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


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


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

 GIT Revision: eddef23af3f7f6c41d23d0ba171cfc643ffab15a


################# 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, LIBINT 2.6.0, LIBPEXSI 1.2.0,
#              LIBXC 6.1.0, LIBVORI 220621, LIBXSMM 1.17, PLUMED 2.8.1,
#              SIRIUS 7.4.3, SPGLIB 1.16.2
#
# Usage: Source this arch file and then run make as instructed.
#        A full toolchain installation is performed as default.
#        Replace or adapt the "module add" commands below if needed.
#
# Author: Matthias Krack (03.02.2023)
#
# \
   if [ "${0}" = "${BASH_SOURCE}" ]; then \
      echo "ERROR: Script ${0##*/} must be sourced"; \
      echo "Usage: source ${0##*/}"; \
      exit 1; \
   fi; \
   this_file=${BASH_SOURCE##*/}; \
   if [ -n "${1}" ]; then \
      gcc_version="${1}"; \
   else \
      gcc_version="9.3.0"; \
   fi; \
   module add daint-gpu; \
   module rm PrgEnv-cray; \
   module add PrgEnv-gnu; \
   module rm gcc; \
   module add gcc/${gcc_version}; \
   module add cray-fftw/3.3.8.10; \
   module add cudatoolkit; \
   echo "Expected setup:"; \
   echo "   cray-mpich/7.7.18"; \
   echo "   craype-haswell"; \
   echo "   daint-gpu/21.09"; \
   echo "   craype/2.7.10"; \
   echo "   cray-libsci/20.09.1"; \
   echo "   PrgEnv-gnu/6.0.10"; \
   echo "   gcc/${gcc_version}"; \
   echo "   cray-fftw/3.3.8.10"; \
   echo "   cudatoolkit/11.0.2_3.38-8.1__g5b73779"; \
   module list; \
   module -f save cp2k_gpu_gnu_psmp; \
   echo "To load the required modules in your batch job script, use:"; \
   echo "   module restore cp2k_gpu_gnu_psmp"; \
   cd tools/toolchain; \
   ./install_cp2k_toolchain.sh --enable-cuda=yes --gpu-ver=P100 -j${maxtasks} --no-arch-files --with-gcc=system --with-libvdwxc --with-pexsi --with-plumed; \
   cd ../..; \
   printf "Sourcing ${PWD}/tools/toolchain/install/setup ... "; \
   source ${PWD}/tools/toolchain/install/setup; \
   printf "done\n"; \
   echo "Check the output above for error messages and consistency!"; \
   echo "If everything is OK, you can build a CP2K production binary with"; \
   echo "   make -j ARCH=${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
USE_LIBINT     := 2.6.0
USE_LIBPEXSI   := 1.2.0
USE_LIBVORI    := 220621
USE_LIBXC      := 6.1.0
USE_LIBXSMM    := 1.17
USE_PLUMED     := 2.8.1
#USE_QUIP       := 0.9.10
USE_SIRIUS     := 7.4.3
USE_SPGLIB     := 1.16.2
# Only needed for SIRIUS
LIBVDWXC_VER   := 0.4.0
SPFFT_VER      := 1.0.6
SPLA_VER       := 1.5.4
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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/01
 job id: 45084942
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/02
 job id: 45084943
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/03
 job id: 45084944
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/04
 job id: 45084945
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/05
 job id: 45084946
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/06
 job id: 45084947
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/07
 job id: 45084948
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/08
 job id: 45084949
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/09
 job id: 45084950
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/10
 job id: 45084951
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/11
 job id: 45084952
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/12
 job id: 45084953
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/13
 job id: 45084954
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/14
 job id: 45084955
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/15
 job id: 45084956
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/16
 job id: 45084957
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/17
 job id: 45084958
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/18
 job id: 45084959
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/19
 job id: 45084960
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/20
 job id: 45084961
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/21
 job id: 45084962
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/22
 job id: 45084963
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/23
 job id: 45084964
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/24
 job id: 45084965
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/25
 job id: 45084966
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/26
 job id: 45084967
 --- 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_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    0.022    0.034  134.519  134.520
 farming_run                          1  2.0  133.912  133.916  134.490  134.493
 -------------------------------------------------------------------------------


 @@@@@@@@@@ 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               1.459573E+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              231                1098811.
 MP_Allreduce          491                2254389.
 MP_Sync                25
 MP_Alltoall            38                9316958.
 MP_SendRecv           120                 384007.
 MP_ISendRecv           45                 235435.
 MP_Wait               191
 MP_comm_split          10
 MP_ISend              127                3867574.
 MP_IRecv              127                3866554.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.009    0.034  115.343  115.343
 qs_energies                          1  2.0    0.000    0.000  115.144  115.147
 mp2_main                             1  3.0    0.000    0.000  113.072  113.076
 mp2_gpw_main                         1  4.0    0.051    0.058  112.078  112.081
 mp2_ri_gpw_compute_in                1  5.0    0.175    0.178   93.116   93.219
 mp2_ri_gpw_compute_in_loop           1  6.0    0.005    0.006   55.398   55.499
 mp2_eri_3c_integrate_gpw           272  7.0    0.153    0.168   41.703   46.645
 get_2c_integrals                     1  6.0    0.000    0.001   37.223   37.540
 integrate_v_rspace                 273  8.0    0.437    0.450   25.073   29.660
 pw_transfer                       6555 10.6    0.367    0.388   27.368   27.821
 fft_wrap_pw1pw2                   5465 11.4    0.045    0.047   26.004   26.286
 grid_integrate_task_list           273  9.0   20.900   25.913   20.900   25.913
 fft_wrap_pw1pw2_100               2178 12.4    1.223    1.409   23.520   23.811
 compute_2c_integrals                 1  7.0    0.002    0.003   19.612   19.614
 compute_2c_integrals_loop_lm         1  8.0    0.003    0.004   18.938   19.344
 mp2_eri_2c_integrate_gpw             1  9.0    2.367    2.436   18.935   19.343
 rpa_ri_compute_en                    1  5.0    0.001    0.001   18.824   18.887
 cp_fm_cholesky_decompose            12  8.2   17.531   17.835   17.531   17.835
 cholesky_decomp                      1  7.0    0.000    0.000   16.454   16.763
 fft3d_s                           5443 13.4   16.093   16.222   16.115   16.244
 ao_to_mo_and_store_B_mult_1        272  7.0   10.855   15.581   10.855   15.581
 calculate_wavefunction             272  8.0    5.457    5.540   12.548   13.189
 rpa_num_int                          1  6.0    0.000    0.001   10.457   10.467
 rpa_num_int_RPA_matrix_operati       8  7.0    0.000    0.000   10.442   10.443
 calc_mat_Q                           8  8.0    0.000    0.000    9.323    9.407
 contract_S_to_Q                      8  9.0    0.000    0.000    8.745    8.829
 calc_potential_gpw                 544  9.5    0.005    0.006    8.297    8.730
 mp2_eri_2c_integrate_gpw_pot_l     272 10.0    0.001    0.001    8.255    8.539
 parallel_gemm_fm                    14  9.1    0.000    0.000    8.325    8.409
 parallel_gemm_fm_cosma              14 10.1    8.325    8.409    8.325    8.409
 potential_pw2rs                    545 10.0    0.107    0.109    7.676    8.281
 create_integ_mat                     1  6.0    0.013    0.028    8.169    8.178
 collocate_single_gaussian          272 10.0    0.040    0.042    7.489    7.718
 array2fm                             1  7.0    0.000    0.000    6.761    7.546
 pw_scatter_s                      2720 13.7    4.424    4.589    4.424    4.589
 pw_gather_s                       2722 13.2    3.848    4.252    3.848    4.252
 array2fm_buffer_send                 1  8.0    2.967    3.173    2.967    3.173
 pw_poisson_solve                   545 10.5    1.130    1.176    2.208    2.480
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="10", plot="h2o_32_ri_rpa_mp2", label="RI-RPA (8n/2r/6t)", y=112.077306, yerr=0.000000
PlotPoint: name="11", plot="h2o_32_ri_rpa_mp2_mem", label="RI-RPA (8n/2r/6t)", y=2730.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_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    0.027    0.037  397.532  397.534
 farming_run                          1  2.0  396.723  396.728  397.497  397.500
 -------------------------------------------------------------------------------


 @@@@@@@@@@ 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               1.229124E+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              744                 385880.
 MP_Allreduce         1941                  22272.
 MP_Sync                37
 MP_Alltoall            77
 MP_SendRecv          2876                2171486.
 MP_ISendRecv         1034                 172620.
 MP_Wait              1346
 MP_comm_split           7
 MP_ISend              264                 362227.
 MP_IRecv              264                 362718.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.020    0.052  210.225  210.226
 qs_energies                          1  2.0    0.000    0.000  209.970  209.990
 scf_env_do_scf                       1  3.0    0.000    0.000  106.943  106.944
 qs_ks_update_qs_env                  5  5.0    0.000    0.000  106.031  106.050
 rebuild_ks_matrix                    4  6.0    0.000    0.000  105.447  105.454
 qs_ks_build_kohn_sham_matrix         4  7.0    0.057    0.064  105.447  105.454
 hfx_ks_matrix                        4  8.0    0.001    0.001  105.058  105.062
 integrate_four_center                4  9.0    0.144    0.456  105.057  105.061
 mp2_main                             1  3.0    0.000    0.000  102.733  102.753
 mp2_gpw_main                         1  4.0    0.032    0.044  101.811  101.831
 integrate_four_center_main           4 10.0    0.066    0.393   96.591   99.050
 integrate_four_center_bin          264 11.0   96.525   99.020   96.525   99.020
 init_scf_loop                        1  4.0    0.000    0.000   92.202   92.202
 mp2_ri_gpw_compute_in                1  5.0    0.064    0.064   75.052   76.168
 mp2_ri_gpw_compute_in_loop           1  6.0    0.002    0.002   54.614   55.731
 mp2_eri_3c_integrate_gpw            91  7.0    0.144    0.158   42.079   47.385
 integrate_v_rspace                  95  8.0    0.399    0.578   28.461   33.627
 pw_transfer                       2240 10.6    0.143    0.179   29.967   30.380
 ao_to_mo_and_store_B_mult_1         91  7.0   10.849   30.045   10.849   30.045
 fft_wrap_pw1pw2                   1868 11.4    0.018    0.022   28.971   29.344
 grid_integrate_task_list            95  9.0   23.744   29.093   23.744   29.093
 mp2_ri_gpw_compute_en                1  5.0    0.056    0.077   26.611   28.396
 fft_wrap_pw1pw2_100                730 12.4    1.306    1.451   26.679   27.151
 mp2_ri_gpw_compute_en_RI_loop        1  6.0    1.853    1.913   24.854   24.863
 get_2c_integrals                     1  6.0    0.000    0.000   20.324   20.373
 compute_2c_integrals                 1  7.0    0.002    0.003   19.307   19.312
 compute_2c_integrals_loop_lm         1  8.0    0.001    0.001   18.933   19.173
 mp2_eri_2c_integrate_gpw             1  9.0    1.734    1.966   18.932   19.172
 fft3d_s                           1823 13.4   18.436   18.915   18.449   18.927
 scf_env_do_scf_inner_loop            4  4.0    0.012    0.596   14.740   14.740
 calculate_wavefunction              91  8.0    2.010    2.041    9.735    9.994
 mp2_ri_gpw_compute_en_expansio     172  7.0    0.555    0.589    8.772    9.305
 potential_pw2rs                    186 10.0    0.034    0.036    8.672    9.184
 local_gemm                         172  8.0    8.218    8.738    8.218    8.738
 mp2_eri_2c_integrate_gpw_pot_l      91 10.0    0.001    0.001    8.281    8.640
 mp2_ri_gpw_compute_en_comm          22  7.0    0.512    0.538    7.838    8.253
 calc_potential_gpw                 182  9.5    0.002    0.003    7.924    8.172
 collocate_single_gaussian           91 10.0    0.017    0.022    7.913    8.141
 mp2_ri_gpw_compute_en_ener         172  7.0    6.346    6.437    6.346    6.437
 mp_sendrecv_dm3                   2068  8.0    5.838    6.307    5.838    6.307
 mp_sync                             37 10.5    3.131    6.009    3.131    6.009
 pw_gather_s                        912 13.2    4.900    5.405    4.900    5.405
 pw_scatter_s                       910 13.7    3.932    4.210    3.932    4.210
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="20", plot="h2o_32_ri_rpa_mp2", label="RI-MP2 (8n/6r/2t)", y=101.810163, yerr=0.000000
PlotPoint: name="21", plot="h2o_32_ri_rpa_mp2_mem", label="RI-MP2 (8n/6r/2t)", y=1516.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/03/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                     29.277748E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               5055360       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      29.1
 marketing flops                     2.107592E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             452.874240E+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                    272.
 MP_Sync               530
 MP_Alltoall          2083                 578368.
