003    0.004   59.163   59.164
 qs_energies                         11  4.9    0.003    0.006   55.968   55.971
 scf_env_do_scf                      11  5.9    0.003    0.005   48.067   48.067
 scf_env_do_scf_inner_loop           99  6.5    0.005    0.008   39.764   39.765
 velocity_verlet                     10  3.0    0.002    0.002   32.102   32.104
 dbcsr_multiply_generic            2055 12.4    0.119    0.127   28.510   28.745
 qs_scf_new_mos                      99  7.5    0.001    0.001   24.784   24.890
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   24.784   24.890
 ot_scf_mini                         99  9.5    0.003    0.003   23.539   23.647
 multiply_cannon                   2055 13.4    0.212    0.223   22.319   23.545
 multiply_cannon_loop              2055 14.4    0.816    0.855   21.164   22.142
 ot_mini                             99 10.5    0.001    0.001   13.530   13.637
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.063   12.189
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.015   12.063   12.189
 multiply_cannon_multrec          16440 15.4    3.752    4.676    9.903   10.789
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.623   10.737
 mp_waitall_1                    139946 16.5    6.629    9.766    6.629    9.766
 qs_ot_get_derivative                99 11.5    0.001    0.001    9.127    9.237
 init_scf_loop                       11  6.9    0.002    0.004    8.268    8.272
 multiply_cannon_metrocomm3       16440 15.4    0.045    0.047    4.182    7.096
 prepare_preconditioner              11  7.9    0.000    0.001    6.520    6.537
 make_preconditioner                 11  8.9    0.001    0.002    6.520    6.537
 sum_up_and_integrate               110 10.3    0.061    0.062    6.236    6.251
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.880    6.234
 integrate_v_rspace                 110 11.3    0.003    0.003    6.175    6.191
 dbcsr_mm_accdrv_process          34862 16.1    5.304    5.669    5.997    6.119
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.666    5.673
 calculate_rho_elec                 110  8.6    0.058    0.059    5.665    5.673
 init_scf_run                        11  5.9    0.000    0.001    5.463    5.464
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.463    5.464
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.924    5.362
 apply_single                       110 13.6    0.000    0.000    4.924    5.362
 qs_ot_get_p                        110 10.4    0.001    0.001    5.215    5.348
 make_m2s                          4110 13.4    0.050    0.052    4.125    4.520
 make_images                       4110 14.4    0.410    0.526    4.012    4.406
 ot_diis_step                        99 11.5    0.011    0.011    4.374    4.374
 multiply_cannon_sync_h2d         16440 15.4    3.247    3.819    3.247    3.819
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.115    3.756
 qs_ot_p2m_diag                      48 11.0    0.042    0.044    3.615    3.619
 pw_transfer                       1331 11.6    0.066    0.073    3.505    3.511
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.398    3.406
 grid_integrate_task_list           110 12.3    3.190    3.369    3.190    3.369
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.251    3.251
 density_rs2pw                      110  9.6    0.004    0.005    2.898    3.080
 fft_wrap_pw1pw2_140                451 13.1    0.578    0.584    2.950    2.959
 wfi_extrapolate                     11  7.9    0.001    0.001    2.941    2.941
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.002    2.799    2.801
 make_images_data                  4110 15.4    0.045    0.049    2.289    2.773
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    2.731    2.741
 cp_fm_diag_elpa_base                48 14.0    2.667    2.700    2.730    2.740
 hybrid_alltoall_any               4261 16.3    0.109    0.385    2.054    2.737
 cp_fm_cholesky_invert               11 10.9    2.545    2.550    2.545    2.550
 calculate_dm_sparse                110  9.5    0.001    0.001    2.514    2.550
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.001    2.478    2.524
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.389    2.448
 calculate_first_density_matrix       1  7.0    0.001    0.002    2.432    2.434
 fft3d_ps                          1111 14.6    1.091    1.101    2.341    2.350
 grid_collocate_task_list           110  9.6    2.219    2.334    2.219    2.334
 multiply_cannon_metrocomm4       14385 15.4    0.048    0.052    0.863    2.314
 mp_irecv_dv                      48980 15.7    0.789    2.182    0.789    2.182
 mp_sum_l                          6594 12.7    1.533    2.114    1.533    2.114
 potential_pw2rs                    110 12.3    0.011    0.011    2.045    2.050
 qs_energies_init_hamiltonians       11  5.9    0.001    0.004    1.998    2.000
 mp_alltoall_d11v                  2046 13.8    1.745    1.970    1.745    1.970
 dbcsr_complete_redistribute        325 12.2    0.322    0.349    1.357    1.808
 cp_fm_upper_to_full                 70 14.2    1.357    1.737    1.357    1.737
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.637    1.652
 acc_transpose_blocks             16440 15.4    0.077    0.079    1.566    1.620
 cp_fm_cholesky_decompose            22 10.9    1.523    1.540    1.523    1.540
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.003    1.377    1.513
 transfer_rs2pw                     451 10.6    0.005    0.006    1.261    1.478
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.453    1.465
 mp_allgather_i34                  2055 14.4    0.468    1.464    0.468    1.464
 mp_waitany                       17072 13.8    1.138    1.356    1.138    1.356
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    0.924    1.350
 qs_ot_get_orbitals                  99 10.5    0.000    0.001    1.258    1.265
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="204", plot="h2o_128_md", label="(8n/4r/3t)", y=60.251000, yerr=0.000000
PlotPoint: name="205", plot="h2o_128_md_mem", label="(8n/4r/3t)", y=631.272727, yerr=8.214078
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_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             741.736448E+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    0.023    0.051   65.205   65.206
 qs_mol_dyn_low                       1  2.0    0.003    0.003   64.964   64.975
 qs_forces                           11  3.9    0.011    0.012   64.895   64.896
 qs_energies                         11  4.9    0.001    0.001   61.500   61.510
 scf_env_do_scf                      11  5.9    0.000    0.001   53.338   53.341
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.007   41.838   41.839
 velocity_verlet                     10  3.0    0.001    0.002   37.049   37.051
 dbcsr_multiply_generic            2055 12.4    0.112    0.119   30.570   30.848
 qs_scf_new_mos                      99  7.5    0.001    0.001   27.344   27.463
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   27.343   27.463
 ot_scf_mini                         99  9.5    0.002    0.003   25.664   25.765
 multiply_cannon                   2055 13.4    0.238    0.254   23.573   24.433
 multiply_cannon_loop              2055 14.4    1.434    1.484   22.163   22.867
 ot_mini                             99 10.5    0.001    0.001   14.786   14.913
 multiply_cannon_multrec          24660 15.4    4.099    6.825   13.037   14.135
 rebuild_ks_matrix                  110  8.3    0.000    0.000   11.925   12.040
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.014   11.925   12.040
 init_scf_loop                       11  6.9    0.000    0.001   11.460   11.461
 qs_ot_get_derivative                99 11.5    0.001    0.001   10.594   10.697
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.531   10.630
 dbcsr_mm_accdrv_process          52304 16.0    7.646    9.454    8.780    9.755
 prepare_preconditioner              11  7.9    0.000    0.000    9.732    9.747
 make_preconditioner                 11  8.9    0.000    0.000    9.732    9.747
 make_full_inverse_cholesky          11  9.9    0.000    0.000    7.922    9.400
 sum_up_and_integrate               110 10.3    0.067    0.072    6.226    6.239
 integrate_v_rspace                 110 11.3    0.003    0.003    6.158    6.171
 mp_waitall_1                    121746 16.5    4.122    6.154    4.122    6.154
 qs_ot_get_p                        110 10.4    0.001    0.001    5.741    5.884
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.757    5.766
 calculate_rho_elec                 110  8.6    0.078    0.081    5.757    5.766
 make_m2s                          4110 13.4    0.060    0.062    5.388    5.734
 make_images                       4110 14.4    0.586    0.710    5.246    5.590
 init_scf_run                        11  5.9    0.000    0.001    5.437    5.438
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.437    5.437
 cp_fm_upper_to_full                 70 14.2    3.324    4.849    3.324    4.849
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.065    4.195
 apply_single                       110 13.6    0.000    0.000    4.065    4.195
 ot_diis_step                        99 11.5    0.011    0.011    4.155    4.155
 qs_ot_p2m_diag                      48 11.0    0.055    0.064    3.902    3.919
 dbcsr_complete_redistribute        325 12.2    0.421    0.468    2.671    3.810
 pw_transfer                       1331 11.6    0.065    0.075    3.612    3.643
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.502    3.553
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.506    3.539
 grid_integrate_task_list           110 12.3    3.265    3.454    3.265    3.454
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.350    3.409
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.333    3.333
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    2.151    3.283
 multiply_cannon_metrocomm3       24660 15.4    0.038    0.040    1.344    3.226
 fft_wrap_pw1pw2_140                451 13.1    0.608    0.629    3.017    3.052
 density_rs2pw                      110  9.6    0.004    0.004    2.882    3.044
 hybrid_alltoall_any               4261 16.3    0.123    0.462    2.303    3.028
 calculate_dm_sparse                110  9.5    0.001    0.001    2.973    3.001
 make_images_data                  4110 15.4    0.049    0.052    2.673    3.000
 wfi_extrapolate                     11  7.9    0.001    0.001    2.975    2.975
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.802    2.919
 mp_alltoall_i22                    605 13.7    1.666    2.840    1.666    2.840
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    2.804    2.813
 cp_fm_diag_elpa_base                48 14.0    2.659    2.720    2.802    2.812
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.002    2.784    2.786
 multiply_cannon_sync_h2d         24660 15.4    2.362    2.654    2.362    2.654
 cp_fm_cholesky_invert               11 10.9    2.587    2.597    2.587    2.597
 acc_transpose_blocks             24660 15.4    0.115    0.120    2.449    2.542
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.429    2.466
 fft3d_ps                          1111 14.6    1.086    1.117    2.389    2.408
 grid_collocate_task_list           110  9.6    2.266    2.376    2.266    2.376
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.368    2.372
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    2.234    2.244
 mp_alltoall_d11v                  2046 13.8    1.786    2.075    1.786    2.075
 potential_pw2rs                    110 12.3    0.013    0.013    2.000    2.010
 jit_kernel_multiply                 10 15.6    0.786    1.849    0.786    1.849
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.806    1.845
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.615    1.711
 cp_fm_cholesky_decompose            22 10.9    1.594    1.657    1.594    1.657
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.635    1.649
 mp_sum_l                          6594 12.7    0.932    1.553    0.932    1.553
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.536    1.552
 acc_transpose_blocks_sync        73980 16.4    1.438    1.534    1.438    1.534
 multiply_cannon_metrocomm4       20550 15.4    0.062    0.066    0.855    1.449
 mp_irecv_dv                      62702 16.1    0.751    1.370    0.751    1.370
 transfer_rs2pw                     451 10.6    0.005    0.006    1.158    1.325
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="206", plot="h2o_128_md", label="(8n/3r/4t)", y=65.206000, yerr=0.000000
PlotPoint: name="207", plot="h2o_128_md_mem", label="(8n/3r/4t)", y=700.727273, yerr=12.270370
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_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             850.771968E+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    0.014    0.034   54.410   54.412
 qs_mol_dyn_low                       1  2.0    0.003    0.003   54.185   54.196
 qs_forces                           11  3.9    0.003    0.003   54.105   54.106
 qs_energies                         11  4.9    0.001    0.002   50.480   50.486
 scf_env_do_scf                      11  5.9    0.000    0.001   42.350   42.351
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.007   34.783   34.784
 velocity_verlet                     10  3.0    0.002    0.002   30.788   30.792
 dbcsr_multiply_generic            2055 12.4    0.104    0.109   23.049   23.267
 qs_scf_new_mos                      99  7.5    0.001    0.001   20.400   20.452
