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


Updating 219e4046e..dfa21c532
Fast-forward
 tools/toolchain/scripts/stage0/install_cmake.sh  | 6 +++---
 tools/toolchain/scripts/stage1/install_mpich.sh  | 4 ++--
 tools/toolchain/scripts/stage6/install_plumed.sh | 4 ++--
 3 files changed, 7 insertions(+), 7 deletions(-)
Current branch master is up to date.


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

 GIT Revision: dfa21c5323b1e001456cb941235f5fd980a7c8df


################# 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 2.6.2, ELPA 2022.11.001.rc2, LIBINT 2.6.0, LIBPEXSI 1.2.0,
#              LIBXC 6.0.0, LIBVORI 220621, LIBXSMM 1.17, PLUMED 2.8.0,
#              SIRIUS 7.3.2, 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.
#
# Author: Matthias Krack (15.12.2022)
#
# \
   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 ${PWD}/tools/toolchain/install/setup; \
   printf "done\n"; \
   echo "Check the output above for error messages and consistency!"; \
   echo "If everything is OK, you can build a CP2K production binary with"; \
   echo "   make -j ARCH=${this_file%.*} VERSION=${this_file##*.}"; \
   echo "Alternatively, you can add further checks, e.g. for regression testing, with"; \
   echo "   make -j ARCH=${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"; \
   return

# Set options
DO_CHECKS      := no
USE_ACC        := yes
USE_COSMA      := 2.6.2
USE_ELPA       := 2022.11.001.rc2
USE_LIBINT     := 2.6.0
USE_LIBPEXSI   := 1.2.0
USE_LIBVORI    := 220621
USE_LIBXC      := 6.0.0
USE_LIBXSMM    := 1.17
USE_PLUMED     := 2.8.0
#USE_QUIP       := 0.9.10
USE_SIRIUS     := 7.3.2
USE_SPGLIB     := 1.16.2
# Only needed for SIRIUS
LIBVDWXC_VER   := 0.4.0
SPFFT_VER      := 1.0.6
SPLA_VER       := 1.5.4
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_prefixed_scalapack.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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/01
 job id: 43668539
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/02
 job id: 43668541
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/03
 job id: 43668544
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/04
 job id: 43668545
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/05
 job id: 43668548
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/06
 job id: 43668549
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/07
 job id: 43668552
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/08
 job id: 43668556
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/09
 job id: 43668559
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/10
 job id: 43668562
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/11
 job id: 43668564
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/12
 job id: 43668566
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/13
 job id: 43668570
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/14
 job id: 43668573
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/15
 job id: 43668576
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/16
 job id: 43668578
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/17
 job id: 43668582
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/18
 job id: 43668583
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/19
 job id: 43668585
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/20
 job id: 43668588
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/21
 job id: 43668593
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/22
 job id: 43668599
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/23
 job id: 43668603
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/24
 job id: 43668612
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/25
 job id: 43668614
 --- 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/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/26
 job id: 43668617
 --- 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 ~~~~~~~

=== 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]"
=== END PLOTS (description) ===


============ RESULTS ============
 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_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          344                      9.
 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    0.023    0.036  135.266  135.267
 farming_run                          1  2.0  134.641  134.642  135.224  135.227
 -------------------------------------------------------------------------------


 @@@@@@@@@@ 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               1.456685E+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              228                1113141.
 MP_Allreduce          485                2282278.
 MP_Sync                27
 MP_Alltoall            38                9316958.
 MP_SendRecv           120                 384007.
 MP_ISendRecv           45                 235435.
 MP_Wait               191
 MP_comm_split           8
 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    0.011    0.029  116.302  116.302
 qs_energies                          1  2.0    0.000    0.000  116.096  116.098
 mp2_main                             1  3.0    0.000    0.000  113.996  113.998
 mp2_gpw_main                         1  4.0    0.019    0.024  112.931  112.933
 mp2_ri_gpw_compute_in                1  5.0    0.172    0.176   93.945   94.301
 mp2_ri_gpw_compute_in_loop           1  6.0    0.004    0.005   55.519   55.876
 mp2_eri_3c_integrate_gpw           272  7.0    0.154    0.174   41.838   47.085
 get_2c_integrals                     1  6.0    0.000    0.001   37.469   38.253
 integrate_v_rspace                 273  8.0    0.435    0.451   25.213   30.232
 pw_transfer                       6555 10.6    0.379    0.401   27.453   28.041
 fft_wrap_pw1pw2                   5465 11.4    0.044    0.046   26.094   26.670
 grid_integrate_task_list           273  9.0   21.018   26.525   21.018   26.525
 fft_wrap_pw1pw2_100               2178 12.4    1.202    1.434   23.657   24.236
 compute_2c_integrals                 1  7.0    0.003    0.005   19.646   19.647
 compute_2c_integrals_loop_lm         1  8.0    0.004    0.004   18.958   19.337
 mp2_eri_2c_integrate_gpw             1  9.0    2.380    2.448   18.954   19.333
 rpa_ri_compute_en                    1  5.0    0.001    0.001   18.878   19.154
 cp_fm_cholesky_decompose            12  8.2   17.791   18.646   17.791   18.646
 cholesky_decomp                      1  7.0    0.000    0.000   16.665   17.487
 fft3d_s                           5443 13.4   16.223   16.657   16.244   16.678
 ao_to_mo_and_store_B_mult_1        272  7.0   10.848   15.569   10.848   15.569
 calculate_wavefunction             272  8.0    5.398    5.564   12.540   13.102
 rpa_num_int                          1  6.0    0.001    0.013   10.584   10.593
 rpa_num_int_RPA_matrix_operati       8  7.0    0.012    0.014   10.525   10.556
 calc_mat_Q                           8  8.0    0.000    0.000    9.338    9.432
 contract_S_to_Q                      8  9.0    0.000    0.000    8.762    8.855
 calc_potential_gpw                 544  9.5    0.005    0.006    8.284    8.713
 mp2_eri_2c_integrate_gpw_pot_l     272 10.0    0.001    0.002    8.260    8.534
 parallel_gemm_fm                    14  9.1    0.000    0.000    8.345    8.436
 parallel_gemm_fm_cosma              14 10.1    8.345    8.436    8.345    8.436
 potential_pw2rs                    545 10.0    0.107    0.109    7.718    8.312
 create_integ_mat                     1  6.0    0.014    0.027    7.843    7.852
 collocate_single_gaussian          272 10.0    0.040    0.043    7.491    7.699
 array2fm                             1  7.0    0.000    0.000    6.716    7.196
 pw_scatter_s                      2720 13.7    4.430    4.594    4.430    4.594
 pw_gather_s                       2722 13.2    3.868    4.209    3.868    4.209
 array2fm_buffer_send                 1  8.0    2.955    3.090    2.955    3.090
 pw_poisson_solve                   545 10.5    1.126    1.167    2.188    2.442
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="10", plot="h2o_32_ri_rpa_mp2", label="RI-RPA (8n/2r/6t)", y=112.932910, yerr=0.000000
PlotPoint: name="11", plot="h2o_32_ri_rpa_mp2_mem", label="RI-RPA (8n/2r/6t)", y=2727.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_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          344                     10.
 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    0.037    0.052  397.788  397.790
 farming_run                          1  2.0  396.776  396.779  397.722  397.728
 -------------------------------------------------------------------------------


 @@@@@@@@@@ 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               1.226834E+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              703                 408373.
 MP_Allreduce         1821                  23730.
 MP_Sync                38
 MP_Alltoall            77               26656128.
 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    0.015    0.049  209.308  209.309
 qs_energies                          1  2.0    0.000    0.000  209.079  209.084
 scf_env_do_scf                       1  3.0    0.000    0.000  106.144  106.144
 qs_ks_update_qs_env                  5  5.0    0.000    0.000  105.092  105.098
 rebuild_ks_matrix                    4  6.0    0.000    0.000  105.091  105.097
 qs_ks_build_kohn_sham_matrix         4  7.0    0.059    0.065  105.091  105.097
 hfx_ks_matrix                        4  8.0    0.001    0.001  104.684  104.687
 integrate_four_center                4  9.0    0.144    0.460  104.683  104.686
 mp2_main                             1  3.0    0.002    0.013  102.629  102.635
 mp2_gpw_main                         1  4.0    0.050    0.111  101.621  101.630
 integrate_four_center_main           4 10.0    0.082    0.462   96.606   99.150
 integrate_four_center_bin          264 11.0   96.524   99.133   96.524   99.133
 init_scf_loop                        1  4.0    0.000    0.000   91.884   91.884
 mp2_ri_gpw_compute_in                1  5.0    0.078    0.141   74.780   75.859
 mp2_ri_gpw_compute_in_loop           1  6.0    0.002    0.013   54.436   55.540
 mp2_eri_3c_integrate_gpw            91  7.0    0.145    0.174   42.134   47.367
 integrate_v_rspace                  95  8.0    0.398    0.567   28.533   33.593
 pw_transfer                       2240 10.6    0.147    0.163   29.816   30.201
 fft_wrap_pw1pw2                   1868 11.4    0.018    0.020   28.852   29.227
 ao_to_mo_and_store_B_mult_1         91  7.0   10.620   29.179   10.620   29.179
 grid_integrate_task_list            95  9.0   23.798   29.055   23.798   29.055
 mp2_ri_gpw_compute_en                1  5.0    0.080    0.097   26.592   28.277
 fft_wrap_pw1pw2_100                730 12.4    1.232    1.323   26.574   26.953
 mp2_ri_gpw_compute_en_RI_loop        1  6.0    1.847    1.897   24.803   24.812
 get_2c_integrals                     1  6.0    0.008    0.066   20.230   20.290
 compute_2c_integrals                 1  7.0    0.010    0.016   19.190   19.223
 compute_2c_integrals_loop_lm         1  8.0    0.032    0.048   18.755   18.943
 mp2_eri_2c_integrate_gpw             1  9.0    1.763    1.872   18.723   18.932
 fft3d_s                           1823 13.4   18.390   18.684   18.404   18.697
 scf_env_do_scf_inner_loop            4  4.0    0.000    0.000   14.259   14.259
 calculate_wavefunction              91  8.0    2.029    2.076    9.745    9.984
 mp2_ri_gpw_compute_en_expansio     172  7.0    0.557    0.586    8.687    9.087
 potential_pw2rs                    186 10.0    0.033    0.034    8.614    9.038
 local_gemm                         172  8.0    8.130    8.514    8.130    8.514
 mp2_eri_2c_integrate_gpw_pot_l      91 10.0    0.001    0.001    8.151    8.390
 mp2_ri_gpw_compute_en_comm          22  7.0    0.499    0.514    7.883    8.154
 calc_potential_gpw                 182  9.5    0.002    0.002    7.862    8.112
 collocate_single_gaussian           91 10.0    0.017    0.020    7.820    8.047
 mp2_ri_gpw_compute_en_ener         172  7.0    6.341    6.435    6.341    6.435
 mp_sendrecv_dm3                   2068  8.0    5.922    6.183    5.922    6.183
 mp_sync                             38 10.4    2.693    5.646    2.693    5.646
 pw_gather_s                        912 13.2    4.928    5.246    4.928    5.246
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="20", plot="h2o_32_ri_rpa_mp2", label="RI-MP2 (8n/6r/2t)", y=101.622063, yerr=0.000000
PlotPoint: name="21", plot="h2o_32_ri_rpa_mp2_mem", label="RI-MP2 (8n/6r/2t)", y=1514.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_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             451.502080E+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                  62385.
 MP_Allreduce        10249                    271.
 MP_Sync               580
 MP_Alltoall          2083                 480111.
 MP_SendRecv         22610                   5520.
 MP_ISendRecv        22610                   5520.
 MP_Wait             37876
 MP_comm_split          50
 MP_ISend            20771                  42672.
 MP_IRecv            20771                  42672.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.014    0.040   54.700   54.701
 qs_mol_dyn_low                       1  2.0    0.003    0.003   54.472   54.481
 qs_forces                           11  3.9    0.002    0.002   54.407   54.408
 qs_energies                         11  4.9    0.001    0.001   52.909   52.919
 scf_env_do_scf                      11  5.9    0.000    0.001   46.831   46.831
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   44.433   44.434
 dbcsr_multiply_generic            2286 12.5    0.093    0.096   34.182   34.672
 qs_scf_new_mos                     108  7.5    0.000    0.001   33.363   33.634
 qs_scf_loop_do_ot                  108  8.5    0.000    0.001   33.363   33.634
 ot_scf_mini                        108  9.5    0.002    0.002   31.655   31.833
 velocity_verlet                     10  3.0    0.001    0.002   27.469   27.470
 multiply_cannon                   2286 13.5    0.183    0.192   25.901   27.464
 multiply_cannon_loop              2286 14.5    1.475    1.549   25.030   26.620
 ot_mini                            108 10.5    0.001    0.001   20.016   20.277
 qs_ot_get_derivative               108 11.5    0.001    0.001   16.993   17.198
 mp_waitall_1                    245248 16.5    8.868   14.743    8.868   14.743
 multiply_cannon_metrocomm3       54864 15.5    0.067    0.073    5.911   12.926
 multiply_cannon_multrec          54864 15.5    4.198    6.531    7.444   10.760
 rebuild_ks_matrix                  119  8.3    0.000    0.000    8.497    8.642
 qs_ks_build_kohn_sham_matrix       119  9.3    0.010    0.011    8.497    8.642
 qs_ks_update_qs_env                119  7.6    0.001    0.001    7.533    7.669
 mp_sum_l                          7207 12.9    5.775    7.507    5.775    7.507
 multiply_cannon_sync_h2d         54864 15.5    5.865    7.481    5.865    7.481
 qs_ot_get_p                        119 10.4    0.001    0.001    6.909    7.188
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    5.875    6.311
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    5.668    5.787
 sum_up_and_integrate               119 10.3    0.012    0.014    5.007    5.014
 integrate_v_rspace                 119 11.3    0.002    0.002    4.995    5.003
 init_scf_run                        11  5.9    0.000    0.001    4.819    4.819
 scf_env_initial_rho_setup           11  6.9    0.002    0.003    4.819    4.819
 qs_rho_update_rho_low              119  7.7    0.000    0.001    4.677    4.778
 calculate_rho_elec                 119  8.7    0.011    0.016    4.677    4.778
 dbcsr_mm_accdrv_process          76910 16.1    1.161    1.775    3.170    4.407
 qs_ot_p2m_diag                      50 11.0    0.004    0.006    3.826    3.862
 multiply_cannon_metrocomm1       54864 15.5    0.051    0.057    1.911    3.572
 rs_pw_transfer                     974 11.9    0.011    0.012    3.281    3.441
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.947    3.171
 apply_single                       119 13.6    0.000    0.000    2.947    3.171
 calculate_dm_sparse                119  9.5    0.000    0.000    2.937    3.088
 cp_dbcsr_syevd                      50 12.0    0.002    0.003    2.995    2.995
 density_rs2pw                      119  9.7    0.004    0.004    2.654    2.751
 ot_diis_step                       108 11.5    0.006    0.006    2.735    2.736
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    2.681    2.682
 cp_fm_redistribute_end              50 14.0    2.426    2.643    2.432    2.645
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    2.482    2.566
 cp_fm_diag_elpa_base                50 14.0    0.210    2.533    0.211    2.545
 jit_kernel_multiply                 13 15.8    1.947    2.541    1.947    2.541
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.495    2.498
 init_scf_loop                       11  6.9    0.000    0.000    2.371    2.371
 potential_pw2rs                    119 12.3    0.004    0.004    2.321    2.345
 make_m2s                          4572 13.5    0.056    0.058    2.211    2.276
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.267    2.269
 wfi_extrapolate                     11  7.9    0.001    0.001    2.261    2.261
 pw_transfer                       1439 11.6    0.051    0.057    2.172    2.256
 make_images                       4572 14.5    0.133    0.138    2.126    2.190
 fft_wrap_pw1pw2                   1201 12.6    0.006    0.007    2.097    2.184
 grid_integrate_task_list           119 12.3    2.019    2.138    2.019    2.138
 acc_transpose_blocks             54864 15.5    0.231    0.248    1.730    2.135
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.948    1.993
 fft3d_ps                          1201 14.6    0.363    0.468    1.877    1.957
 mp_sum_d                          4125 12.0    1.343    1.903    1.343    1.903
 mp_alltoall_d11v                  2130 13.8    1.668    1.861    1.668    1.861
 fft_wrap_pw1pw2_140                487 13.2    0.078    0.093    1.597    1.684
 mp_waitany                       12084 13.8    1.288    1.425    1.288    1.425
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.403    1.424
 grid_collocate_task_list           119  9.7    1.288    1.346    1.288    1.346
 prepare_preconditioner              11  7.9    0.000    0.000    1.188    1.220
 make_preconditioner                 11  8.9    0.000    0.000    1.188    1.220
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.125    1.168
 make_images_sizes                 4572 15.5    0.004    0.005    0.911    1.158
 mp_alltoall_i44                   4572 16.5    0.907    1.154    0.907    1.154
 dbcsr_dot_sd                      1205 11.9    0.047    0.057    0.744    1.112
 mp_alltoall_z22v                  1201 16.6    1.046    1.104    1.046    1.104
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="100", plot="h2o_64_md", label="(8n/12r/1t)", y=54.701000, yerr=0.000000
PlotPoint: name="101", plot="h2o_64_md_mem", label="(8n/12r/1t)", y=430.272727, yerr=1.052349
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_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             487.858176E+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                  62664.
 MP_Allreduce        10226                    305.
 MP_Sync               104
 MP_Alltoall          2060                1086286.