 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    0.022    0.038   52.552   52.554
 qs_mol_dyn_low                       1  2.0    0.003    0.003   51.896   51.904
 qs_forces                           11  3.9    0.002    0.002   51.832   51.832
 qs_energies                         11  4.9    0.001    0.001   50.343   50.357
 scf_env_do_scf                      11  5.9    0.000    0.001   43.899   43.899
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.023   41.806   41.806
 dbcsr_multiply_generic            2286 12.5    0.093    0.097   32.331   32.815
 qs_scf_new_mos                     108  7.5    0.000    0.001   31.689   31.961
 qs_scf_loop_do_ot                  108  8.5    0.000    0.001   31.689   31.960
 ot_scf_mini                        108  9.5    0.002    0.002   30.073   30.266
 multiply_cannon                   2286 13.5    0.183    0.191   25.805   27.482
 multiply_cannon_loop              2286 14.5    1.449    1.547   25.117   26.838
 velocity_verlet                     10  3.0    0.001    0.001   25.768   25.768
 ot_mini                            108 10.5    0.001    0.001   17.928   18.193
 qs_ot_get_derivative               108 11.5    0.001    0.002   15.057   15.243
 mp_waitall_1                    245248 16.5    7.827   14.285    7.827   14.285
 multiply_cannon_metrocomm3       54864 15.5    0.069    0.075    5.702   13.123
 multiply_cannon_multrec          54864 15.5    4.334    6.715    7.954   11.538
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.924    8.071
 qs_ks_build_kohn_sham_matrix       119  9.3    0.010    0.011    7.923    8.071
 qs_ot_get_p                        119 10.4    0.001    0.001    7.640    7.916
 multiply_cannon_sync_h2d         54864 15.5    6.040    7.281    6.040    7.281
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.992    7.119
 mp_sum_l                          7207 12.9    4.591    6.350    4.591    6.350
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    5.556    6.053
 init_scf_run                        11  5.9    0.000    0.001    5.238    5.238
 scf_env_initial_rho_setup           11  6.9    0.000    0.001    5.238    5.238
 qs_ot_p2m_diag                      50 11.0    0.004    0.006    5.059    5.088
 dbcsr_mm_accdrv_process          76910 16.1    1.111    1.811    3.541    5.047
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    4.495    4.592
 sum_up_and_integrate               119 10.3    0.014    0.031    4.547    4.553
 integrate_v_rspace                 119 11.3    0.002    0.003    4.532    4.542
 cp_dbcsr_syevd                      50 12.0    0.002    0.003    4.359    4.359
 qs_rho_update_rho_low              119  7.7    0.001    0.001    4.176    4.269
 calculate_rho_elec                 119  8.7    0.012    0.017    4.176    4.268
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    4.153    4.153
 cp_fm_redistribute_end              50 14.0    2.119    4.126    2.126    4.129
 cp_fm_diag_elpa_base                50 14.0    1.997    4.018    2.001    4.026
 jit_kernel_multiply                 13 15.8    2.370    3.148    2.370    3.148
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.902    3.097
 apply_single                       119 13.6    0.000    0.000    2.902    3.097
 calculate_first_density_matrix       1  7.0    0.000    0.000    3.079    3.087
 calculate_dm_sparse                119  9.5    0.000    0.001    2.862    2.994
 rs_pw_transfer                     974 11.9    0.012    0.012    2.753    2.871
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.853    2.855
 multiply_cannon_metrocomm1       54864 15.5    0.054    0.060    1.448    2.730
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.587    2.649
 ot_diis_step                       108 11.5    0.006    0.006    2.627    2.627
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    2.336    2.388
 density_rs2pw                      119  9.7    0.004    0.005    2.238    2.378
 acc_transpose_blocks             54864 15.5    0.223    0.252    1.806    2.361
 grid_integrate_task_list           119 12.3    2.024    2.108    2.024    2.108
 wfi_extrapolate                     11  7.9    0.001    0.001    2.095    2.095
 init_scf_loop                       11  6.9    0.000    0.000    2.077    2.077
 potential_pw2rs                    119 12.3    0.004    0.004    1.898    1.913
 pw_transfer                       1439 11.6    0.053    0.059    1.797    1.868
 fft_wrap_pw1pw2                   1201 12.6    0.007    0.007    1.721    1.795
 mp_sum_d                          4133 12.0    1.171    1.736    1.171    1.736
 make_m2s                          4572 13.5    0.054    0.056    1.629    1.676
 make_images                       4572 14.5    0.133    0.139    1.546    1.593
 fft3d_ps                          1201 14.6    0.370    0.472    1.491    1.558
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.410    1.427
 mp_waitany                       12084 13.8    1.249    1.425    1.249    1.425
 fft_wrap_pw1pw2_140                487 13.2    0.082    0.097    1.325    1.406
 grid_collocate_task_list           119  9.7    1.288    1.360    1.288    1.360
 mp_alltoall_d11v                  2130 13.8    1.224    1.350    1.224    1.350
 acc_transpose_blocks_kernels     54864 16.5    0.239    0.380    0.869    1.213
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="100", plot="h2o_64_md", label="(8n/12r/1t)", y=52.554000, yerr=0.000000
PlotPoint: name="101", plot="h2o_64_md_mem", label="(8n/12r/1t)", y=431.181818, yerr=1.113404
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/04/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                     57.173320E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               3066240       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      47.9
 marketing flops                     2.107592E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             489.758720E+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                54
 MP_Alltoall          2060                1030427.
 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    0.032    0.063   40.377   40.379
 qs_mol_dyn_low                       1  2.0    0.003    0.004   40.023   40.031
 qs_forces                           11  3.9    0.002    0.003   39.960   39.961
 qs_energies                         11  4.9    0.001    0.005   38.265   38.268
 scf_env_do_scf                      11  5.9    0.001    0.002   32.391   32.392
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.008   29.798   29.799
 dbcsr_multiply_generic            2286 12.5    0.100    0.103   22.470   22.863
 qs_scf_new_mos                     108  7.5    0.001    0.001   20.557   20.806
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   20.556   20.805
 ot_scf_mini                        108  9.5    0.002    0.003   19.672   19.840
 multiply_cannon                   2286 13.5    0.208    0.218   17.348   18.825
 velocity_verlet                     10  3.0    0.002    0.012   18.379   18.380
 multiply_cannon_loop              2286 14.5    0.897    0.977   16.257   17.729
 ot_mini                            108 10.5    0.001    0.001   12.281   12.514
 mp_waitall_1                    200699 16.5    6.157   11.887    6.157   11.887
 multiply_cannon_metrocomm3       27432 15.5    0.069    0.072    4.442   10.475
 qs_ot_get_derivative               108 11.5    0.001    0.001    9.818    9.992
 multiply_cannon_multrec          27432 15.5    2.044    4.642    6.311    9.290
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.252    7.388
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.014    7.251    7.388
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.404    6.527
 dbcsr_mm_accdrv_process          47894 16.0    3.139    5.466    4.198    6.190
 qs_ot_get_p                        119 10.4    0.002    0.009    4.574    4.802
 init_scf_run                        11  5.9    0.000    0.001    4.655    4.655
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    4.655    4.655
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    3.620    4.609
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    3.192    4.294
 apply_single                       119 13.6    0.000    0.000    3.192    4.294
 sum_up_and_integrate               119 10.3    0.024    0.027    4.232    4.238
 integrate_v_rspace                 119 11.3    0.002    0.003    4.207    4.215
 mp_sum_l                          7207 12.9    2.215    4.202    2.215    4.202
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.923    3.954
 calculate_rho_elec                 119  8.7    0.021    0.024    3.923    3.953
 rs_pw_transfer                     974 11.9    0.010    0.012    2.641    3.159
 qs_ot_p2m_diag                      50 11.0    0.008    0.012    3.063    3.083
 calculate_first_density_matrix       1  7.0    0.000    0.002    3.034    3.035
 multiply_cannon_sync_h2d         27432 15.5    2.189    2.833    2.189    2.833
 density_rs2pw                      119  9.7    0.004    0.004    2.240    2.773
 make_m2s                          4572 13.5    0.052    0.055    2.472    2.694
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    2.633    2.634
 make_images                       4572 14.5    0.201    0.238    2.384    2.604
 init_scf_loop                       11  6.9    0.001    0.003    2.572    2.573
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.519    2.522
 jit_kernel_multiply                 10 16.0    1.007    2.415    1.007    2.415
 ot_diis_step                       108 11.5    0.010    0.011    2.411    2.412
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.313    2.351
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    2.297    2.297
 cp_fm_redistribute_end              50 14.0    1.162    2.268    1.166    2.270
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    2.130    2.221
 cp_fm_diag_elpa_base                50 14.0    1.072    2.177    1.100    2.215
 calculate_dm_sparse                119  9.5    0.000    0.001    2.113    2.195
 pw_transfer                       1439 11.6    0.065    0.071    2.076    2.117
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.009    1.984    2.028
 potential_pw2rs                    119 12.3    0.006    0.006    1.962    1.973
 grid_integrate_task_list           119 12.3    1.832    1.910    1.832    1.910
 acc_transpose_blocks             27432 15.5    0.109    0.115    1.336    1.854
 fft3d_ps                          1201 14.6    0.516    0.567    1.686    1.724
 prepare_preconditioner              11  7.9    0.000    0.001    1.562    1.588
 make_preconditioner                 11  8.9    0.000    0.001    1.562    1.588
 fft_wrap_pw1pw2_140                487 13.2    0.079    0.085    1.508    1.550
 make_images_data                  4572 15.5    0.045    0.051    1.137    1.541
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.458    1.514
 wfi_extrapolate                     11  7.9    0.001    0.001    1.476    1.476
 hybrid_alltoall_any               4725 16.4    0.051    0.112    0.992    1.454
 grid_collocate_task_list           119  9.7    1.232    1.357    1.232    1.357
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.336    1.343
 mp_alltoall_d11v                  2130 13.8    1.190    1.333    1.190    1.333
 mp_allgather_i34                  2286 14.5    0.532    1.295    0.532    1.295
 acc_transpose_blocks_kernels     27432 16.5    0.182    0.271    0.804    1.229
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.175    1.224
 mp_waitany                        5720 13.7    0.550    1.096    0.550    1.096
 rs_pw_transfer_RS2PW_140           130 11.5    0.138    0.145    0.574    1.095
 mp_sum_d                          4133 12.0    0.612    1.090    0.612    1.090
 jit_kernel_transpose                 5 15.5    0.622    0.959    0.622    0.959
 qs_energies_init_hamiltonians       11  5.9    0.000    0.004    0.954    0.955
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.905    0.919
 multiply_cannon_metrocomm1       27432 15.5    0.032    0.036    0.509    0.890
 mp_alltoall_z22v                  1201 16.6    0.713    0.814    0.713    0.814
 rs_pw_transfer_PW2RS_50            119 14.3    0.589    0.609    0.761    0.810
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="102", plot="h2o_64_md", label="(8n/6r/2t)", y=40.379000, yerr=0.000000
PlotPoint: name="103", plot="h2o_64_md_mem", label="(8n/6r/2t)", y=467.727273, yerr=0.862439
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/05/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                     59.051995E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               3143552       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      46.8
 marketing flops                     2.107587E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             522.190848E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                  950976
 MPI messages size (bytes):
  total size                       203.844256E+09
  min size                           0.000000E+00
  max size                           1.638400E+06
  average size                     214.352688E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192              253512               2076770304
      8192 < size <=    32768              179424               2939682816
     32768 < size <=   131072              181440              14863564800
    131072 < size <=  4194304              330176             183964913216
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3622                  63497.
 MP_Allreduce        10075                    307.
 MP_Sync                54
 MP_Alltoall          1821                1607811.
 MP_SendRecv         11067                  57667.
 MP_ISendRecv        11067                  57667.
 MP_Wait             21987
 MP_ISend             9880                  92618.