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   20.399   20.451
 ot_scf_mini                         99  9.5    0.002    0.002   19.162   19.209
 multiply_cannon                   2055 13.4    0.238    0.253   17.619   18.960
 multiply_cannon_loop              2055 14.4    0.609    0.634   16.385   16.751
 rebuild_ks_matrix                  110  8.3    0.000    0.000   11.535   11.594
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.014   11.534   11.594
 ot_mini                             99 10.5    0.001    0.001   10.681   10.728
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.261   10.313
 multiply_cannon_multrec           8220 15.4    3.153    4.752    7.546    8.967
 init_scf_loop                       11  6.9    0.000    0.001    7.522    7.522
 mp_waitall_1                    103326 16.6    5.828    7.494    5.828    7.494
 qs_ot_get_derivative                99 11.5    0.001    0.001    6.952    6.998
 sum_up_and_integrate               110 10.3    0.080    0.082    6.179    6.193
 integrate_v_rspace                 110 11.3    0.004    0.004    6.098    6.111
 prepare_preconditioner              11  7.9    0.000    0.000    5.886    5.893
 make_preconditioner                 11  8.9    0.000    0.000    5.886    5.893
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.875    5.885
 calculate_rho_elec                 110  8.6    0.114    0.114    5.874    5.884
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.491    5.560
 dbcsr_mm_accdrv_process          17442 15.9    3.103    4.123    4.252    5.168
 init_scf_run                        11  5.9    0.000    0.001    5.014    5.014
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.013    5.014
 multiply_cannon_metrocomm3        8220 15.4    0.019    0.020    3.159    4.765
 qs_ot_get_p                        110 10.4    0.001    0.001    4.545    4.611
 make_m2s                          4110 13.4    0.038    0.040    4.109    4.376
 make_images                       4110 14.4    0.655    0.718    3.980    4.242
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    3.771    3.811
 apply_single                       110 13.6    0.000    0.000    3.770    3.811
 pw_transfer                       1331 11.6    0.065    0.071    3.777    3.795
 ot_diis_step                        99 11.5    0.012    0.012    3.708    3.708
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.670    3.692
 grid_integrate_task_list           110 12.3    3.386    3.496    3.386    3.496
 qs_ot_p2m_diag                      48 11.0    0.081    0.084    3.224    3.227
 fft_wrap_pw1pw2_140                451 13.1    0.777    0.792    3.193    3.219
 density_rs2pw                      110  9.6    0.004    0.004    2.854    2.976
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    2.889    2.889
 cp_fm_cholesky_invert               11 10.9    2.813    2.816    2.813    2.816
 wfi_extrapolate                     11  7.9    0.001    0.001    2.671    2.671
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    2.667    2.668
 hybrid_alltoall_any               4261 16.3    0.201    0.848    2.234    2.664
 multiply_cannon_sync_h2d          8220 15.4    2.332    2.522    2.332    2.522
 make_images_data                  4110 15.4    0.040    0.046    2.190    2.507
 calculate_dm_sparse                110  9.5    0.001    0.001    2.459    2.502
 grid_collocate_task_list           110  9.6    2.363    2.491    2.363    2.491
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.486    2.488
 fft3d_ps                          1111 14.6    1.138    1.169    2.334    2.347
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    2.332    2.340
 cp_fm_diag_elpa_base                48 14.0    2.278    2.299    2.331    2.338
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.248    2.250
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.126    2.151
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    1.972    2.014
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.791    1.993
 potential_pw2rs                    110 12.3    0.016    0.016    1.930    1.935
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    1.872    1.901
 mp_alltoall_d11v                  2046 13.8    1.694    1.896    1.694    1.896
 cp_fm_cholesky_decompose            22 10.9    1.639    1.651    1.639    1.651
 qs_env_update_s_mstruct             11  6.9    0.001    0.002    1.495    1.615
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.601    1.609
 dbcsr_complete_redistribute        325 12.2    0.569    0.587    1.395    1.482
 mp_allgather_i34                  2055 14.4    0.402    1.457    0.402    1.457
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.423    1.434
 multiply_cannon_metrocomm4        6165 15.4    0.019    0.020    0.481    1.430
 acc_transpose_blocks              8220 15.4    0.039    0.041    1.369    1.402
 mp_irecv_dv                      24056 15.7    0.454    1.387    0.454    1.387
 qs_create_task_list                 11  7.9    0.001    0.001    1.212    1.312
 generate_qs_task_list               11  8.9    0.375    0.441    1.212    1.311
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.204    1.236
 transfer_rs2pw                     451 10.6    0.005    0.005    1.084    1.234
 mp_waitany                        9240 13.8    1.044    1.216    1.044    1.216
 jit_kernel_multiply                  7 15.5    0.832    1.201    0.832    1.201
 multiply_cannon_metrocomm1        8220 15.4    0.022    0.022    0.675    1.138
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="208", plot="h2o_128_md", label="(8n/2r/6t)", y=54.412000, yerr=0.000000
PlotPoint: name="209", plot="h2o_128_md_mem", label="(8n/2r/6t)", y=800.545455, yerr=12.055656
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_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               1.393054E+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    0.017    0.039   86.564   86.565
 qs_mol_dyn_low                       1  2.0    0.003    0.004   86.267   86.277
 qs_forces                           11  3.9    0.003    0.003   86.203   86.204
 qs_energies                         11  4.9    0.001    0.001   82.140   82.141
 scf_env_do_scf                      11  5.9    0.000    0.001   72.270   72.271
 velocity_verlet                     10  3.0    0.002    0.002   55.581   55.587
 scf_env_do_scf_inner_loop           99  6.5    0.004    0.007   43.837   43.839
 dbcsr_multiply_generic            2055 12.4    0.119    0.124   29.458   29.631
 init_scf_loop                       11  6.9    0.001    0.001   28.363   28.366
 qs_scf_new_mos                      99  7.5    0.001    0.001   26.679   26.769
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   26.678   26.768
 prepare_preconditioner              11  7.9    0.000    0.000   26.367   26.382
 make_preconditioner                 11  8.9    0.000    0.000   26.367   26.382
 make_full_inverse_cholesky          11  9.9    0.000    0.000   20.348   25.828
 ot_scf_mini                         99  9.5    0.002    0.002   24.895   24.978
 multiply_cannon                   2055 13.4    0.335    0.356   22.354   23.053
 multiply_cannon_loop              2055 14.4    0.809    0.823   20.562   20.978
 cp_fm_upper_to_full                 70 14.2   12.751   18.490   12.751   18.490
 ot_mini                             99 10.5    0.001    0.001   14.148   14.230
 rebuild_ks_matrix                  110  8.3    0.000    0.001   13.573   13.673
 qs_ks_build_kohn_sham_matrix       110  9.3    0.014    0.014   13.573   13.673
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.316   12.406
 dbcsr_complete_redistribute        325 12.2    1.022    1.049    7.588   10.892
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    6.564    9.870
 multiply_cannon_multrec           8220 15.4    4.056    4.227    9.717    9.817
 qs_ot_get_derivative                99 11.5    0.001    0.001    9.404    9.486
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    6.003    9.270
 mp_alltoall_i22                    605 13.7    5.632    8.973    5.632    8.973
 mp_waitall_1                     84994 16.7    7.449    8.452    7.449    8.452
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.957    6.991
 calculate_rho_elec                 110  8.6    0.225    0.225    6.957    6.991
 sum_up_and_integrate               110 10.3    0.150    0.151    6.757    6.772
 integrate_v_rspace                 110 11.3    0.004    0.004    6.607    6.621
 make_m2s                          4110 13.4    0.044    0.045    5.319    5.834
 dbcsr_mm_accdrv_process          11614 15.7    3.917    4.116    5.513    5.721
 make_images                       4110 14.4    0.893    0.947    5.131    5.646
 init_scf_run                        11  5.9    0.000    0.001    5.620    5.620
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.619    5.620
 qs_ot_get_p                        110 10.4    0.001    0.001    5.487    5.582
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.861    5.382
 apply_single                       110 13.6    0.000    0.000    4.861    5.382
 multiply_cannon_metrocomm3        8220 15.4    0.019    0.019    4.837    5.161
 cp_fm_cholesky_invert               11 10.9    5.117    5.121    5.117    5.121
 pw_transfer                       1331 11.6    0.075    0.075    4.822    4.827
 ot_diis_step                        99 11.5    0.015    0.016    4.728    4.728
 fft_wrap_pw1pw2                   1111 12.6    0.009    0.009    4.705    4.710
 fft_wrap_pw1pw2_140                451 13.1    1.278    1.284    4.127    4.134
 qs_ot_p2m_diag                      48 11.0    0.151    0.156    3.900    3.908
 grid_integrate_task_list           110 12.3    3.674    3.746    3.674    3.746
 qs_energies_init_hamiltonians       11  5.9    0.002    0.002    3.650    3.651
 hybrid_alltoall_any               4261 16.3    0.263    0.566    2.820    3.533
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    2.988    3.465
 density_rs2pw                      110  9.6    0.004    0.004    3.429    3.440
 make_images_data                  4110 15.4    0.045    0.048    2.800    3.427
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.388    3.388
 wfi_extrapolate                     11  7.9    0.001    0.001    3.284    3.284
 multiply_cannon_sync_h2d          8220 15.4    3.151    3.180    3.151    3.180
 calculate_dm_sparse                110  9.5    0.001    0.001    3.147    3.174
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.869    2.875
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    2.812    2.812
 cp_fm_diag_elpa_base                48 14.0    2.266    2.471    2.810    2.810
 fft3d_ps                          1111 14.6    1.296    1.305    2.758    2.765
 grid_collocate_task_list           110  9.6    2.666    2.685    2.666    2.685
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.632    2.676
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.363    2.397
 qs_env_update_s_mstruct             11  6.9    0.004    0.006    2.168    2.234
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.223    2.223
 potential_pw2rs                    110 12.3    0.021    0.022    2.179    2.182
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    2.091    2.163
 mp_alltoall_d11v                  2046 13.8    2.024    2.093    2.024    2.093
 cp_fm_cholesky_decompose            22 10.9    1.928    1.952    1.928    1.952
 qs_create_task_list                 11  7.9    0.002    0.004    1.878    1.921
 generate_qs_task_list               11  8.9    0.728    0.782    1.876    1.919
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.857    1.867
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.775    1.825
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="210", plot="h2o_128_md", label="(8n/1r/12t)", y=86.565000, yerr=0.000000
PlotPoint: name="211", plot="h2o_128_md_mem", label="(8n/1r/12t)", y=1257.454545, yerr=53.382605
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/15/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420239992832       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528891191296       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514751E+12       0.0%      0.0%    100.0%
 flops max/rank                      1.094965E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755938624       0.0%      0.0%    100.0%
 number of processed stacks              11950464       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     565.3
 marketing flops                   144.580175E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank             630.603776E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                10348896
 MPI messages size (bytes):
  total size                         4.491514E+12
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     434.009000E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               65736                        0
       128 < size <=     8192                1232                 10092544
      8192 < size <=    32768             3576680              95640223744
     32768 < size <=   131072             1294784              74079797248
    131072 < size <=  4194304             5148576            3175954870160
   4194304 < size <= 16777216              261888            1145794321408
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3992                  57905.
 MP_Allreduce        11059                    797.
 MP_Sync                87
 MP_Alltoall          2226                2529110.
 MP_SendRecv         24320                  18752.