 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    0.045    0.061   41.583   41.584
 qs_mol_dyn_low                       1  2.0    0.003    0.003   41.265   41.272
 qs_forces                           11  3.9    0.002    0.004   40.314   40.315
 qs_energies                         11  4.9    0.001    0.006   38.583   38.587
 scf_env_do_scf                      11  5.9    0.000    0.001   33.224   33.224
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   30.461   30.461
 dbcsr_multiply_generic            2286 12.5    0.103    0.105   21.824   22.169
 qs_scf_new_mos                     108  7.5    0.001    0.001   20.854   21.104
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   20.854   21.103
 velocity_verlet                     10  3.0    0.001    0.002   20.090   20.109
 ot_scf_mini                        108  9.5    0.002    0.003   19.918   20.089
 multiply_cannon                   2286 13.5    0.209    0.218   16.445   18.182
 multiply_cannon_loop              2286 14.5    0.895    0.970   15.230   16.560
 ot_mini                            108 10.5    0.001    0.001   12.145   12.383
 mp_waitall_1                    200699 16.5    6.076   11.175    6.076   11.175
 qs_ot_get_derivative               108 11.5    0.001    0.001    9.639    9.812
 multiply_cannon_metrocomm3       27432 15.5    0.068    0.070    4.179    9.448
 multiply_cannon_multrec          27432 15.5    1.983    4.397    5.854    8.605
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.540    7.679
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.014    7.540    7.678
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.675    6.801
 dbcsr_mm_accdrv_process          47894 16.0    3.000    5.142    3.801    5.630
 qs_ot_get_p                        119 10.4    0.001    0.001    4.802    5.035
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    3.698    4.543
 sum_up_and_integrate               119 10.3    0.024    0.027    4.525    4.531
 integrate_v_rspace                 119 11.3    0.002    0.002    4.500    4.509
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    3.070    4.139
 apply_single                       119 13.6    0.000    0.000    3.070    4.139
 init_scf_run                        11  5.9    0.000    0.001    4.094    4.095
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    4.094    4.095
 mp_sum_l                          7207 12.9    2.148    4.036    2.148    4.036
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.958    3.985
 calculate_rho_elec                 119  8.7    0.021    0.024    3.957    3.984
 qs_ot_p2m_diag                      50 11.0    0.009    0.013    3.209    3.227
 rs_pw_transfer                     974 11.9    0.009    0.011    3.039    3.126
 make_m2s                          4572 13.5    0.054    0.056    2.783    2.997
 make_images                       4572 14.5    0.201    0.239    2.692    2.905
 multiply_cannon_sync_h2d         27432 15.5    2.197    2.832    2.197    2.832
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    2.760    2.760
 init_scf_loop                       11  6.9    0.000    0.000    2.738    2.739
 calculate_first_density_matrix       1  7.0    0.000    0.001    2.491    2.494
 ot_diis_step                       108 11.5    0.011    0.011    2.445    2.446
 density_rs2pw                      119  9.7    0.004    0.004    2.294    2.371
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    2.270    2.358
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    2.344    2.345
 cp_fm_redistribute_end              50 14.0    1.923    2.298    1.929    2.300
 potential_pw2rs                    119 12.3    0.006    0.006    2.252    2.275
 cp_fm_diag_elpa_base                50 14.0    0.355    2.179    0.368    2.230
 calculate_dm_sparse                119  9.5    0.001    0.001    2.102    2.179
 pw_transfer                       1439 11.6    0.063    0.066    1.987    2.019
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.945    1.947
 fft_wrap_pw1pw2                   1201 12.6    0.007    0.008    1.897    1.932
 grid_integrate_task_list           119 12.3    1.823    1.922    1.823    1.922
 prepare_preconditioner              11  7.9    0.000    0.000    1.749    1.782
 make_preconditioner                 11  8.9    0.000    0.000    1.749    1.782
 jit_kernel_multiply                  9 16.1    0.750    1.769    0.750    1.769
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.709    1.750
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.642    1.701
 make_images_data                  4572 15.5    0.045    0.051    1.229    1.658
 fft3d_ps                          1201 14.6    0.504    0.559    1.606    1.636
 hybrid_alltoall_any               4725 16.4    0.051    0.111    1.066    1.580
 wfi_extrapolate                     11  7.9    0.001    0.001    1.544    1.544
 acc_transpose_blocks             27432 15.5    0.107    0.112    1.203    1.516
 fft_wrap_pw1pw2_140                487 13.2    0.075    0.082    1.413    1.453
 mp_alltoall_d11v                  2130 13.8    1.344    1.449    1.344    1.449
 mp_allgather_i34                  2286 14.5    0.657    1.424    0.657    1.424
 grid_collocate_task_list           119  9.7    1.240    1.306    1.240    1.306
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.282    1.289
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.226    1.274
 mp_sum_d                          4125 12.0    0.635    1.094    0.635    1.094
 make_images_sizes                 4572 15.5    0.005    0.005    0.731    1.032
 mp_alltoall_i44                   4572 16.5    0.726    1.028    0.726    1.028
 mp_sum_dm                          438  4.9    0.959    1.005    0.959    1.005
 qs_energies_init_hamiltonians       11  5.9    0.000    0.002    0.951    0.953
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.925    0.938
 rs_pw_transfer_PW2RS_50            119 14.3    0.585    0.605    0.858    0.938
 md_write_output                     11  3.9    0.020    0.921    0.021    0.935
 update_particle_set                 20  4.0    0.000    0.000    0.913    0.934
 md_output                           10  3.0    0.000    0.000    0.022    0.933
 mp_alltoall_z22v                  1201 16.6    0.833    0.907    0.833    0.907
 acc_transpose_blocks_kernels     27432 16.5    0.181    0.271    0.677    0.902
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="102", plot="h2o_64_md", label="(8n/6r/2t)", y=41.584000, yerr=0.000000
PlotPoint: name="103", plot="h2o_64_md_mem", label="(8n/6r/2t)", y=464.818182, yerr=1.402477
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/05/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                     59.051995E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               3143552       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      46.8
 marketing flops                     2.107587E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             521.666560E+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             3672                  62660.
 MP_Allreduce        10225                    303.
 MP_Sync               104
 MP_Alltoall          1821                1607811.
 MP_SendRecv         11067                  57667.
 MP_ISendRecv        11067                  57667.
 MP_Wait             21987
 MP_comm_split          50
 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    0.085    0.191   35.718   35.720
 qs_mol_dyn_low                       1  2.0    0.004    0.004   35.201   35.208
 qs_forces                           11  3.9    0.003    0.004   34.152   34.155
 qs_energies                         11  4.9    0.003    0.008   32.554   32.559
 scf_env_do_scf                      11  5.9    0.001    0.002   27.443   27.444
 scf_env_do_scf_inner_loop          108  6.5    0.006    0.013   24.628   24.630
 dbcsr_multiply_generic            2286 12.5    0.096    0.100   17.360   17.464
 velocity_verlet                     10  3.0    0.001    0.002   17.265   17.297
 qs_scf_new_mos                     108  7.5    0.001    0.001   16.092   16.118
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   16.092   16.118
 ot_scf_mini                        108  9.5    0.003    0.004   15.333   15.345
 multiply_cannon                   2286 13.5    0.197    0.202   13.504   14.184
 multiply_cannon_loop              2286 14.5    0.634    0.664   12.583   13.270
 ot_mini                            108 10.5    0.001    0.001    9.415    9.432
 qs_ot_get_derivative               108 11.5    0.001    0.001    7.855    7.868
 multiply_cannon_multrec          18288 15.5    1.969    2.932    7.006    7.256
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.656    6.681
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.015    6.656    6.681
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.905    5.928
 dbcsr_mm_accdrv_process          38222 16.0    4.148    5.778    4.954    5.874
 sum_up_and_integrate               119 10.3    0.030    0.031    4.234    4.239
 integrate_v_rspace                 119 11.3    0.002    0.003    4.203    4.212
 mp_waitall_1                    158411 16.6    3.039    4.077    3.039    4.077
 init_scf_run                        11  5.9    0.000    0.001    3.802    3.802
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    3.802    3.802
 qs_ot_get_p                        119 10.4    0.001    0.001    3.654    3.681
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.986    3.605
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.523    3.531
 calculate_rho_elec                 119  8.7    0.030    0.031    3.523    3.531
 rs_pw_transfer                     974 11.9    0.009    0.009    2.684    2.819
 init_scf_loop                       11  6.9    0.002    0.005    2.780    2.784
 calculate_first_density_matrix       1  7.0    0.001    0.004    2.507    2.508
 multiply_cannon_metrocomm3       18288 15.5    0.045    0.045    1.546    2.457
 qs_ot_p2m_diag                      50 11.0    0.012    0.013    2.441    2.445
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.055    2.384
 apply_single                       119 13.6    0.000    0.000    2.055    2.384
 make_m2s                          4572 13.5    0.046    0.048    2.123    2.267
 density_rs2pw                      119  9.7    0.004    0.004    2.078    2.204
 make_images                       4572 14.5    0.192    0.202    2.035    2.179
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    2.156    2.157
 potential_pw2rs                    119 12.3    0.007    0.008    1.994    2.005
 calculate_dm_sparse                119  9.5    0.001    0.001    1.960    1.978
 prepare_preconditioner              11  7.9    0.000    0.000    1.934    1.936
 make_preconditioner                 11  8.9    0.001    0.002    1.934    1.936
 grid_integrate_task_list           119 12.3    1.802    1.907    1.802    1.907
 pw_transfer                       1439 11.6    0.064    0.066    1.864    1.875
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.866    1.869
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.775    1.860
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.849    1.852
 cp_fm_redistribute_end              50 14.0    1.387    1.836    1.389    1.838
 cp_fm_diag_elpa_base                50 14.0    0.429    1.743    0.445    1.789
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.777    1.786
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.773    1.784
 mp_sum_l                          7207 12.9    1.411    1.754    1.411    1.754
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.667    1.679
 multiply_cannon_sync_h2d         18288 15.5    1.379    1.614    1.379    1.614
 ot_diis_step                       108 11.5    0.011    0.011    1.528    1.529
 fft3d_ps                          1201 14.6    0.509    0.524    1.461    1.474
 jit_kernel_multiply                  7 16.1    0.755    1.387    0.755    1.387
 fft_wrap_pw1pw2_140                487 13.2    0.085    0.088    1.316    1.330
 acc_transpose_blocks             18288 15.5    0.075    0.077    1.281    1.312
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.300    1.305
 grid_collocate_task_list           119  9.7    1.205    1.285    1.205    1.285
 wfi_extrapolate                     11  7.9    0.001    0.001    1.244    1.244
 make_images_data                  4572 15.5    0.045    0.049    0.913    1.094
 mp_sum_dm                          438  4.9    1.026    1.061    1.026    1.061
 md_write_output                     11  3.9    0.032    1.019    0.034    1.032
 md_output                           10  3.0    0.000    0.000    0.035    1.030
 update_particle_set                 20  4.0    0.000    0.000    0.996    1.029
 qs_energies_init_hamiltonians       11  5.9    0.002    0.011    1.010    1.017
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.958    0.990
 hybrid_alltoall_any               4725 16.4    0.055    0.114    0.783    0.978
 mp_alltoall_d11v                  2130 13.8    0.856    0.974    0.856    0.974
 acc_transpose_blocks_kernels     18288 16.5    0.209    0.218    0.845    0.868
 cp_fm_cholesky_invert               11 10.9    0.833    0.838    0.833    0.838
 mp_alltoall_z22v                  1201 16.6    0.765    0.831    0.765    0.831
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.825    0.830
 mp_allgather_i34                  2286 14.5    0.381    0.773    0.381    0.773
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.650    0.736
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="104", plot="h2o_64_md", label="(8n/4r/3t)", y=35.720000, yerr=0.000000
PlotPoint: name="105", plot="h2o_64_md_mem", label="(8n/4r/3t)", y=496.363636, yerr=2.143605
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_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             553.512960E+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             3672                  62659.
 MP_Allreduce        10224                    344.
 MP_Sync               104
 MP_Alltoall          1582                2412273.
 MP_SendRecv          8211                  74133.
 MP_ISendRecv         8211                  74133.
 MP_Wait             16271
 MP_comm_split          50
 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    0.089    0.175   36.831   36.832
 qs_mol_dyn_low                       1  2.0    0.003    0.004   36.460   36.468
 qs_forces                           11  3.9    0.003    0.005   35.777   35.779
 qs_energies                         11  4.9    0.002    0.006   34.079   34.085
 scf_env_do_scf                      11  5.9    0.001    0.002   28.043   28.045
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   24.550   24.550
 dbcsr_multiply_generic            2286 12.5    0.112    0.128   19.304   19.456
 velocity_verlet                     10  3.0    0.002    0.002   18.328   18.355
 qs_scf_new_mos                     108  7.5    0.001    0.001   16.413   16.471
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   16.413   16.470
 multiply_cannon                   2286 13.5    0.232    0.272   15.462   16.087
 ot_scf_mini                        108  9.5    0.003    0.003   15.471   15.524
 multiply_cannon_loop              2286 14.5    0.935    0.962   14.480   14.987
 multiply_cannon_multrec          27432 15.5    2.344    3.078    9.274    9.763
 ot_mini                            108 10.5    0.001    0.001    9.546    9.612
 dbcsr_mm_accdrv_process          47916 15.9    5.948    7.671    6.837    8.070
 qs_ot_get_derivative               108 11.5    0.001    0.001    7.702    7.757
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.479    6.531
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.016    6.479    6.530
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.766    5.812
 init_scf_run                        11  5.9    0.000    0.001    4.648    4.649
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    4.648    4.648
 sum_up_and_integrate               119 10.3    0.035    0.038    3.765    3.772
 integrate_v_rspace                 119 11.3    0.002    0.002    3.730    3.738
 init_scf_loop                       11  6.9    0.001    0.005    3.473    3.473
 qs_ot_get_p                        119 10.4    0.001    0.001    3.299    3.378
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.276    3.307
 calculate_rho_elec                 119  8.7    0.040    0.046    3.275    3.307
 calculate_first_density_matrix       1  7.0    0.000    0.002    3.270    3.272
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.721    3.249
 mp_waitall_1                    137007 16.6    2.239    3.077    2.239    3.077
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.715    2.717
 jit_kernel_multiply                 10 16.1    0.829    2.659    0.829    2.659
 prepare_preconditioner              11  7.9    0.000    0.000    2.624    2.632
 make_preconditioner                 11  8.9    0.000    0.001    2.624    2.632
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.186    2.608
 apply_single                       119 13.6    0.000    0.000    2.186    2.608
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.543    2.562
 make_full_inverse_cholesky          11  9.9    0.000    0.000    2.232    2.554
 make_m2s                          4572 13.5    0.056    0.058    2.297    2.462
 make_images                       4572 14.5    0.273    0.335    2.188    2.352
 rs_pw_transfer                     974 11.9    0.008    0.009    2.062    2.199
 calculate_dm_sparse                119  9.5    0.000    0.001    2.098    2.144
 qs_ot_p2m_diag                      50 11.0    0.015    0.023    2.007    2.016
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.950    1.978
 grid_integrate_task_list           119 12.3    1.819    1.901    1.819    1.901
 density_rs2pw                      119  9.7    0.004    0.004    1.777    1.901
 ot_diis_step                       108 11.5    0.012    0.012    1.801    1.801
 pw_transfer                       1439 11.6    0.063    0.067    1.746    1.776
 mp_sum_l                          7207 12.9    1.153    1.732    1.153    1.732
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.656    1.689
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.688    1.688
 multiply_cannon_metrocomm3       27432 15.5    0.038    0.039    0.977    1.574
 potential_pw2rs                    119 12.3    0.008    0.009    1.556    1.559
 acc_transpose_blocks             27432 15.5    0.112    0.113    1.471    1.494
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.449    1.450
 cp_fm_redistribute_end              50 14.0    0.960    1.426    0.961    1.426
 cp_fm_diag_elpa_base                50 14.0    0.444    1.361    0.463    1.400
 fft_wrap_pw1pw2_140                487 13.2    0.084    0.092    1.336    1.370
 fft3d_ps                          1201 14.6    0.534    0.586    1.338    1.363
 wfi_extrapolate                     11  7.9    0.001    0.001    1.331    1.331
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.275    1.287
 grid_collocate_task_list           119  9.7    1.220    1.283    1.220    1.283
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    1.128    1.131
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.109    1.125
 cp_fm_upper_to_full                 72 13.5    0.799    1.107    0.799    1.107
 make_images_data                  4572 15.5    0.045    0.048    0.907    1.069
 multiply_cannon_sync_h2d         27432 15.5    0.994    1.067    0.994    1.067
 dbcsr_complete_redistribute        329 12.2    0.117    0.145    0.788    1.065
 hybrid_alltoall_any               4725 16.4    0.062    0.151    0.784    1.021
 multiply_cannon_metrocomm1       27432 15.5    0.033    0.034    0.315    0.884
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.792    0.872
 acc_transpose_blocks_kernels     27432 16.5    0.267    0.275    0.851    0.860
 mp_alltoall_d11v                  2130 13.8    0.756    0.847    0.756    0.847
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    0.563    0.832
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.805    0.810
 cp_fm_cholesky_invert               11 10.9    0.795    0.798    0.795    0.798
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="106", plot="h2o_64_md", label="(8n/3r/4t)", y=36.832000, yerr=0.000000
PlotPoint: name="107", plot="h2o_64_md_mem", label="(8n/3r/4t)", y=525.363636, yerr=3.674797
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_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             609.103872E+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             3672                  62658.
 MP_Allreduce        10224                    344.
 MP_Sync               104
 MP_Alltoall          1582                3682667.
 MP_SendRecv          5355                  94533.
 MP_ISendRecv         5355                  94533.