 MP_IRecv             9880                  92618.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.017    0.029   34.104   34.106
 qs_mol_dyn_low                       1  2.0    0.003    0.004   33.785   33.794
 qs_forces                           11  3.9    0.012    0.068   33.533   33.536
 qs_energies                         11  4.9    0.002    0.006   31.901   31.908
 scf_env_do_scf                      11  5.9    0.002    0.011   26.619   26.619
 scf_env_do_scf_inner_loop          108  6.5    0.006    0.033   23.830   23.831
 dbcsr_multiply_generic            2286 12.5    0.094    0.096   17.215   17.321
 velocity_verlet                     10  3.0    0.001    0.002   15.668   15.675
 qs_scf_new_mos                     108  7.5    0.001    0.001   15.475   15.489
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   15.474   15.488
 ot_scf_mini                        108  9.5    0.002    0.003   14.747   14.757
 multiply_cannon                   2286 13.5    0.197    0.204   13.883   14.712
 multiply_cannon_loop              2286 14.5    0.630    0.665   13.079   13.899
 ot_mini                            108 10.5    0.001    0.001    9.213    9.226
 qs_ot_get_derivative               108 11.5    0.031    0.076    7.695    7.705
 multiply_cannon_multrec          18288 15.5    1.922    2.933    7.210    7.620
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.649    6.664
 qs_ks_build_kohn_sham_matrix       119  9.3    0.014    0.028    6.648    6.663
 dbcsr_mm_accdrv_process          38222 16.0    4.231    5.811    5.204    6.032
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.894    5.908
 mp_waitall_1                    158411 16.6    3.010    4.266    3.010    4.266
 sum_up_and_integrate               119 10.3    0.033    0.037    4.045    4.062
 integrate_v_rspace                 119 11.3    0.003    0.007    4.012    4.032
 init_scf_run                        11  5.9    0.000    0.001    3.975    3.975
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.975    3.975
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    3.105    3.734
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.604    3.613
 calculate_rho_elec                 119  8.7    0.031    0.031    3.603    3.613
 qs_ot_get_p                        119 10.4    0.001    0.001    3.346    3.368
 multiply_cannon_metrocomm3       18288 15.5    0.045    0.047    1.755    2.889
 init_scf_loop                       11  6.9    0.001    0.003    2.763    2.764
 rs_pw_transfer                     974 11.9    0.010    0.010    2.456    2.714
 calculate_first_density_matrix       1  7.0    0.002    0.006    2.692    2.693
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.048    2.374
 apply_single                       119 13.6    0.000    0.000    2.048    2.374
 density_rs2pw                      119  9.7    0.004    0.005    2.111    2.369
 jit_kernel_multiply                 10 16.1    0.921    2.349    0.921    2.349
 calculate_dm_sparse                119  9.5    0.000    0.000    2.294    2.306
 qs_ot_p2m_diag                      50 11.0    0.012    0.013    2.249    2.254
 pw_transfer                       1439 11.6    0.066    0.072    2.023    2.051
 cp_dbcsr_syevd                      50 12.0    0.003    0.004    1.986    1.986
 make_m2s                          4572 13.5    0.045    0.046    1.812    1.966
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.009    1.930    1.959
 make_images                       4572 14.5    0.191    0.204    1.727    1.879
 grid_integrate_task_list           119 12.3    1.802    1.876    1.802    1.876
 potential_pw2rs                    119 12.3    0.007    0.008    1.820    1.840
 prepare_preconditioner              11  7.9    0.000    0.000    1.758    1.761
 make_preconditioner                 11  8.9    0.000    0.001    1.758    1.761
 cp_fm_diag_elpa                     50 13.0    0.000    0.001    1.730    1.740
 cp_fm_diag_elpa_base                50 14.0    1.705    1.716    1.727    1.737
 make_full_inverse_cholesky          11  9.9    0.001    0.004    1.610    1.696
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.660    1.665
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.649    1.651
 fft3d_ps                          1201 14.6    0.527    0.544    1.608    1.639
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.568    1.575
 multiply_cannon_sync_h2d         18288 15.5    1.393    1.565    1.393    1.565
 fft_wrap_pw1pw2_140                487 13.2    0.091    0.097    1.488    1.517
 acc_transpose_blocks             18288 15.5    0.076    0.077    1.280    1.514
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.505    1.510
 mp_sum_l                          7207 12.9    1.141    1.492    1.141    1.492
 ot_diis_step                       108 11.5    0.011    0.011    1.490    1.490
 grid_collocate_task_list           119  9.7    1.216    1.384    1.216    1.384
 wfi_extrapolate                     11  7.9    0.001    0.001    1.177    1.177
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    1.066    1.071
 acc_transpose_blocks_kernels     18288 16.5    0.209    0.216    0.841    1.068
 make_images_data                  4572 15.5    0.045    0.049    0.815    0.981
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.900    0.922
 mp_waitany                        9880 13.7    0.610    0.894    0.610    0.894
 hybrid_alltoall_any               4725 16.4    0.055    0.113    0.704    0.894
 rs_pw_transfer_RS2PW_140           130 11.5    0.121    0.137    0.589    0.854
 jit_kernel_transpose                 5 15.6    0.631    0.852    0.631    0.852
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.827    0.828
 mp_alltoall_z22v                  1201 16.6    0.643    0.752    0.643    0.752
 cp_fm_cholesky_invert               11 10.9    0.744    0.747    0.744    0.747
 mp_alltoall_d11v                  2130 13.8    0.664    0.747    0.664    0.747
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.655    0.725
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="104", plot="h2o_64_md", label="(8n/4r/3t)", y=34.106000, yerr=0.000000
PlotPoint: name="105", plot="h2o_64_md_mem", label="(8n/4r/3t)", y=496.545455, yerr=1.437399
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/06/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                    114.044384E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               3805952       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      38.6
 marketing flops                     2.107592E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             556.433408E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1042416
 MPI messages size (bytes):
  total size                       150.443262E+09
  min size                           0.000000E+00
  max size                           1.188816E+06
  average size                     144.321719E+03
 MPI breakdown and total messages size (bytes):
             size <=      128              228256                        0
       128 < size <=     8192              126888               1039466496
      8192 < size <=    32768              191472               3137077248
     32768 < size <=   131072              295800              25899827200
    131072 < size <=  4194304              200000             120367247040
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3622                  63496.
 MP_Allreduce        10074                    349.
 MP_Sync                54
 MP_Alltoall          1582                2412273.
 MP_SendRecv          8211                  74133.
 MP_ISendRecv         8211                  74133.
 MP_Wait             16271
 MP_ISend             7280                 135929.
 MP_IRecv             7280                 135929.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.016    0.032   36.934   36.936
 qs_mol_dyn_low                       1  2.0    0.003    0.004   36.751   36.756
 qs_forces                           11  3.9    0.002    0.002   36.317   36.318
 qs_energies                         11  4.9    0.001    0.004   34.585   34.590
 scf_env_do_scf                      11  5.9    0.001    0.002   28.687   28.689
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.007   25.232   25.232
 dbcsr_multiply_generic            2286 12.5    0.098    0.101   19.018   19.126
 velocity_verlet                     10  3.0    0.001    0.001   18.193   18.195
 qs_scf_new_mos                     108  7.5    0.001    0.001   16.564   16.613
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   16.563   16.613
 multiply_cannon                   2286 13.5    0.226    0.265   15.389   15.782
 ot_scf_mini                        108  9.5    0.003    0.004   15.623   15.673
 multiply_cannon_loop              2286 14.5    0.934    0.965   14.429   14.712
 ot_mini                            108 10.5    0.001    0.001    9.528    9.591
 multiply_cannon_multrec          27432 15.5    2.332    3.034    8.775    9.325
 qs_ot_get_derivative               108 11.5    0.001    0.002    7.726    7.778
 dbcsr_mm_accdrv_process          47916 15.9    5.262    7.187    6.350    7.616
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.713    6.768
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.014    6.712    6.767
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.963    6.011
 init_scf_run                        11  5.9    0.000    0.001    4.519    4.520
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    4.519    4.519
 sum_up_and_integrate               119 10.3    0.036    0.039    3.922    3.930
 integrate_v_rspace                 119 11.3    0.003    0.003    3.885    3.894
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.638    3.668
 calculate_rho_elec                 119  8.7    0.040    0.046    3.638    3.667
 qs_ot_get_p                        119 10.4    0.001    0.001    3.482    3.555
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    3.089    3.495
 init_scf_loop                       11  6.9    0.001    0.002    3.433    3.434
 calculate_first_density_matrix       1  7.0    0.001    0.003    2.959    2.961
 mp_waitall_1                    137007 16.6    2.253    2.955    2.253    2.955
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.583    2.606
 prepare_preconditioner              11  7.9    0.000    0.000    2.571    2.579
 make_preconditioner                 11  8.9    0.000    0.001    2.571    2.579
 make_full_inverse_cholesky          11  9.9    0.004    0.028    2.181    2.507
 rs_pw_transfer                     974 11.9    0.009    0.010    2.130    2.326
 make_m2s                          4572 13.5    0.055    0.056    2.201    2.303
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.001    2.252    2.265
 density_rs2pw                      119  9.7    0.004    0.005    2.049    2.240
 qs_ot_p2m_diag                      50 11.0    0.015    0.023    2.190    2.199
 make_images                       4572 14.5    0.271    0.331    2.093    2.194
 pw_transfer                       1439 11.6    0.066    0.071    2.140    2.181
 calculate_dm_sparse                119  9.5    0.000    0.000    2.118    2.175
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.042    2.174
 apply_single                       119 13.6    0.000    0.000    2.042    2.174
 jit_kernel_multiply                 10 15.7    1.027    2.125    1.027    2.125
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    2.047    2.093
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.937    1.963
 grid_integrate_task_list           119 12.3    1.817    1.884    1.817    1.884
 acc_transpose_blocks             27432 15.5    0.113    0.116    1.751    1.876
 cp_dbcsr_syevd                      50 12.0    0.003    0.004    1.868    1.868
 ot_diis_step                       108 11.5    0.012    0.012    1.762    1.762
 fft3d_ps                          1201 14.6    0.562    0.616    1.720    1.757
 fft_wrap_pw1pw2_140                487 13.2    0.089    0.097    1.677    1.727
 potential_pw2rs                    119 12.3    0.008    0.010    1.676    1.681
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.610    1.619
 cp_fm_diag_elpa_base                50 14.0    1.574    1.591    1.607    1.616
 multiply_cannon_metrocomm3       27432 15.5    0.038    0.039    0.963    1.552
 wfi_extrapolate                     11  7.9    0.022    0.171    1.502    1.502
 grid_collocate_task_list           119  9.7    1.222    1.378    1.222    1.378
 mp_sum_l                          7207 12.9    1.007    1.315    1.007    1.315
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.300    1.310
 acc_transpose_blocks_kernels     27432 16.5    0.295    0.397    1.126    1.241
 dbcsr_complete_redistribute        329 12.2    0.120    0.147    0.921    1.225
 cp_fm_upper_to_full                 72 14.2    0.818    1.168    0.818    1.168
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.108    1.128
 qs_energies_init_hamiltonians       11  5.9    0.001    0.003    1.110    1.111
 multiply_cannon_sync_h2d         27432 15.5    0.989    1.070    0.989    1.070
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    0.715    1.010
 jit_kernel_transpose                 5 15.6    0.831    0.966    0.831    0.966
 make_images_data                  4572 15.5    0.045    0.049    0.844    0.964
 mp_alltoall_d11v                  2130 13.8    0.755    0.953    0.755    0.953
 hybrid_alltoall_any               4725 16.4    0.062    0.150    0.740    0.904
 mp_alltoall_i22                    627 13.8    0.579    0.902    0.579    0.902
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.791    0.872
 multiply_cannon_metrocomm1       27432 15.5    0.034    0.036    0.404    0.853
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.840    0.846
 mp_alltoall_z22v                  1201 16.6    0.740    0.783    0.740    0.783
 cp_fm_cholesky_invert               11 10.9    0.762    0.766    0.762    0.766
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="106", plot="h2o_64_md", label="(8n/3r/4t)", y=36.936000, yerr=0.000000
PlotPoint: name="107", plot="h2o_64_md_mem", label="(8n/3r/4t)", y=528.454545, yerr=2.387986
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_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             609.501184E+06
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  219456
 MPI messages size (bytes):
  total size                        97.042514E+09
  min size                           0.000000E+00
  max size                           3.276800E+06
  average size                     442.195750E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768              101892               3336634368
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304              116112              93705670464
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         8156                     20.
 MP_Alltoall          8655                  64935.
 MP_ISend            36532                 168375.
 MP_IRecv            36532                 168349.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3622                  63495.
 MP_Allreduce        10074                    348.
 MP_Sync                54
 MP_Alltoall          1582                3682667.
 MP_SendRecv          5355                  94533.
 MP_ISendRecv         5355                  94533.
 MP_Wait             11335
 MP_ISend             5200                 225425.