 MP_ISendRecv        24320                  18752.
 MP_Wait             42476
 MP_ISend            16020                 108028.
 MP_IRecv            16020                 108028.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.012    0.031  205.751  205.753
 qs_mol_dyn_low                       1  2.0    0.003    0.004  205.338  205.352
 qs_forces                           11  3.9    0.005    0.005  205.254  205.256
 qs_energies                         11  4.9    0.001    0.002  199.674  199.694
 scf_env_do_scf                      11  5.9    0.001    0.001  183.317  183.321
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.008  163.077  163.079
 dbcsr_multiply_generic            2507 12.6    0.180    0.185  125.476  126.002
 qs_scf_new_mos                     117  7.6    0.001    0.001  123.995  124.291
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001  123.994  124.290
 velocity_verlet                     10  3.0    0.001    0.003  123.378  123.379
 ot_scf_mini                        117  9.6    0.003    0.003  117.282  117.562
 multiply_cannon                   2507 13.6    0.240    0.251  101.603  103.685
 multiply_cannon_loop              2507 14.6    2.387    2.456   99.463  101.257
 ot_mini                            117 10.6    0.001    0.001   65.972   66.267
 multiply_cannon_multrec          60168 15.6   31.967   35.098   41.614   44.064
 qs_ot_get_derivative               117 11.6    0.001    0.001   41.144   41.411
 rebuild_ks_matrix                  128  8.3    0.001    0.001   33.443   33.779
 qs_ks_build_kohn_sham_matrix       128  9.3    0.015    0.017   33.442   33.778
 mp_waitall_1                    267128 16.5   28.592   31.669   28.592   31.669
 qs_ks_update_qs_env                128  7.6    0.001    0.001   30.040   30.394
 qs_ot_get_p                        128 10.4    0.001    0.001   29.038   29.440
 multiply_cannon_sync_h2d         60168 15.6   26.617   28.303   26.617   28.303
 apply_preconditioner_dbcsr         128 12.6    0.000    0.001   24.361   25.148
 apply_single                       128 13.6    0.001    0.001   24.361   25.147
 ot_diis_step                       117 11.6    0.008    0.008   24.559   24.561
 qs_ot_p2m_diag                      83 11.4    0.079    0.091   22.434   22.493
 init_scf_loop                       11  6.9    0.000    0.001   20.169   20.170
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002   19.582   19.803
 cp_dbcsr_syevd                      83 12.4    0.005    0.005   19.624   19.625
 multiply_cannon_metrocomm3       60168 15.6    0.121    0.126   16.205   17.932
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   16.719   16.749
 cp_fm_diag_elpa_base                83 14.4   16.655   16.691   16.715   16.744
 prepare_preconditioner              11  7.9    0.000    0.000   15.586   15.635
 make_preconditioner                 11  8.9    0.000    0.000   15.586   15.635
 make_full_inverse_cholesky          11  9.9    0.000    0.000   14.832   15.005
 make_m2s                          5014 13.6    0.105    0.113   13.736   14.056
 sum_up_and_integrate               128 10.3    0.089    0.107   13.871   13.892
 make_images                       5014 14.6    0.398    0.417   13.554   13.883
 integrate_v_rspace                 128 11.3    0.004    0.005   13.782   13.804
 qs_rho_update_rho_low              128  7.7    0.001    0.001   12.911   13.053
 calculate_rho_elec                 128  8.7    0.045    0.064   12.910   13.053
 init_scf_run                        11  5.9    0.000    0.001   12.230   12.231
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   12.230   12.230
 mp_sum_l                          7950 12.9    8.869   10.155    8.869   10.155
 dbcsr_mm_accdrv_process         124484 16.2    4.609    4.778    9.210    9.721
 wfi_extrapolate                     11  7.9    0.001    0.001    9.082    9.082
 cp_fm_cholesky_invert               11 10.9    8.863    8.871    8.863    8.871
 calculate_dm_sparse                128  9.5    0.001    0.001    8.513    8.652
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    8.179    8.333
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    8.135    8.209
 make_images_data                  5014 15.6    0.067    0.074    6.765    7.744
 multiply_cannon_metrocomm1       60168 15.6    0.097    0.101    5.969    7.598
 pw_transfer                       1547 11.6    0.074    0.090    7.417    7.591
 density_rs2pw                      128  9.7    0.006    0.007    6.604    7.493
 grid_integrate_task_list           128 12.3    7.072    7.443    7.072    7.443
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.012    7.214    7.385
 hybrid_alltoall_any               5200 16.5    0.296    2.274    5.931    7.246
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.003    6.599    6.609
 fft_wrap_pw1pw2_140                523 13.2    1.136    1.174    6.380    6.544
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.740    5.863
 fft3d_ps                          1291 14.7    2.188    2.835    5.210    5.531
 mp_alltoall_d11v                  2415 14.1    4.159    5.396    4.159    5.396
 grid_collocate_task_list           128  9.7    4.843    5.267    4.843    5.267
 cp_fm_cholesky_decompose            22 10.9    4.582    4.596    4.582    4.596
 potential_pw2rs                    128 12.3    0.009    0.011    4.378    4.399
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="400", plot="h2o_256_md", label="(8n/12r/1t)", y=205.753000, yerr=0.000000
PlotPoint: name="401", plot="h2o_256_md_mem", label="(8n/12r/1t)", y=597.272727, yerr=6.823634
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_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             843.694080E+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                6067735.
 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    0.022    0.037  187.841  187.844
 qs_mol_dyn_low                       1  2.0    0.003    0.004  187.300  187.313
 qs_forces                           11  3.9    0.005    0.007  187.218  187.221
 qs_energies                         11  4.9    0.002    0.006  180.468  180.480
 scf_env_do_scf                      11  5.9    0.001    0.005  164.111  164.122
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.008  131.723  131.726
 velocity_verlet                     10  3.0    0.002    0.002  118.173  118.174
 dbcsr_multiply_generic            2507 12.6    0.188    0.193   97.265   98.492
 qs_scf_new_mos                     117  7.6    0.001    0.001   93.392   93.977
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   93.391   93.976
 ot_scf_mini                        117  9.6    0.004    0.005   88.594   89.212
 multiply_cannon                   2507 13.6    0.502    0.556   77.246   81.764
 multiply_cannon_loop              2507 14.6    1.582    1.650   73.830   76.558
 ot_mini                            117 10.6    0.001    0.001   50.089   50.647
 mp_waitall_1                    214728 16.6   23.894   38.382   23.894   38.382
 multiply_cannon_multrec          30084 15.6   20.959   25.198   31.559   36.250
 rebuild_ks_matrix                  128  8.3    0.001    0.001   32.213   32.895
 qs_ks_build_kohn_sham_matrix       128  9.3    0.017    0.020   32.213   32.894
 init_scf_loop                       11  6.9    0.001    0.003   32.299   32.300
 qs_ks_update_qs_env                128  7.6    0.001    0.001   28.966   29.585
 qs_ot_get_derivative               117 11.6    0.001    0.002   28.138   28.753
 multiply_cannon_metrocomm3       30084 15.6    0.096    0.102   15.643   28.587
 prepare_preconditioner              11  7.9    0.000    0.000   27.984   28.062
 make_preconditioner                 11  8.9    0.001    0.006   27.984   28.062
 make_full_inverse_cholesky          11  9.9    0.000    0.000   26.681   27.240
 apply_preconditioner_dbcsr         128 12.6    0.000    0.000   22.061   23.237
 apply_single                       128 13.6    0.001    0.001   22.061   23.237
 ot_diis_step                       117 11.6    0.014    0.015   21.778   21.780
 qs_ot_get_p                        128 10.4    0.001    0.001   20.539   21.226
 multiply_cannon_sync_h2d         30084 15.6   17.931   19.757   17.931   19.757
 cp_fm_cholesky_invert               11 10.9   16.331   16.343   16.331   16.343
 make_m2s                          5014 13.6    0.090    0.096   14.069   15.813
 qs_ot_p2m_diag                      83 11.4    0.189    0.217   15.628   15.662
 make_images                       5014 14.6    1.191    1.396   13.861   15.609
 cp_dbcsr_syevd                      83 12.4    0.005    0.006   14.437   14.437
 sum_up_and_integrate               128 10.3    0.116    0.134   13.949   13.978
 integrate_v_rspace                 128 11.3    0.003    0.004   13.833   13.864
 qs_rho_update_rho_low              128  7.7    0.001    0.001   13.200   13.228
 calculate_rho_elec                 128  8.7    0.087    0.104   13.199   13.227
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002   11.154   11.615
 init_scf_run                        11  5.9    0.000    0.001   11.453   11.455
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   11.453   11.455
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   11.333   11.370
 cp_fm_diag_elpa_base                83 14.4   11.082   11.165   11.328   11.360
 multiply_cannon_metrocomm4       27577 15.6    0.105    0.119    3.890   11.021
 dbcsr_mm_accdrv_process          62242 16.2    5.426    6.215   10.049   10.658
 mp_irecv_dv                      69486 16.3    3.685   10.618    3.685   10.618
 make_images_data                  5014 15.6    0.067    0.075    8.314   10.288
 hybrid_alltoall_any               5200 16.5    0.352    1.515    7.134    9.944
 pw_transfer                       1547 11.6    0.085    0.095    8.476    8.531
 wfi_extrapolate                     11  7.9    0.001    0.001    8.316    8.316
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.011    8.252    8.309
 grid_integrate_task_list           128 12.3    7.183    7.508    7.183    7.508
 fft_wrap_pw1pw2_140                523 13.2    1.225    1.268    7.342    7.420
 density_rs2pw                      128  9.7    0.006    0.007    6.925    7.302
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    6.285    7.080
 cp_fm_cholesky_decompose            22 10.9    6.793    6.892    6.793    6.892
 calculate_dm_sparse                128  9.5    0.001    0.001    6.487    6.616
 mp_sum_l                          7950 12.9    4.156    6.372    4.156    6.372
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.088    6.098
 fft3d_ps                          1291 14.7    2.833    3.001    5.799    5.839
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    5.350    5.414
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.181    5.397
 grid_collocate_task_list           128  9.7    5.007    5.348    5.007    5.348
 mp_allgather_i34                  2507 14.6    1.935    5.043    1.935    5.043
 mp_alltoall_d11v                  2415 14.1    4.076    4.844    4.076    4.844
 potential_pw2rs                    128 12.3    0.015    0.017    4.381    4.394
 mp_sum_d                          4470 12.1    2.611    3.975    2.611    3.975
 dbcsr_complete_redistribute        395 12.7    0.774    0.855    3.072    3.923
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="402", plot="h2o_256_md", label="(8n/6r/2t)", y=187.844000, yerr=0.000000
PlotPoint: name="403", plot="h2o_256_md_mem", label="(8n/6r/2t)", y=803.363636, yerr=4.248481
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/17/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1410022950912       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1924145348608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1957871443968       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1963542011904       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2714615709696       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4377645416448       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5350455508992       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5395653328896       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6594687401984       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11444706349056       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15019182452736       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15019182452736       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                        92.796564E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.906045E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6705499488       0.0%      0.0%    100.0%
 number of processed stacks               3951168       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1697.1
 marketing flops                   143.507742E+12
 -------------------------------------------------------------------------------
 # multiplications                           2485
 max memory usage/rank             968.912896E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                 1033760
 MPI messages size (bytes):
  total size                         2.695213E+12
  min size                           0.000000E+00
  max size                          26.214400E+06
  average size                       2.607194E+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              279168              36591108096
    131072 < size <=  4194304              654272             987691483136
   4194304 < size <= 16777216               65184             925172558800
  16777216 < size                           28448             745747251200
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3995                  58307.