 MP_Wait             11335
 MP_comm_split          50
 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    0.012    0.033   28.506   28.506
 qs_mol_dyn_low                       1  2.0    0.003    0.003   28.160   28.168
 qs_forces                           11  3.9    0.002    0.002   28.096   28.099
 qs_energies                         11  4.9    0.001    0.001   26.417   26.421
 scf_env_do_scf                      11  5.9    0.000    0.001   21.285   21.285
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   18.780   18.781
 velocity_verlet                     10  3.0    0.009    0.011   14.164   14.167
 dbcsr_multiply_generic            2286 12.5    0.099    0.101   12.702   12.773
 qs_scf_new_mos                     108  7.5    0.001    0.001   11.220   11.246
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   11.219   11.245
 multiply_cannon                   2286 13.5    0.231    0.239   10.141   10.595
 ot_scf_mini                        108  9.5    0.002    0.002   10.536   10.563
 multiply_cannon_loop              2286 14.5    0.329    0.339    9.237    9.408
 multiply_cannon_multrec           9144 15.5    1.855    2.137    6.306    6.515
 ot_mini                            108 10.5    0.001    0.001    5.971    6.000
 rebuild_ks_matrix                  119  8.3    0.000    0.000    5.781    5.804
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    5.781    5.803
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.162    5.183
 qs_ot_get_derivative               108 11.5    0.001    0.001    4.678    4.704
 dbcsr_mm_accdrv_process          12550 15.8    3.306    4.074    4.351    4.423
 init_scf_run                        11  5.9    0.000    0.001    3.655    3.655
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.655    3.655
 sum_up_and_integrate               119 10.3    0.037    0.041    3.549    3.556
 integrate_v_rspace                 119 11.3    0.002    0.003    3.512    3.518
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.225    3.237
 calculate_rho_elec                 119  8.7    0.059    0.061    3.225    3.236
 qs_ot_get_p                        119 10.4    0.001    0.001    2.800    2.835
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.528    2.531
 init_scf_loop                       11  6.9    0.000    0.000    2.482    2.483
 make_m2s                          4572 13.5    0.036    0.037    1.767    1.928
 grid_integrate_task_list           119 12.3    1.844    1.918    1.844    1.918
 qs_ot_p2m_diag                      50 11.0    0.022    0.023    1.894    1.897
 jit_kernel_multiply                  9 15.8    1.007    1.891    1.007    1.891
 calculate_dm_sparse                119  9.5    0.000    0.000    1.853    1.871
 mp_waitall_1                    115863 16.7    1.436    1.842    1.436    1.842
 make_images                       4572 14.5    0.270    0.304    1.676    1.835
 prepare_preconditioner              11  7.9    0.000    0.000    1.762    1.766
 make_preconditioner                 11  8.9    0.000    0.000    1.762    1.766
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.759    1.761
 rs_pw_transfer                     974 11.9    0.008    0.008    1.657    1.747
 pw_transfer                       1439 11.6    0.064    0.066    1.723    1.731
 density_rs2pw                      119  9.7    0.003    0.004    1.618    1.715
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.695    1.696
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.652    1.680
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.632    1.641
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.606    1.614
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    1.585    1.598
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.408    1.409
 cp_fm_redistribute_end              50 14.0    0.704    1.389    0.704    1.390
 cp_fm_diag_elpa_base                50 14.0    0.640    1.318    0.684    1.375
 grid_collocate_task_list           119  9.7    1.271    1.364    1.271    1.364
 fft_wrap_pw1pw2_140                487 13.2    0.082    0.085    1.328    1.339
 potential_pw2rs                    119 12.3    0.010    0.010    1.332    1.336
 fft3d_ps                          1201 14.6    0.540    0.551    1.299    1.306
 ot_diis_step                       108 11.5    0.013    0.013    1.278    1.279
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.264    1.270
 qs_energies_init_hamiltonians       11  5.9    0.003    0.009    1.263    1.266
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.167    1.179
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    1.153    1.171
 apply_single                       119 13.6    0.000    0.000    1.152    1.171
 wfi_extrapolate                     11  7.9    0.001    0.001    1.076    1.076
 hybrid_alltoall_any               4725 16.4    0.062    0.175    0.811    1.055
 acc_transpose_blocks              9144 15.5    0.038    0.040    1.020    1.027
 make_images_data                  4572 15.5    0.039    0.042    0.825    1.015
 mp_alltoall_d11v                  2130 13.8    0.845    0.954    0.845    0.954
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.868    0.918
 cp_fm_cholesky_invert               11 10.9    0.880    0.882    0.880    0.882
 acc_transpose_blocks_kernels      9144 16.5    0.116    0.119    0.781    0.784
 multiply_cannon_sync_h2d          9144 15.5    0.711    0.782    0.711    0.782
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    0.708    0.769
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.743    0.745
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.719    0.729
 jit_kernel_transpose                 5 15.6    0.665    0.667    0.665    0.667
 mp_alltoall_z22v                  1201 16.6    0.633    0.665    0.633    0.665
 mp_allgather_i34                  2286 14.5    0.238    0.643    0.238    0.643
 multiply_cannon_metrocomm3        9144 15.5    0.019    0.019    0.299    0.605
 qs_create_task_list                 11  7.9    0.002    0.011    0.551    0.575
 generate_qs_task_list               11  8.9    0.190    0.212    0.550    0.574
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="108", plot="h2o_64_md", label="(8n/2r/6t)", y=28.506000, yerr=0.000000
PlotPoint: name="109", plot="h2o_64_md_mem", label="(8n/2r/6t)", y=576.181818, yerr=6.712515
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_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             760.201216E+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                  63729.
 MP_Allreduce        10074                    433.
 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    0.019    0.061   41.429   41.430
 qs_mol_dyn_low                       1  2.0    0.003    0.003   41.134   41.142
 qs_forces                           11  3.9    0.002    0.002   40.543   40.544
 qs_energies                         11  4.9    0.001    0.001   38.578   38.582
 scf_env_do_scf                      11  5.9    0.001    0.001   33.003   33.003
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.006   25.090   25.091
 velocity_verlet                     10  3.0    0.002    0.002   23.660   23.732
 dbcsr_multiply_generic            2286 12.5    0.101    0.101   17.647   17.897
 qs_scf_new_mos                     108  7.5    0.001    0.001   16.137   16.236
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   16.136   16.235
 ot_scf_mini                        108  9.5    0.002    0.002   15.038   15.136
 multiply_cannon                   2286 13.5    0.304    0.316   13.597   14.588
 multiply_cannon_loop              2286 14.5    0.342    0.348   12.318   13.273
 ot_mini                            108 10.5    0.001    0.001    9.010    9.129
 multiply_cannon_multrec           9144 15.5    3.386    4.716    8.516    8.652
 init_scf_loop                       11  6.9    0.000    0.000    7.886    7.889
 qs_ot_get_derivative               108 11.5    0.001    0.001    6.962    7.061
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.912    7.056
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.013    6.912    7.056
 prepare_preconditioner              11  7.9    0.000    0.000    6.958    6.971
 make_preconditioner                 11  8.9    0.000    0.000    6.958    6.971
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.510    6.848
 dbcsr_mm_accdrv_process          12550 15.8    4.136    5.627    5.007    6.393
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.220    6.349
 cp_fm_upper_to_full                 72 14.2    3.183    4.572    3.183    4.572
 sum_up_and_integrate               119 10.3    0.064    0.066    3.754    3.759
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.710    3.714
 calculate_rho_elec                 119  8.7    0.118    0.121    3.710    3.713
 integrate_v_rspace                 119 11.3    0.003    0.003    3.689    3.696
 init_scf_run                        11  5.9    0.000    0.001    3.546    3.547
 scf_env_initial_rho_setup           11  6.9    0.002    0.002    3.546    3.546
 mp_waitall_1                     94719 16.7    2.573    3.491    2.573    3.491
 qs_ot_get_p                        119 10.4    0.001    0.001    3.262    3.403
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.514    2.932
 dbcsr_complete_redistribute        329 12.2    0.286    0.291    1.999    2.805
 make_m2s                          4572 13.5    0.039    0.040    2.428    2.621
 make_images                       4572 14.5    0.352    0.380    2.306    2.498
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    1.686    2.497
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.194    2.470
 apply_single                       119 13.6    0.000    0.000    2.194    2.470
 mp_alltoall_i22                    627 13.8    1.419    2.269    1.419    2.269
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.443    2.245
 multiply_cannon_metrocomm3        9144 15.5    0.020    0.020    1.356    2.238
 calculate_dm_sparse                119  9.5    0.000    0.000    2.158    2.173
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.107    2.108
 pw_transfer                       1439 11.6    0.067    0.068    2.062    2.066
 ot_diis_step                       108 11.5    0.014    0.014    2.018    2.018
 grid_integrate_task_list           119 12.3    2.005    2.017    2.005    2.017
 qs_ot_p2m_diag                      50 11.0    0.043    0.044    1.971    1.973
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.966    1.970
 mp_sum_l                          7207 12.9    1.089    1.885    1.089    1.885
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.841    1.842
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.774    1.824
 density_rs2pw                      119  9.7    0.003    0.003    1.795    1.817
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    1.752    1.753
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.688    1.689
 fft_wrap_pw1pw2_140                487 13.2    0.087    0.089    1.626    1.632
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.572    1.618
 fft3d_ps                          1201 14.6    0.568    0.578    1.601    1.604
 cp_fm_cholesky_invert               11 10.9    1.547    1.550    1.547    1.550
 hybrid_alltoall_any               4725 16.4    0.086    0.147    1.242    1.524
 grid_collocate_task_list           119  9.7    1.447    1.465    1.447    1.465
 rs_pw_transfer                     974 11.9    0.009    0.009    1.434    1.457
 make_images_data                  4572 15.5    0.043    0.046    1.196    1.452
 jit_kernel_multiply                  8 15.4    0.844    1.399    0.844    1.399
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.398    1.399
 cp_fm_diag_elpa_base                50 14.0    1.255    1.305    1.397    1.397
 wfi_extrapolate                     11  7.9    0.001    0.001    1.378    1.378
 potential_pw2rs                    119 12.3    0.014    0.014    1.267    1.272
 mp_alltoall_d11v                  2130 13.8    1.220    1.230    1.220    1.230
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.211    1.216
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.165    1.185
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    1.090    1.105
 multiply_cannon_sync_h2d          9144 15.5    1.043    1.048    1.043    1.048
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.987    1.024
 qs_create_task_list                 11  7.9    0.001    0.001    0.942    0.953
 generate_qs_task_list               11  8.9    0.371    0.390    0.942    0.952
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.905    0.919
 mp_alltoall_z22v                  1201 16.6    0.897    0.918    0.897    0.918
 acc_transpose_blocks              9144 15.5    0.038    0.038    0.891    0.895
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="110", plot="h2o_64_md", label="(8n/1r/12t)", y=41.430000, yerr=0.000000
PlotPoint: name="111", plot="h2o_64_md_mem", label="(8n/1r/12t)", y=709.545455, yerr=15.698081
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_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             503.590912E+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             3521                  65372.
 MP_Allreduce         9840                    486.
 MP_Sync               100
 MP_Alltoall          1938                1383689.
 MP_SendRecv         20900                   9096.
 MP_ISendRecv        20900                   9096.
 MP_Wait             37268
 MP_comm_split          48
 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    0.017    0.029   85.921   85.922
 qs_mol_dyn_low                       1  2.0    0.003    0.003   85.622   85.632
 qs_forces                           11  3.9    0.002    0.003   85.525   85.526
 qs_energies                         11  4.9    0.001    0.001   82.643   82.660
 scf_env_do_scf                      11  5.9    0.000    0.001   73.609   73.612
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.006   67.458   67.458
 dbcsr_multiply_generic            2055 12.4    0.119    0.134   53.178   53.416
 qs_scf_new_mos                      99  7.5    0.000    0.001   49.832   49.943
 qs_scf_loop_do_ot                   99  8.5    0.000    0.001   49.831   49.942
 ot_scf_mini                         99  9.5    0.002    0.002   47.380   47.500
 velocity_verlet                     10  3.0    0.001    0.002   43.833   43.834
 multiply_cannon                   2055 13.4    0.180    0.190   42.858   43.768
 multiply_cannon_loop              2055 14.4    1.535    1.578   41.714   42.660
 ot_mini                             99 10.5    0.001    0.001   28.547   28.645
 qs_ot_get_derivative                99 11.5    0.001    0.001   21.575   21.683
 multiply_cannon_multrec          49320 15.4   12.081   12.910   17.084   17.895
 rebuild_ks_matrix                  110  8.3    0.000    0.001   14.934   15.108
 qs_ks_build_kohn_sham_matrix       110  9.3    0.011    0.012   14.934   15.108
 qs_ks_update_qs_env                110  7.6    0.001    0.001   13.144   13.296
 mp_waitall_1                    220248 16.4   12.217   13.273   12.217   13.273
 multiply_cannon_sync_h2d         49320 15.4    9.870   10.479    9.870   10.479
 qs_ot_get_p                        110 10.4    0.001    0.001   10.126   10.274
 multiply_cannon_metrocomm3       49320 15.4    0.079    0.083    7.035    8.258
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    7.380    7.919
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    7.192    7.783
 apply_single                       110 13.6    0.000    0.001    7.192    7.783
 sum_up_and_integrate               110 10.3    0.036    0.043    7.399    7.414
 integrate_v_rspace                 110 11.3    0.002    0.003    7.363    7.386
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    7.000    7.067
 init_scf_run                        11  5.9    0.000    0.001    6.962    6.963
 scf_env_initial_rho_setup           11  6.9    0.006    0.007    6.962    6.962
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.570    6.697
 calculate_rho_elec                 110  8.6    0.020    0.024    6.570    6.697
 ot_diis_step                        99 11.5    0.005    0.006    6.626    6.626
 qs_ot_p2m_diag                      48 11.0    0.012    0.019    6.543    6.570
 init_scf_loop                       11  6.9    0.000    0.000    6.119    6.119
 mp_sum_l                          6514 12.8    5.392    6.035    5.392    6.035
 cp_dbcsr_syevd                      48 12.0    0.002    0.003    5.515    5.516
 dbcsr_mm_accdrv_process          87628 16.1    2.059    2.160    4.883    5.180
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    4.927    4.929
 cp_fm_redistribute_end              48 14.0    4.296    4.894    4.300    4.896
 cp_fm_diag_elpa_base                48 14.0    0.589    4.735    0.593    4.764
 make_m2s                          4110 13.4    0.063    0.068    4.457    4.567
 make_images                       4110 14.4    0.178    0.191    4.359    4.473
 rs_pw_transfer                     902 11.9    0.011    0.013    4.170    4.473
 wfi_extrapolate                     11  7.9    0.001    0.001    4.166    4.166
 multiply_cannon_metrocomm1       49320 15.4    0.060    0.062    2.932    3.989
 calculate_dm_sparse                110  9.5    0.000    0.001    3.823    3.972
 density_rs2pw                      110  9.6    0.004    0.005    3.635    3.909
 prepare_preconditioner              11  7.9    0.000    0.000    3.877    3.892
 make_preconditioner                 11  8.9    0.000    0.000    3.876    3.892
 make_full_inverse_cholesky          11  9.9    0.000    0.000    3.636    3.692
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    3.646    3.650
 qs_ot_get_orbitals                  99 10.5    0.000    0.001    3.428    3.502
 grid_integrate_task_list           110 12.3    3.223    3.386    3.223    3.386
 pw_transfer                       1331 11.6    0.054    0.064    3.217    3.296
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    3.242    3.286
 fft_wrap_pw1pw2                   1111 12.6    0.007    0.008    3.129    3.210
 potential_pw2rs                    110 12.3    0.006    0.007    2.943    2.975
 mp_alltoall_d11v                  2046 13.8    2.331    2.767    2.331    2.767
 fft3d_ps                          1111 14.6    0.751    0.838    2.667    2.743
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.688    2.700
 fft_wrap_pw1pw2_140                451 13.1    0.168    0.190    2.497    2.576
 jit_kernel_multiply                 13 15.9    2.541    2.558    2.541    2.558
 acc_transpose_blocks             49320 15.4    0.225    0.234    2.195    2.258
 mp_sum_d                          3879 11.9    1.645    2.195    1.645    2.195
 grid_collocate_task_list           110  9.6    2.085    2.174    2.085    2.174
 cp_fm_cholesky_invert               11 10.9    2.149    2.155    2.149    2.155
 make_images_data                  4110 15.4    0.042    0.045    1.943    2.095
 mp_waitany                       14300 13.8    1.859    2.040    1.859    2.040
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.936    1.959
 hybrid_alltoall_any               4261 16.3    0.081    0.475    1.691    1.911
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="200", plot="h2o_128_md", label="(8n/12r/1t)", y=85.922000, yerr=0.000000
PlotPoint: name="201", plot="h2o_128_md_mem", label="(8n/12r/1t)", y=477.909091, yerr=3.058655
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_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             587.567104E+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             3521                  65587.
 MP_Allreduce         9839                    562.
 MP_Sync               100
 MP_Alltoall          1717                2244248.
 MP_SendRecv         10340                  26400.
 MP_ISendRecv        10340                  26400.