 MP_IRecv             5200                 225425.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.030    0.039   29.077   29.078
 qs_mol_dyn_low                       1  2.0    0.003    0.003   28.644   28.651
 qs_forces                           11  3.9    0.003    0.004   28.487   28.488
 qs_energies                         11  4.9    0.001    0.001   26.763   26.765
 scf_env_do_scf                      11  5.9    0.000    0.001   21.856   21.856
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.007   19.221   19.221
 velocity_verlet                     10  3.0    0.001    0.001   14.705   14.714
 dbcsr_multiply_generic            2286 12.5    0.090    0.094   12.334   12.470
 qs_scf_new_mos                     108  7.5    0.001    0.001   11.107   11.129
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   11.106   11.128
 ot_scf_mini                        108  9.5    0.002    0.002   10.438   10.463
 multiply_cannon                   2286 13.5    0.229    0.239    9.814   10.143
 multiply_cannon_loop              2286 14.5    0.328    0.340    8.925    9.198
 multiply_cannon_multrec           9144 15.5    1.595    1.825    5.840    6.087
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.050    6.073
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    6.050    6.072
 ot_mini                            108 10.5    0.001    0.001    5.891    5.920
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.389    5.409
 qs_ot_get_derivative               108 11.5    0.003    0.015    4.613    4.636
 dbcsr_mm_accdrv_process          12550 15.8    3.048    4.136    4.144    4.215
 sum_up_and_integrate               119 10.3    0.039    0.042    3.716    3.721
 integrate_v_rspace                 119 11.3    0.003    0.003    3.677    3.683
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.608    3.614
 calculate_rho_elec                 119  8.7    0.060    0.061    3.607    3.613
 init_scf_run                        11  5.9    0.000    0.001    3.441    3.442
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.441    3.441
 qs_ot_get_p                        119 10.4    0.001    0.001    2.789    2.835
 init_scf_loop                       11  6.9    0.000    0.000    2.615    2.617
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.278    2.279
 pw_transfer                       1439 11.6    0.066    0.069    2.187    2.197
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    2.093    2.104
 density_rs2pw                      119  9.7    0.004    0.004    1.938    2.083
 mp_waitall_1                    115863 16.7    1.611    2.070    1.611    2.070
 grid_integrate_task_list           119 12.3    1.845    1.922    1.845    1.922
 make_m2s                          4572 13.5    0.034    0.035    1.713    1.867
 prepare_preconditioner              11  7.9    0.000    0.000    1.853    1.857
 make_preconditioner                 11  8.9    0.000    0.000    1.853    1.857
 qs_ot_p2m_diag                      50 11.0    0.022    0.023    1.849    1.852
 rs_pw_transfer                     974 11.9    0.008    0.008    1.709    1.837
 calculate_dm_sparse                119  9.5    0.000    0.000    1.791    1.810
 make_images                       4572 14.5    0.268    0.301    1.624    1.777
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.741    1.767
 fft3d_ps                          1201 14.6    0.566    0.577    1.751    1.759
 fft_wrap_pw1pw2_140                487 13.2    0.087    0.090    1.730    1.743
 jit_kernel_multiply                  9 15.8    1.058    1.659    1.058    1.659
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.655    1.655
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.653    1.654
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    1.543    1.566
 potential_pw2rs                    119 12.3    0.010    0.010    1.441    1.444
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.426    1.435
 grid_collocate_task_list           119  9.7    1.271    1.391    1.271    1.391
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.361    1.368
 cp_fm_diag_elpa_base                50 14.0    1.333    1.350    1.359    1.366
 ot_diis_step                       108 11.5    0.013    0.013    1.263    1.263
 qs_energies_init_hamiltonians       11  5.9    0.004    0.005    1.235    1.235
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.214    1.220
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    1.147    1.176
 apply_single                       119 13.6    0.000    0.000    1.147    1.176
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.119    1.132
 wfi_extrapolate                     11  7.9    0.001    0.001    1.112    1.113
 hybrid_alltoall_any               4725 16.4    0.062    0.174    0.766    0.999
 cp_fm_cholesky_invert               11 10.9    0.963    0.967    0.963    0.967
 make_images_data                  4572 15.5    0.039    0.042    0.787    0.965
 acc_transpose_blocks              9144 15.5    0.038    0.039    0.944    0.955
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.867    0.921
 mp_alltoall_d11v                  2130 13.8    0.770    0.880    0.770    0.880
 multiply_cannon_sync_h2d          9144 15.5    0.705    0.787    0.705    0.787
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.783    0.785
 multiply_cannon_metrocomm3        9144 15.5    0.019    0.019    0.466    0.756
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    0.685    0.735
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.717    0.727
 acc_transpose_blocks_kernels      9144 16.5    0.117    0.120    0.704    0.712
 mp_alltoall_z22v                  1201 16.6    0.632    0.682    0.632    0.682
 mp_allgather_i34                  2286 14.5    0.222    0.621    0.222    0.621
 dbcsr_complete_redistribute        329 12.2    0.212    0.241    0.586    0.619
 yz_to_x                            606 15.1    0.265    0.276    0.593    0.609
 jit_kernel_transpose                 5 15.6    0.588    0.594    0.588    0.594
 x_to_yz                            595 16.2    0.276    0.289    0.581    0.587
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="108", plot="h2o_64_md", label="(8n/2r/6t)", y=29.078000, yerr=0.000000
PlotPoint: name="109", plot="h2o_64_md_mem", label="(8n/2r/6t)", y=573.454545, yerr=6.813938
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_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             744.660992E+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    0.018    0.035   42.198   42.199
 qs_mol_dyn_low                       1  2.0    0.003    0.003   41.975   41.985
 qs_forces                           11  3.9    0.002    0.002   41.904   41.908
 qs_energies                         11  4.9    0.001    0.001   39.899   39.902
 scf_env_do_scf                      11  5.9    0.001    0.001   33.758   33.758
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.008   25.797   25.798
 velocity_verlet                     10  3.0    0.001    0.001   23.686   23.692
 dbcsr_multiply_generic            2286 12.5    0.097    0.099   17.537   17.718
 qs_scf_new_mos                     108  7.5    0.001    0.001   15.820   15.920
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   15.819   15.920
 ot_scf_mini                        108  9.5    0.002    0.002   14.736   14.838
 multiply_cannon                   2286 13.5    0.306    0.315   13.689   14.594
 multiply_cannon_loop              2286 14.5    0.343    0.350   12.420   13.367
 ot_mini                            108 10.5    0.001    0.001    8.821    8.939
 multiply_cannon_multrec           9144 15.5    3.400    4.863    8.600    8.697
 init_scf_loop                       11  6.9    0.000    0.000    7.931    7.933
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.434    7.579
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.013    7.434    7.579
 prepare_preconditioner              11  7.9    0.000    0.000    6.948    6.962
 make_preconditioner                 11  8.9    0.000    0.000    6.948    6.962
 qs_ot_get_derivative               108 11.5    0.001    0.001    6.802    6.904
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.725    6.857
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.477    6.838
 dbcsr_mm_accdrv_process          12550 15.8    4.137    5.664    5.078    6.415
 cp_fm_upper_to_full                 72 14.2    3.212    4.626    3.212    4.626
 qs_rho_update_rho_low              119  7.7    0.001    0.001    4.349    4.382
 calculate_rho_elec                 119  8.7    0.118    0.121    4.349    4.382
 sum_up_and_integrate               119 10.3    0.066    0.067    4.099    4.105
 integrate_v_rspace                 119 11.3    0.004    0.004    4.033    4.041
 init_scf_run                        11  5.9    0.000    0.001    3.792    3.792
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.791    3.792
 mp_waitall_1                     94719 16.7    2.411    3.394    2.411    3.394
 qs_ot_get_p                        119 10.4    0.001    0.001    3.187    3.324
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.512    2.946
 pw_transfer                       1439 11.6    0.069    0.069    2.867    2.874
 dbcsr_complete_redistribute        329 12.2    0.287    0.291    2.011    2.870
 fft_wrap_pw1pw2                   1201 12.6    0.009    0.009    2.768    2.776
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    1.701    2.543
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.192    2.449
 apply_single                       119 13.6    0.000    0.000    2.191    2.448
 make_m2s                          4572 13.5    0.038    0.038    2.272    2.446
 fft3d_ps                          1201 14.6    0.599    0.607    2.391    2.397
 mp_alltoall_i22                    627 13.8    1.505    2.377    1.505    2.377
 fft_wrap_pw1pw2_140                487 13.2    0.095    0.097    2.323    2.332
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.317    2.331
 make_images                       4572 14.5    0.356    0.389    2.150    2.324
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.466    2.302
 calculate_dm_sparse                119  9.5    0.000    0.000    2.273    2.285
 density_rs2pw                      119  9.7    0.004    0.004    2.259    2.278
 multiply_cannon_metrocomm3        9144 15.5    0.020    0.020    1.366    2.257
 qs_energies_init_hamiltonians       11  5.9    0.322    0.323    2.084    2.088
 grid_integrate_task_list           119 12.3    2.055    2.065    2.055    2.065
 ot_diis_step                       108 11.5    0.014    0.015    1.993    1.993
 qs_ot_p2m_diag                      50 11.0    0.043    0.043    1.933    1.934
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.929    1.929
 mp_sum_l                          7207 12.9    1.033    1.742    1.033    1.742
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.685    1.737
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.661    1.662
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.610    1.634
 rs_pw_transfer                     974 11.9    0.009    0.010    1.501    1.524
 grid_collocate_task_list           119  9.7    1.487    1.501    1.487    1.501
 jit_kernel_multiply                  8 15.5    0.914    1.500    0.914    1.500
 potential_pw2rs                    119 12.3    0.014    0.015    1.491    1.493
 cp_fm_cholesky_invert               11 10.9    1.458    1.462    1.458    1.462
 wfi_extrapolate                     11  7.9    0.001    0.001    1.394    1.394
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.373    1.373
 cp_fm_diag_elpa_base                50 14.0    1.227    1.280    1.372    1.372
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.338    1.349
 hybrid_alltoall_any               4725 16.4    0.087    0.147    1.114    1.321
 make_images_data                  4572 15.5    0.043    0.047    1.046    1.271
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.136    1.157
 mp_alltoall_d11v                  2130 13.8    1.127    1.156    1.127    1.156
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    1.099    1.118
 multiply_cannon_sync_h2d          9144 15.5    1.041    1.046    1.041    1.046
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.001    0.983    1.030
 yz_to_x                            606 15.1    0.460    0.469    0.964    0.975
 qs_create_task_list                 11  7.9    0.001    0.001    0.936    0.950
 generate_qs_task_list               11  8.9    0.369    0.388    0.936    0.949
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.920    0.933
 acc_transpose_blocks              9144 15.5    0.038    0.039    0.911    0.923
 mp_alltoall_z22v                  1201 16.6    0.841    0.877    0.841    0.877
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="110", plot="h2o_64_md", label="(8n/1r/12t)", y=42.199000, yerr=0.000000
PlotPoint: name="111", plot="h2o_64_md_mem", label="(8n/1r/12t)", y=701.181818, yerr=13.690197
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/09/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                    198.287135E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               8410880       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     117.0
 marketing flops                    15.646302E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank             501.075968E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 8483040
 MPI messages size (bytes):
  total size                         1.160510E+12
  min size                           0.000000E+00
  max size                           1.161504E+06
  average size                     136.803609E+03
 MPI breakdown and total messages size (bytes):
             size <=      128             1836752                        0
       128 < size <=     8192             1040592               8524529664
      8192 < size <=    32768             1486976              24362614784
     32768 < size <=   131072             2491776             216971345920
    131072 < size <=  4194304             1626944             910632720448
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3473                  66218.
 MP_Allreduce         9696                    492.
 MP_Sync                52
 MP_Alltoall          1938                1386274.
 MP_SendRecv         20900                   9096.
 MP_ISendRecv        20900                   9096.
 MP_Wait             37268
 MP_ISend            14300                  82312.
 MP_IRecv            14300                  82312.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.018    0.049   82.969   82.970
 qs_mol_dyn_low                       1  2.0    0.003    0.003   82.658   82.668
 qs_forces                           11  3.9    0.004    0.011   82.585   82.586
 qs_energies                         11  4.9    0.008    0.055   79.329   79.343
 scf_env_do_scf                      11  5.9    0.001    0.001   69.902   69.911
 scf_env_do_scf_inner_loop           99  6.5    0.008    0.041   64.248   64.249
 dbcsr_multiply_generic            2055 12.4    0.105    0.107   50.713   51.130
 qs_scf_new_mos                      99  7.5    0.000    0.001   46.672   46.802
 qs_scf_loop_do_ot                   99  8.5    0.001    0.008   46.672   46.802
 ot_scf_mini                         99  9.5    0.003    0.008   44.346   44.441
 multiply_cannon                   2055 13.4    0.183    0.188   42.431   43.272
 velocity_verlet                     10  3.0    0.001    0.002   42.802   42.802
 multiply_cannon_loop              2055 14.4    1.496    1.539   41.440   42.364
 ot_mini                             99 10.5    0.001    0.001   26.060   26.154
 qs_ot_get_derivative                99 11.5    0.001    0.001   19.301   19.404
 multiply_cannon_multrec          49320 15.4   12.485   13.233   17.388   18.077
 rebuild_ks_matrix                  110  8.3    0.000    0.001   14.759   14.932
 qs_ks_build_kohn_sham_matrix       110  9.3    0.011    0.013   14.759   14.932
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.962   13.130
 mp_waitall_1                    220248 16.4   10.666   11.590   10.666   11.590
 multiply_cannon_sync_h2d         49320 15.4   10.373   10.947   10.373   10.947
 qs_ot_get_p                        110 10.4    0.001    0.002    9.812   10.158
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    7.422    7.997
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    7.188    7.777
 apply_single                       110 13.6    0.000    0.001    7.188    7.776
 multiply_cannon_metrocomm3       49320 15.4    0.079    0.082    6.380    7.535
 init_scf_run                        11  5.9    0.000    0.001    7.391    7.391
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    7.390    7.391
 sum_up_and_integrate               110 10.3    0.038    0.055    7.195    7.212
 integrate_v_rspace                 110 11.3    0.003    0.005    7.157    7.186
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.888    7.010
 calculate_rho_elec                 110  8.6    0.021    0.026    6.887    7.009
 qs_ot_p2m_diag                      48 11.0    0.039    0.226    6.624    6.820
 ot_diis_step                        99 11.5    0.005    0.006    6.560    6.560
 cp_dbcsr_syevd                      48 12.0    0.002    0.003    5.807    5.807
 init_scf_loop                       11  6.9    0.001    0.003    5.626    5.632
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    5.280    5.351
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    5.231    5.257
 cp_fm_diag_elpa_base                48 14.0    5.217    5.243    5.229    5.255
 dbcsr_mm_accdrv_process          87628 16.1    1.903    1.976    4.777    5.177
 mp_sum_l                          6514 12.8    3.954    4.671    3.954    4.671
 rs_pw_transfer                     902 11.9    0.012    0.013    3.897    4.547
 density_rs2pw                      110  9.6    0.004    0.005    3.668    4.333
 wfi_extrapolate                     11  7.9    0.001    0.001    4.042    4.042
 make_m2s                          4110 13.4    0.061    0.065    3.872    4.001
 calculate_dm_sparse                110  9.5    0.000    0.001    3.818    3.925
 make_images                       4110 14.4    0.177    0.193    3.776    3.908
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    3.860    3.865
 multiply_cannon_metrocomm1       49320 15.4    0.062    0.065    2.412    3.680
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    3.500    3.562
 pw_transfer                       1331 11.6    0.055    0.069    3.334    3.398
 grid_integrate_task_list           110 12.3    3.239    3.396    3.239    3.396
 prepare_preconditioner              11  7.9    0.000    0.000    3.351    3.363
 make_preconditioner                 11  8.9    0.000    0.001    3.351    3.363
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.246    3.313
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    3.184    3.253
 make_full_inverse_cholesky          11  9.9    0.000    0.000    3.131    3.180
 calculate_first_density_matrix       1  7.0    0.001    0.005    3.067    3.072
 fft3d_ps                          1111 14.6    0.776    0.882    2.772    2.828
 fft_wrap_pw1pw2_140                451 13.1    0.171    0.190    2.754    2.825
 mp_waitany                       14300 13.8    1.964    2.780    1.964    2.780
 jit_kernel_multiply                 13 15.9    2.597    2.769    2.597    2.769
 potential_pw2rs                    110 12.3    0.006    0.007    2.711    2.737
 mp_alltoall_d11v                  2046 13.8    2.093    2.543    2.093    2.543
 acc_transpose_blocks             49320 15.4    0.211    0.219    2.297    2.370
 grid_collocate_task_list           110  9.6    2.106    2.357    2.106    2.357
 mp_sum_d                          3887 11.9    1.711    2.255    1.711    2.255
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.940    1.959
 make_images_data                  4110 15.4    0.042    0.045    1.767    1.910
 cp_fm_cholesky_invert               11 10.9    1.832    1.836    1.832    1.836
 hybrid_alltoall_any               4261 16.3    0.082    0.478    1.539    1.792
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.765    1.786
 rs_pw_transfer_RS2PW_140           121 11.5    0.167    0.174    1.023    1.730
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="200", plot="h2o_128_md", label="(8n/12r/1t)", y=82.970000, yerr=0.000000
PlotPoint: name="201", plot="h2o_128_md_mem", label="(8n/12r/1t)", y=476.454545, yerr=1.970862
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_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             588.038144E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1972800
 MPI messages size (bytes):
  total size                         1.077520E+12
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     546.188250E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               14916                        0
       128 < size <=     8192              222984               1826684928
      8192 < size <=    32768              520356              13399818240
     32768 < size <=   131072              372336              35386294272
    131072 < size <=  4194304              787758             788321309808
   4194304 < size <= 16777216               54450             238588003280
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3473                  66437.