 MP_Allreduce        11065                   1000.
 MP_Sync                86
 MP_Alltoall          1700                9383497.
 MP_SendRecv          7874                  75008.
 MP_ISendRecv         7874                  75008.
 MP_Wait             21654
 MP_ISend            11660                 275234.
 MP_IRecv            11660                 275234.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.039    0.136  173.364  173.366
 qs_mol_dyn_low                       1  2.0    0.003    0.006  172.830  172.844
 qs_forces                           11  3.9    0.005    0.010  172.740  172.742
 qs_energies                         11  4.9    0.003    0.009  166.197  166.207
 scf_env_do_scf                      11  5.9    0.001    0.001  149.812  149.814
 scf_env_do_scf_inner_loop          116  6.6    0.003    0.008  115.484  115.485
 velocity_verlet                     10  3.0    0.001    0.002  110.237  110.239
 dbcsr_multiply_generic            2485 12.5    0.181    0.188   81.265   82.267
 qs_scf_new_mos                     116  7.6    0.001    0.001   78.935   79.218
 qs_scf_loop_do_ot                  116  8.6    0.001    0.001   78.934   79.217
 ot_scf_mini                        116  9.6    0.004    0.009   74.701   75.017
 multiply_cannon                   2485 13.5    0.506    0.528   61.982   66.399
 multiply_cannon_loop              2485 14.5    1.130    1.196   58.912   61.608
 ot_mini                            116 10.6    0.001    0.002   42.302   42.627
 init_scf_loop                       11  6.9    0.001    0.003   34.230   34.232
 mp_waitall_1                    169034 16.6   24.435   33.768   24.435   33.768
 rebuild_ks_matrix                  127  8.3    0.001    0.001   29.911   30.322
 qs_ks_build_kohn_sham_matrix       127  9.3    0.016    0.018   29.910   30.322
 prepare_preconditioner              11  7.9    0.000    0.000   30.222   30.273
 make_preconditioner                 11  8.9    0.000    0.001   30.222   30.273
 make_full_inverse_cholesky          11  9.9    0.000    0.000   27.844   29.288
 qs_ks_update_qs_env                127  7.6    0.001    0.001   26.938   27.319
 multiply_cannon_multrec          19880 15.5   12.897   16.269   22.252   25.528
 multiply_cannon_metrocomm3       19880 15.5    0.062    0.066   15.414   24.589
 qs_ot_get_derivative               116 11.6    0.001    0.002   22.590   22.912
 apply_preconditioner_dbcsr         127 12.6    0.000    0.001   19.855   20.831
 apply_single                       127 13.6    0.001    0.001   19.855   20.831
 ot_diis_step                       116 11.6    0.018    0.023   19.601   19.601
 qs_ot_get_p                        127 10.4    0.001    0.001   17.914   18.319
 make_m2s                          4970 13.5    0.080    0.085   14.397   15.717
 make_images                       4970 14.5    1.155    1.262   14.167   15.485
 multiply_cannon_sync_h2d         19880 15.5   13.482   15.407   13.482   15.407
 cp_fm_cholesky_invert               11 10.9   14.065   14.073   14.065   14.073
 sum_up_and_integrate               127 10.3    0.131    0.145   13.856   13.886
 qs_ot_p2m_diag                      82 11.4    0.263    0.269   13.832   13.840
 integrate_v_rspace                 127 11.3    0.004    0.004   13.725   13.753
 qs_rho_update_rho_low              127  7.7    0.001    0.001   13.329   13.360
 calculate_rho_elec                 127  8.7    0.129    0.144   13.329   13.360
 cp_dbcsr_syevd                      82 12.4    0.005    0.005   12.788   12.788
 init_scf_run                        11  5.9    0.000    0.001   10.563   10.563
 scf_env_initial_rho_setup           11  6.9    0.001    0.002   10.563   10.563
 make_images_data                  4970 15.5    0.062    0.072    8.583   10.286
 cp_fm_diag_elpa                     82 13.4    0.000    0.000    9.693    9.710
 cp_fm_diag_elpa_base                82 14.4    9.300    9.438    9.690    9.708
 hybrid_alltoall_any               5155 16.4    0.449    2.042    7.489    9.558
 multiply_cannon_metrocomm4       17395 15.5    0.066    0.075    3.501    9.490
 mp_irecv_dv                      49801 16.2    3.374    9.234    3.374    9.234
 qs_ot_get_derivative_diag           76 12.4    0.002    0.002    8.814    9.069
 dbcsr_mm_accdrv_process          41158 16.2    5.689    5.979    8.813    8.948
 pw_transfer                       1535 11.6    0.085    0.101    8.524    8.621
 fft_wrap_pw1pw2                   1281 12.7    0.010    0.011    8.302    8.404
 grid_integrate_task_list           127 12.3    7.262    7.623    7.262    7.623
 fft_wrap_pw1pw2_140                519 13.2    1.303    1.343    7.402    7.510
 wfi_extrapolate                     11  7.9    0.001    0.001    7.406    7.406
 density_rs2pw                      127  9.7    0.006    0.006    6.737    7.220
 cp_fm_cholesky_decompose            22 10.9    7.058    7.152    7.058    7.152
 cp_fm_upper_to_full                104 14.8    5.634    7.137    5.634    7.137
 dbcsr_complete_redistribute        393 12.7    1.172    1.194    4.620    6.338
 calculate_dm_sparse                127  9.5    0.001    0.001    5.827    5.927
 fft3d_ps                          1281 14.7    2.735    2.953    5.687    5.753
 grid_collocate_task_list           127  9.7    5.129    5.529    5.129    5.529
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.496    5.505
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    4.543    5.233
 copy_fm_to_dbcsr                   208 11.6    0.002    0.009    3.472    5.189
 mp_alltoall_d11v                  2401 14.1    4.264    4.929    4.264    4.929
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.001    4.551    4.694
 mp_allgather_i34                  2485 14.5    1.557    4.489    1.557    4.489
 qs_energies_init_hamiltonians       11  5.9    0.009    0.067    4.480    4.481
 mp_sum_l                          7884 12.9    3.094    4.383    3.094    4.383
 potential_pw2rs                    127 12.3    0.020    0.023    4.298    4.310
 transfer_fm_to_dbcsr                11  9.9    0.019    0.025    2.359    4.066
 qs_ot_get_orbitals                 116 10.6    0.001    0.001    3.923    3.963
 mp_alltoall_i22                    712 14.1    1.969    3.802    1.969    3.802
 transfer_rs2pw                     519 10.6    0.006    0.007    3.213    3.735
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    3.468    3.509
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="404", plot="h2o_256_md", label="(8n/4r/3t)", y=173.366000, yerr=0.000000
PlotPoint: name="405", plot="h2o_256_md_mem", label="(8n/4r/3t)", y=913.181818, yerr=14.082989
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/18/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1430457200640       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1962800054272       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1986252263424       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1992003932160       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2753958699008       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4454954827776       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5444944789504       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5492290093056       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6712799002624       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11613077360640       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15239167967232       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15239167967232       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19911132921856       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        94.233007E+12       0.0%      0.0%    100.0%
 flops max/rank                      4.387242E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6806383584       0.0%      0.0%    100.0%
 number of processed stacks               6026880       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1129.3
 marketing flops                   145.651870E+12
 -------------------------------------------------------------------------------
 # multiplications                           2529
 max memory usage/rank               1.166393E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1153224
 MPI messages size (bytes):
  total size                         2.039489E+12
  min size                           0.000000E+00
  max size                          17.653760E+06
  average size                       1.768511E+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              322096              36390305792
    131072 < size <=  4194304              721976             792118951936
   4194304 < size <= 16777216               70800             669922014800
  16777216 < size                           30960             541065216000
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4043                  57626.
 MP_Allreduce        11184                   1079.
 MP_Sync                88
 MP_Alltoall          1724               12509627.
 MP_SendRecv          5934                  75008.
 MP_ISendRecv         5934                  75008.
 MP_Wait             22612
 MP_ISend            15064                 244788.
 MP_IRecv            15064                 244788.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.019    0.043  188.659  188.662
 qs_mol_dyn_low                       1  2.0    0.003    0.004  188.167  188.183
 qs_forces                           11  3.9    0.004    0.005  188.065  188.075
 qs_energies                         11  4.9    0.003    0.009  180.924  180.938
 scf_env_do_scf                      11  5.9    0.001    0.002  163.345  163.360
 velocity_verlet                     10  3.0    0.002    0.002  125.062  125.066
 scf_env_do_scf_inner_loop          118  6.6    0.004    0.013  117.276  117.278
 dbcsr_multiply_generic            2529 12.6    0.241    0.261   81.541   82.378
 qs_scf_new_mos                     118  7.6    0.001    0.001   80.814   81.145
 qs_scf_loop_do_ot                  118  8.6    0.001    0.001   80.813   81.145
 ot_scf_mini                        118  9.6    0.003    0.004   76.177   76.526
 multiply_cannon                   2529 13.6    0.563    0.602   56.463   58.976
 multiply_cannon_loop              2529 14.6    1.870    1.949   52.575   54.513
 init_scf_loop                       11  6.9    0.001    0.008   45.948   45.952
 ot_mini                            118 10.6    0.001    0.001   43.249   43.588
 prepare_preconditioner              11  7.9    0.000    0.000   41.845   41.877
 make_preconditioner                 11  8.9    0.000    0.001   41.845   41.877
 make_full_inverse_cholesky          11  9.9    0.012    0.022   35.539   40.547
 multiply_cannon_multrec          30348 15.6   13.862   19.547   26.921   32.297
 rebuild_ks_matrix                  129  8.3    0.001    0.001   29.548   29.830
 qs_ks_build_kohn_sham_matrix       129  9.3    0.017    0.019   29.547   29.829
 mp_waitall_1                    149172 16.7   17.029   27.531   17.029   27.531
 qs_ks_update_qs_env                129  7.6    0.001    0.001   26.660   26.906
 qs_ot_get_derivative               118 11.6    0.001    0.002   23.414   23.755
 make_m2s                          5058 13.6    0.098    0.102   20.483   21.580
 make_images                       5058 14.6    1.986    2.345   20.175   21.272
 apply_preconditioner_dbcsr         129 12.6    0.000    0.001   19.186   19.747
 apply_single                       129 13.6    0.001    0.001   19.186   19.747
 ot_diis_step                       118 11.6    0.018    0.020   19.706   19.709
 qs_ot_get_p                        129 10.4    0.001    0.003   18.926   19.297
 cp_fm_upper_to_full                106 14.8   11.390   16.815   11.390   16.815
 cp_fm_cholesky_invert               11 10.9   15.936   15.945   15.936   15.945
 multiply_cannon_metrocomm3       30348 15.6    0.050    0.053    6.242   15.412
 qs_ot_p2m_diag                      84 11.4    0.347    0.395   14.715   14.769
 sum_up_and_integrate               129 10.3    0.141    0.153   14.117   14.145
 integrate_v_rspace                 129 11.3    0.004    0.004   13.975   14.008
 qs_rho_update_rho_low              129  7.7    0.001    0.001   13.693   13.745
 calculate_rho_elec                 129  8.7    0.174    0.191   13.692   13.744
 cp_dbcsr_syevd                      84 12.4    0.005    0.006   13.299   13.300
 dbcsr_mm_accdrv_process          62780 16.2    8.561    9.345   12.627   13.128
 dbcsr_complete_redistribute        397 12.7    1.703    2.115    9.373   13.127
 make_images_data                  5058 15.6    0.068    0.076   10.940   12.825
 hybrid_alltoall_any               5245 16.5    0.534    2.225    9.757   11.841
 copy_fm_to_dbcsr                   210 11.7    0.005    0.031    8.021   11.806
 init_scf_run                        11  5.9    0.000    0.001   11.612   11.613
 scf_env_initial_rho_setup           11  6.9    0.002    0.005   11.612   11.613
 multiply_cannon_sync_h2d         30348 15.6   10.500   11.352   10.500   11.352
 cp_fm_diag_elpa                     84 13.4    0.000    0.000   10.223   10.237
 cp_fm_diag_elpa_base                84 14.4    9.267    9.598   10.217   10.234
 qs_ot_get_derivative_diag           78 12.4    0.002    0.002    9.870   10.115
 transfer_fm_to_dbcsr                11  9.9    0.001    0.007    6.282    9.921
 mp_alltoall_i22                    720 14.1    5.757    9.555    5.757    9.555
 pw_transfer                       1559 11.6    0.086    0.101    8.997    9.075
 fft_wrap_pw1pw2                   1301 12.7    0.010    0.011    8.769    8.851
 fft_wrap_pw1pw2_140                527 13.2    1.464    1.493    7.830    7.922
 grid_integrate_task_list           129 12.3    7.576    7.862    7.576    7.862
 wfi_extrapolate                     11  7.9    0.001    0.001    7.638    7.638
 cp_fm_cholesky_decompose            22 10.9    7.456    7.560    7.456    7.560
 multiply_cannon_metrocomm4       25290 15.6    0.085    0.097    2.799    7.140
 density_rs2pw                      129  9.7    0.006    0.006    6.711    6.957
 mp_irecv_dv                      76751 16.2    2.644    6.858    2.644    6.858
 calculate_dm_sparse                129  9.5    0.001    0.001    6.424    6.517
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.223    6.246
 fft3d_ps                          1301 14.7    2.866    2.926    5.917    5.975
 grid_collocate_task_list           129  9.7    5.333    5.682    5.333    5.682
 mp_alltoall_d11v                  2429 14.1    4.699    5.048    4.699    5.048
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.003    4.636    4.752
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    4.466    4.566
 qs_energies_init_hamiltonians       11  5.9    0.002    0.004    4.486    4.487
 qs_ot_get_orbitals                 118 10.6    0.001    0.001    4.268    4.337
 potential_pw2rs                    129 12.3    0.024    0.024    4.278    4.295
 calculate_first_density_matrix       1  7.0    0.007    0.067    3.776    3.780
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="406", plot="h2o_256_md", label="(8n/3r/4t)", y=188.662000, yerr=0.000000
PlotPoint: name="407", plot="h2o_256_md_mem", label="(8n/3r/4t)", y=1094.909091, yerr=19.430316
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/19/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420242647040       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528903135232       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514766E+12       0.0%      0.0%    100.0%
 flops max/rank                      5.865089E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755941440       0.0%      0.0%    100.0%
 number of processed stacks               1960712       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    3445.7
 marketing flops                   144.579337E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank               1.558876E+09
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  240672
 MPI messages size (bytes):
  total size                         1.331455E+12
  min size                           0.000000E+00
  max size                          52.428800E+06
  average size                       5.532238E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                 132                  8650752
    131072 < size <=  4194304              113904              59718500352
   4194304 < size <= 16777216              104976             550376570880
  16777216 < size                           20208             721350232272
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         8931                     51.