 MP_Wait             22352
 MP_comm_split          48
 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    0.075    0.110   71.721   71.724
 qs_mol_dyn_low                       1  2.0    0.011    0.065   71.233   71.241
 qs_forces                           11  3.9    0.003    0.004   70.974   70.975
 qs_energies                         11  4.9    0.012    0.046   67.550   67.555
 scf_env_do_scf                      11  5.9    0.001    0.001   58.740   58.743
 scf_env_do_scf_inner_loop           99  6.5    0.005    0.027   50.452   50.457
 dbcsr_multiply_generic            2055 12.4    0.115    0.120   38.433   38.750
 velocity_verlet                     10  3.0    0.013    0.021   37.327   37.330
 qs_scf_new_mos                      99  7.5    0.001    0.001   34.139   34.250
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   34.139   34.249
 multiply_cannon                   2055 13.4    0.223    0.247   31.250   32.858
 ot_scf_mini                         99  9.5    0.003    0.004   32.428   32.527
 multiply_cannon_loop              2055 14.4    0.923    0.949   29.886   30.981
 ot_mini                             99 10.5    0.001    0.001   18.827   18.936
 multiply_cannon_multrec          24660 15.4    7.533    9.227   13.780   15.316
 rebuild_ks_matrix                  110  8.3    0.000    0.001   13.959   14.098
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.014   13.958   14.098
 qs_ot_get_derivative                99 11.5    0.001    0.001   12.958   13.060
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.232   12.357
 mp_waitall_1                    176588 16.5    8.301   11.279    8.301   11.279
 multiply_cannon_metrocomm3       24660 15.4    0.070    0.071    5.454    8.468
 init_scf_loop                       11  6.9    0.001    0.003    8.248    8.271
 multiply_cannon_sync_h2d         24660 15.4    6.944    8.037    6.944    8.037
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    6.532    7.260
 apply_single                       110 13.6    0.000    0.001    6.532    7.260
 qs_ot_get_p                        110 10.4    0.001    0.001    6.914    7.046
 sum_up_and_integrate               110 10.3    0.053    0.059    6.842    6.866
 integrate_v_rspace                 110 11.3    0.002    0.003    6.789    6.813
 dbcsr_mm_accdrv_process          52282 16.1    4.673    5.339    6.089    6.413
 init_scf_run                        11  5.9    0.000    0.001    6.302    6.309
 scf_env_initial_rho_setup           11  6.9    0.001    0.003    6.301    6.309
 prepare_preconditioner              11  7.9    0.000    0.000    6.150    6.165
 make_preconditioner                 11  8.9    0.000    0.001    6.150    6.165
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.057    6.069
 calculate_rho_elec                 110  8.6    0.039    0.047    6.057    6.069
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.702    5.871
 ot_diis_step                        99 11.5    0.010    0.010    5.805    5.805
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    4.809    5.517
 make_m2s                          4110 13.4    0.059    0.062    4.527    4.971
 make_images                       4110 14.4    0.399    0.441    4.415    4.858
 qs_ot_p2m_diag                      48 11.0    0.029    0.044    4.810    4.832
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    4.343    4.344
 pw_transfer                       1331 11.6    0.066    0.071    3.574    3.737
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.711    3.714
 cp_fm_redistribute_end              48 14.0    2.771    3.678    2.773    3.678
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.009    3.467    3.630
 cp_fm_diag_elpa_base                48 14.0    0.866    3.520    0.900    3.610
 wfi_extrapolate                     11  7.9    0.001    0.001    3.542    3.542
 density_rs2pw                      110  9.6    0.004    0.004    3.308    3.505
 rs_pw_transfer                     902 11.9    0.012    0.013    3.283    3.446
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.364    3.430
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    3.310    3.311
 grid_integrate_task_list           110 12.3    3.143    3.301    3.143    3.301
 calculate_dm_sparse                110  9.5    0.001    0.001    3.074    3.113
 fft_wrap_pw1pw2_140                451 13.1    0.200    0.217    2.874    3.038
 make_images_data                  4110 15.4    0.047    0.051    2.535    3.009
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.950    2.998
 fft3d_ps                          1111 14.6    1.074    1.280    2.825    2.973
 cp_fm_cholesky_invert               11 10.9    2.924    2.932    2.924    2.932
 hybrid_alltoall_any               4261 16.3    0.102    0.444    2.221    2.902
 mp_sum_l                          6514 12.8    2.070    2.861    2.070    2.861
 potential_pw2rs                    110 12.3    0.008    0.008    2.680    2.716
 calculate_first_density_matrix       1  7.0    0.001    0.002    2.668    2.677
 grid_collocate_task_list           110  9.6    2.119    2.300    2.119    2.300
 mp_alltoall_d11v                  2046 13.8    1.960    2.232    1.960    2.232
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    2.050    2.072
 qs_energies_init_hamiltonians       11  5.9    0.001    0.004    1.917    1.920
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.892    1.905
 multiply_cannon_metrocomm4       22605 15.4    0.072    0.078    0.809    1.891
 mp_allgather_i34                  2055 14.4    0.691    1.765    0.691    1.765
 jit_kernel_multiply                  9 16.3    1.065    1.762    1.065    1.762
 mp_irecv_dv                      57340 16.2    0.686    1.681    0.686    1.681
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.597    1.609
 mp_alltoall_z22v                  1111 16.6    1.488    1.579    1.488    1.579
 dbcsr_complete_redistribute        325 12.2    0.240    0.296    1.269    1.543
 acc_transpose_blocks             24660 15.4    0.109    0.111    1.519    1.537
 cp_fm_cholesky_decompose            22 10.9    1.482    1.487    1.482    1.487
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.001    1.368    1.474
 mp_sum_d                          3879 11.9    1.055    1.469    1.055    1.469
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="202", plot="h2o_128_md", label="(8n/6r/2t)", y=71.724000, yerr=0.000000
PlotPoint: name="203", plot="h2o_128_md_mem", label="(8n/6r/2t)", y=555.454545, yerr=6.906698
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_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             660.434944E+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             3521                  65578.
 MP_Allreduce         9838                    559.
 MP_Sync               100
 MP_Alltoall          1496                4511006.
 MP_SendRecv          6820                  27424.
 MP_ISendRecv         6820                  27424.
 MP_Wait             25498
 MP_comm_split          48
 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    0.080    0.153   62.832   62.834
 qs_mol_dyn_low                       1  2.0    0.003    0.005   62.278   62.288
 qs_forces                           11  3.9    0.003    0.006   62.201   62.203
 qs_energies                         11  4.9    0.002    0.010   58.958   58.963
 scf_env_do_scf                      11  5.9    0.001    0.002   50.359   50.359
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.007   41.297   41.299
 velocity_verlet                     10  3.0    0.002    0.002   33.517   33.518
 dbcsr_multiply_generic            2055 12.4    0.110    0.117   29.047   29.358
 qs_scf_new_mos                      99  7.5    0.001    0.001   26.242   26.352
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   26.242   26.352
 ot_scf_mini                         99  9.5    0.003    0.004   24.974   25.100
 multiply_cannon                   2055 13.4    0.213    0.233   22.237   23.731
 multiply_cannon_loop              2055 14.4    0.616    0.634   20.962   21.978
 ot_mini                             99 10.5    0.001    0.001   14.022   14.156
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.541   12.665
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.016   12.540   12.664
 qs_ks_update_qs_env                110  7.6    0.001    0.001   11.076   11.187
 multiply_cannon_multrec          16440 15.4    3.959    5.289    9.728   10.964
 mp_waitall_1                    139946 16.5    7.310   10.352    7.310   10.352
 qs_ot_get_derivative                99 11.5    0.001    0.001    9.566    9.690
 init_scf_loop                       11  6.9    0.001    0.005    9.022    9.030
 multiply_cannon_metrocomm3       16440 15.4    0.044    0.045    4.293    7.280
 prepare_preconditioner              11  7.9    0.000    0.000    7.162    7.184
 make_preconditioner                 11  8.9    0.000    0.001    7.162    7.184
 make_full_inverse_cholesky          11  9.9    0.000    0.000    6.471    6.847
 sum_up_and_integrate               110 10.3    0.060    0.061    6.692    6.708
 integrate_v_rspace                 110 11.3    0.003    0.004    6.631    6.648
 qs_ot_get_p                        110 10.4    0.001    0.002    6.055    6.190
 init_scf_run                        11  5.9    0.000    0.001    6.106    6.107
 scf_env_initial_rho_setup           11  6.9    0.001    0.003    6.106    6.106
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.849    5.858
 calculate_rho_elec                 110  8.6    0.058    0.059    5.848    5.857
 dbcsr_mm_accdrv_process          34862 16.1    4.604    5.198    5.625    5.796
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.955    5.386
 apply_single                       110 13.6    0.000    0.000    4.955    5.386
 make_m2s                          4110 13.4    0.052    0.054    4.473    4.852
 make_images                       4110 14.4    0.392    0.510    4.355    4.734
 ot_diis_step                        99 11.5    0.011    0.011    4.411    4.412
 multiply_cannon_sync_h2d         16440 15.4    3.700    4.386    3.700    4.386
 qs_ot_p2m_diag                      48 11.0    0.042    0.044    4.270    4.281
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.890    3.890
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.260    3.880
 pw_transfer                       1331 11.6    0.065    0.072    3.420    3.447
 grid_integrate_task_list           110 12.3    3.191    3.395    3.191    3.395
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.313    3.341
 density_rs2pw                      110  9.6    0.004    0.005    3.079    3.310
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.302    3.306
 cp_fm_redistribute_end              48 14.0    2.061    3.273    2.064    3.273
 rs_pw_transfer                     902 11.9    0.011    0.011    3.005    3.253
 cp_fm_diag_elpa_base                48 14.0    1.141    3.103    1.202    3.213
 make_images_data                  4110 15.4    0.043    0.047    2.564    3.071
 wfi_extrapolate                     11  7.9    0.001    0.001    3.036    3.036
 calculate_first_density_matrix       1  7.0    0.001    0.005    2.970    2.972
 hybrid_alltoall_any               4261 16.3    0.105    0.372    2.267    2.930
 cp_fm_cholesky_invert               11 10.9    2.921    2.929    2.921    2.929
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.002    2.827    2.830
 fft_wrap_pw1pw2_140                451 13.1    0.209    0.214    2.748    2.783
 fft3d_ps                          1111 14.6    1.067    1.105    2.628    2.659
 calculate_dm_sparse                110  9.5    0.001    0.001    2.553    2.577
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.489    2.572
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.463    2.507
 potential_pw2rs                    110 12.3    0.010    0.011    2.462    2.480
 mp_sum_l                          6514 12.8    1.773    2.444    1.773    2.444
 mp_alltoall_d11v                  2046 13.8    1.987    2.419    1.987    2.419
 multiply_cannon_metrocomm4       14385 15.4    0.045    0.048    0.865    2.410
 grid_collocate_task_list           110  9.6    2.178    2.405    2.178    2.405
 mp_irecv_dv                      48980 15.7    0.795    2.285    0.795    2.285
 dbcsr_complete_redistribute        325 12.2    0.322    0.350    1.566    2.037
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    2.019    2.021
 cp_fm_upper_to_full                 70 13.6    1.395    1.879    1.395    1.879
 mp_allgather_i34                  2055 14.4    0.600    1.735    0.600    1.735
 cp_fm_cholesky_decompose            22 10.9    1.703    1.730    1.703    1.730
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.671    1.686
 copy_fm_to_dbcsr                   174 11.2    0.001    0.002    1.073    1.538
 jit_kernel_multiply                  8 16.6    0.633    1.509    0.633    1.509
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.001    1.357    1.499
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.479    1.493
 mp_waitany                       17072 13.8    1.195    1.430    1.195    1.430
 mp_alltoall_z22v                  1111 16.6    1.347    1.378    1.347    1.378
 rs_gather_matrices                 110 12.3    0.138    0.150    0.924    1.370
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.322    1.336
 parallel_gemm_fm                    81  9.0    0.000    0.000    1.312    1.315
 parallel_gemm_fm_cosma              81 10.0    1.312    1.315    1.312    1.315
 make_basis_sm                       11  9.8    0.000    0.002    1.293    1.295
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="204", plot="h2o_128_md", label="(8n/4r/3t)", y=62.834000, yerr=0.000000
PlotPoint: name="205", plot="h2o_128_md_mem", label="(8n/4r/3t)", y=624.909091, yerr=8.229156
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_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             733.253632E+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             3521                  65576.
 MP_Allreduce         9838                    600.
 MP_Sync               100
 MP_Alltoall          1496                5863162.
 MP_SendRecv          5060                  43184.
 MP_ISendRecv         5060                  43184.
 MP_Wait             20042
 MP_comm_split          48
 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    0.044    0.075   70.528   70.530
 qs_mol_dyn_low                       1  2.0    0.003    0.004   70.190   70.199
 qs_forces                           11  3.9    0.016    0.037   70.103   70.104
 qs_energies                         11  4.9    0.005    0.008   66.618   66.634
 scf_env_do_scf                      11  5.9    0.001    0.002   57.908   57.911
 scf_env_do_scf_inner_loop           99  6.5    0.004    0.009   44.478   44.481
 velocity_verlet                     10  3.0    0.006    0.021   39.662   39.664
 dbcsr_multiply_generic            2055 12.4    0.123    0.133   30.971   31.294
 qs_scf_new_mos                      99  7.5    0.001    0.001   29.273   29.377
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   29.273   29.376
 ot_scf_mini                         99  9.5    0.004    0.006   27.583   27.694
 multiply_cannon                   2055 13.4    0.244    0.269   23.052   24.137
 multiply_cannon_loop              2055 14.4    0.883    0.909   21.270   22.013
 ot_mini                             99 10.5    0.001    0.001   15.325   15.444
 multiply_cannon_multrec          24660 15.4    4.217    6.865   12.620   13.738
 init_scf_loop                       11  6.9    0.003    0.004   13.376   13.384
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.541   12.632
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.016   12.540   12.632
 prepare_preconditioner              11  7.9    0.000    0.000   11.511   11.526
 make_preconditioner                 11  8.9    0.003    0.021   11.511   11.526
 qs_ks_update_qs_env                110  7.6    0.001    0.001   11.130   11.213
 make_full_inverse_cholesky          11  9.9    0.000    0.000    9.689   11.183
 qs_ot_get_derivative                99 11.5    0.001    0.001   11.055   11.165
 dbcsr_mm_accdrv_process          52304 16.0    6.848    8.443    8.258    9.202
 mp_waitall_1                    121746 16.5    5.156    7.319    5.156    7.319
 qs_ot_get_p                        110 10.4    0.001    0.001    7.056    7.204
 sum_up_and_integrate               110 10.3    0.067    0.071    6.785    6.797
 integrate_v_rspace                 110 11.3    0.002    0.003    6.717    6.731
 make_m2s                          4110 13.4    0.062    0.064    5.982    6.539
 make_images                       4110 14.4    0.576    0.696    5.838    6.391
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.970    5.980
 calculate_rho_elec                 110  8.6    0.077    0.080    5.970    5.980
 init_scf_run                        11  5.9    0.000    0.001    5.861    5.863
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    5.861    5.863
 qs_ot_p2m_diag                      48 11.0    0.055    0.064    4.891    4.904
 cp_fm_upper_to_full                 70 13.8    3.350    4.769    3.350    4.769
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    4.364    4.366
 ot_diis_step                        99 11.5    0.011    0.011    4.220    4.220
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.100    4.207
 apply_single                       110 13.6    0.000    0.000    4.100    4.206
 dbcsr_complete_redistribute        325 12.2    0.408    0.458    2.889    4.058
 cp_fm_cholesky_invert               11 10.9    3.698    3.712    3.698    3.712
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.649    3.652
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.546    3.602
 cp_fm_redistribute_end              48 14.0    1.820    3.595    1.823    3.598
 multiply_cannon_metrocomm3       24660 15.4    0.036    0.037    1.679    3.568
 cp_fm_diag_elpa_base                48 14.0    1.687    3.439    1.770    3.549
 pw_transfer                       1331 11.6    0.065    0.073    3.488    3.527
 make_images_data                  4110 15.4    0.047    0.051    2.980    3.522
 hybrid_alltoall_any               4261 16.3    0.120    0.458    2.581    3.453
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.382    3.435
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.382    3.424
 grid_integrate_task_list           110 12.3    3.273    3.405    3.273    3.405
 copy_fm_to_dbcsr                   174 11.2    0.001    0.002    2.250    3.404
 multiply_cannon_sync_h2d         24660 15.4    3.167    3.312    3.167    3.312
 density_rs2pw                      110  9.6    0.004    0.004    3.104    3.241
 wfi_extrapolate                     11  7.9    0.001    0.001    3.200    3.200
 rs_pw_transfer                     902 11.9    0.010    0.011    2.976    3.164
 calculate_dm_sparse                110  9.5    0.001    0.001    2.998    3.024
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.002    2.994    2.996
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.810    2.947
 mp_alltoall_i22                    605 13.7    1.720    2.925    1.720    2.925
 fft_wrap_pw1pw2_140                451 13.1    0.201    0.211    2.748    2.790
 fft3d_ps                          1111 14.6    1.065    1.096    2.688    2.719
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.552    2.582
 calculate_first_density_matrix       1  7.0    0.002    0.003    2.565    2.568
 potential_pw2rs                    110 12.3    0.012    0.013    2.515    2.529
 grid_collocate_task_list           110  9.6    2.220    2.447    2.220    2.447
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    2.305    2.320
 mp_alltoall_d11v                  2046 13.8    2.072    2.219    2.072    2.219
 cp_fm_cholesky_decompose            22 10.9    2.159    2.201    2.159    2.201
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.835    1.862
 mp_allgather_i34                  2055 14.4    0.886    1.800    0.886    1.800
 mp_sum_l                          6514 12.8    1.249    1.771    1.249    1.771
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.001    1.600    1.703
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.662    1.674
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.559    1.573
 acc_transpose_blocks             24660 15.4    0.106    0.108    1.505    1.530
 jit_kernel_multiply                  8 15.9    1.080    1.486    1.080    1.486
 mp_alltoall_z22v                  1111 16.6    1.407    1.476    1.407    1.476
 multiply_cannon_metrocomm4       20550 15.4    0.057    0.061    0.838    1.439
 mp_waitany                       13376 13.8    1.177    1.431    1.177    1.431
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="206", plot="h2o_128_md", label="(8n/3r/4t)", y=70.530000, yerr=0.000000
PlotPoint: name="207", plot="h2o_128_md_mem", label="(8n/3r/4t)", y=694.454545, yerr=10.210188
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_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             826.060800E+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             3521                  65574.
 MP_Allreduce         9838                    640.
 MP_Sync               100
 MP_Alltoall          1496                8504061.
 MP_SendRecv          3300                  54848.
 MP_ISendRecv         3300                  54848.