 MP_Allreduce         9695                    570.
 MP_Sync                52
 MP_Alltoall          1717                2462973.
 MP_SendRecv         10340                  26400.
 MP_ISendRecv        10340                  26400.
 MP_Wait             22352
 MP_ISend            10164                 155761.
 MP_IRecv            10164                 155761.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.044    0.054   71.266   71.268
 qs_mol_dyn_low                       1  2.0    0.003    0.003   70.804   70.814
 qs_forces                           11  3.9    0.003    0.003   70.731   70.732
 qs_energies                         11  4.9    0.001    0.001   67.384   67.388
 scf_env_do_scf                      11  5.9    0.000    0.001   58.306   58.309
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.008   50.348   50.349
 dbcsr_multiply_generic            2055 12.4    0.115    0.119   38.793   38.997
 velocity_verlet                     10  3.0    0.001    0.001   36.767   36.768
 qs_scf_new_mos                      99  7.5    0.001    0.001   33.870   34.052
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   33.869   34.051
 multiply_cannon                   2055 13.4    0.221    0.242   32.059   33.365
 ot_scf_mini                         99  9.5    0.003    0.003   32.199   32.369
 multiply_cannon_loop              2055 14.4    0.925    0.953   30.743   31.676
 ot_mini                             99 10.5    0.001    0.001   18.779   18.958
 multiply_cannon_multrec          24660 15.4    7.599    9.789   14.282   16.326
 rebuild_ks_matrix                  110  8.3    0.000    0.000   13.907   14.023
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.014   13.907   14.022
 qs_ot_get_derivative                99 11.5    0.001    0.002   12.972   13.142
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.262   12.354
 mp_waitall_1                    176588 16.5    8.079   10.443    8.079   10.443
 multiply_cannon_metrocomm3       24660 15.4    0.070    0.072    5.642    8.494
 multiply_cannon_sync_h2d         24660 15.4    7.075    8.308    7.075    8.308
 init_scf_loop                       11  6.9    0.000    0.000    7.918    7.919
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    6.509    7.213
 apply_single                       110 13.6    0.000    0.001    6.509    7.212
 dbcsr_mm_accdrv_process          52282 16.1    4.712    6.236    6.522    7.057
 qs_ot_get_p                        110 10.4    0.001    0.001    6.762    6.986
 init_scf_run                        11  5.9    0.000    0.001    6.720    6.721
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    6.720    6.720
 sum_up_and_integrate               110 10.3    0.054    0.063    6.685    6.701
 integrate_v_rspace                 110 11.3    0.003    0.003    6.630    6.652
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.266    6.276
 calculate_rho_elec                 110  8.6    0.040    0.048    6.265    6.275
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    5.189    5.909
 prepare_preconditioner              11  7.9    0.000    0.000    5.831    5.853
 make_preconditioner                 11  8.9    0.000    0.000    5.831    5.853
 ot_diis_step                        99 11.5    0.010    0.010    5.753    5.754
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.415    5.586
 qs_ot_p2m_diag                      48 11.0    0.029    0.045    4.822    4.843
 make_m2s                          4110 13.4    0.057    0.059    4.242    4.696
 make_images                       4110 14.4    0.402    0.447    4.133    4.584
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    4.387    4.387
 density_rs2pw                      110  9.6    0.004    0.005    3.410    3.983
 pw_transfer                       1331 11.6    0.066    0.076    3.763    3.906
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    3.805    3.806
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.009    3.656    3.802
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.780    3.790
 cp_fm_diag_elpa_base                48 14.0    3.732    3.755    3.778    3.787
 rs_pw_transfer                     902 11.9    0.012    0.014    3.067    3.652
 wfi_extrapolate                     11  7.9    0.001    0.001    3.583    3.584
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    3.473    3.509
 grid_integrate_task_list           110 12.3    3.151    3.360    3.151    3.360
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.230    3.325
 fft_wrap_pw1pw2_140                451 13.1    0.203    0.220    3.052    3.202
 fft3d_ps                          1111 14.6    1.109    1.339    3.004    3.142
 calculate_first_density_matrix       1  7.0    0.000    0.000    3.031    3.034
 calculate_dm_sparse                110  9.5    0.001    0.001    2.982    3.010
 cp_fm_cholesky_invert               11 10.9    2.774    2.781    2.774    2.781
 make_images_data                  4110 15.4    0.046    0.050    2.288    2.742
 hybrid_alltoall_any               4261 16.3    0.103    0.445    1.997    2.659
 mp_sum_l                          6514 12.8    1.867    2.600    1.867    2.600
 potential_pw2rs                    110 12.3    0.008    0.008    2.510    2.523
 grid_collocate_task_list           110  9.6    2.058    2.476    2.058    2.476
 jit_kernel_multiply                 10 16.2    1.456    2.361    1.456    2.361
 mp_alltoall_d11v                  2046 13.8    1.706    2.038    1.706    2.038
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.971    1.987
 qs_energies_init_hamiltonians       11  5.9    0.001    0.004    1.851    1.852
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.811    1.829
 mp_waitany                       10164 13.8    1.209    1.759    1.209    1.759
 acc_transpose_blocks             24660 15.4    0.112    0.118    1.613    1.732
 multiply_cannon_metrocomm4       22605 15.4    0.074    0.078    0.771    1.713
 mp_allgather_i34                  2055 14.4    0.639    1.630    0.639    1.630
 mp_irecv_dv                      57340 16.2    0.646    1.593    0.646    1.593
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.543    1.553
 rs_pw_transfer_RS2PW_140           121 11.5    0.206    0.216    0.938    1.518
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.368    1.476
 dbcsr_complete_redistribute        325 12.2    0.241    0.308    1.158    1.433
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="202", plot="h2o_128_md", label="(8n/6r/2t)", y=71.268000, yerr=0.000000
PlotPoint: name="203", plot="h2o_128_md_mem", label="(8n/6r/2t)", y=555.272727, yerr=6.239040
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_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             658.657280E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                  854880
 MPI messages size (bytes):
  total size                       708.322787E+09
  min size                           0.000000E+00
  max size                           6.553600E+06
  average size                     828.564000E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768              222984               7302414336
     32768 < size <=   131072              153888              10085203968
    131072 < size <=  4194304              389376             200257044480
   4194304 < size <= 16777216               82208             490679162176
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3473                  66428.
 MP_Allreduce         9694                    567.
 MP_Sync                52
 MP_Alltoall          1496                4511006.
 MP_SendRecv          6820                  27424.
 MP_ISendRecv         6820                  27424.
 MP_Wait             25498
 MP_ISend            17072                 115022.
 MP_IRecv            17072                 115022.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.201    0.609   63.124   63.126
 qs_mol_dyn_low                       1  2.0    0.003    0.006   62.104   62.114
 qs_forces                           11  3.9    0.003    0.005   62.032   62.034
 qs_energies                         11  4.9    0.002    0.005   58.821   58.825
 scf_env_do_scf                      11  5.9    0.001    0.002   50.404   50.404
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.006   41.471   41.472
 velocity_verlet                     10  3.0    0.001    0.002   33.360   33.362
 dbcsr_multiply_generic            2055 12.4    0.107    0.112   29.424   29.666
 qs_scf_new_mos                      99  7.5    0.001    0.001   26.188   26.289
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   26.187   26.289
 ot_scf_mini                         99  9.5    0.003    0.004   24.948   25.071
 multiply_cannon                   2055 13.4    0.213    0.230   22.857   23.857
 multiply_cannon_loop              2055 14.4    0.616    0.629   21.580   22.540
 ot_mini                             99 10.5    0.001    0.001   14.391   14.511
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.554   12.686
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.016   12.553   12.686
 qs_ks_update_qs_env                110  7.6    0.001    0.001   11.070   11.191
 multiply_cannon_multrec          16440 15.4    4.005    5.054   10.126   11.077
 mp_waitall_1                    139946 16.5    7.238   10.260    7.238   10.260
 qs_ot_get_derivative                99 11.5    0.002    0.010    9.933   10.055
 init_scf_loop                       11  6.9    0.001    0.003    8.896    8.897
 multiply_cannon_metrocomm3       16440 15.4    0.044    0.046    4.543    7.365
 prepare_preconditioner              11  7.9    0.000    0.000    7.060    7.077
 make_preconditioner                 11  8.9    0.000    0.001    7.059    7.077
 make_full_inverse_cholesky          11  9.9    0.000    0.001    6.396    6.752
 sum_up_and_integrate               110 10.3    0.061    0.062    6.695    6.709
 integrate_v_rspace                 110 11.3    0.003    0.003    6.634    6.648
 dbcsr_mm_accdrv_process          34862 16.1    4.803    5.414    5.976    6.277
 qs_rho_update_rho_low              110  7.6    0.001    0.002    6.244    6.257
 calculate_rho_elec                 110  8.6    0.059    0.059    6.244    6.257
 init_scf_run                        11  5.9    0.000    0.001    5.911    5.911
 scf_env_initial_rho_setup           11  6.9    0.006    0.046    5.911    5.911
 qs_ot_get_p                        110 10.4    0.001    0.001    5.750    5.876
 apply_preconditioner_dbcsr         110 12.6    0.001    0.010    5.159    5.717
 apply_single                       110 13.6    0.000    0.000    5.158    5.716
 make_m2s                          4110 13.4    0.050    0.051    4.205    4.628
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.697    4.527
 make_images                       4110 14.4    0.394    0.511    4.091    4.514
 density_rs2pw                      110  9.6    0.004    0.005    3.313    4.493
 ot_diis_step                        99 11.5    0.011    0.018    4.427    4.428
 multiply_cannon_sync_h2d         16440 15.4    3.704    4.330    3.704    4.330
 rs_pw_transfer                     902 11.9    0.011    0.012    2.950    4.087
 qs_ot_p2m_diag                      48 11.0    0.042    0.044    4.072    4.080
 pw_transfer                       1331 11.6    0.066    0.074    3.773    3.781
 cp_dbcsr_syevd                      48 12.0    0.003    0.004    3.715    3.715
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.009    3.666    3.677
 grid_integrate_task_list           110 12.3    3.165    3.400    3.165    3.400
 cp_fm_diag_elpa                     48 13.0    0.000    0.001    3.142    3.150
 cp_fm_diag_elpa_base                48 14.0    3.071    3.102    3.139    3.148
 fft_wrap_pw1pw2_140                451 13.1    0.213    0.219    3.114    3.123
 wfi_extrapolate                     11  7.9    0.001    0.002    3.031    3.031
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.002    3.020    3.022
 fft3d_ps                          1111 14.6    1.092    1.108    2.963    2.974
 make_images_data                  4110 15.4    0.043    0.048    2.388    2.896
 mp_sum_l                          6514 12.8    2.078    2.847    2.078    2.847
 cp_fm_cholesky_invert               11 10.9    2.818    2.823    2.818    2.823
 hybrid_alltoall_any               4261 16.3    0.105    0.374    2.156    2.818
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.001    2.678    2.720
 calculate_first_density_matrix       1  7.0    0.001    0.003    2.633    2.635
 calculate_dm_sparse                110  9.5    0.001    0.001    2.511    2.546
 grid_collocate_task_list           110  9.6    2.080    2.480    2.080    2.480
 potential_pw2rs                    110 12.3    0.010    0.010    2.441    2.449
 mp_waitany                       17072 13.8    1.261    2.445    1.261    2.445
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.375    2.441
 mp_alltoall_d11v                  2046 13.8    1.883    2.321    1.883    2.321
 multiply_cannon_metrocomm4       14385 15.4    0.045    0.048    0.857    2.262
 mp_irecv_dv                      48980 15.7    0.787    2.138    0.787    2.138
 rs_pw_transfer_RS2PW_140           121 11.5    0.176    0.182    0.923    2.050
 qs_energies_init_hamiltonians       11  5.9    0.002    0.009    2.046    2.047
 dbcsr_complete_redistribute        325 12.2    0.319    0.347    1.496    1.952
 jit_kernel_multiply                  8 16.4    0.782    1.901    0.782    1.901
 cp_fm_upper_to_full                 70 14.2    1.396    1.763    1.396    1.763
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.685    1.700
 cp_fm_cholesky_decompose            22 10.9    1.669    1.688    1.669    1.688
 mp_allgather_i34                  2055 14.4    0.600    1.627    0.600    1.627
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.469    1.483
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    0.996    1.444
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.367    1.444
 rs_gather_matrices                 110 12.3    0.234    0.264    0.952    1.343
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.283    1.290
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="204", plot="h2o_128_md", label="(8n/4r/3t)", y=63.126000, yerr=0.000000
PlotPoint: name="205", plot="h2o_128_md_mem", label="(8n/4r/3t)", y=624.272727, yerr=8.904451
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_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             723.410944E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                  937080
 MPI messages size (bytes):
  total size                       523.723932E+09
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     558.889250E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6996                        0
       128 < size <=     8192                 264                  2162688
      8192 < size <=    32768              304932               8165326848
     32768 < size <=   131072              110640               6338641920
    131072 < size <=  4194304              489498             400769458320
   4194304 < size <= 16777216               24750             108449092400
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3473                  66426.
 MP_Allreduce         9694                    608.
 MP_Sync                52
 MP_Alltoall          1496                5863162.
 MP_SendRecv          5060                  43184.