 MP_Alltoall          9654                 799394.
 MP_ISend            40068                2102573.
 MP_IRecv            40068                2101676.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4010                  58089.
 MP_Allreduce        11102                   1166.
 MP_Sync                87
 MP_Alltoall          1712               18838222.
 MP_SendRecv          3840                 122880.
 MP_ISendRecv         3840                 122880.
 MP_Wait             16122
 MP_ISend            10680                 423556.
 MP_IRecv            10680                 423556.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.042    0.049  168.134  168.136
 qs_mol_dyn_low                       1  2.0    0.003    0.004  167.557  167.569
 qs_forces                           11  3.9    0.004    0.005  167.468  167.471
 qs_energies                         11  4.9    0.001    0.002  160.113  160.118
 scf_env_do_scf                      11  5.9    0.001    0.001  142.925  142.939
 velocity_verlet                     10  3.0    0.002    0.002  110.697  110.701
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.008  107.521  107.523
 dbcsr_multiply_generic            2507 12.6    0.180    0.188   71.616   72.083
 qs_scf_new_mos                     117  7.6    0.001    0.001   70.918   71.013
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   70.917   71.012
 ot_scf_mini                        117  9.6    0.003    0.003   66.514   66.597
 multiply_cannon                   2507 13.6    0.556    0.586   53.115   56.609
 multiply_cannon_loop              2507 14.6    0.806    0.846   50.194   51.056
 ot_mini                            117 10.6    0.001    0.001   37.258   37.337
 init_scf_loop                       11  6.9    0.001    0.001   35.251   35.253
 prepare_preconditioner              11  7.9    0.000    0.000   31.412   31.435
 make_preconditioner                 11  8.9    0.000    0.000   31.412   31.435
 mp_waitall_1                    125778 16.7   24.450   30.502   24.450   30.502
 make_full_inverse_cholesky          11  9.9    0.017    0.027   29.326   29.616
 rebuild_ks_matrix                  128  8.3    0.001    0.001   28.979   29.092
 qs_ks_build_kohn_sham_matrix       128  9.3    0.017    0.018   28.979   29.092
 qs_ks_update_qs_env                128  7.6    0.001    0.001   26.433   26.535
 multiply_cannon_multrec          10028 15.6   10.450   14.821   18.029   20.893
 qs_ot_get_derivative               117 11.6    0.001    0.002   20.282   20.370
 multiply_cannon_metrocomm3       10028 15.6    0.026    0.027   12.524   19.541
 cp_fm_cholesky_invert               11 10.9   17.910   17.916   17.910   17.916
 apply_preconditioner_dbcsr         128 12.6    0.000    0.000   16.997   17.128
 apply_single                       128 13.6    0.001    0.001   16.996   17.128
 ot_diis_step                       117 11.6    0.020    0.020   16.908   16.909
 qs_ot_get_p                        128 10.4    0.001    0.001   16.565   16.654
 make_m2s                          5014 13.6    0.066    0.068   14.703   15.539
 make_images                       5014 14.6    2.186    2.610   14.398   15.231
 sum_up_and_integrate               128 10.3    0.182    0.192   14.130   14.171
 integrate_v_rspace                 128 11.3    0.004    0.004   13.948   13.998
 qs_rho_update_rho_low              128  7.7    0.001    0.001   13.899   13.933
 calculate_rho_elec                 128  8.7    0.256    0.266   13.899   13.933
 qs_ot_p2m_diag                      83 11.4    0.496    0.501   12.884   12.901
 cp_dbcsr_syevd                      83 12.4    0.005    0.006   11.726   11.727
 multiply_cannon_sync_h2d         10028 15.6   10.907   11.410   10.907   11.410
 init_scf_run                        11  5.9    0.000    0.001   10.332   10.332
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   10.332   10.332
 hybrid_alltoall_any               5200 16.5    0.846    3.805    8.324    9.750
 make_images_data                  5014 15.6    0.056    0.064    8.458    9.700
 pw_transfer                       1547 11.6    0.085    0.094    9.190    9.205
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.010    8.967    8.989
 cp_fm_diag_elpa                     83 13.4    0.000    0.000    8.890    8.902
 cp_fm_diag_elpa_base                83 14.4    8.642    8.723    8.882    8.894
 grid_integrate_task_list           128 12.3    7.787    8.091    7.787    8.091
 qs_ot_get_derivative_diag           77 12.4    0.002    0.003    7.947    8.012
 fft_wrap_pw1pw2_140                523 13.2    1.818    1.851    7.965    7.993
 cp_fm_cholesky_decompose            22 10.9    7.829    7.975    7.829    7.975
 dbcsr_mm_accdrv_process          20762 16.1    3.427    4.460    7.229    7.925
 wfi_extrapolate                     11  7.9    0.001    0.001    7.363    7.363
 multiply_cannon_metrocomm1       10028 15.6    0.030    0.030    4.249    7.058
 density_rs2pw                      128  9.7    0.006    0.006    6.617    6.930
 calculate_dm_sparse                128  9.5    0.001    0.001    6.063    6.127
 grid_collocate_task_list           128  9.7    5.564    5.829    5.564    5.829
 fft3d_ps                          1291 14.7    2.759    2.835    5.678    5.709
 dbcsr_complete_redistribute        395 12.7    2.122    2.199    5.170    5.475
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    5.282    5.282
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.136    5.154
 mp_alltoall_d11v                  2415 14.1    4.506    4.878    4.506    4.878
 mp_allgather_i34                  2507 14.6    1.098    4.524    1.098    4.524
 potential_pw2rs                    128 12.3    0.027    0.027    4.178    4.189
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.039    4.115
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    3.590    3.856
 multiply_cannon_metrocomm4        7521 15.6    0.027    0.029    1.719    3.795
 mp_irecv_dv                      28860 15.9    1.679    3.706    1.679    3.706
 copy_fm_to_dbcsr                   209 11.7    0.001    0.002    3.363    3.689
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    3.576    3.641
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    3.555    3.582
 copy_dbcsr_to_fm                   186 11.8    0.004    0.004    3.415    3.490
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    3.451    3.462
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="408", plot="h2o_256_md", label="(8n/2r/6t)", y=168.136000, yerr=0.000000
PlotPoint: name="409", plot="h2o_256_md_mem", label="(8n/2r/6t)", y=1468.909091, yerr=11.147397
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/20/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                     11.696234E+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               1964048       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    3439.8
 marketing flops                   144.579337E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank               3.131343E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                  100280
 MPI messages size (bytes):
  total size                         1.136195E+12
  min size                           0.000000E+00
  max size                         104.857600E+06
  average size                      11.330227E+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               45208              35089547264
   4194304 < size <= 16777216               44352             379752284160
  16777216 < size                           10104             721350232272
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4010                  59022.
 MP_Allreduce        11102                   1503.
 MP_Sync                87
 MP_Alltoall          1712               36974125.
 MP_SendRecv          1792                 218624.
 MP_ISendRecv         1792                 218624.
 MP_Wait              9802
 MP_ISend             6408                1080322.