 MP_Wait             13926
 MP_comm_split          48
 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    0.043    0.070   57.091   57.092
 qs_mol_dyn_low                       1  2.0    0.003    0.003   56.705   56.714
 qs_forces                           11  3.9    0.002    0.002   56.354   56.356
 qs_energies                         11  4.9    0.001    0.001   52.738   52.744
 scf_env_do_scf                      11  5.9    0.000    0.001   44.223   44.224
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.006   36.055   36.056
 velocity_verlet                     10  3.0    0.029    0.059   31.822   31.839
 dbcsr_multiply_generic            2055 12.4    0.105    0.107   23.523   23.713
 qs_scf_new_mos                      99  7.5    0.001    0.001   21.522   21.561
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   21.522   21.561
 ot_scf_mini                         99  9.5    0.002    0.002   20.250   20.269
 multiply_cannon                   2055 13.4    0.247    0.270   17.701   19.216
 multiply_cannon_loop              2055 14.4    0.321    0.334   16.338   16.731
 rebuild_ks_matrix                  110  8.3    0.000    0.000   11.696   11.717
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.013   11.696   11.717
 ot_mini                             99 10.5    0.001    0.001   10.720   10.732
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.448   10.466
 multiply_cannon_multrec           8220 15.4    3.219    4.441    7.679    8.660
 init_scf_loop                       11  6.9    0.000    0.000    8.109    8.111
 mp_waitall_1                    103326 16.6    6.307    7.900    6.307    7.900
 qs_ot_get_derivative                99 11.5    0.001    0.001    6.943    6.959
 prepare_preconditioner              11  7.9    0.000    0.000    6.446    6.453
 make_preconditioner                 11  8.9    0.000    0.000    6.446    6.453
 sum_up_and_integrate               110 10.3    0.080    0.081    6.373    6.388
 integrate_v_rspace                 110 11.3    0.003    0.003    6.293    6.306
 make_full_inverse_cholesky          11  9.9    0.000    0.000    6.012    6.097
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.834    5.845
 calculate_rho_elec                 110  8.6    0.115    0.116    5.833    5.844
 qs_ot_get_p                        110 10.4    0.001    0.001    5.510    5.525
 init_scf_run                        11  5.9    0.000    0.001    5.383    5.383
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.383    5.383
 dbcsr_mm_accdrv_process          17442 15.9    2.966    3.896    4.330    5.254
 make_m2s                          4110 13.4    0.040    0.042    4.467    4.735
 make_images                       4110 14.4    0.637    0.690    4.334    4.603
 multiply_cannon_metrocomm3        8220 15.4    0.017    0.018    2.928    4.230
 qs_ot_p2m_diag                      48 11.0    0.081    0.084    4.044    4.050
 ot_diis_step                        99 11.5    0.012    0.012    3.754    3.755
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.715    3.716
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    3.664    3.702
 apply_single                       110 13.6    0.000    0.000    3.664    3.702
 grid_integrate_task_list           110 12.3    3.361    3.492    3.361    3.492
 pw_transfer                       1331 11.6    0.065    0.069    3.474    3.487
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.367    3.384
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.142    3.144
 cp_fm_cholesky_invert               11 10.9    3.110    3.114    3.110    3.114
 cp_fm_redistribute_end              48 14.0    0.804    3.104    0.809    3.106
 cp_fm_diag_elpa_base                48 14.0    2.106    2.898    2.285    3.057
 multiply_cannon_sync_h2d          8220 15.4    2.919    3.023    2.919    3.023
 make_images_data                  4110 15.4    0.039    0.044    2.542    2.996
 density_rs2pw                      110  9.6    0.004    0.004    2.849    2.952
 hybrid_alltoall_any               4261 16.3    0.200    0.865    2.419    2.925
 fft_wrap_pw1pw2_140                451 13.1    0.210    0.214    2.825    2.851
 wfi_extrapolate                     11  7.9    0.001    0.001    2.801    2.801
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.699    2.701
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    2.666    2.667
 calculate_dm_sparse                110  9.5    0.001    0.001    2.614    2.653
 fft3d_ps                          1111 14.6    1.126    1.165    2.627    2.641
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.494    2.495
 grid_collocate_task_list           110  9.6    2.327    2.493    2.327    2.493
 rs_pw_transfer                     902 11.9    0.010    0.010    2.329    2.467
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.320    2.332
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    2.097    2.107
 potential_pw2rs                    110 12.3    0.015    0.015    2.069    2.075
 mp_alltoall_d11v                  2046 13.8    1.809    2.018    1.809    2.018
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.769    1.997
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    1.937    1.950
 cp_fm_cholesky_decompose            22 10.9    1.864    1.887    1.864    1.887
 mp_allgather_i34                  2055 14.4    0.547    1.676    0.547    1.676
 dbcsr_complete_redistribute        325 12.2    0.554    0.584    1.532    1.632
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    1.507    1.626
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.583    1.586
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.547    1.562
 qs_create_task_list                 11  7.9    0.001    0.001    1.229    1.328
 generate_qs_task_list               11  8.9    0.379    0.447    1.229    1.327
 mp_alltoall_z22v                  1111 16.6    1.266    1.290    1.266    1.290
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.201    1.226
 mp_waitany                        9240 13.8    1.084    1.215    1.084    1.215
 jit_kernel_multiply                  6 15.7    1.057    1.206    1.057    1.206
 multiply_cannon_metrocomm1        8220 15.4    0.021    0.022    0.916    1.169
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="208", plot="h2o_128_md", label="(8n/2r/6t)", y=57.092000, yerr=0.000000
PlotPoint: name="209", plot="h2o_128_md_mem", label="(8n/2r/6t)", y=775.000000, yerr=11.249242
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_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               1.358004E+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                  67104.
 MP_Allreduce         9672                    819.
 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    0.020    0.040   85.469   85.469
 qs_mol_dyn_low                       1  2.0    0.003    0.003   84.964   84.972
 qs_forces                           11  3.9    0.002    0.003   84.678   84.679
 qs_energies                         11  4.9    0.001    0.001   80.620   80.624
 scf_env_do_scf                      11  5.9    0.001    0.001   70.729   70.730
 velocity_verlet                     10  3.0    0.003    0.003   54.833   54.866
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.006   42.450   42.451
 dbcsr_multiply_generic            2055 12.4    0.119    0.122   28.400   28.500
 init_scf_loop                       11  6.9    0.000    0.000   28.207   28.208
 prepare_preconditioner              11  7.9    0.000    0.000   26.269   26.277
 make_preconditioner                 11  8.9    0.000    0.000   26.269   26.277
 qs_scf_new_mos                      99  7.5    0.001    0.001   26.076   26.142
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   26.076   26.141
 make_full_inverse_cholesky          11  9.9    0.000    0.000   20.591   25.749
 ot_scf_mini                         99  9.5    0.002    0.002   24.302   24.359
 multiply_cannon                   2055 13.4    0.340    0.381   21.454   22.116
 multiply_cannon_loop              2055 14.4    0.340    0.342   19.667   19.978
 cp_fm_upper_to_full                 70 14.2   12.681   18.081   12.681   18.081
 ot_mini                             99 10.5    0.001    0.001   13.519   13.578
 rebuild_ks_matrix                  110  8.3    0.001    0.001   13.113   13.151
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.013   13.113   13.151
 qs_ks_update_qs_env                110  7.6    0.001    0.001   11.928   11.963
 dbcsr_complete_redistribute        325 12.2    1.022    1.047    7.252   10.503
 multiply_cannon_multrec           8220 15.4    4.379    4.597    9.513    9.650
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    6.233    9.483
 qs_ot_get_derivative                99 11.5    0.001    0.001    8.944    9.001
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    5.663    8.891
 mp_alltoall_i22                    605 13.7    5.291    8.523    5.291    8.523
 mp_waitall_1                     84994 16.7    7.541    8.449    7.541    8.449
 sum_up_and_integrate               110 10.3    0.151    0.152    6.647    6.663
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.478    6.517
 calculate_rho_elec                 110  8.6    0.227    0.227    6.477    6.516
 integrate_v_rspace                 110 11.3    0.003    0.004    6.496    6.512
 make_m2s                          4110 13.4    0.045    0.046    5.223    5.740
 init_scf_run                        11  5.9    0.000    0.001    5.669    5.669
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.669    5.669
 qs_ot_get_p                        110 10.4    0.001    0.001    5.601    5.669
 make_images                       4110 14.4    0.881    0.934    5.034    5.549
 cp_fm_cholesky_invert               11 10.9    5.365    5.369    5.365    5.369
 dbcsr_mm_accdrv_process          11614 15.7    3.268    3.629    4.993    5.246
 multiply_cannon_metrocomm3        8220 15.4    0.018    0.019    4.810    5.165
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.671    5.152
 apply_single                       110 13.6    0.000    0.000    4.671    5.152
 ot_diis_step                        99 11.5    0.015    0.015    4.550    4.550
 qs_ot_p2m_diag                      48 11.0    0.151    0.156    4.080    4.087
 multiply_cannon_sync_h2d          8220 15.4    3.953    3.959    3.953    3.959
 pw_transfer                       1331 11.6    0.074    0.075    3.781    3.788
 grid_integrate_task_list           110 12.3    3.654    3.710    3.654    3.710
 fft_wrap_pw1pw2                   1111 12.6    0.009    0.009    3.664    3.671
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.636    3.637
 qs_energies_init_hamiltonians       11  5.9    0.000    0.000    3.626    3.628
 hybrid_alltoall_any               4261 16.3    0.255    0.552    2.897    3.570
 make_images_data                  4110 15.4    0.042    0.045    2.838    3.506
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    2.854    3.288
 wfi_extrapolate                     11  7.9    0.001    0.001    3.233    3.233
 fft_wrap_pw1pw2_140                451 13.1    0.215    0.216    3.174    3.177
 calculate_dm_sparse                110  9.5    0.001    0.001    3.146    3.170
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.027    3.028
 cp_fm_diag_elpa_base                48 14.0    2.496    2.680    3.026    3.026
 density_rs2pw                      110  9.6    0.004    0.004    2.969    2.986
 fft3d_ps                          1111 14.6    1.267    1.275    2.875    2.881
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.862    2.866
 grid_collocate_task_list           110  9.6    2.624    2.649    2.624    2.649
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.391    2.425
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.356    2.371
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.330    2.331
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    2.166    2.225
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    2.093    2.174
 rs_pw_transfer                     902 11.9    0.010    0.011    2.136    2.172
 mp_alltoall_d11v                  2046 13.8    2.048    2.099    2.048    2.099
 potential_pw2rs                    110 12.3    0.021    0.021    2.087    2.089
 cp_fm_cholesky_decompose            22 10.9    2.044    2.065    2.044    2.065
 qs_create_task_list                 11  7.9    0.001    0.001    1.898    1.945
 generate_qs_task_list               11  8.9    0.737    0.792    1.897    1.943
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.789    1.793
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.744    1.780
 jit_kernel_multiply                 10 15.3    1.525    1.729    1.525    1.729
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="210", plot="h2o_128_md", label="(8n/1r/12t)", y=85.469000, yerr=0.000000
PlotPoint: name="211", plot="h2o_128_md_mem", label="(8n/1r/12t)", y=1216.818182, yerr=67.064173
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/15/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420242647040       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528903135232       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514766E+12       0.0%      0.0%    100.0%
 flops max/rank                      1.094965E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755941440       0.0%      0.0%    100.0%
 number of processed stacks              11950464       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     565.3
 marketing flops                   144.580175E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank             627.732480E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                10348896
 MPI messages size (bytes):
  total size                         4.491514E+12
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     434.009000E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               65736                        0
       128 < size <=     8192                1232                 10092544
      8192 < size <=    32768             3576680              95640223744
     32768 < size <=   131072             1294784              74079797248
    131072 < size <=  4194304             5148576            3175955383376
   4194304 < size <= 16777216              261888            1145794321408
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4093                  56650.
 MP_Allreduce        11273                    784.
 MP_Sync               170
 MP_Alltoall          2226                2529087.
 MP_SendRecv         24320                  18752.
 MP_ISendRecv        24320                  18752.
 MP_Wait             42476
 MP_comm_split          83
 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    0.017    0.033  204.136  204.138
 qs_mol_dyn_low                       1  2.0    0.003    0.006  203.744  203.761
 qs_forces                           11  3.9    0.003    0.003  203.653  203.654
 qs_energies                         11  4.9    0.001    0.001  198.138  198.154
 scf_env_do_scf                      11  5.9    0.001    0.001  181.047  181.051
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.008  160.188  160.189
 dbcsr_multiply_generic            2507 12.6    0.177    0.182  123.748  124.844
 velocity_verlet                     10  3.0    0.001    0.001  122.730  122.732
 qs_scf_new_mos                     117  7.6    0.001    0.001  121.298  121.549
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001  121.297  121.548
 ot_scf_mini                        117  9.6    0.003    0.003  114.711  114.939
 multiply_cannon                   2507 13.6    0.237    0.246  100.505  102.751
 multiply_cannon_loop              2507 14.6    2.090    2.156   98.278  100.654
 ot_mini                            117 10.6    0.001    0.001   65.539   65.792
 multiply_cannon_multrec          60168 15.6   33.176   35.485   41.430   43.627
 qs_ot_get_derivative               117 11.6    0.001    0.001   40.568   40.810
 rebuild_ks_matrix                  128  8.3    0.001    0.001   33.297   33.664
 qs_ks_build_kohn_sham_matrix       128  9.3    0.015    0.017   33.296   33.663
 mp_waitall_1                    267128 16.5   28.195   30.783   28.195   30.783
 qs_ks_update_qs_env                128  7.6    0.001    0.001   29.963   30.286
 multiply_cannon_sync_h2d         60168 15.6   27.389   29.253   27.389   29.253
 qs_ot_get_p                        128 10.4    0.001    0.001   27.326   27.531
 apply_preconditioner_dbcsr         128 12.6    0.000    0.001   24.253   25.270
 apply_single                       128 13.6    0.001    0.001   24.252   25.269
 ot_diis_step                       117 11.6    0.007    0.008   24.601   24.603
 qs_ot_p2m_diag                      83 11.4    0.077    0.091   20.694   20.808
 init_scf_loop                       11  6.9    0.000    0.000   20.781   20.782
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002   18.870   18.996
 cp_dbcsr_syevd                      83 12.4    0.004    0.005   18.141   18.142
 multiply_cannon_metrocomm3       60168 15.6    0.116    0.123   15.342   17.684
 prepare_preconditioner              11  7.9    0.000    0.000   16.203   16.244
 make_preconditioner                 11  8.9    0.000    0.000   16.202   16.244
 make_full_inverse_cholesky          11  9.9    0.000    0.000   15.417   15.603
 cp_fm_diag_elpa                     83 13.4    0.000    0.001   15.228   15.234
 cp_fm_redistribute_end              83 14.4   12.039   15.154   12.053   15.158
 cp_fm_diag_elpa_base                83 14.4    3.056   14.767    3.091   14.893
 make_m2s                          5014 13.6    0.107    0.116   14.043   14.450
 make_images                       5014 14.6    0.400    0.417   13.858   14.272
 sum_up_and_integrate               128 10.3    0.089    0.107   14.034   14.050
 integrate_v_rspace                 128 11.3    0.003    0.004   13.945   13.963
 qs_rho_update_rho_low              128  7.7    0.001    0.001   12.787   12.874
 calculate_rho_elec                 128  8.7    0.045    0.063   12.787   12.874
 init_scf_run                        11  5.9    0.000    0.001   12.813   12.814
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   12.813   12.814
 cp_fm_cholesky_invert               11 10.9    9.347    9.354    9.347    9.354
 mp_sum_l                          7870 13.0    7.940    9.230    7.940    9.230
 wfi_extrapolate                     11  7.9    0.001    0.001    9.086    9.086
 calculate_dm_sparse                128  9.5    0.001    0.001    8.397    8.526
 multiply_cannon_metrocomm1       60168 15.6    0.089    0.094    6.102    8.380
 dbcsr_mm_accdrv_process         124484 16.2    3.229    3.425    7.819    8.347
 make_images_data                  5014 15.6    0.066    0.071    6.924    7.922
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    7.735    7.921
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    7.755    7.840
 grid_integrate_task_list           128 12.3    7.105    7.519    7.105    7.519
 hybrid_alltoall_any               5200 16.5    0.290    2.264    6.046    7.435
 pw_transfer                       1547 11.6    0.075    0.108    6.896    7.161
 density_rs2pw                      128  9.7    0.006    0.007    6.552    7.097
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.013    6.692    6.932
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.003    6.719    6.727
 rs_pw_transfer                    1046 11.9    0.016    0.018    5.803    6.403
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.826    5.924
 fft_wrap_pw1pw2_140                523 13.2    0.446    0.509    5.736    5.920
 mp_alltoall_d11v                  2415 14.1    4.311    5.765    4.311    5.765
 fft3d_ps                          1291 14.7    2.093    2.571    5.485    5.674
 grid_collocate_task_list           128  9.7    4.727    5.086    4.727    5.086
 cp_fm_cholesky_decompose            22 10.9    4.645    4.660    4.645    4.660
 potential_pw2rs                    128 12.3    0.009    0.010    4.497    4.525
 mp_sum_d                          4464 12.2    3.737    4.388    3.737    4.388
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="400", plot="h2o_256_md", label="(8n/12r/1t)", y=204.138000, yerr=0.000000
PlotPoint: name="401", plot="h2o_256_md_mem", label="(8n/12r/1t)", y=594.272727, yerr=6.994685
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/16/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1410023282688       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1924145348608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1957871443968       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1963544850432       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2714615709696       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4377645416448       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5350455508992       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5395653328896       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6594687401984       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11444707676160       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15019188129792       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15019188129792       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19624853225472       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        92.796579E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.166472E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6705500928       0.0%      0.0%    100.0%
 number of processed stacks               5925696       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1131.6
 marketing flops                   143.508480E+12
 -------------------------------------------------------------------------------
 # multiplications                           2485
 max memory usage/rank             829.190144E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 2385600
 MPI messages size (bytes):
  total size                         4.069300E+12
  min size                           0.000000E+00
  max size                          17.653760E+06
  average size                       1.705776E+06
 MPI breakdown and total messages size (bytes):
             size <=      128               14916                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768               70188               2295595008
     32768 < size <=   131072              716032              54973693952
    131072 < size <=  4194304             1363760            1386318135296
   4194304 < size <= 16777216              153648            1453843137296
  16777216 < size                           67056            1171888537600
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4085                  57200.
 MP_Allreduce        11252                    947.
 MP_Sync               168
 MP_Alltoall          1955                5191665.
 MP_SendRecv         11938                  47072.
 MP_ISendRecv        11938                  47072.
 MP_Wait             25718
 MP_comm_split          82
 MP_ISend            11660                 212488.