 MP_ISendRecv         5060                  43184.
 MP_Wait             20042
 MP_ISend            13376                 163145.
 MP_IRecv            13376                 163145.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.025    0.054   67.508   67.511
 qs_mol_dyn_low                       1  2.0    0.003    0.004   67.189   67.198
 qs_forces                           11  3.9    0.004    0.012   67.117   67.118
 qs_energies                         11  4.9    0.006    0.022   63.647   63.651
 scf_env_do_scf                      11  5.9    0.002    0.006   54.340   54.347
 scf_env_do_scf_inner_loop           99  6.5    0.006    0.015   42.052   42.054
 velocity_verlet                     10  3.0    0.001    0.002   37.321   37.323
 dbcsr_multiply_generic            2055 12.4    0.113    0.119   30.181   30.468
 qs_scf_new_mos                      99  7.5    0.001    0.001   26.696   26.812
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   26.695   26.811
 ot_scf_mini                         99  9.5    0.003    0.003   25.080   25.199
 multiply_cannon                   2055 13.4    0.242    0.258   23.128   24.518
 multiply_cannon_loop              2055 14.4    0.883    0.902   21.755   22.330
 ot_mini                             99 10.5    0.001    0.001   14.198   14.340
 multiply_cannon_multrec          24660 15.4    4.251    6.853   12.648   13.833
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.458   12.582
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.015   12.458   12.582
 init_scf_loop                       11  6.9    0.006    0.023   12.245   12.250
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.997   11.110
 qs_ot_get_derivative                99 11.5    0.002    0.010   10.057   10.183
 prepare_preconditioner              11  7.9    0.000    0.001    9.910    9.926
 make_preconditioner                 11  8.9    0.000    0.002    9.910    9.926
 make_full_inverse_cholesky          11  9.9    0.000    0.000    8.133    9.585
 dbcsr_mm_accdrv_process          52304 16.0    6.769    8.217    8.250    9.176
 sum_up_and_integrate               110 10.3    0.068    0.072    6.660    6.677
 integrate_v_rspace                 110 11.3    0.003    0.004    6.591    6.605
 init_scf_run                        11  5.9    0.000    0.001    6.508    6.509
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    6.508    6.508
 qs_ot_get_p                        110 10.4    0.001    0.001    6.303    6.493
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.276    6.286
 calculate_rho_elec                 110  8.6    0.078    0.081    6.275    6.285
 mp_waitall_1                    121746 16.5    4.429    6.281    4.429    6.281
 make_m2s                          4110 13.4    0.060    0.061    5.466    5.755
 make_images                       4110 14.4    0.579    0.700    5.325    5.609
 cp_fm_upper_to_full                 70 14.2    3.329    4.825    3.329    4.825
 ot_diis_step                        99 11.5    0.011    0.011    4.103    4.103
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.014    4.103
 apply_single                       110 13.6    0.000    0.000    4.013    4.103
 qs_ot_p2m_diag                      48 11.0    0.054    0.063    4.062    4.077
 pw_transfer                       1331 11.6    0.065    0.074    3.990    4.019
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.009    3.884    3.917
 dbcsr_complete_redistribute        325 12.2    0.415    0.458    2.703    3.826
 density_rs2pw                      110  9.6    0.004    0.004    3.196    3.706
 calculate_dm_sparse                110  9.5    0.001    0.001    3.642    3.670
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.589    3.590
 grid_integrate_task_list           110 12.3    3.257    3.459    3.257    3.459
 calculate_first_density_matrix       1  7.0    0.004    0.027    3.368    3.371
 fft_wrap_pw1pw2_140                451 13.1    0.203    0.215    3.326    3.365
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.281    3.340
 multiply_cannon_sync_h2d         24660 15.4    3.187    3.331    3.187    3.331
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    2.167    3.287
 fft3d_ps                          1111 14.6    1.096    1.132    3.173    3.195
 make_images_data                  4110 15.4    0.047    0.051    2.765    3.082
 multiply_cannon_metrocomm3       24660 15.4    0.035    0.036    1.504    3.081
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.995    3.059
 wfi_extrapolate                     11  7.9    0.001    0.001    3.047    3.048
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.031    3.041
 cp_fm_diag_elpa_base                48 14.0    2.879    2.941    3.028    3.039
 rs_pw_transfer                     902 11.9    0.010    0.012    2.496    3.020
 hybrid_alltoall_any               4261 16.3    0.120    0.457    2.311    3.011
 mp_alltoall_i22                    605 13.7    1.684    2.872    1.684    2.872
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.768    2.857
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.777    2.779
 cp_fm_cholesky_invert               11 10.9    2.725    2.733    2.725    2.733
 grid_collocate_task_list           110  9.6    2.180    2.465    2.180    2.465
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.416    2.454
 potential_pw2rs                    110 12.3    0.012    0.013    2.291    2.300
 qs_energies_init_hamiltonians       11  5.9    0.001    0.005    2.293    2.295
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    2.261    2.279
 acc_transpose_blocks             24660 15.4    0.107    0.108    2.212    2.231
 mp_alltoall_d11v                  2046 13.8    1.785    2.042    1.785    2.042
 jit_kernel_multiply                 10 15.8    1.148    1.825    1.148    1.825
 cp_fm_cholesky_decompose            22 10.9    1.691    1.732    1.691    1.732
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.702    1.732
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.706    1.717
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.597    1.707
 acc_transpose_blocks_kernels     24660 16.4    0.302    0.307    1.569    1.576
 mp_waitany                       13376 13.8    1.087    1.571    1.087    1.571
 mp_allgather_i34                  2055 14.4    0.469    1.542    0.469    1.542
 multiply_cannon_metrocomm4       20550 15.4    0.058    0.061    0.835    1.532
 mp_irecv_dv                      62702 16.1    0.734    1.452    0.734    1.452
 mp_sum_l                          6514 12.8    0.907    1.408    0.907    1.408
 rs_pw_transfer_RS2PW_140           121 11.5    0.169    0.178    0.829    1.359
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="206", plot="h2o_128_md", label="(8n/3r/4t)", y=67.511000, yerr=0.000000
PlotPoint: name="207", plot="h2o_128_md_mem", label="(8n/3r/4t)", y=687.181818, yerr=5.637830
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_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             855.928832E+06
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  197280
 MPI messages size (bytes):
  total size                       339.125567E+09
  min size                           0.000000E+00
  max size                          13.107200E+06
  average size                       1.719006E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 132                  4325376
     32768 < size <=   131072               88656              11620319232
    131072 < size <=  4194304               89424             117209825280
   4194304 < size <= 16777216               17616             210291069504
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         7346                     33.
 MP_Alltoall          8043                 263767.
 MP_ISend            32836                 654203.
 MP_IRecv            32836                 654587.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3473                  66424.
 MP_Allreduce         9694                    649.
 MP_Sync                52
 MP_Alltoall          1496                8504061.
 MP_SendRecv          3300                  54848.
 MP_ISendRecv         3300                  54848.
 MP_Wait             13926
 MP_ISend             9240                 278857.
 MP_IRecv             9240                 278857.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.041    0.074   57.861   57.862
 qs_mol_dyn_low                       1  2.0    0.003    0.003   57.243   57.313
 qs_forces                           11  3.9    0.003    0.003   57.167   57.168
 qs_energies                         11  4.9    0.001    0.001   53.440   53.445
 scf_env_do_scf                      11  5.9    0.000    0.001   44.686   44.686
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.008   36.650   36.651
 velocity_verlet                     10  3.0    0.001    0.001   31.734   31.737
 dbcsr_multiply_generic            2055 12.4    0.103    0.108   23.871   24.068
 qs_scf_new_mos                      99  7.5    0.001    0.001   21.188   21.235
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   21.188   21.234
 ot_scf_mini                         99  9.5    0.002    0.002   19.946   19.973
 multiply_cannon                   2055 13.4    0.245    0.256   18.304   19.841
 multiply_cannon_loop              2055 14.4    0.320    0.332   16.943   17.362
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.232   12.269
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.013   12.231   12.269
 ot_mini                             99 10.5    0.001    0.001   10.999   11.017
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.875   10.906
 multiply_cannon_multrec           8220 15.4    3.245    4.468    8.263    9.222
 init_scf_loop                       11  6.9    0.000    0.000    7.989    7.991
 mp_waitall_1                    103326 16.6    6.041    7.704    6.041    7.704
 qs_ot_get_derivative                99 11.5    0.001    0.002    7.219    7.244
 sum_up_and_integrate               110 10.3    0.080    0.082    6.661    6.674
 integrate_v_rspace                 110 11.3    0.003    0.003    6.581    6.593
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.516    6.527
 calculate_rho_elec                 110  8.6    0.116    0.116    6.516    6.526
 prepare_preconditioner              11  7.9    0.000    0.000    6.207    6.210
 make_preconditioner                 11  8.9    0.000    0.000    6.207    6.210
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.789    5.865
 dbcsr_mm_accdrv_process          17442 15.9    2.933    3.987    4.889    5.783
 init_scf_run                        11  5.9    0.000    0.001    5.577    5.577
 scf_env_initial_rho_setup           11  6.9    0.008    0.010    5.577    5.577
 qs_ot_get_p                        110 10.4    0.001    0.001    5.009    5.033
 make_m2s                          4110 13.4    0.038    0.040    4.286    4.554
 make_images                       4110 14.4    0.641    0.700    4.157    4.425
 multiply_cannon_metrocomm3        8220 15.4    0.017    0.018    2.914    4.329
 pw_transfer                       1331 11.6    0.066    0.074    4.251    4.273
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.009    4.143    4.168
 ot_diis_step                        99 11.5    0.012    0.012    3.757    3.758
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    3.672    3.694
 apply_single                       110 13.6    0.000    0.000    3.671    3.694
 density_rs2pw                      110  9.6    0.004    0.004    3.237    3.613
 fft_wrap_pw1pw2_140                451 13.1    0.216    0.219    3.568    3.605
 qs_ot_p2m_diag                      48 11.0    0.081    0.084    3.596    3.600
 grid_integrate_task_list           110 12.3    3.356    3.540    3.356    3.540
 fft3d_ps                          1111 14.6    1.152    1.181    3.384    3.398
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.293    3.294
 multiply_cannon_sync_h2d          8220 15.4    2.909    3.061    2.909    3.061
 cp_fm_cholesky_invert               11 10.9    3.008    3.012    3.008    3.012
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.955    2.957
 make_images_data                  4110 15.4    0.038    0.043    2.449    2.890
 wfi_extrapolate                     11  7.9    0.001    0.001    2.779    2.779
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    2.759    2.767
 cp_fm_diag_elpa_base                48 14.0    2.700    2.730    2.757    2.765
 hybrid_alltoall_any               4261 16.3    0.200    0.859    2.349    2.762
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.692    2.696
 qs_energies_init_hamiltonians       11  5.9    0.010    0.013    2.693    2.694
 rs_pw_transfer                     902 11.9    0.010    0.011    2.264    2.665
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.602    2.618
 grid_collocate_task_list           110  9.6    2.278    2.538    2.278    2.538
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    2.526    2.538
 calculate_dm_sparse                110  9.5    0.001    0.001    2.476    2.521
 potential_pw2rs                    110 12.3    0.015    0.015    2.191    2.196
 jit_kernel_multiply                  8 15.7    1.646    2.181    1.646    2.181
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.771    1.988
 mp_alltoall_d11v                  2046 13.8    1.658    1.924    1.658    1.924
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    1.812    1.825
 cp_fm_cholesky_decompose            22 10.9    1.734    1.749    1.734    1.749
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.694    1.700
 mp_allgather_i34                  2055 14.4    0.546    1.669    0.546    1.669
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    1.520    1.636
 dbcsr_complete_redistribute        325 12.2    0.563    0.586    1.472    1.578
 mp_waitany                        9240 13.8    1.082    1.511    1.082    1.511
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.436    1.449
 qs_create_task_list                 11  7.9    0.001    0.001    1.226    1.324
 generate_qs_task_list               11  8.9    0.378    0.446    1.225    1.323
 multiply_cannon_metrocomm1        8220 15.4    0.021    0.022    0.818    1.202
 rs_pw_transfer_RS2PW_140           121 11.5    0.161    0.165    0.802    1.201
 rs_gather_matrices                 110 12.3    0.325    0.367    0.942    1.200
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.152    1.167
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="208", plot="h2o_128_md", label="(8n/2r/6t)", y=57.862000, yerr=0.000000
PlotPoint: name="209", plot="h2o_128_md_mem", label="(8n/2r/6t)", y=796.000000, yerr=18.645009
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_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               1.349460E+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    0.034    0.070   92.417   92.420
 qs_mol_dyn_low                       1  2.0    0.003    0.003   92.051   92.060
 qs_forces                           11  3.9    0.003    0.003   91.973   91.973
 qs_energies                         11  4.9    0.001    0.001   87.768   87.770
 scf_env_do_scf                      11  5.9    0.001    0.001   75.569   75.570
 velocity_verlet                     10  3.0    0.001    0.001   56.795   56.802
 scf_env_do_scf_inner_loop           99  6.5    0.006    0.028   46.531   46.533
 dbcsr_multiply_generic            2055 12.4    0.118    0.122   31.225   31.306
 init_scf_loop                       11  6.9    0.000    0.000   28.963   28.967
 qs_scf_new_mos                      99  7.5    0.001    0.001   27.812   27.835
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   27.812   27.835