 MP_IRecv             6408                1080322.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.139    0.179  287.641  287.646
 qs_mol_dyn_low                       1  2.0    0.003    0.003  286.943  286.963
 qs_forces                           11  3.9    0.005    0.005  286.849  286.855
 qs_energies                         11  4.9    0.002    0.002  278.075  278.087
 scf_env_do_scf                      11  5.9    0.001    0.001  255.696  255.704
 velocity_verlet                     10  3.0    0.002    0.002  208.430  208.437
 scf_env_do_scf_inner_loop          117  6.6    0.004    0.008  132.580  132.581
 init_scf_loop                       11  6.9    0.001    0.001  122.842  122.844
 prepare_preconditioner              11  7.9    0.000    0.000  118.049  118.071
 make_preconditioner                 11  8.9    0.000    0.000  118.049  118.071
 make_full_inverse_cholesky          11  9.9    0.037    0.039   94.304  115.209
 qs_scf_new_mos                     117  7.6    0.001    0.001   89.285   89.345
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   89.285   89.344
 ot_scf_mini                        117  9.6    0.004    0.004   84.409   84.434
 dbcsr_multiply_generic            2507 12.6    0.212    0.223   81.996   82.535
 cp_fm_upper_to_full                105 14.8   52.354   75.078   52.354   75.078
 multiply_cannon                   2507 13.6    0.680    0.732   58.841   59.831
 multiply_cannon_loop              2507 14.6    1.038    1.059   54.825   56.286
 ot_mini                            117 10.6    0.001    0.001   44.542   44.580
 dbcsr_complete_redistribute        395 12.7    4.019    4.098   29.738   42.434
 copy_fm_to_dbcsr                   209 11.7    0.001    0.002   26.241   38.907
 transfer_fm_to_dbcsr                11  9.9    0.030    0.031   23.701   36.230
 rebuild_ks_matrix                  128  8.3    0.001    0.001   34.003   34.045
 qs_ks_build_kohn_sham_matrix       128  9.3    0.018    0.018   34.003   34.045
 mp_alltoall_i22                    716 14.1   21.487   33.972   21.487   33.972
 cp_fm_cholesky_invert               11 10.9   32.984   32.990   32.984   32.990
 mp_waitall_1                    103674 16.8   28.040   32.301   28.040   32.301
 qs_ks_update_qs_env                128  7.6    0.001    0.001   31.564   31.606
 qs_ot_get_p                        128 10.4    0.001    0.001   24.993   25.064
 qs_ot_get_derivative               117 11.6    0.002    0.002   24.456   24.479
 qs_ot_p2m_diag                      83 11.4    0.881    0.893   20.980   21.011
 multiply_cannon_metrocomm3       10028 15.6    0.025    0.027   18.822   20.364
 make_m2s                          5014 13.6    0.077    0.079   18.611   20.081
 ot_diis_step                       117 11.6    0.022    0.022   20.056   20.056
 make_images                       5014 14.6    3.088    3.294   18.130   19.606
 apply_preconditioner_dbcsr         128 12.6    0.000    0.000   19.400   19.522
 apply_single                       128 13.6    0.001    0.001   19.400   19.522
 cp_dbcsr_syevd                      83 12.4    0.006    0.006   19.194   19.195
 multiply_cannon_multrec          10028 15.6   10.310   12.124   18.078   18.157
 qs_rho_update_rho_low              128  7.7    0.001    0.001   16.332   16.345
 calculate_rho_elec                 128  8.7    0.481    0.482   16.332   16.344
 sum_up_and_integrate               128 10.3    0.321    0.323   16.174   16.262
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   16.066   16.067
 cp_fm_diag_elpa_base                83 14.4   11.656   13.241   16.061   16.062
 integrate_v_rspace                 128 11.3    0.004    0.005   15.853   15.942
 multiply_cannon_sync_h2d         10028 15.6   14.322   14.357   14.322   14.357
 hybrid_alltoall_any               5200 16.5    1.315    3.065   10.790   12.975
 make_images_data                  5014 15.6    0.065    0.069   10.517   12.685
 init_scf_run                        11  5.9    0.000    0.001   12.084   12.086
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   12.084   12.085
 pw_transfer                       1547 11.6    0.092    0.093   11.131   11.142
 fft_wrap_pw1pw2                   1291 12.7    0.011    0.011   10.896   10.908
 fft_wrap_pw1pw2_140                523 13.2    3.062    3.099    9.744    9.756
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002    9.662    9.677
 dbcsr_mm_accdrv_process          20762 16.1    4.256    6.141    7.519    9.405
 wfi_extrapolate                     11  7.9    0.001    0.001    8.970    8.971
 cp_fm_cholesky_decompose            22 10.9    8.771    8.816    8.771    8.816
 grid_integrate_task_list           128 12.3    8.561    8.762    8.561    8.762
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    8.102    8.105
 density_rs2pw                      128  9.7    0.005    0.006    7.380    7.422
 mp_alltoall_d11v                  2415 14.1    6.853    7.005    6.853    7.005
 calculate_dm_sparse                128  9.5    0.001    0.001    6.757    6.788
 grid_collocate_task_list           128  9.7    6.417    6.498    6.417    6.498
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.339    6.388
 copy_dbcsr_to_fm                   186 11.8    0.004    0.004    6.150    6.208
 fft3d_ps                          1291 14.7    2.854    2.866    6.127    6.172
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="410", plot="h2o_256_md", label="(8n/1r/12t)", y=287.646000, yerr=0.000000
PlotPoint: name="411", plot="h2o_256_md_mem", label="(8n/1r/12t)", y=2870.090909, yerr=149.323599
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_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               1.259635E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                  458208
 MPI messages size (bytes):
  total size                         3.456111E+12
  min size                           0.000000E+00
  max size                          18.735064E+06
  average size                       7.542668E+06
 MPI breakdown and total messages size (bytes):
             size <=      128              112896                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 224                  5687808
     32768 < size <=   131072               10528                813356544
    131072 < size <=  4194304               36422              76284728544
   4194304 < size <= 16777216              294266            3312457683808
  16777216 < size                            3872              66548597808
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 255646.
 MP_Allreduce         3139                   6114.
 MP_Sync                 4
 MP_Alltoall            54
 MP_SendRecv           285                  19200.
 MP_ISendRecv          285                  19200.
 MP_Wait              1017
 MP_ISend              642                 197829.
 MP_IRecv              642                 197607.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.126    0.383   86.407   86.432
 qs_energies                          1  2.0    0.000    0.000   84.850   84.866
 ls_scf                               1  3.0    0.000    0.000   83.921   83.934
 dbcsr_multiply_generic             111  6.7    0.014    0.015   72.784   72.939
 multiply_cannon                    111  7.7    0.017    0.020   56.045   57.171
 multiply_cannon_loop               111  8.7    0.220    0.237   52.576   53.960
 ls_scf_main                          1  4.0    0.000    0.000   52.350   52.351
 density_matrix_trs4                  2  5.0    0.002    0.003   46.819   46.893
 ls_scf_init_scf                      1  4.0    0.000    0.000   28.539   28.540
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   27.420   27.470
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   25.240   25.264
 mp_waitall_1                     11031 10.9   22.366   24.632   22.366   24.632
 multiply_cannon_multrec           2664  9.7    8.161    8.925   15.651   17.396
 multiply_cannon_sync_h2d          2664  9.7   13.612   15.509   13.612   15.509
 make_m2s                           222  7.7    0.009    0.011   13.099   13.630
 make_images                        222  8.7    0.099    0.110   13.077   13.611
 multiply_cannon_metrocomm1        2664  9.7    0.010    0.011    9.598   11.624
 multiply_cannon_metrocomm3        2664  9.7    0.009    0.011    5.481    8.356
 make_images_data                   222  9.7    0.004    0.005    7.619    8.192
 dbcsr_mm_accdrv_process           4760 10.4    0.582    0.684    7.109    8.064
 hybrid_alltoall_any                227 10.6    0.216    1.840    6.551    8.003
 dbcsr_mm_accdrv_process_sort      4760 11.4    6.325    7.231    6.325    7.231
 calculate_norms                   4752  9.8    5.522    6.247    5.522    6.247
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.990    5.155
 mp_sum_l                           887  5.1    3.226    4.643    3.226    4.643
 make_images_sizes                  222  9.7    0.000    0.000    0.726    3.636
 mp_alltoall_i44                    222 10.7    0.725    3.636    0.725    3.636
 multiply_cannon_metrocomm4        2442  9.7    0.012    0.015    2.047    3.562
 mp_irecv_dv                       6231 10.9    2.031    3.535    2.031    3.535
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    2.322    3.300
 arnoldi_extremal                     4  6.8    0.000    0.000    3.221    3.246
 arnoldi_normal_ev                    4  7.8    0.001    0.003    3.220    3.246
 build_subspace                      16  8.4    0.009    0.012    3.129    3.131
 ls_scf_post                          1  4.0    0.000    0.000    3.032    3.044
 ls_scf_store_result                  1  5.0    0.000    0.000    2.846    2.891
 dbcsr_special_finalize             555  9.7    0.005    0.006    2.397    2.864
 dbcsr_merge_single_wm              555 10.7    0.478    0.632    2.389    2.855
 make_images_pack                   222  9.7    2.210    2.638    2.212    2.640
 dbcsr_matrix_vector_mult           304  9.0    0.006    0.013    2.314    2.555
 dbcsr_sort_data                    658 11.4    2.168    2.537    2.168    2.537
 dbcsr_matrix_vector_mult_local     304 10.0    2.068    2.458    2.070    2.460
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.332    2.444
 buffer_matrices_ensure_size        222  8.7    1.790    2.149    1.790    2.149
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.769    1.770
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.760    1.761
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.002    1.760    1.761
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="500", plot="h2o_32_nrep3_ls", label="(8n/12r/1t)", y=86.432000, yerr=0.000000
PlotPoint: name="501", plot="h2o_32_nrep3_ls_mem", label="(8n/12r/1t)", y=1140.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_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               2.138710E+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    0.051    0.069   91.013   91.014
 qs_energies                          1  2.0    0.000    0.001   90.415   90.442
 ls_scf                               1  3.0    0.001    0.008   88.708   88.735
 dbcsr_multiply_generic             111  6.7    0.015    0.016   74.743   75.080
 multiply_cannon                    111  7.7    0.027    0.043   52.858   57.564
 ls_scf_main                          1  4.0    0.001    0.003   54.910   54.916
 multiply_cannon_loop               111  8.7    0.135    0.148   50.005   53.814
 density_matrix_trs4                  2  5.0    0.002    0.004   49.213   49.442
 mp_waitall_1                      9105 10.9   20.910   30.290   20.910   30.290
 ls_scf_init_scf                      1  4.0    0.000    0.001   30.039   30.042
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   28.842   28.942
 multiply_cannon_multrec           1332  9.7   13.256   16.739   22.661   27.259
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.003   26.455   26.466
 multiply_cannon_metrocomm3        1332  9.7    0.007    0.008   11.576   20.688
 make_m2s                           222  7.7    0.006    0.007   15.218   15.834
 make_images                        222  8.7    1.376    1.703   15.187   15.805
 dbcsr_mm_accdrv_process           4041 10.4    0.338    0.510    9.002   10.573
 dbcsr_mm_accdrv_process_sort      4041 11.4    8.510   10.031    8.510   10.031
 make_images_data                   222  9.7    0.004    0.005    8.848    9.840
 hybrid_alltoall_any                227 10.6    0.543    2.535    8.208    9.718
 mp_sum_l                           887  5.1    5.203    8.791    5.203    8.791
 multiply_cannon_metrocomm4        1221  9.7    0.007    0.009    3.190    8.018
 mp_irecv_dv                       3311 11.0    3.169    7.949    3.169    7.949
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.964    7.191
 calculate_norms                   2376  9.8    6.069    6.702    6.069    6.702