 MP_IRecv            11660                 212488.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.035    0.053  194.652  194.654
 qs_mol_dyn_low                       1  2.0    0.004    0.009  194.022  194.034
 qs_forces                           11  3.9    0.013    0.079  193.898  193.916
 qs_energies                         11  4.9    0.002    0.007  187.000  187.016
 scf_env_do_scf                      11  5.9    0.001    0.002  170.445  170.455
 scf_env_do_scf_inner_loop          116  6.6    0.003    0.010  135.916  135.919
 velocity_verlet                     10  3.0    0.005    0.019  121.673  121.675
 dbcsr_multiply_generic            2485 12.5    0.186    0.191   97.790   98.941
 qs_scf_new_mos                     116  7.6    0.001    0.001   96.665   97.084
 qs_scf_loop_do_ot                  116  8.6    0.001    0.001   96.664   97.083
 ot_scf_mini                        116  9.6    0.004    0.005   91.878   92.346
 multiply_cannon                   2485 13.5    0.477    0.532   77.333   82.288
 multiply_cannon_loop              2485 14.5    1.241    1.278   73.893   76.139
 ot_mini                            116 10.6    0.001    0.002   50.057   50.475
 mp_waitall_1                    212858 16.6   24.677   37.948   24.677   37.948
 multiply_cannon_multrec          29820 15.5   22.124   27.100   31.693   36.923
 init_scf_loop                       11  6.9    0.001    0.005   34.432   34.438
 rebuild_ks_matrix                  127  8.3    0.001    0.001   33.250   33.623
 qs_ks_build_kohn_sham_matrix       127  9.3    0.017    0.021   33.250   33.622
 qs_ks_update_qs_env                127  7.6    0.001    0.001   29.915   30.254
 prepare_preconditioner              11  7.9    0.000    0.000   29.964   30.007
 make_preconditioner                 11  8.9    0.002    0.012   29.964   30.007
 make_full_inverse_cholesky          11  9.9    0.000    0.000   28.626   29.185
 qs_ot_get_derivative               116 11.6    0.001    0.002   28.270   28.733
 multiply_cannon_metrocomm3       29820 15.5    0.093    0.100   15.423   27.580
 qs_ot_get_p                        127 10.4    0.001    0.001   23.486   24.064
 apply_preconditioner_dbcsr         127 12.6    0.000    0.000   21.828   22.996
 apply_single                       127 13.6    0.001    0.001   21.828   22.996
 multiply_cannon_sync_h2d         29820 15.5   19.389   21.665   19.389   21.665
 ot_diis_step                       116 11.6    0.015    0.020   21.603   21.605
 qs_ot_p2m_diag                      82 11.4    0.185    0.213   18.556   18.595
 cp_fm_cholesky_invert               11 10.9   17.548   17.563   17.548   17.563
 cp_dbcsr_syevd                      82 12.4    0.005    0.005   17.364   17.367
 make_m2s                          4970 13.5    0.092    0.097   14.636   16.209
 make_images                       4970 14.5    1.145    1.331   14.425   15.998
 sum_up_and_integrate               127 10.3    0.115    0.133   14.729   14.768
 integrate_v_rspace                 127 11.3    0.003    0.003   14.613   14.658
 cp_fm_diag_elpa                     82 13.4    0.000    0.001   14.053   14.063
 cp_fm_redistribute_end              82 14.4    8.197   13.967    8.209   13.968
 cp_fm_diag_elpa_base                82 14.4    5.507   13.413    5.736   13.800
 qs_rho_update_rho_low              127  7.7    0.001    0.001   13.244   13.282
 calculate_rho_elec                 127  8.7    0.087    0.105   13.243   13.282
 init_scf_run                        11  5.9    0.000    0.001   11.676   11.677
 scf_env_initial_rho_setup           11  6.9    0.001    0.003   11.676   11.677
 qs_ot_get_derivative_diag           76 12.4    0.002    0.002   11.190   11.512
 make_images_data                  4970 15.5    0.064    0.070    8.717   10.471
 hybrid_alltoall_any               5155 16.4    0.340    1.505    7.389    9.948
 multiply_cannon_metrocomm4       27335 15.5    0.093    0.107    3.619    9.800
 dbcsr_mm_accdrv_process          61726 16.2    4.472    5.158    9.033    9.644
 mp_irecv_dv                      68888 16.3    3.430    9.424    3.430    9.424
 wfi_extrapolate                     11  7.9    0.001    0.001    8.451    8.451
 pw_transfer                       1535 11.6    0.085    0.104    7.940    8.010
 fft_wrap_pw1pw2                   1281 12.7    0.010    0.011    7.717    7.783
 cp_fm_cholesky_decompose            22 10.9    7.500    7.580    7.500    7.580
 density_rs2pw                      127  9.7    0.006    0.006    7.050    7.531
 grid_integrate_task_list           127 12.3    7.084    7.471    7.084    7.471
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    6.276    7.057
 fft_wrap_pw1pw2_140                519 13.2    0.464    0.508    6.622    6.700
 rs_pw_transfer                    1038 11.9    0.014    0.016    6.234    6.675
 calculate_dm_sparse                127  9.5    0.001    0.002    6.481    6.639
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.244    6.251
 fft3d_ps                          1281 14.7    2.755    2.927    6.104    6.155
 mp_sum_l                          7804 13.0    4.068    5.555    4.068    5.555
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.379    5.490
 qs_ot_get_orbitals                 116 10.6    0.001    0.001    5.360    5.415
 potential_pw2rs                    127 12.3    0.015    0.017    5.268    5.292
 grid_collocate_task_list           127  9.7    4.873    5.254    4.873    5.254
 mp_allgather_i34                  2485 14.5    2.022    5.161    2.022    5.161
 mp_alltoall_d11v                  2401 14.1    4.282    4.809    4.282    4.809
 dbcsr_complete_redistribute        393 12.7    0.769    0.843    3.253    4.152
 mp_sum_d                          4442 12.2    2.778    4.111    2.778    4.111
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="402", plot="h2o_256_md", label="(8n/6r/2t)", y=194.654000, yerr=0.000000
PlotPoint: name="403", plot="h2o_256_md_mem", label="(8n/6r/2t)", y=789.454545, yerr=2.310594
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/17/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420239992832       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528891191296       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514751E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.928533E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755938624       0.0%      0.0%    100.0%
 number of processed stacks               3984192       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1695.7
 marketing flops                   144.579337E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank             935.723008E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                 1042912
 MPI messages size (bytes):
  total size                         2.716210E+12
  min size                           0.000000E+00
  max size                          26.214400E+06
  average size                       2.604448E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 264                  8650752
     32768 < size <=   131072              281856              36943429632
    131072 < size <=  4194304              660064             996105256960
   4194304 < size <= 16777216               65632             931530938576
  16777216 < size                           28672             751619276800
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4075                  57335.
 MP_Allreduce        11226                    986.
 MP_Sync               170
 MP_Alltoall          1712                9388896.
 MP_SendRecv          7936                  75008.
 MP_ISendRecv         7936                  75008.
 MP_Wait             21820
 MP_comm_split          83
 MP_ISend            11748                 275205.
 MP_IRecv            11748                 275205.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.031    0.066  180.650  180.652
 qs_mol_dyn_low                       1  2.0    0.006    0.023  179.907  179.930
 qs_forces                           11  3.9    0.011    0.066  178.697  178.728
 qs_energies                         11  4.9    0.004    0.021  172.032  172.044
 scf_env_do_scf                      11  5.9    0.001    0.002  156.285  156.291
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.008  119.986  119.988
 velocity_verlet                     10  3.0    0.004    0.022  115.838  115.874
 dbcsr_multiply_generic            2507 12.6    0.183    0.191   82.397   83.471
 qs_scf_new_mos                     117  7.6    0.001    0.001   82.458   82.745
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   82.458   82.744
 ot_scf_mini                        117  9.6    0.004    0.005   78.300   78.661
 multiply_cannon                   2507 13.6    0.498    0.524   61.934   66.190
 multiply_cannon_loop              2507 14.6    0.853    0.882   58.609   61.240
 ot_mini                            117 10.6    0.001    0.001   43.105   43.488
 init_scf_loop                       11  6.9    0.001    0.003   36.189   36.195
 mp_waitall_1                    170520 16.6   25.401   34.874   25.401   34.874
 prepare_preconditioner              11  7.9    0.000    0.000   32.062   32.113
 make_preconditioner                 11  8.9    0.000    0.002   32.062   32.112
 rebuild_ks_matrix                  128  8.3    0.001    0.001   30.843   31.371
 qs_ks_build_kohn_sham_matrix       128  9.3    0.016    0.020   30.842   31.370
 make_full_inverse_cholesky          11  9.9    0.000    0.000   29.663   31.114
 qs_ks_update_qs_env                128  7.6    0.001    0.001   27.797   28.275
 multiply_cannon_multrec          20056 15.6   13.592   16.668   22.354   25.395
 multiply_cannon_metrocomm3       20056 15.6    0.060    0.064   14.933   24.559
 qs_ot_get_derivative               117 11.6    0.001    0.002   23.387   23.759
 qs_ot_get_p                        128 10.4    0.001    0.002   20.568   21.050
 apply_preconditioner_dbcsr         128 12.6    0.000    0.000   19.843   20.871
 apply_single                       128 13.6    0.001    0.001   19.843   20.871
 ot_diis_step                       117 11.6    0.018    0.027   19.616   19.617
 make_m2s                          5014 13.6    0.084    0.091   15.292   16.384
 make_images                       5014 14.6    1.186    1.287   15.055   16.149
 qs_ot_p2m_diag                      83 11.4    0.265    0.273   16.129   16.136
 multiply_cannon_sync_h2d         20056 15.6   14.250   15.931   14.250   15.931
 cp_fm_cholesky_invert               11 10.9   15.111   15.121   15.111   15.121
 cp_dbcsr_syevd                      83 12.4    0.005    0.005   15.099   15.100
 sum_up_and_integrate               128 10.3    0.132    0.149   14.671   14.707
 integrate_v_rspace                 128 11.3    0.003    0.004   14.539   14.575
 qs_rho_update_rho_low              128  7.7    0.001    0.001   13.503   13.544
 calculate_rho_elec                 128  8.7    0.132    0.146   13.503   13.544
 cp_fm_diag_elpa                     83 13.4    0.000    0.001   11.939   11.940
 cp_fm_redistribute_end              83 14.4    4.511   11.864    4.526   11.866
 cp_fm_diag_elpa_base                83 14.4    6.904   11.255    7.316   11.723
 make_images_data                  5014 15.6    0.060    0.068    9.461   11.029
 init_scf_run                        11  5.9    0.000    0.001   10.607   10.607
 scf_env_initial_rho_setup           11  6.9    0.001    0.004   10.607   10.607
 hybrid_alltoall_any               5200 16.5    0.427    1.967    8.211   10.143
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002    9.190    9.464
 multiply_cannon_metrocomm4       17549 15.6    0.062    0.070    3.421    9.078
 mp_irecv_dv                      50230 16.2    3.300    8.833    3.300    8.833
 pw_transfer                       1547 11.6    0.085    0.108    8.322    8.439
 dbcsr_mm_accdrv_process          41502 16.2    4.431    5.111    8.209    8.347
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.011    8.098    8.221
 cp_fm_cholesky_decompose            22 10.9    7.741    7.777    7.741    7.777
 grid_integrate_task_list           128 12.3    7.286    7.671    7.286    7.671
 wfi_extrapolate                     11  7.9    0.001    0.003    7.549    7.550
 cp_fm_upper_to_full                105 14.5    5.758    7.479    5.758    7.479
 density_rs2pw                      128  9.7    0.006    0.006    6.880    7.254
 fft_wrap_pw1pw2_140                523 13.2    0.477    0.537    7.045    7.175
 dbcsr_complete_redistribute        395 12.7    1.170    1.200    4.677    6.452
 fft3d_ps                          1291 14.7    2.696    2.892    6.367    6.436
 calculate_dm_sparse                128  9.5    0.001    0.002    5.796    5.896
 rs_pw_transfer                    1046 11.9    0.014    0.014    5.467    5.844
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.523    5.530
 grid_collocate_task_list           128  9.7    5.080    5.492    5.080    5.492
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    4.701    5.377
 copy_fm_to_dbcsr                   209 11.7    0.002    0.002    3.413    5.185
 mp_allgather_i34                  2507 14.6    1.850    5.098    1.850    5.098
 mp_alltoall_d11v                  2415 14.1    4.483    5.059    4.483    5.059
 potential_pw2rs                    128 12.3    0.020    0.022    4.967    4.994
 mp_sum_l                          7870 13.0    3.370    4.703    3.370    4.703
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.556    4.669
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    2.380    4.126
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    4.015    4.045
 mp_alltoall_i22                    716 14.1    1.985    3.945    1.985    3.945
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    3.808    3.809
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="404", plot="h2o_256_md", label="(8n/4r/3t)", y=180.652000, yerr=0.000000
PlotPoint: name="405", plot="h2o_256_md_mem", label="(8n/4r/3t)", y=888.181818, yerr=9.349946
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/18/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1430460020736       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1958505086976       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1986244964352       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1992000282624       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2753956716544       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4454954827776       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5444944789504       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5492290093056       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6712799002624       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11613089636352       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15239146475520       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15239146475520       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19911124992000       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        94.228663E+12       0.0%      0.0%    100.0%
 flops max/rank                      4.387043E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6806316384       0.0%      0.0%    100.0%
 number of processed stacks               6024576       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1129.8
 marketing flops                   145.647559E+12
 -------------------------------------------------------------------------------
 # multiplications                           2527
 max memory usage/rank               1.140462E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1152312
 MPI messages size (bytes):
  total size                         2.039354E+12
  min size                           0.000000E+00
  max size                          17.653760E+06
  average size                       1.769794E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                6996                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 396                  8650752
     32768 < size <=   131072              321600              36333158400
    131072 < size <=  4194304              721560             792041881600
   4194304 < size <= 16777216               70800             669921260160
  16777216 < size                           30960             541065216000
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4107                  56895.
 MP_Allreduce        11306                   1065.
 MP_Sync               170
 MP_Alltoall          1724               12509439.
 MP_SendRecv          5934                  75008.
 MP_ISendRecv         5934                  75008.
 MP_Wait             22612
 MP_comm_split          83
 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    0.026    0.053  187.579  187.580
 qs_mol_dyn_low                       1  2.0    0.003    0.004  187.161  187.173
 qs_forces                           11  3.9    0.003    0.007  187.052  187.057
 qs_energies                         11  4.9    0.002    0.007  180.067  180.079
 scf_env_do_scf                      11  5.9    0.001    0.002  163.366  163.378
 velocity_verlet                     10  3.0    0.002    0.002  124.855  124.858
 scf_env_do_scf_inner_loop          118  6.6    0.003    0.008  116.943  116.944
 qs_scf_new_mos                     118  7.6    0.001    0.001   80.702   80.988
 qs_scf_loop_do_ot                  118  8.6    0.001    0.001   80.702   80.987
 dbcsr_multiply_generic            2527 12.6    0.192    0.198   80.121   80.847
 ot_scf_mini                        118  9.6    0.004    0.005   76.181   76.467
 multiply_cannon                   2527 13.6    0.562    0.596   55.033   58.079
 multiply_cannon_loop              2527 14.6    1.188    1.214   51.384   53.202
 init_scf_loop                       11  6.9    0.001    0.004   46.295   46.296
 ot_mini                            118 10.6    0.001    0.001   42.775   43.047
 prepare_preconditioner              11  7.9    0.000    0.000   42.223   42.246
 make_preconditioner                 11  8.9    0.000    0.002   42.223   42.246
 make_full_inverse_cholesky          11  9.9    0.000    0.000   35.885   40.846
 multiply_cannon_multrec          30324 15.6   14.216   19.475   26.167   30.857
 rebuild_ks_matrix                  129  8.3    0.001    0.001   29.376   29.688
 qs_ks_build_kohn_sham_matrix       129  9.3    0.017    0.019   29.376   29.687
 mp_waitall_1                    149060 16.7   17.805   27.022   17.805   27.022
 qs_ks_update_qs_env                129  7.6    0.001    0.001   26.618   26.892
 qs_ot_get_derivative               118 11.6    0.001    0.002   23.084   23.377
 make_m2s                          5054 13.6    0.100    0.105   20.675   21.531
 make_images                       5054 14.6    1.965    2.307   20.365   21.222
 qs_ot_get_p                        129 10.4    0.001    0.001   19.548   19.908
 apply_preconditioner_dbcsr         129 12.6    0.000    0.001   19.137   19.670
 apply_single                       129 13.6    0.001    0.001   19.137   19.670
 ot_diis_step                       118 11.6    0.018    0.019   19.567   19.569
 cp_fm_upper_to_full                105 14.7   10.965   16.267   10.965   16.267
 cp_fm_cholesky_invert               11 10.9   16.190   16.199   16.190   16.199
 multiply_cannon_metrocomm3       30324 15.6    0.047    0.050    6.541   15.488
 qs_ot_p2m_diag                      83 11.4    0.343    0.390   15.347   15.396
 sum_up_and_integrate               129 10.3    0.141    0.153   14.270   14.300
 integrate_v_rspace                 129 11.3    0.003    0.003   14.129   14.163
 cp_dbcsr_syevd                      83 12.4    0.005    0.005   14.058   14.061
 qs_rho_update_rho_low              129  7.7    0.001    0.001   13.435   13.466
 calculate_rho_elec                 129  8.7    0.176    0.192   13.434   13.465
 make_images_data                  5054 15.6    0.064    0.068   11.216   12.962
 multiply_cannon_sync_h2d         30324 15.6   11.832   12.732   11.832   12.732
 dbcsr_complete_redistribute        395 12.7    1.511    1.635    8.987   12.678
 dbcsr_mm_accdrv_process          62756 16.2    7.415    8.476   11.524   11.967
 hybrid_alltoall_any               5240 16.5    0.528    2.219    9.909   11.619
 copy_fm_to_dbcsr                   209 11.7    0.002    0.002    7.584   11.280
 cp_fm_diag_elpa                     83 13.4    0.000    0.001   10.970   10.973
 cp_fm_redistribute_end              83 14.4    1.895   10.898    1.912   10.905
 cp_fm_diag_elpa_base                83 14.4    8.358   10.283    8.956   10.765
 init_scf_run                        11  5.9    0.000    0.001   10.729   10.731
 scf_env_initial_rho_setup           11  6.9    0.001    0.002   10.729   10.731
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    6.315    9.948
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002    9.493    9.700
 mp_alltoall_i22                    718 14.1    5.573    9.277    5.573    9.277
 pw_transfer                       1559 11.6    0.085    0.102    8.065    8.144
 fft_wrap_pw1pw2                   1301 12.7    0.010    0.011    7.837    7.923
 grid_integrate_task_list           129 12.3    7.593    7.886    7.593    7.886
 cp_fm_cholesky_decompose            22 10.9    7.636    7.788    7.636    7.788
 wfi_extrapolate                     11  7.9    0.001    0.001    7.588    7.589
 multiply_cannon_metrocomm4       25270 15.6    0.076    0.086    2.800    7.068
 fft_wrap_pw1pw2_140                527 13.2    0.486    0.498    6.902    6.993
 density_rs2pw                      129  9.7    0.006    0.006    6.465    6.873
 mp_irecv_dv                      76685 16.2    2.653    6.799    2.653    6.799
 calculate_dm_sparse                129  9.5    0.001    0.001    6.199    6.283
 fft3d_ps                          1301 14.7    2.848    2.983    6.053    6.131
 mp_alltoall_d11v                  2423 14.1    4.978    6.008    4.978    6.008
 grid_collocate_task_list           129  9.7    5.241    5.699    5.241    5.699
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.466    5.513
 rs_pw_transfer                    1054 12.0    0.013    0.015    4.695    5.087
 qs_ot_get_derivative_taylor         41 13.0    0.001    0.001    4.517    4.626
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.360    4.477
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    4.424    4.425
 potential_pw2rs                    129 12.3    0.023    0.023    4.326    4.347
 qs_ot_get_orbitals                 118 10.6    0.001    0.001    4.195    4.252
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="406", plot="h2o_256_md", label="(8n/3r/4t)", y=187.580000, yerr=0.000000
PlotPoint: name="407", plot="h2o_256_md_mem", label="(8n/3r/4t)", y=1079.272727, yerr=16.749985
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/19/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                      5.865088E+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               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               1.525207E+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                       5.532237E+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             721350092304
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         8931                     51.