 prepare_preconditioner              11  7.9    0.000    0.000   26.917   26.922
 make_preconditioner                 11  8.9    0.000    0.000   26.917   26.922
 make_full_inverse_cholesky          11  9.9    0.000    0.000   20.994   26.389
 ot_scf_mini                         99  9.5    0.002    0.002   26.063   26.091
 multiply_cannon                   2055 13.4    0.344    0.371   23.895   24.945
 multiply_cannon_loop              2055 14.4    0.340    0.345   22.093   22.982
 cp_fm_upper_to_full                 70 14.2   13.016   18.657   13.016   18.657
 ot_mini                             99 10.5    0.001    0.001   14.980   15.008
 rebuild_ks_matrix                  110  8.3    0.001    0.001   14.384   14.419
 qs_ks_build_kohn_sham_matrix       110  9.3    0.014    0.014   14.384   14.418
 qs_ks_update_qs_env                110  7.6    0.001    0.001   13.030   13.061
 multiply_cannon_multrec           8220 15.4    4.669    4.916   11.593   11.904
 dbcsr_complete_redistribute        325 12.2    1.016    1.040    7.533   10.818
 qs_ot_get_derivative                99 11.5    0.057    0.067   10.463   10.486
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    6.484    9.761
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    5.908    9.148
 mp_waitall_1                     84994 16.7    7.855    8.943    7.855    8.943
 mp_alltoall_i22                    605 13.7    5.537    8.803    5.537    8.803
 qs_rho_update_rho_low              110  7.6    0.001    0.001    7.946    7.984
 calculate_rho_elec                 110  8.6    0.227    0.228    7.945    7.984
 init_scf_run                        11  5.9    0.000    0.001    7.899    7.899
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    7.898    7.899
 sum_up_and_integrate               110 10.3    0.151    0.153    7.559    7.570
 integrate_v_rspace                 110 11.3    0.004    0.004    7.407    7.417
 dbcsr_mm_accdrv_process          11614 15.7    3.547    4.163    6.780    7.228
 qs_ot_get_p                        110 10.4    0.001    0.001    5.888    5.926
 multiply_cannon_metrocomm3        8220 15.4    0.018    0.018    5.072    5.869
 make_m2s                          4110 13.4    0.043    0.044    5.263    5.758
 make_images                       4110 14.4    0.887    0.942    5.076    5.569
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.882    5.448
 apply_single                       110 13.6    0.000    0.000    4.882    5.448
 cp_fm_cholesky_invert               11 10.9    5.384    5.389    5.384    5.389
 pw_transfer                       1331 11.6    0.075    0.075    5.381    5.389
 fft_wrap_pw1pw2                   1111 12.6    0.009    0.010    5.264    5.272
 fft_wrap_pw1pw2_140                451 13.1    0.221    0.223    4.562    4.570
 ot_diis_step                        99 11.5    0.015    0.015    4.491    4.491
 calculate_dm_sparse                110  9.5    0.001    0.001    4.468    4.484
 fft3d_ps                          1111 14.6    1.300    1.306    4.456    4.467
 calculate_first_density_matrix       1  7.0    0.000    0.000    4.370    4.371
 qs_ot_p2m_diag                      48 11.0    0.151    0.155    4.318    4.324
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.565    4.259
 density_rs2pw                      110  9.6    0.004    0.004    3.933    3.973
 multiply_cannon_sync_h2d          8220 15.4    3.946    3.956    3.946    3.956
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.874    3.875
 grid_integrate_task_list           110 12.3    3.695    3.791    3.695    3.791
 jit_kernel_multiply                 10 15.3    3.033    3.726    3.033    3.726
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    3.695    3.695
 hybrid_alltoall_any               4261 16.3    0.259    0.563    2.907    3.584
 make_images_data                  4110 15.4    0.042    0.045    2.843    3.493
 wfi_extrapolate                     11  7.9    0.001    0.001    3.398    3.399
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.248    3.248
 cp_fm_diag_elpa_base                48 14.0    2.696    2.900    3.246    3.246
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    3.018    3.036
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    3.020    3.024
 grid_collocate_task_list           110  9.6    2.659    2.750    2.659    2.750
 potential_pw2rs                    110 12.3    0.021    0.022    2.575    2.581
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.514    2.534
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.438    2.451
 rs_pw_transfer                     902 11.9    0.011    0.011    2.388    2.425
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    2.208    2.280
 mp_alltoall_d11v                  2046 13.8    2.065    2.212    2.065    2.212
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    2.092    2.172
 cp_fm_cholesky_decompose            22 10.9    2.091    2.112    2.091    2.112
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.962    1.965
 qs_create_task_list                 11  7.9    0.001    0.001    1.898    1.946
 generate_qs_task_list               11  8.9    0.735    0.787    1.897    1.945
 mp_sum_l                          6514 12.8    1.182    1.860    1.182    1.860
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="210", plot="h2o_128_md", label="(8n/1r/12t)", y=92.420000, yerr=0.000000
PlotPoint: name="211", plot="h2o_128_md_mem", label="(8n/1r/12t)", y=1212.818182, yerr=60.259768
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/15/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                      1.103326E+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              12044928       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     565.1
 marketing flops                   145.647559E+12
 -------------------------------------------------------------------------------
 # multiplications                           2527
 max memory usage/rank             629.030912E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                10431456
 MPI messages size (bytes):
  total size                         4.526012E+12
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     433.881156E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               65736                        0
       128 < size <=     8192                1232                 10092544
      8192 < size <=    32768             3605352              96403587072
     32768 < size <=   131072             1305088              74666999808
    131072 < size <=  4194304             5190114            3200148350408
   4194304 < size <= 16777216              263934            1154745839544
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4024                  57456.
 MP_Allreduce        11059                    800.
 MP_Sync                87
 MP_Alltoall          2242                2521907.
 MP_SendRecv         24510                  18752.
 MP_ISendRecv        24510                  18752.
 MP_Wait             42802
 MP_ISend            16140                 108019.
 MP_IRecv            16140                 108019.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.023    0.042  210.752  210.754
 qs_mol_dyn_low                       1  2.0    0.003    0.004  210.327  210.341
 qs_forces                           11  3.9    0.005    0.005  210.235  210.236
 qs_energies                         11  4.9    0.001    0.001  204.641  204.659
 scf_env_do_scf                      11  5.9    0.001    0.001  186.837  186.841
 scf_env_do_scf_inner_loop          118  6.6    0.003    0.008  165.732  165.733
 dbcsr_multiply_generic            2527 12.6    0.181    0.186  125.925  126.575
 velocity_verlet                     10  3.0    0.001    0.001  125.443  125.444
 qs_scf_new_mos                     118  7.6    0.001    0.001  124.883  125.050
 qs_scf_loop_do_ot                  118  8.6    0.001    0.001  124.882  125.049
 ot_scf_mini                        118  9.6    0.003    0.003  118.262  118.415
 multiply_cannon                   2527 13.6    0.262    0.285  102.784  104.571
 multiply_cannon_loop              2527 14.6    2.073    2.122  100.349  102.394
 ot_mini                            118 10.6    0.001    0.001   65.794   65.950
 multiply_cannon_multrec          60648 15.6   33.785   35.734   42.521   44.631
 qs_ot_get_derivative               118 11.6    0.009    0.020   40.847   40.991
 rebuild_ks_matrix                  129  8.3    0.001    0.001   34.608   34.728
 qs_ks_build_kohn_sham_matrix       129  9.3    0.016    0.018   34.607   34.728
 mp_waitall_1                    269254 16.5   28.393   31.390   28.393   31.390
 qs_ks_update_qs_env                129  7.6    0.001    0.001   31.188   31.314
 qs_ot_get_p                        129 10.4    0.001    0.001   30.320   30.579
 multiply_cannon_sync_h2d         60648 15.6   27.932   29.669   27.932   29.669
 apply_preconditioner_dbcsr         129 12.6    0.000    0.001   24.522   25.212
 apply_single                       129 13.6    0.001    0.001   24.522   25.212
 ot_diis_step                       118 11.6    0.008    0.008   24.727   24.728
 qs_ot_p2m_diag                      83 11.4    0.079    0.091   23.700   23.741
 cp_dbcsr_syevd                      83 12.4    0.004    0.005   21.135   21.136
 init_scf_loop                       11  6.9    0.000    0.001   21.030   21.031
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002   19.134   19.246
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   18.107   18.139
 cp_fm_diag_elpa_base                83 14.4   18.031   18.081   18.103   18.136
 multiply_cannon_metrocomm3       60648 15.6    0.116    0.121   15.783   17.562
 prepare_preconditioner              11  7.9    0.000    0.000   16.051   16.108
 make_preconditioner                 11  8.9    0.000    0.000   16.051   16.108
 make_full_inverse_cholesky          11  9.9    0.000    0.000   15.292   15.481
 sum_up_and_integrate               129 10.3    0.091    0.109   14.556   14.574
 integrate_v_rspace                 129 11.3    0.004    0.005   14.465   14.486
 make_m2s                          5054 13.6    0.105    0.113   13.817   14.189
 qs_rho_update_rho_low              129  7.7    0.001    0.001   14.036   14.189
 calculate_rho_elec                 129  8.7    0.046    0.065   14.036   14.188
 make_images                       5054 14.6    0.405    0.424   13.634   14.018
 init_scf_run                        11  5.9    0.000    0.001   13.591   13.591
 scf_env_initial_rho_setup           11  6.9    0.014    0.018   13.591   13.591
 density_rs2pw                      129  9.7    0.006    0.007    7.333   10.536
 cp_fm_cholesky_invert               11 10.9    9.170    9.178    9.170    9.178
 rs_pw_transfer                    1054 12.0    0.017    0.021    5.946    9.166
 wfi_extrapolate                     11  7.9    0.001    0.001    9.157    9.157
 calculate_dm_sparse                129  9.5    0.001    0.001    9.046    9.138
 mp_sum_l                          7930 13.1    8.048    9.078    8.048    9.078
 dbcsr_mm_accdrv_process         125468 16.2    3.138    3.252    8.291    8.965
 pw_transfer                       1559 11.6    0.077    0.094    8.123    8.361
 qs_ot_get_derivative_taylor         41 13.0    0.001    0.001    8.166    8.287
 fft_wrap_pw1pw2                   1301 12.7    0.011    0.012    7.915    8.159
 qs_ot_get_orbitals                 118 10.6    0.001    0.001    7.927    8.006
 grid_integrate_task_list           129 12.3    7.111    7.690    7.111    7.690
 make_images_data                  5054 15.6    0.067    0.071    6.722    7.620
 multiply_cannon_metrocomm1       60648 15.6    0.089    0.094    6.064    7.414
 cp_dbcsr_sm_fm_multiply             37  9.5    0.003    0.003    7.132    7.141
 fft_wrap_pw1pw2_140                527 13.2    0.448    0.520    6.846    7.129
 hybrid_alltoall_any               5240 16.5    0.294    2.278    5.886    7.076
 fft3d_ps                          1301 14.7    2.124    2.912    6.690    6.866
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    6.225    6.303
 mp_waitany                       16140 13.9    2.671    5.993    2.671    5.993
 grid_collocate_task_list           129  9.7    4.601    5.833    4.601    5.833
 mp_alltoall_d11v                  2423 14.1    4.221    5.666    4.221    5.666
 rs_pw_transfer_RS2PW_140           140 11.5    0.283    0.304    2.109    5.330
 potential_pw2rs                    129 12.3    0.009    0.011    4.876    4.894
 cp_fm_cholesky_decompose            22 10.9    4.700    4.715    4.700    4.715
 mp_sum_d                          4497 12.1    3.604    4.288    3.604    4.288
 calculate_first_density_matrix       1  7.0    0.000    0.000    4.252    4.261
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="400", plot="h2o_256_md", label="(8n/12r/1t)", y=210.754000, yerr=0.000000
PlotPoint: name="401", plot="h2o_256_md_mem", label="(8n/12r/1t)", y=594.363636, yerr=6.595766
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/16/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1430460020736       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1958505086976       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1986244964352       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1992000282624       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2753956716544       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4454954827776       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5444944789504       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5492290093056       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6712799002624       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11613089636352       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15239146475520       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15239146475520       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19911124992000       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        94.228663E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.199914E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6806316384       0.0%      0.0%    100.0%
 number of processed stacks               6022464       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1130.2
 marketing flops                   145.647559E+12
 -------------------------------------------------------------------------------
 # multiplications                           2527
 max memory usage/rank             828.485632E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 2425920
 MPI messages size (bytes):
  total size                         4.132350E+12
  min size                           0.000000E+00
  max size                          17.653760E+06
  average size                       1.703416E+06
 MPI breakdown and total messages size (bytes):
             size <=      128               14916                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768               71436               2336489472
     32768 < size <=   131072              728832              55956209664
    131072 < size <=  4194304             1386864            1409906900992
   4194304 < size <= 16777216              155760            1473826772352
  16777216 < size                           68112            1190343475200
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4030                  57824.
 MP_Allreduce        11073                    964.
 MP_Sync                87
 MP_Alltoall          1983                5621117.
 MP_SendRecv         12126                  47072.
 MP_ISendRecv        12126                  47072.
 MP_Wait             26114
 MP_ISend            11836                 212447.