 multiply_cannon_sync_h2d          1332  9.7    4.871    6.496    4.871    6.496
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.991    5.215
 arnoldi_extremal                     4  6.8    0.000    0.000    4.687    4.703
 arnoldi_normal_ev                    4  7.8    0.001    0.005    4.687    4.703
 build_subspace                      16  8.4    0.014    0.021    4.408    4.412
 ls_scf_post                          1  4.0    0.004    0.029    3.757    3.785
 ls_scf_store_result                  1  5.0    0.000    0.000    3.440    3.579
 dbcsr_matrix_vector_mult           304  9.0    0.010    0.022    3.142    3.374
 dbcsr_matrix_vector_mult_local     304 10.0    2.741    3.223    2.744    3.224
 mp_allgather_i34                   111  8.7    0.845    3.103    0.845    3.103
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.600    2.678
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.004    1.131    2.455
 dbcsr_data_new                    4174 10.1    2.107    2.409    2.107    2.409
 make_images_pack                   222  9.7    1.823    2.119    1.826    2.121
 dbcsr_sort_data                    436 11.2    1.825    2.031    1.825    2.031
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.853    1.856
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.840    1.842
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.004    1.840    1.842
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="502", plot="h2o_32_nrep3_ls", label="(8n/6r/2t)", y=91.014000, yerr=0.000000
PlotPoint: name="503", plot="h2o_32_nrep3_ls_mem", label="(8n/6r/2t)", y=1746.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_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               2.914509E+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    0.044    0.092   92.810   92.812
 qs_energies                          1  2.0    0.000    0.001   92.134   92.137
 ls_scf                               1  3.0    0.000    0.000   90.661   90.666
 dbcsr_multiply_generic             111  6.7    0.017    0.021   75.379   75.697
 ls_scf_main                          1  4.0    0.000    0.002   56.755   56.759
 multiply_cannon                    111  7.7    0.030    0.041   52.214   56.175
 multiply_cannon_loop               111  8.7    0.116    0.133   49.448   53.474
 density_matrix_trs4                  2  5.0    0.002    0.005   50.872   51.039
 mp_waitall_1                      7281 11.0   23.606   33.725   23.606   33.725
 ls_scf_init_scf                      1  4.0    0.000    0.001   30.259   30.262
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   29.076   29.145
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   26.728   26.740
 multiply_cannon_multrec            888  9.7   12.625   15.472   21.297   24.790
 multiply_cannon_metrocomm3         888  9.7    0.004    0.004   11.087   23.727
 make_m2s                           222  7.7    0.006    0.007   16.350   17.105
 make_images                        222  8.7    1.589    1.849   16.312   17.065
 make_images_data                   222  9.7    0.004    0.004    9.475   10.641
 hybrid_alltoall_any                227 10.6    0.641    2.938    9.009   10.220
 dbcsr_mm_accdrv_process           3754 10.4    0.321    0.497    8.206    9.458
 dbcsr_mm_accdrv_process_sort      3754 11.4    7.773    8.961    7.773    8.961
 mp_sum_l                           887  5.1    5.111    8.648    5.111    8.648
 multiply_cannon_metrocomm4         777  9.7    0.004    0.005    2.502    7.456
 mp_irecv_dv                       2335 11.1    2.487    7.400    2.487    7.400
 multiply_cannon_metrocomm1         888  9.7    0.003    0.003    3.691    7.389
 multiply_cannon_sync_h2d           888  9.7    6.014    7.131    6.014    7.131
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.902    6.890
 arnoldi_extremal                     4  6.8    0.000    0.000    5.052    5.070
 arnoldi_normal_ev                    4  7.8    0.001    0.005    5.052    5.070
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.696    4.893
 calculate_norms                   1584  9.8    4.397    4.754    4.397    4.754
 build_subspace                      16  8.4    0.014    0.020    4.749    4.754
 mp_allgather_i34                   111  8.7    0.878    3.766    0.878    3.766
 dbcsr_matrix_vector_mult           304  9.0    0.010    0.022    3.427    3.759
 ls_scf_post                          1  4.0    0.000    0.001    3.647    3.650
 dbcsr_matrix_vector_mult_local     304 10.0    3.026    3.603    3.028    3.605
 ls_scf_store_result                  1  5.0    0.000    0.000    3.384    3.470
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.845    2.929
 dbcsr_data_new                    4116  9.9    2.122    2.462    2.122    2.462
 make_images_sizes                  222  9.7    0.000    0.000    1.055    2.212
 mp_alltoall_i44                    222 10.7    1.055    2.212    1.055    2.212
 dbcsr_sort_data                    325 11.1    1.853    2.206    1.853    2.206
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.889    1.891
 make_images_pack                   222  9.7    1.624    1.883    1.627    1.886
 dbcsr_finalize                     304  7.8    0.026    0.032    1.612    1.875
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.870    1.872
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.002    1.870    1.872
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="504", plot="h2o_32_nrep3_ls", label="(8n/4r/3t)", y=92.812000, yerr=0.000000
PlotPoint: name="505", plot="h2o_32_nrep3_ls_mem", label="(8n/4r/3t)", y=2226.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_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               3.412017E+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    0.052    0.094   96.843   96.844
 qs_energies                          1  2.0    0.000    0.001   96.136   96.141
 ls_scf                               1  3.0    0.000    0.000   94.360   94.364
 dbcsr_multiply_generic             111  6.7    0.018    0.023   78.162   78.438
 ls_scf_main                          1  4.0    0.000    0.002   58.572   58.574
 multiply_cannon                    111  7.7    0.046    0.109   51.448   56.345
 density_matrix_trs4                  2  5.0    0.003    0.008   52.493   52.591
 multiply_cannon_loop               111  8.7    0.152    0.170   46.386   49.748
 ls_scf_init_scf                      1  4.0    0.000    0.001   32.586   32.588
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   31.379   31.450
 mp_waitall_1                      6369 11.0   22.255   29.691   22.255   29.691
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.002   28.919   28.932
 multiply_cannon_multrec           1332  9.7   14.173   17.705   22.188   25.803
 make_m2s                           222  7.7    0.007    0.008   21.015   22.388
 make_images                        222  8.7    3.142    3.598   20.965   22.341
 multiply_cannon_metrocomm3        1332  9.7    0.003    0.004    8.950   17.666
 make_images_data                   222  9.7    0.004    0.004   11.690   13.311
 hybrid_alltoall_any                227 10.6    0.799    3.785   11.075   12.809
 dbcsr_mm_accdrv_process           3641 10.4    0.310    0.483    7.654    9.210
 dbcsr_mm_accdrv_process_sort      3641 11.4    7.213    8.715    7.213    8.715
 mp_sum_l                           887  5.1    4.127    7.352    4.127    7.352
 multiply_cannon_sync_h2d          1332  9.7    5.403    6.099    5.403    6.099
 multiply_cannon_metrocomm4        1110  9.7    0.005    0.007    2.108    6.068
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.003    2.446    6.032
 mp_irecv_dv                       3229 10.9    2.083    6.020    2.083    6.020
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.191    5.796
 arnoldi_extremal                     4  6.8    0.000    0.000    5.192    5.207
 arnoldi_normal_ev                    4  7.8    0.001    0.005    5.192    5.207
 build_subspace                      16  8.4    0.014    0.021    4.861    4.868
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.502    4.657
 calculate_norms                   2376  9.8    4.192    4.514    4.192    4.514
 mp_allgather_i34                   111  8.7    2.175    4.479    2.175    4.479
 dbcsr_matrix_vector_mult           304  9.0    0.010    0.021    3.603    3.890
 dbcsr_matrix_vector_mult_local     304 10.0    3.199    3.705    3.202    3.707
 dbcsr_sort_data                    658 11.4    3.121    3.445    3.121    3.445
 ls_scf_post                          1  4.0    0.000    0.001    3.201    3.206
 dbcsr_special_finalize             555  9.7    0.006    0.007    2.876    3.200
 dbcsr_merge_single_wm              555 10.7    0.539    0.653    2.867    3.192
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    3.011    3.053
 ls_scf_store_result                  1  5.0    0.000    0.000    2.953    3.004
 dbcsr_data_release               10477 10.7    1.579    2.438    1.579    2.438
 dbcsr_finalize                     304  7.8    0.049    0.061    1.794    1.974
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="506", plot="h2o_32_nrep3_ls", label="(8n/3r/4t)", y=96.844000, yerr=0.000000
PlotPoint: name="507", plot="h2o_32_nrep3_ls_mem", label="(8n/3r/4t)", y=2730.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_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               4.739686E+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    0.039    0.057   91.765   91.767
 qs_energies                          1  2.0    0.000    0.000   91.014   91.019
 ls_scf                               1  3.0    0.000    0.000   89.071   89.076
 dbcsr_multiply_generic             111  6.7    0.018    0.019   70.666   70.834
 ls_scf_main                          1  4.0    0.000    0.000   56.437   56.438
 multiply_cannon                    111  7.7    0.088    0.153   52.405   55.932
 multiply_cannon_loop               111  8.7    0.089    0.096   49.851   51.330
 density_matrix_trs4                  2  5.0    0.002    0.003   49.446   49.506
 ls_scf_init_scf                      1  4.0    0.000    0.000   29.233   29.234
 mp_waitall_1                      5436 11.0   24.311   28.601   24.311   28.601
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   27.981   28.011
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   25.884   25.897
 multiply_cannon_multrec            444  9.7   13.654   16.087   20.830   22.998
 multiply_cannon_metrocomm1         444  9.7    0.002    0.002   10.537   15.412
 multiply_cannon_metrocomm3         444  9.7    0.001    0.002    6.281   14.606
 make_m2s                           222  7.7    0.005    0.005   13.585   14.498
 make_images                        222  8.7    2.042    2.476   13.518   14.430
 hybrid_alltoall_any                227 10.6    0.804    3.853    8.109    9.694
 make_images_data                   222  9.7    0.003    0.004    8.312    9.595
 multiply_cannon_sync_h2d           444  9.7    6.686    8.082    6.686    8.082
 dbcsr_mm_accdrv_process           3003 10.4    0.351    0.397    6.872    7.987
 dbcsr_mm_accdrv_process_sort      3003 11.4    6.509    7.592    6.509    7.592
 arnoldi_extremal                     4  6.8    0.000    0.000    5.844    5.859
 arnoldi_normal_ev                    4  7.8    0.002    0.005    5.843    5.859
 build_subspace                      16  8.4    0.015    0.020    5.449    5.456
 mp_sum_l                           887  5.1    2.676    4.690    2.676    4.690
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.467    4.677
 dbcsr_matrix_vector_mult           304  9.0    0.011    0.021    4.191    4.403
 dbcsr_matrix_vector_mult_local     304 10.0    3.711    4.177    3.713    4.179
 multiply_cannon_metrocomm4         333  9.7    0.001    0.002    1.561    3.944
 mp_irecv_dv                       1241 11.2    1.547    3.919    1.547    3.919
 calculate_norms                    792  9.8    3.620    3.769    3.620    3.769
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    1.876    3.706
 mp_allgather_i34                   111  8.7    1.130    3.611    1.130    3.611
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    3.528    3.599
 ls_scf_post                          1  4.0    0.000    0.000    3.401    3.406
 make_images_sizes                  222  9.7    0.000    0.000    0.888    3.315
 mp_alltoall_i44                    222 10.7    0.887    3.315    0.887    3.315
 ls_scf_store_result                  1  5.0    0.000    0.000    3.199    3.228
 dbcsr_finalize                     304  7.8    0.062    0.077    2.195    2.286
 dbcsr_data_new                    4608  9.7    1.786    2.196    1.786    2.196
 dbcsr_merge_all                    275  8.9    0.478    0.523    2.053    2.127
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.044    2.045
 rebuild_ks_matrix                    3  7.3    0.000    0.000    2.011    2.011