 MP_Alltoall          9654                 799394.
 MP_ISend            40068                2102572.
 MP_IRecv            40068                2101675.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3992                  58352.
 MP_Allreduce        10977                   1175.
 MP_Sync                87
 MP_Alltoall          1712               18838210.
 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    0.019    0.035  177.367  177.368
 qs_mol_dyn_low                       1  2.0    0.003    0.003  176.982  176.995
 qs_forces                           11  3.9    0.003    0.003  176.883  176.885
 qs_energies                         11  4.9    0.001    0.001  169.522  169.531
 scf_env_do_scf                      11  5.9    0.001    0.001  151.528  151.543
 velocity_verlet                     10  3.0    0.002    0.002  115.280  115.285
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.008  114.585  114.586
 qs_scf_new_mos                     117  7.6    0.001    0.001   78.294   78.426
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   78.293   78.425
 dbcsr_multiply_generic            2507 12.6    0.183    0.188   75.683   76.423
 ot_scf_mini                        117  9.6    0.003    0.004   73.851   73.973
 multiply_cannon                   2507 13.6    0.584    0.608   55.232   59.648
 multiply_cannon_loop              2507 14.6    0.444    0.454   50.616   51.889
 ot_mini                            117 10.6    0.001    0.001   40.190   40.307
 init_scf_loop                       11  6.9    0.000    0.000   36.775   36.776
 mp_waitall_1                    125778 16.7   26.863   34.721   26.863   34.721
 prepare_preconditioner              11  7.9    0.000    0.000   32.909   32.935
 make_preconditioner                 11  8.9    0.000    0.000   32.909   32.935
 make_full_inverse_cholesky          11  9.9    0.000    0.000   30.793   31.087
 rebuild_ks_matrix                  128  8.3    0.001    0.001   28.929   29.048
 qs_ks_build_kohn_sham_matrix       128  9.3    0.017    0.017   28.928   29.047
 qs_ks_update_qs_env                128  7.6    0.001    0.001   26.408   26.519
 multiply_cannon_multrec          10028 15.6   10.374   14.181   18.117   21.160
 qs_ot_get_p                        128 10.4    0.001    0.001   20.701   20.817
 qs_ot_get_derivative               117 11.6    0.001    0.002   20.259   20.387
 apply_preconditioner_dbcsr         128 12.6    0.000    0.000   19.374   19.871
 apply_single                       128 13.6    0.001    0.001   19.374   19.871
 ot_diis_step                       117 11.6    0.020    0.020   19.858   19.858
 multiply_cannon_metrocomm3       10028 15.6    0.023    0.024   12.237   19.220
 cp_fm_cholesky_invert               11 10.9   19.020   19.026   19.020   19.026
 make_m2s                          5014 13.6    0.068    0.073   16.663   18.691
 make_images                       5014 14.6    2.299    2.922   16.355   18.382
 qs_ot_p2m_diag                      83 11.4    0.496    0.501   16.711   16.728
 cp_dbcsr_syevd                      83 12.4    0.005    0.005   15.542   15.544
 sum_up_and_integrate               128 10.3    0.181    0.190   14.289   14.337
 integrate_v_rspace                 128 11.3    0.004    0.004   14.107   14.166
 qs_rho_update_rho_low              128  7.7    0.001    0.001   13.525   13.549
 calculate_rho_elec                 128  8.7    0.258    0.269   13.524   13.548
 make_images_data                  5014 15.6    0.052    0.062   10.203   12.764
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   12.364   12.374
 cp_fm_diag_elpa_base                83 14.4   12.113   12.202   12.359   12.369
 hybrid_alltoall_any               5200 16.5    0.812    3.551    9.912   12.346
 multiply_cannon_sync_h2d         10028 15.6   11.549   12.210   11.549   12.210
 init_scf_run                        11  5.9    0.000    0.001   11.189   11.190
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   11.189   11.190
 multiply_cannon_metrocomm1       10028 15.6    0.029    0.029    5.047    8.436
 cp_fm_cholesky_decompose            22 10.9    8.226    8.339    8.226    8.339
 qs_ot_get_derivative_diag           77 12.4    0.002    0.003    8.222    8.313
 dbcsr_mm_accdrv_process          20762 16.1    2.740    3.427    7.370    8.215
 pw_transfer                       1547 11.6    0.084    0.091    8.157    8.174
 grid_integrate_task_list           128 12.3    7.764    8.089    7.764    8.089
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.010    7.936    7.955
 wfi_extrapolate                     11  7.9    0.001    0.001    7.478    7.478
 mp_allgather_i34                  2507 14.6    2.823    7.213    2.823    7.213
 fft_wrap_pw1pw2_140                523 13.2    0.502    0.524    6.906    6.931
 density_rs2pw                      128  9.7    0.005    0.006    6.252    6.570
 calculate_dm_sparse                128  9.5    0.001    0.001    6.112    6.197
 fft3d_ps                          1291 14.7    2.728    2.816    6.099    6.131
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.024    6.061
 dbcsr_complete_redistribute        395 12.7    2.106    2.179    5.382    5.775
 grid_collocate_task_list           128  9.7    5.484    5.752    5.484    5.752
 mp_alltoall_d11v                  2415 14.1    5.035    5.550    5.035    5.550
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    5.241    5.242
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.852    4.918
 rs_pw_transfer                    1046 11.9    0.012    0.013    4.261    4.616
 potential_pw2rs                    128 12.3    0.026    0.027    4.255    4.271
 multiply_cannon_metrocomm4        7521 15.6    0.024    0.027    1.892    4.113
 mp_irecv_dv                      28860 15.9    1.855    4.027    1.855    4.027
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    3.550    3.876
 copy_fm_to_dbcsr                   209 11.7    0.002    0.002    3.474    3.840
 copy_dbcsr_to_fm                   186 11.8    0.004    0.004    3.692    3.815
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    3.715    3.747
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    3.556    3.594
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="408", plot="h2o_256_md", label="(8n/2r/6t)", y=177.368000, yerr=0.000000
PlotPoint: name="409", plot="h2o_256_md_mem", label="(8n/2r/6t)", y=1425.000000, yerr=53.084838
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_performance_tests/20/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1410022950912       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1924145348608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1957871443968       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        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                     11.606412E+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               1947808       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    3442.6
 marketing flops                   143.507742E+12
 -------------------------------------------------------------------------------
 # multiplications                           2485
 max memory usage/rank               3.044594E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                   99400
 MPI messages size (bytes):
  total size                         1.127422E+12
  min size                           0.000000E+00
  max size                         104.857600E+06
  average size                      11.342272E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                 572                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                  44                  2883584
    131072 < size <=  4194304               44768              34745614336
   4194304 < size <= 16777216               43984             376564613120
  16777216 < size                           10032             716108490000
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3995                  59242.
 MP_Allreduce        10985                   1515.
 MP_Sync                86
 MP_Alltoall          1700               36954382.
 MP_SendRecv          1778                 218624.
 MP_ISendRecv         1778                 218624.
 MP_Wait              9728
 MP_ISend             6360                1080477.
 MP_IRecv             6360                1080477.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.023    0.041  290.677  290.678
 qs_mol_dyn_low                       1  2.0    0.003    0.003  290.139  290.151
 qs_forces                           11  3.9    0.003    0.003  290.042  290.047
 qs_energies                         11  4.9    0.001    0.001  281.348  281.364
 scf_env_do_scf                      11  5.9    0.001    0.001  259.473  259.482
 velocity_verlet                     10  3.0    0.013    0.014  209.866  209.873
 scf_env_do_scf_inner_loop          116  6.6    0.003    0.008  133.790  133.793
 init_scf_loop                       11  6.9    0.000    0.000  125.411  125.415
 prepare_preconditioner              11  7.9    0.000    0.000  120.688  120.709
 make_preconditioner                 11  8.9    0.000    0.000  120.688  120.709
 make_full_inverse_cholesky          11  9.9    0.000    0.000   97.142  117.830
 qs_scf_new_mos                     116  7.6    0.001    0.001   91.917   91.953
 qs_scf_loop_do_ot                  116  8.6    0.001    0.001   91.916   91.952
 ot_scf_mini                        116  9.6    0.004    0.004   87.192   87.237
 dbcsr_multiply_generic            2485 12.5    0.212    0.220   82.096   82.294
 cp_fm_upper_to_full                104 14.8   52.264   74.738   52.264   74.738
 multiply_cannon                   2485 13.5    0.702    0.741   57.422   58.483
 multiply_cannon_loop              2485 14.5    0.467    0.482   53.882   54.514
 ot_mini                            116 10.6    0.001    0.001   44.124   44.197
 dbcsr_complete_redistribute        393 12.7    3.971    4.015   29.344   41.806
 copy_fm_to_dbcsr                   208 11.6    0.001    0.002   25.875   38.334
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000   23.500   35.861
 cp_fm_cholesky_invert               11 10.9   35.118   35.125   35.118   35.125
 mp_alltoall_i22                    712 14.1   21.308   33.860   21.308   33.860
 rebuild_ks_matrix                  127  8.3    0.001    0.001   33.324   33.433
 qs_ks_build_kohn_sham_matrix       127  9.3    0.017    0.017   33.324   33.433
 qs_ks_update_qs_env                127  7.6    0.001    0.001   31.026   31.126
 mp_waitall_1                    102768 16.8   27.440   30.322   27.440   30.322
 qs_ot_get_p                        127 10.4    0.001    0.001   27.841   27.969
 qs_ot_get_derivative               116 11.6    0.002    0.002   24.246   24.292
 qs_ot_p2m_diag                      82 11.4    0.868    0.873   23.670   23.695
 cp_dbcsr_syevd                      82 12.4    0.005    0.006   21.924   21.927
 make_m2s                          4970 13.5    0.079    0.084   19.821   20.639
 make_images                       4970 14.5    3.747    3.890   19.341   20.163
 ot_diis_step                       116 11.6    0.022    0.022   19.819   19.819
 apply_preconditioner_dbcsr         127 12.6    0.000    0.000   19.061   19.227
 apply_single                       127 13.6    0.001    0.001   19.060   19.227
 cp_fm_diag_elpa                     82 13.4    0.000    0.000   18.599   18.600
 cp_fm_diag_elpa_base                82 14.4   14.313   15.886   18.594   18.595
 multiply_cannon_metrocomm3        9940 15.5    0.024    0.024   18.126   18.585
 multiply_cannon_multrec           9940 15.5   10.355   12.080   17.674   17.780
 sum_up_and_integrate               127 10.3    0.319    0.320   15.814   15.900
 integrate_v_rspace                 127 11.3    0.004    0.004   15.495   15.582
 multiply_cannon_sync_h2d          9940 15.5   15.533   15.539   15.533   15.539
 qs_rho_update_rho_low              127  7.7    0.001    0.001   15.143   15.172
 calculate_rho_elec                 127  8.7    0.479    0.479   15.143   15.172
 hybrid_alltoall_any               5155 16.4    1.287    3.007   10.602   12.264
 make_images_data                  4970 15.5    0.060    0.064   10.462   12.026
 init_scf_run                        11  5.9    0.000    0.001   11.916   11.916
 scf_env_initial_rho_setup           11  6.9    0.001    0.002   11.916   11.916
 qs_ot_get_derivative_diag           76 12.4    0.002    0.002    9.511    9.541
 cp_fm_cholesky_decompose            22 10.9    9.465    9.488    9.465    9.488
 dbcsr_mm_accdrv_process          20590 16.0    3.723    5.646    7.084    8.876
 wfi_extrapolate                     11  7.9    0.001    0.001    8.860    8.860
 pw_transfer                       1535 11.6    0.090    0.091    8.668    8.696
 grid_integrate_task_list           127 12.3    8.478    8.674    8.478    8.674
 fft_wrap_pw1pw2                   1281 12.7    0.011    0.011    8.436    8.462
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    7.972    7.974
 fft_wrap_pw1pw2_140                519 13.2    0.535    0.538    7.407    7.436
 mp_alltoall_d11v                  2401 14.1    7.127    7.276    7.127    7.276
 calculate_dm_sparse                127  9.5    0.001    0.001    6.572    6.659
 fft3d_ps                          1281 14.7    2.740    2.751    6.495    6.517
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.337    6.382
 grid_collocate_task_list           127  9.7    6.287    6.321    6.287    6.321
 density_rs2pw                      127  9.7    0.005    0.005    6.227    6.287
 copy_dbcsr_to_fm                   185 11.7    0.004    0.004    6.180    6.198
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="410", plot="h2o_256_md", label="(8n/1r/12t)", y=290.678000, yerr=0.000000
PlotPoint: name="411", plot="h2o_256_md_mem", label="(8n/1r/12t)", y=2756.090909, yerr=150.631069
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_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               1.261257E+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                 255669.
 MP_Allreduce         3059                   6274.
 MP_Sync                 4
 MP_Alltoall            54               19767085.
 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    0.018    0.034   85.631   85.632
 qs_energies                          1  2.0    0.000    0.000   85.178   85.186
 ls_scf                               1  3.0    0.000    0.000   84.270   84.277
 dbcsr_multiply_generic             111  6.7    0.015    0.018   72.988   73.169
 multiply_cannon                    111  7.7    0.018    0.021   56.263   57.682
 multiply_cannon_loop               111  8.7    0.209    0.224   52.805   54.343
 ls_scf_main                          1  4.0    0.000    0.000   52.613   52.613
 density_matrix_trs4                  2  5.0    0.002    0.003   47.058   47.151
 ls_scf_init_scf                      1  4.0    0.000    0.000   28.599   28.600
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   27.517   27.569
 mp_waitall_1                     11031 10.9   22.691   25.947   22.691   25.947
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   25.348   25.372
 multiply_cannon_multrec           2664  9.7    8.159    8.991   15.475   17.310
 multiply_cannon_sync_h2d          2664  9.7   13.700   15.770   13.700   15.770
 make_m2s                           222  7.7    0.009    0.011   13.095   13.645
 make_images                        222  8.7    0.099    0.109   13.073   13.624
 multiply_cannon_metrocomm1        2664  9.7    0.010    0.011    9.923   12.566
 make_images_data                   222  9.7    0.004    0.005    7.679    8.222
 hybrid_alltoall_any                227 10.6    0.215    1.831    6.609    8.118
 dbcsr_mm_accdrv_process           4760 10.4    0.513    0.623    6.934    7.914
 multiply_cannon_metrocomm3        2664  9.7    0.009    0.011    5.411    7.741
 dbcsr_mm_accdrv_process_sort      4760 11.4    6.223    7.108    6.223    7.108
 calculate_norms                   4752  9.8    5.535    6.281    5.535    6.281
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.139    5.279
 mp_sum_l                           807  5.4    3.101    4.375    3.101    4.375
 multiply_cannon_metrocomm4        2442  9.7    0.012    0.015    2.053    3.719
 mp_irecv_dv                       6231 10.9    2.035    3.689    2.035    3.689
 arnoldi_extremal                     4  6.8    0.000    0.000    3.547    3.582
 arnoldi_normal_ev                    4  7.8    0.001    0.002    3.547    3.582
 make_images_sizes                  222  9.7    0.000    0.000    0.762    3.535
 mp_alltoall_i44                    222 10.7    0.762    3.535    0.762    3.535
 build_subspace                      16  8.4    0.009    0.012    3.449    3.451
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    2.289    3.137
 ls_scf_post                          1  4.0    0.000    0.000    3.057    3.065
 ls_scf_store_result                  1  5.0    0.000    0.000    2.880    2.917
 dbcsr_special_finalize             555  9.7    0.005    0.006    2.303    2.669
 dbcsr_merge_single_wm              555 10.7    0.459    0.622    2.295    2.661
 dbcsr_matrix_vector_mult           304  9.0    0.004    0.010    2.418    2.654
 make_images_pack                   222  9.7    2.204    2.630    2.206    2.632
 dbcsr_matrix_vector_mult_local     304 10.0    2.063    2.456    2.065    2.458
 dbcsr_sort_data                    658 11.4    2.096    2.419    2.096    2.419
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.240    2.364
 buffer_matrices_ensure_size        222  8.7    1.763    2.138    1.763    2.138
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.747    1.749
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.738    1.739
 qs_ks_build_kohn_sham_matrix         3  8.3    0.000    0.001    1.738    1.739
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="500", plot="h2o_32_nrep3_ls", label="(8n/12r/1t)", y=85.632000, yerr=0.000000
PlotPoint: name="501", plot="h2o_32_nrep3_ls_mem", label="(8n/12r/1t)", y=1142.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_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               2.104816E+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                 266696.
 MP_Allreduce         3058                  10339.