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.002    2.011    2.011
 qs_energies_init_hamiltonians        1  3.0    0.000    0.001    1.927    1.927
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="508", plot="h2o_32_nrep3_ls", label="(8n/2r/6t)", y=91.767000, yerr=0.000000
PlotPoint: name="509", plot="h2o_32_nrep3_ls_mem", label="(8n/2r/6t)", y=3771.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_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               8.802087E+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    0.114    0.135  106.804  106.805
 qs_energies                          1  2.0    0.000    0.000  105.297  105.306
 ls_scf                               1  3.0    0.000    0.000  102.349  102.359
 dbcsr_multiply_generic             111  6.7    0.024    0.028   76.099   76.237
 ls_scf_main                          1  4.0    0.000    0.000   63.636   63.637
 density_matrix_trs4                  2  5.0    0.002    0.003   54.699   54.756
 multiply_cannon                    111  7.7    0.202    0.320   49.665   51.670
 multiply_cannon_loop               111  8.7    0.100    0.119   46.683   47.434
 ls_scf_init_scf                      1  4.0    0.000    0.000   34.931   34.932
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   33.419   33.444
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   30.717   30.725
 mp_waitall_1                      4527 11.1   21.828   25.284   21.828   25.284
 make_m2s                           222  7.7    0.005    0.005   22.765   23.834
 make_images                        222  8.7    3.576    3.870   22.657   23.726
 multiply_cannon_multrec            444  9.7   17.842   18.533   22.556   23.256
 hybrid_alltoall_any                227 10.6    1.654    3.605   12.824   15.855
 make_images_data                   222  9.7    0.003    0.004   13.129   15.234
 multiply_cannon_metrocomm3         444  9.7    0.001    0.001   10.105   11.921
 multiply_cannon_sync_h2d           444  9.7    8.789    8.846    8.789    8.846
 arnoldi_extremal                     4  6.8    0.000    0.000    7.377    7.386
 arnoldi_normal_ev                    4  7.8    0.003    0.009    7.377    7.386
 build_subspace                      16  8.4    0.026    0.036    6.833    6.847
 dbcsr_matrix_vector_mult           304  9.0    0.017    0.034    5.487    5.632
 dbcsr_matrix_vector_mult_local     304 10.0    5.080    5.379    5.083    5.381
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    5.084    5.175
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.849    5.086
 dbcsr_mm_accdrv_process           1814 10.4    0.311    0.360    4.526    4.667
 dbcsr_mm_accdrv_process_sort      1814 11.4    4.191    4.321    4.191    4.321
 ls_scf_post                          1  4.0    0.000    0.000    3.782    3.792
 make_images_sizes                  222  9.7    0.000    0.000    1.485    3.711
 mp_alltoall_i44                    222 10.7    1.485    3.711    1.485    3.711
 ls_scf_store_result                  1  5.0    0.000    0.000    3.506    3.544
 mp_allgather_i34                   111  8.7    1.077    3.462    1.077    3.462
 calculate_norms                    792  9.8    3.229    3.268    3.229    3.268
 dbcsr_finalize                     304  7.8    0.082    0.089    3.073    3.165
 dbcsr_merge_all                    275  8.9    0.888    0.919    2.858    2.941
 qs_energies_init_hamiltonians        1  3.0    0.001    0.001    2.917    2.917
 dbcsr_complete_redistribute          5  7.6    1.434    1.478    2.735    2.848
 dbcsr_sort_data                    325 11.1    2.439    2.500    2.439    2.500
 matrix_ls_to_qs                      2  6.0    0.000    0.000    2.387    2.496
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.417    2.419
 rebuild_ks_matrix                    3  7.3    0.000    0.000    2.346    2.348
 qs_ks_build_kohn_sham_matrix         3  8.3    0.002    0.002    2.346    2.348
 dbcsr_data_new                    6591  9.6    1.791    2.298    1.791    2.298
 dbcsr_new_transposed                 4  7.5    0.241    0.252    2.274    2.284
 dbcsr_frobenius_norm                74  6.6    2.054    2.135    2.212    2.247
 dbcsr_add_d                        103  6.2    0.000    0.000    2.127    2.205
 dbcsr_add_anytype                  103  7.2    0.859    0.891    2.126    2.205
 dbcsr_data_release               12724 10.6    1.983    2.176    1.983    2.176
 compute_matrix_preconditioner        1  6.0    0.002    0.002    2.157    2.162
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="510", plot="h2o_32_nrep3_ls", label="(8n/1r/12t)", y=106.805000, yerr=0.000000
PlotPoint: name="511", plot="h2o_32_nrep3_ls_mem", label="(8n/1r/12t)", y=6985.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/992aa927d070b294a3f7bcdbda4f1ad818fbb7c6_performance_tests/27/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32        7009386627072       0.0%      0.0%    100.0%
 flops     9 x     9 x    32        7335108845568       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        9866241589248       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        9884108906496       0.0%      0.0%    100.0%
 flops    22 x    22 x    32       13354440523776       0.0%      0.0%    100.0%
 flops    32 x    32 x     9       20607185977344       0.0%      0.0%    100.0%
 flops    32 x    32 x    22       25186560638976       0.0%      0.0%    100.0%
 flops     9 x    32 x    32       28458319085568       0.0%      0.0%    100.0%
 flops    22 x    32 x    32       34782389993472       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       42881542373376       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       55680402235392       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       55680402235392       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       72328573419520       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                       383.054662E+12       0.0%      0.0%    100.0%
 flops max/rank                    733.641090E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                        26899403712       0.0%      0.0%    100.0%
 number of processed stacks             118860288       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     226.3
 marketing flops                   780.439111E+12
 -------------------------------------------------------------------------------
 # multiplications                           1445
 max memory usage/rank             588.648448E+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                4802993.
 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    0.025    0.058  227.299  227.303
 qs_mol_dyn_low                       1  2.0    0.005    0.023  226.259  226.280
 qs_forces                            5  3.8    0.006    0.056  226.129  226.135
 qs_energies                          5  4.8    0.003    0.021  223.169  223.210
 scf_env_do_scf                       5  5.8    0.000    0.002  209.220  209.225
 scf_env_do_scf_inner_loop          105  6.6    0.002    0.006  183.057  183.059
 qs_scf_new_mos                     105  7.6    0.000    0.001  143.565  143.740
 qs_scf_loop_do_ot                  105  8.6    0.001    0.001  143.565  143.739
 ot_scf_mini                        105  9.6    0.003    0.004  133.691  133.802
 dbcsr_multiply_generic            1445 12.2    0.126    0.134  132.091  132.480
 multiply_cannon                   1445 13.2    0.274    0.286  113.357  115.528
 multiply_cannon_loop              1445 14.2    2.838    3.013  111.776  113.157
 velocity_verlet                      4  3.0    0.003    0.021  104.905  104.908
 ot_mini                            105 10.6    0.001    0.002   59.541   59.668
 qs_ot_get_p                        112 10.4    0.001    0.001   44.327   44.697
 multiply_cannon_multrec          69360 15.2   29.771   35.243   39.501   44.605
 mp_waitall_1                    488190 16.1   34.441   40.743   34.441   40.743
 qs_ot_get_derivative                55 11.6    0.001    0.001   37.848   38.018
 qs_ot_p2m_diag                      40 11.0    0.020    0.031   33.377   33.462
 multiply_cannon_sync_h2d         69360 15.2   29.275   33.326   29.275   33.326
 multiply_cannon_metrocomm3       69360 15.2    0.202    0.215   25.441   32.538
 cp_dbcsr_syevd                      40 12.0    0.002    0.002   30.058   30.059
 rebuild_ks_matrix                  110  8.4    0.000    0.000   28.519   28.680
 qs_ks_build_kohn_sham_matrix       110  9.4    0.012    0.016   28.518   28.680
 qs_ks_update_qs_env                112  7.6    0.001    0.001   26.202   26.354
 init_scf_loop                        7  6.6    0.000    0.001   26.134   26.135
 cp_fm_syevd                         40 13.0    0.000    0.000   24.968   25.118
 apply_preconditioner_dbcsr          62 12.6    0.000    0.001   22.941   23.239
 apply_single                        62 13.6    0.000    0.000   22.941   23.239
 prepare_preconditioner               7  7.6    0.000    0.000   21.341   21.369
 make_preconditioner                  7  8.6    0.000    0.000   21.341   21.369
 ot_new_cg_direction                 55 11.6    0.001    0.002   20.965   20.965
 cp_fm_redistribute_end              40 14.0   10.149   20.258   10.154   20.259
 cp_fm_syevd_base                    40 14.0   10.096   20.205   10.096   20.205
 qs_rho_update_rho_low              110  7.6    0.001    0.002   16.669   17.067
 calculate_rho_elec                 110  8.6    0.030    0.032   16.669   17.066
 qs_ot_get_orbitals                 105 10.6    0.001    0.001   14.663   14.892
 make_full_inverse_cholesky           7  9.6    0.000    0.000   14.330   14.397
 qs_ot_get_derivative_taylor         37 12.8    0.001    0.001   13.540   13.651
 mp_sum_l                          4764 12.2   12.092   12.857   12.092   12.857
 calculate_dm_sparse                110  9.5    0.000    0.001   11.410   11.633
 pw_transfer                       1645 12.4    0.080    0.105   11.211   11.405
 density_rs2pw                      110  9.6    0.005    0.007   10.962   11.382
 init_scf_run                         5  5.8    0.000    0.001   11.279   11.281
 scf_env_initial_rho_setup            5  6.8    0.002    0.007   11.279   11.280
 fft_wrap_pw1pw2                   1425 13.5    0.012    0.015   11.072   11.265
 dbcsr_mm_accdrv_process         154766 15.8    6.132    6.335    9.598   10.399
 qs_ot_get_derivative_diag           18 12.0    0.000    0.001   10.232   10.307
 qs_vxc_create                      110 10.4    0.003    0.009   10.161   10.201
 cp_fm_cholesky_invert                7 10.6   10.072   10.079   10.072   10.079
 fft_wrap_pw1pw2_240                915 15.0    1.154    1.238    9.730    9.943
 check_diag                          80 13.5    8.594    8.886    9.423    9.575
 sum_up_and_integrate                60 10.3    0.028    0.036    8.421    8.431
 integrate_v_rspace                  60 11.3    0.002    0.006    8.393    8.404
 transfer_rs2pw                     445 10.6    0.007    0.009    7.793    8.224
 fft3d_pb                           915 16.0    2.397    2.575    7.916    8.099
 multiply_cannon_metrocomm1       69360 15.2    0.100    0.108    4.648    7.966
 acc_transpose_blocks             69360 15.2    0.356    0.372    6.973    7.679
 xc_rho_set_and_dset_create         110 12.4    0.077    0.099    7.186    7.431
 cp_dbcsr_sm_fm_multiply             15  9.3    0.001    0.003    6.928    6.945
 xc_vxc_pw_create                    60 11.3    0.039    0.050    6.774    6.813
 make_full_single_inverse             7  9.6    0.001    0.001    6.748    6.778
 make_m2s                          2890 13.2    0.079    0.087    6.166    6.762
 make_images                       2890 14.2    0.240    0.259    6.060    6.657
 cp_dbcsr_sm_fm_multiply_core        15 10.3    0.000    0.000    6.580    6.644
 calculate_first_density_matrix       1  7.0    0.000    0.002    6.503    6.516
 xc_pw_derive                       510 13.4    0.005    0.006    5.945    6.031
 mp_alltoall_z22v                  2340 17.7    4.905    5.224    4.905    5.224
 mp_waitany                        7680 13.5    4.477    4.968    4.477    4.968
 acc_transpose_blocks_kernels     69360 16.2    0.844    0.893    4.221    4.775
 multiply_cannon_metrocomm4       67915 15.2    0.186    0.205    2.014    4.705
 potential_pw2rs                     60 12.3    0.003    0.003    4.673    4.695
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="601", plot="h2o_512_md", label="(64n/12r/1t)", y=227.303000, yerr=0.000000
PlotPoint: name="602", plot="h2o_512_md_mem", label="(64n/12r/1t)", y=560.400000, yerr=2.059126
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


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

CommitSHA: 992aa927d070b294a3f7bcdbda4f1ad818fbb7c6
Summary: empty
Status: OK