 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    0.085   90.751   90.762
 qs_energies                          1  2.0    0.000    0.000   90.057   90.061
 ls_scf                               1  3.0    0.000    0.000   88.723   88.726
 dbcsr_multiply_generic             111  6.7    0.015    0.016   74.612   74.888
 multiply_cannon                    111  7.7    0.028    0.040   52.961   56.942
 ls_scf_main                          1  4.0    0.000    0.000   54.487   54.488
 multiply_cannon_loop               111  8.7    0.116    0.122   49.721   53.103
 density_matrix_trs4                  2  5.0    0.002    0.003   48.890   49.051
 ls_scf_init_scf                      1  4.0    0.000    0.000   30.792   30.794
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   29.523   29.621
 mp_waitall_1                      9105 10.9   20.348   28.460   20.348   28.460
 multiply_cannon_multrec           1332  9.7   13.209   16.760   22.433   27.098
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.087   27.097
 multiply_cannon_metrocomm3        1332  9.7    0.007    0.008   11.378   19.869
 make_m2s                           222  7.7    0.006    0.007   14.931   15.543
 make_images                        222  8.7    1.577    1.937   14.901   15.514
 dbcsr_mm_accdrv_process           4041 10.4    0.287    0.469    8.821   10.394
 dbcsr_mm_accdrv_process_sort      4041 11.4    8.402    9.942    8.402    9.942
 make_images_data                   222  9.7    0.004    0.004    8.352    9.250
 mp_sum_l                           807  5.4    5.422    8.749    5.422    8.749
 hybrid_alltoall_any                227 10.6    0.524    2.460    7.799    8.637
 multiply_cannon_metrocomm4        1221  9.7    0.006    0.008    3.211    7.898
 mp_irecv_dv                       3311 11.0    3.191    7.845    3.191    7.845
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    4.279    6.965
 calculate_norms                   2376  9.8    6.026    6.673    6.026    6.673
 multiply_cannon_sync_h2d          1332  9.7    4.835    6.139    4.835    6.139
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.967    5.139
 arnoldi_extremal                     4  6.8    0.000    0.000    4.822    4.838
 arnoldi_normal_ev                    4  7.8    0.001    0.005    4.822    4.838
 build_subspace                      16  8.4    0.014    0.021    4.561    4.564
 ls_scf_post                          1  4.0    0.000    0.000    3.443    3.447
 dbcsr_matrix_vector_mult           304  9.0    0.005    0.017    3.236    3.432
 ls_scf_store_result                  1  5.0    0.000    0.000    3.164    3.267
 dbcsr_matrix_vector_mult_local     304 10.0    2.737    3.218    2.739    3.220
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.004    1.254    2.765
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.517    2.615
 make_images_pack                   222  9.7    2.023    2.416    2.026    2.418
 mp_allgather_i34                   111  8.7    0.942    2.131    0.942    2.131
 dbcsr_sort_data                    436 11.2    1.846    2.051    1.846    2.051
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.894    1.896
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.881    1.883
 qs_ks_build_kohn_sham_matrix         3  8.3    0.006    0.018    1.881    1.883
 dbcsr_data_new                    4174 10.1    1.609    1.837    1.609    1.837
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="502", plot="h2o_32_nrep3_ls", label="(8n/6r/2t)", y=90.762000, yerr=0.000000
PlotPoint: name="503", plot="h2o_32_nrep3_ls_mem", label="(8n/6r/2t)", y=1723.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_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               2.700460E+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                 265470.
 MP_Allreduce         3058                  11181.
 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    0.055    0.114   93.612   93.614
 qs_energies                          1  2.0    0.000    0.000   92.899   92.913
 ls_scf                               1  3.0    0.000    0.001   91.471   91.484
 dbcsr_multiply_generic             111  6.7    0.016    0.022   76.059   76.336
 ls_scf_main                          1  4.0    0.000    0.000   57.276   57.281
 multiply_cannon                    111  7.7    0.041    0.129   52.470   55.871
 multiply_cannon_loop               111  8.7    0.100    0.107   48.938   52.400
 density_matrix_trs4                  2  5.0    0.002    0.003   51.353   51.547
 mp_waitall_1                      7281 11.0   23.826   33.575   23.826   33.575
 ls_scf_init_scf                      1  4.0    0.000    0.001   30.618   30.619
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   29.444   29.510
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.056   27.072
 multiply_cannon_multrec            888  9.7   12.529   15.410   21.045   24.541
 multiply_cannon_metrocomm3         888  9.7    0.004    0.004   10.835   22.607
 make_m2s                           222  7.7    0.006    0.008   17.266   18.452
 make_images                        222  8.7    1.969    2.302   17.228   18.414
 make_images_data                   222  9.7    0.003    0.004    9.976   11.031
 hybrid_alltoall_any                227 10.6    0.620    2.868    9.577   10.918
 dbcsr_mm_accdrv_process           3754 10.4    0.239    0.409    8.034    9.235
 dbcsr_mm_accdrv_process_sort      3754 11.4    7.665    8.826    7.665    8.826
 mp_sum_l                           807  5.4    4.809    7.603    4.809    7.603
 multiply_cannon_sync_h2d           888  9.7    6.075    7.597    6.075    7.597
 multiply_cannon_metrocomm1         888  9.7    0.003    0.003    3.634    7.301
 multiply_cannon_metrocomm4         777  9.7    0.004    0.005    2.450    7.193
 mp_irecv_dv                       2335 11.1    2.434    7.134    2.434    7.134
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.572    5.810
 arnoldi_extremal                     4  6.8    0.000    0.000    5.197    5.218
 arnoldi_normal_ev                    4  7.8    0.001    0.005    5.197    5.218
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.920    5.105
 build_subspace                      16  8.4    0.014    0.021    4.878    4.883
 calculate_norms                   1584  9.8    4.267    4.602    4.267    4.602
 mp_allgather_i34                   111  8.7    1.356    3.862    1.356    3.862
 dbcsr_matrix_vector_mult           304  9.0    0.005    0.016    3.461    3.800
 ls_scf_post                          1  4.0    0.000    0.001    3.577    3.592
 dbcsr_matrix_vector_mult_local     304 10.0    3.016    3.589    3.018    3.591
 ls_scf_store_result                  1  5.0    0.000    0.000    3.319    3.402
 ls_scf_dm_to_ks                      2  5.0    0.000    0.001    2.771    2.879
 dbcsr_sort_data                    325 11.1    1.912    2.151    1.912    2.151
 make_images_pack                   222  9.7    1.813    2.129    1.816    2.131
 make_images_sizes                  222  9.7    0.000    0.000    0.952    2.069
 mp_alltoall_i44                    222 10.7    0.952    2.068    0.952    2.068
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.902    1.904
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.883    1.885
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.001    1.883    1.885
 dbcsr_finalize                     304  7.8    0.026    0.032    1.612    1.880
 dbcsr_data_release                9322 10.9    1.315    1.874    1.315    1.874
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="504", plot="h2o_32_nrep3_ls", label="(8n/4r/3t)", y=93.614000, yerr=0.000000
PlotPoint: name="505", plot="h2o_32_nrep3_ls_mem", label="(8n/4r/3t)", y=2201.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_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               3.318047E+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                 266696.
 MP_Allreduce         3058                  13371.
 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    0.062    0.070   97.213   97.216
 qs_energies                          1  2.0    0.005    0.043   96.477   96.552
 ls_scf                               1  3.0    0.002    0.012   94.818   94.854
 dbcsr_multiply_generic             111  6.7    0.016    0.018   78.518   78.820
 ls_scf_main                          1  4.0    0.000    0.002   58.696   58.702
 multiply_cannon                    111  7.7    0.063    0.139   51.659   56.127
 density_matrix_trs4                  2  5.0    0.003    0.016   52.641   52.735
 multiply_cannon_loop               111  8.7    0.115    0.127   46.615   49.272
 ls_scf_init_scf                      1  4.0    0.000    0.003   32.857   32.881
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   31.465   31.539
 mp_waitall_1                      6369 11.0   22.833   29.259   22.833   29.259
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   28.979   28.994
 multiply_cannon_multrec           1332  9.7   14.237   17.448   22.066   24.950
 make_m2s                           222  7.7    0.007    0.008   21.204   22.642
 make_images                        222  8.7    3.133    3.594   21.154   22.594
 multiply_cannon_metrocomm3        1332  9.7    0.003    0.004    9.186   16.941
 make_images_data                   222  9.7    0.004    0.004   11.873   13.453
 hybrid_alltoall_any                227 10.6    0.796    3.766   11.254   12.993
 dbcsr_mm_accdrv_process           3641 10.4    0.218    0.398    7.471    9.018
 dbcsr_mm_accdrv_process_sort      3641 11.4    7.099    8.597    7.099    8.597
 mp_sum_l                           807  5.4    4.063    7.880    4.063    7.880
 multiply_cannon_sync_h2d          1332  9.7    5.530    6.318    5.530    6.318
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.102    6.275
 multiply_cannon_metrocomm4        1110  9.7    0.004    0.006    2.075    5.900
 mp_irecv_dv                       3229 10.9    2.052    5.845    2.052    5.845
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.003    2.604    5.355
 arnoldi_extremal                     4  6.8    0.000    0.000    5.184    5.199
 arnoldi_normal_ev                    4  7.8    0.001    0.004    5.184    5.199
 build_subspace                      16  8.4    0.014    0.021    4.848    4.854
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.518    4.669
 mp_allgather_i34                   111  8.7    2.161    4.546    2.161    4.546
 calculate_norms                   2376  9.8    4.193    4.505    4.193    4.505
 dbcsr_matrix_vector_mult           304  9.0    0.006    0.016    3.568    3.872
 dbcsr_matrix_vector_mult_local     304 10.0    3.183    3.678    3.185    3.680
 dbcsr_sort_data                    658 11.4    3.079    3.366    3.079    3.366
 ls_scf_post                          1  4.0    0.005    0.039    3.264    3.303
 dbcsr_special_finalize             555  9.7    0.006    0.007    2.818    3.202
 dbcsr_merge_single_wm              555 10.7    0.537    0.662    2.810    3.193
 ls_scf_store_result                  1  5.0    0.000    0.000    2.997    3.063
 ls_scf_dm_to_ks                      2  5.0    0.000    0.010    2.907    2.961
 dbcsr_data_release               10477 10.7    1.580    2.370    1.580    2.370
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.049    2.074
 rebuild_ks_matrix                    3  7.3    0.000    0.000    2.026    2.052
 qs_ks_build_kohn_sham_matrix         3  8.3    0.010    0.080    2.026    2.052
 dbcsr_finalize                     304  7.8    0.049    0.062    1.804    1.980
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="506", plot="h2o_32_nrep3_ls", label="(8n/3r/4t)", y=97.216000, yerr=0.000000
PlotPoint: name="507", plot="h2o_32_nrep3_ls_mem", label="(8n/3r/4t)", y=2739.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_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               4.624093E+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                 265558.
 MP_Allreduce         3049                  15663.
 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    0.044    0.059   99.241   99.243
 qs_energies                          1  2.0    0.000    0.000   98.457   98.463
 ls_scf                               1  3.0    0.000    0.000   96.533   96.539
 dbcsr_multiply_generic             111  6.7    0.017    0.018   78.140   78.375
 ls_scf_main                          1  4.0    0.000    0.000   62.141   62.142
 multiply_cannon                    111  7.7    0.084    0.167   55.256   60.016
 density_matrix_trs4                  2  5.0    0.002    0.003   55.125   55.188
 multiply_cannon_loop               111  8.7    0.070    0.083   50.754   52.891
 mp_waitall_1                      5436 11.0   26.767   31.316   26.767   31.316
 ls_scf_init_scf                      1  4.0    0.000    0.000   30.660   30.666
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   29.477   29.509
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.285   27.298
 multiply_cannon_multrec            444  9.7   14.021   16.452   21.036   22.587
 make_m2s                           222  7.7    0.005    0.005   18.152   20.609
 make_images                        222  8.7    3.720    4.425   18.090   20.550
 multiply_cannon_metrocomm1         444  9.7    0.002    0.002   11.190   16.760
 multiply_cannon_metrocomm3         444  9.7    0.001    0.001    6.149   14.923
 make_images_data                   222  9.7    0.003    0.004   10.229   12.748
 hybrid_alltoall_any                227 10.6    0.788    3.757    9.914   12.649
 dbcsr_mm_accdrv_process           3003 10.4    0.186    0.342    6.717    7.824
 multiply_cannon_sync_h2d           444  9.7    6.545    7.776    6.545    7.776
 dbcsr_mm_accdrv_process_sort      3003 11.4    6.403    7.476    6.403    7.476
 mp_allgather_i34                   111  8.7    2.727    7.060    2.727    7.060
 arnoldi_extremal                     4  6.8    0.000    0.000    5.956    5.968
 arnoldi_normal_ev                    4  7.8    0.001    0.004    5.955    5.968
 build_subspace                      16  8.4    0.015    0.020    5.556    5.566
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.672    4.812
 mp_sum_l                           807  5.4    2.772    4.464    2.772    4.464
 dbcsr_matrix_vector_mult           304  9.0    0.007    0.017    4.272    4.427
 dbcsr_matrix_vector_mult_local     304 10.0    3.690    4.164    3.692    4.166
 multiply_cannon_metrocomm4         333  9.7    0.001    0.002    1.644    3.952
 mp_irecv_dv                       1241 11.2    1.627    3.916    1.627    3.916
 make_images_sizes                  222  9.7    0.000    0.000    1.274    3.838
 mp_alltoall_i44                    222 10.7    1.273    3.837    1.273    3.837
 ls_scf_post                          1  4.0    0.000    0.000    3.732    3.738
 calculate_norms                    792  9.8    3.542    3.682    3.542    3.682
 ls_scf_store_result                  1  5.0    0.000    0.000    3.512    3.557
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    3.384    3.503
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    1.888    3.356
 dbcsr_finalize                     304  7.8    0.062    0.078    2.203    2.327
 dbcsr_merge_all                    275  8.9    0.472    0.529    2.049    2.162
 dbcsr_data_release               10123 10.8    1.340    2.063    1.340    2.063
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="508", plot="h2o_32_nrep3_ls", label="(8n/2r/6t)", y=99.243000, yerr=0.000000
PlotPoint: name="509", plot="h2o_32_nrep3_ls_mem", label="(8n/2r/6t)", y=3655.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/dfa21c5323b1e001456cb941235f5fd980a7c8df_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               8.779985E+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                 284111.
 MP_Allreduce         3043                  21950.
 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    0.079    0.102  108.524  108.525
 qs_energies                          1  2.0    0.000    0.000  107.091  107.106
 ls_scf                               1  3.0    0.000    0.000  104.212  104.226
 dbcsr_multiply_generic             111  6.7    0.023    0.028   77.789   77.943
 ls_scf_main                          1  4.0    0.000    0.000   66.346   66.346
 density_matrix_trs4                  2  5.0    0.002    0.003   57.456   57.516
 multiply_cannon                    111  7.7    0.133    0.228   49.899   52.223
 multiply_cannon_loop               111  8.7    0.067    0.070   46.609   47.693
 ls_scf_init_scf                      1  4.0    0.000    0.000   34.199   34.199
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   32.846   32.863
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   30.006   30.017
 mp_waitall_1                      4527 11.1   22.266   25.582   22.266   25.582
 make_m2s                           222  7.7    0.005    0.005   23.857   24.676
 make_images                        222  8.7    4.582    4.990   23.751   24.568
 multiply_cannon_multrec            444  9.7   17.916   18.708   22.526   23.091
 hybrid_alltoall_any                227 10.6    1.658    3.621   12.928   15.670
 make_images_data                   222  9.7    0.003    0.003   13.064   15.347
 multiply_cannon_metrocomm3         444  9.7    0.001    0.001   10.534   11.571
 multiply_cannon_sync_h2d           444  9.7    8.836    8.894    8.836    8.894
 arnoldi_extremal                     4  6.8    0.000    0.000    7.810    7.825
 arnoldi_normal_ev                    4  7.8    0.002    0.008    7.810    7.825
 build_subspace                      16  8.4    0.025    0.037    7.258    7.271
 dbcsr_matrix_vector_mult           304  9.0    0.009    0.025    5.739    5.909
 dbcsr_matrix_vector_mult_local     304 10.0    5.029    5.335    5.031    5.338
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.064    5.310
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    4.829    4.935
 dbcsr_mm_accdrv_process           1814 10.4    0.265    0.359    4.439    4.614
 dbcsr_mm_accdrv_process_sort      1814 11.4    4.117    4.255    4.117    4.255
 ls_scf_post                          1  4.0    0.000    0.000    3.668    3.681
 make_images_sizes                  222  9.7    0.000    0.000    1.454    3.672
 mp_alltoall_i44                    222 10.7    1.454    3.672    1.454    3.672
 ls_scf_store_result                  1  5.0    0.000    0.000    3.416    3.430
 calculate_norms                    792  9.8    3.251    3.290    3.251    3.290
 dbcsr_finalize                     304  7.8    0.082    0.089    3.086    3.141
 dbcsr_merge_all                    275  8.9    0.893    0.916    2.872    2.919
 dbcsr_complete_redistribute          5  7.6    1.424    1.460    2.778    2.905
 dbcsr_data_release               12724 10.6    2.349    2.871    2.349    2.871
 qs_energies_init_hamiltonians        1  3.0    0.001    0.001    2.849    2.849
 mp_allgather_i34                   111  8.7    0.929    2.807    0.929    2.807
 mp_sum_l                           807  5.4    1.701    2.561    1.701    2.561
 matrix_ls_to_qs                      2  6.0    0.000    0.000    2.414    2.549
 dbcsr_sort_data                    325 11.1    2.442    2.523    2.442    2.523
 dbcsr_new_transposed                 4  7.5    0.253    0.273    2.355    2.373
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.237    2.240
 dbcsr_frobenius_norm                74  6.6    2.055    2.134    2.191    2.221
 dbcsr_add_d                        103  6.2    0.000    0.000    2.133    2.208
 dbcsr_add_anytype                  103  7.2    0.859    0.894    2.133    2.208
 mp_alltoall_d11v                    48  9.2    2.151    2.207    2.151    2.207
 rebuild_ks_matrix                    3  7.3    0.000    0.000    2.171    2.174
 qs_ks_build_kohn_sham_matrix         3  8.3    0.000    0.001    2.171    2.173
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="510", plot="h2o_32_nrep3_ls", label="(8n/1r/12t)", y=108.525000, yerr=0.000000
PlotPoint: name="511", plot="h2o_32_nrep3_ls_mem", label="(8n/1r/12t)", y=6839.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


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

CommitSHA: dfa21c5323b1e001456cb941235f5fd980a7c8df
Summary: empty
Status: OK