 MP_IRecv            11836                 212447.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.026    0.089  195.205  195.206
 qs_mol_dyn_low                       1  2.0    0.003    0.005  194.761  194.775
 qs_forces                           11  3.9    0.006    0.014  194.674  194.675
 qs_energies                         11  4.9    0.002    0.006  187.801  187.811
 scf_env_do_scf                      11  5.9    0.008    0.061  170.848  170.858
 scf_env_do_scf_inner_loop          118  6.6    0.004    0.015  136.916  136.925
 velocity_verlet                     10  3.0    0.001    0.005  122.313  122.315
 dbcsr_multiply_generic            2527 12.6    0.188    0.194   98.734   99.884
 qs_scf_new_mos                     118  7.6    0.001    0.001   95.817   96.331
 qs_scf_loop_do_ot                  118  8.6    0.004    0.029   95.816   96.330
 ot_scf_mini                        118  9.6    0.022    0.151   90.969   91.594
 multiply_cannon                   2527 13.6    0.483    0.537   78.288   82.965
 multiply_cannon_loop              2527 14.6    1.257    1.298   74.961   77.333
 ot_mini                            118 10.6    0.001    0.001   50.437   51.029
 mp_waitall_1                    216438 16.6   24.696   38.575   24.696   38.575
 multiply_cannon_multrec          30324 15.6   22.192   26.010   32.075   36.390
 rebuild_ks_matrix                  129  8.3    0.001    0.001   34.148   34.735
 qs_ks_build_kohn_sham_matrix       129  9.3    0.017    0.019   34.148   34.735
 init_scf_loop                       11  6.9    0.045    0.357   33.832   33.833
 qs_ks_update_qs_env                129  7.6    0.001    0.001   30.761   31.300
 qs_ot_get_derivative               118 11.6    0.078    0.128   28.328   28.990
 prepare_preconditioner              11  7.9    0.000    0.000   28.891   28.944
 make_preconditioner                 11  8.9    0.000    0.001   28.891   28.944
 multiply_cannon_metrocomm3       30324 15.6    0.095    0.101   15.652   28.127
 make_full_inverse_cholesky          11  9.9    0.000    0.000   27.553   28.088
 apply_preconditioner_dbcsr         129 12.6    0.000    0.000   22.097   23.248
 apply_single                       129 13.6    0.001    0.001   22.097   23.248
 qs_ot_get_p                        129 10.4    0.001    0.001   22.107   22.894
 ot_diis_step                       118 11.6    0.014    0.015   21.936   21.939
 multiply_cannon_sync_h2d         30324 15.6   19.437   21.506   19.437   21.506
 qs_ot_p2m_diag                      83 11.4    0.187    0.215   17.213   17.247
 cp_fm_cholesky_invert               11 10.9   16.828   16.840   16.828   16.840
 make_m2s                          5054 13.6    0.089    0.094   14.480   16.068
 cp_dbcsr_syevd                      83 12.4    0.005    0.006   16.054   16.055
 make_images                       5054 14.6    1.179    1.375   14.273   15.864
 sum_up_and_integrate               129 10.3    0.118    0.135   15.264   15.298
 integrate_v_rspace                 129 11.3    0.004    0.005   15.145   15.186
 qs_rho_update_rho_low              129  7.7    0.001    0.001   14.531   14.565
 calculate_rho_elec                 129  8.7    0.089    0.107   14.531   14.564
 cp_fm_diag_elpa                     83 13.4    0.000    0.001   12.839   12.867
 cp_fm_diag_elpa_base                83 14.4   12.573   12.649   12.833   12.864
 init_scf_run                        11  5.9    0.000    0.001   12.089   12.090
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   12.088   12.090
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002   10.951   11.387
 make_images_data                  5054 15.6    0.065    0.073    8.824   10.666
 multiply_cannon_metrocomm4       27797 15.6    0.098    0.113    3.787   10.440
 density_rs2pw                      129  9.7    0.006    0.007    7.821   10.240
 mp_irecv_dv                      70031 16.3    3.590   10.039    3.590   10.039
 hybrid_alltoall_any               5240 16.5    0.346    1.517    7.510    9.952
 dbcsr_mm_accdrv_process          62734 16.2    4.530    5.329    9.337    9.943
 pw_transfer                       1559 11.6    0.088    0.113    9.316    9.393
 fft_wrap_pw1pw2                   1301 12.7    0.011    0.013    9.088    9.167
 rs_pw_transfer                    1054 12.0    0.015    0.017    6.117    8.560
 wfi_extrapolate                     11  7.9    0.001    0.001    8.463    8.463
 fft_wrap_pw1pw2_140                527 13.2    0.478    0.529    7.950    8.043
 grid_integrate_task_list           129 12.3    7.235    7.679    7.235    7.679
 fft3d_ps                          1301 14.7    2.775    2.957    7.437    7.495
 qs_ot_get_derivative_taylor         41 13.0    0.001    0.001    6.554    7.314
 cp_fm_cholesky_decompose            22 10.9    7.073    7.182    7.073    7.182
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.644    6.653
 calculate_dm_sparse                129  9.5    0.001    0.001    6.497    6.632
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.789    5.964
 mp_sum_l                          7930 13.1    4.184    5.885    4.184    5.885
 grid_collocate_task_list           129  9.7    4.745    5.884    4.745    5.884
 potential_pw2rs                    129 12.3    0.015    0.018    5.420    5.443
 qs_ot_get_orbitals                 118 10.6    0.001    0.001    5.354    5.414
 mp_allgather_i34                  2527 14.6    1.884    5.196    1.884    5.196
 mp_waitany                       11836 13.9    2.629    5.099    2.629    5.099
 mp_alltoall_d11v                  2423 14.1    4.224    4.758    4.224    4.758
 rs_pw_transfer_RS2PW_140           140 11.5    0.354    0.384    2.156    4.579
 dbcsr_complete_redistribute        395 12.7    0.775    0.878    3.554    4.464
 mp_sum_d                          4500 12.1    2.747    4.116    2.747    4.116
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="402", plot="h2o_256_md", label="(8n/6r/2t)", y=195.206000, yerr=0.000000
PlotPoint: name="403", plot="h2o_256_md_mem", label="(8n/6r/2t)", y=789.545455, yerr=4.599677
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/17/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1410022121472       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       11444702699520       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                        92.796573E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.906045E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6705499744       0.0%      0.0%    100.0%
 number of processed stacks               3951168       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1697.1
 marketing flops                   143.507742E+12
 -------------------------------------------------------------------------------
 # multiplications                           2485
 max memory usage/rank             940.171264E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                 1033760
 MPI messages size (bytes):
  total size                         2.695213E+12
  min size                           0.000000E+00
  max size                          26.214400E+06
  average size                       2.607194E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 264                  8650752
     32768 < size <=   131072              279168              36591108096
    131072 < size <=  4194304              654272             987691483136
   4194304 < size <= 16777216               65184             925172769472
  16777216 < size                           28448             745747251200
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4003                  58198.
 MP_Allreduce        11005                   1007.
 MP_Sync                86
 MP_Alltoall          1700                9383497.
 MP_SendRecv          7874                  75008.
 MP_ISendRecv         7874                  75008.
 MP_Wait             21654
 MP_ISend            11660                 275234.
 MP_IRecv            11660                 275234.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.126    0.620  180.705  180.710
 qs_mol_dyn_low                       1  2.0    0.005    0.020  179.248  179.336
 qs_forces                           11  3.9    0.012    0.013  178.591  178.599
 qs_energies                         11  4.9    0.004    0.023  171.468  171.483
 scf_env_do_scf                      11  5.9    0.001    0.002  154.790  154.791
 scf_env_do_scf_inner_loop          116  6.6    0.004    0.009  119.249  119.250
 velocity_verlet                     10  3.0    0.001    0.001  113.443  113.447
 dbcsr_multiply_generic            2485 12.5    0.178    0.184   82.010   83.190
 qs_scf_new_mos                     116  7.6    0.001    0.001   80.621   80.888
 qs_scf_loop_do_ot                  116  8.6    0.001    0.001   80.620   80.888
 ot_scf_mini                        116  9.6    0.004    0.005   76.526   76.861
 multiply_cannon                   2485 13.5    0.502    0.526   61.994   66.781
 multiply_cannon_loop              2485 14.5    0.844    0.865   58.694   61.364
 ot_mini                            116 10.6    0.001    0.001   42.522   42.859
 init_scf_loop                       11  6.9    0.027    0.218   35.436   35.437
 mp_waitall_1                    169034 16.6   25.112   34.074   25.112   34.074
 rebuild_ks_matrix                  127  8.3    0.001    0.001   31.488   31.899
 qs_ks_build_kohn_sham_matrix       127  9.3    0.016    0.017   31.487   31.899
 prepare_preconditioner              11  7.9    0.000    0.001   31.280   31.357
 make_preconditioner                 11  8.9    0.000    0.002   31.280   31.357
 make_full_inverse_cholesky          11  9.9    0.000    0.000   28.955   30.380
 qs_ks_update_qs_env                127  7.6    0.001    0.001   27.970   28.345
 multiply_cannon_multrec          19880 15.5   13.485   16.087   22.157   24.751
 multiply_cannon_metrocomm3       19880 15.5    0.058    0.064   15.123   24.121
 qs_ot_get_derivative               116 11.6    0.003    0.008   23.009   23.339
 apply_preconditioner_dbcsr         127 12.6    0.000    0.000   19.638   20.554
 apply_single                       127 13.6    0.001    0.001   19.638   20.553
 qs_ot_get_p                        127 10.4    0.001    0.001   19.417   19.881
 ot_diis_step                       116 11.6    0.017    0.018   19.410   19.411
 make_m2s                          4970 13.5    0.080    0.084   14.979   15.997
 make_images                       4970 14.5    1.178    1.256   14.750   15.763
 multiply_cannon_sync_h2d         19880 15.5   14.171   15.750   14.171   15.750
 sum_up_and_integrate               127 10.3    0.135    0.147   15.153   15.229
 qs_ot_p2m_diag                      82 11.4    0.262    0.269   15.123   15.135
 integrate_v_rspace                 127 11.3    0.004    0.005   15.017   15.090
 cp_fm_cholesky_invert               11 10.9   14.651   14.660   14.651   14.660
 qs_rho_update_rho_low              127  7.7    0.001    0.001   14.523   14.555
 calculate_rho_elec                 127  8.7    0.131    0.146   14.522   14.554
 cp_dbcsr_syevd                      82 12.4    0.005    0.005   14.103   14.104
 init_scf_run                        11  5.9    0.000    0.001   11.540   11.540
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   11.540   11.540
 cp_fm_diag_elpa                     82 13.4    0.000    0.000   10.867   10.881
 cp_fm_diag_elpa_base                82 14.4   10.451   10.619   10.863   10.878
 make_images_data                  4970 15.5    0.061    0.068    9.288   10.679
 hybrid_alltoall_any               5155 16.4    0.428    1.958    8.063   10.099
 pw_transfer                       1535 11.6    0.086    0.108    9.649    9.812
 fft_wrap_pw1pw2                   1281 12.7    0.011    0.012    9.425    9.596
 density_rs2pw                      127  9.7    0.006    0.007    7.417    9.593
 qs_ot_get_derivative_diag           76 12.4    0.002    0.002    8.949    9.179
 multiply_cannon_metrocomm4       17395 15.5    0.061    0.071    3.385    8.932
 mp_irecv_dv                      49801 16.2    3.263    8.693    3.263    8.693
 fft_wrap_pw1pw2_140                519 13.2    0.475    0.524    8.361    8.538
 dbcsr_mm_accdrv_process          41158 16.2    4.349    4.905    8.130    8.287
 fft3d_ps                          1281 14.7    2.657    2.884    7.700    7.833
 grid_integrate_task_list           127 12.3    7.243    7.733    7.243    7.733
 wfi_extrapolate                     11  7.9    0.001    0.001    7.539    7.540
 rs_pw_transfer                    1038 11.9    0.014    0.015    5.282    7.480
 cp_fm_cholesky_decompose            22 10.9    7.379    7.398    7.379    7.398
 cp_fm_upper_to_full                104 14.8    5.716    7.195    5.716    7.195
 dbcsr_complete_redistribute        393 12.7    1.170    1.204    4.599    6.334
 calculate_dm_sparse                127  9.5    0.001    0.001    6.083    6.193
 grid_collocate_task_list           127  9.7    4.857    5.789    4.857    5.789
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.630    5.639
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    4.748    5.415
 potential_pw2rs                    127 12.3    0.020    0.022    5.295    5.368
 mp_allgather_i34                  2485 14.5    1.819    5.154    1.819    5.154
 copy_fm_to_dbcsr                   208 11.6    0.002    0.002    3.420    5.152
 mp_alltoall_d11v                  2401 14.1    4.391    4.904    4.391    4.904
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.001    4.721    4.853
 mp_sum_l                          7804 13.0    3.265    4.831    3.265    4.831
 mp_waitany                       11660 13.9    2.378    4.639    2.378    4.639
 rs_pw_transfer_RS2PW_140           138 11.5    0.330    0.346    1.938    4.116
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    4.029    4.074
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    2.306    4.024
 qs_ot_get_orbitals                 116 10.6    0.001    0.001    3.987    4.022
 mp_alltoall_i22                    712 14.1    1.934    3.843    1.934    3.843
 qs_energies_init_hamiltonians       11  5.9    0.001    0.003    3.822    3.824
 calculate_first_density_matrix       1  7.0    0.000    0.003    3.806    3.812
 mp_sum_d                          4448 12.1    2.668    3.801    2.668    3.801
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="404", plot="h2o_256_md", label="(8n/4r/3t)", y=180.710000, yerr=0.000000
PlotPoint: name="405", plot="h2o_256_md_mem", label="(8n/4r/3t)", y=889.727273, yerr=10.921962
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/18/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                      4.320337E+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               5927808       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1131.2
 marketing flops                   143.508480E+12
 -------------------------------------------------------------------------------
 # multiplications                           2485
 max memory usage/rank               1.151177E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1133160
 MPI messages size (bytes):
  total size                         2.008142E+12
  min size                           0.000000E+00
  max size                          17.653760E+06
  average size                       1.772161E+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              315952              35695099904
    131072 < size <=  4194304              709496             778939400192
   4194304 < size <= 16777216               69840             660837542000
  16777216 < size                           30480             532676608000
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3995                  58309.
 MP_Allreduce        10985                   1091.
 MP_Sync                86
 MP_Alltoall          1700               12496381.
 MP_SendRecv          5842                  75008.
 MP_ISendRecv         5842                  75008.
 MP_Wait             22272
 MP_ISend            14840                 244848.
 MP_IRecv            14840                 244848.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.047    0.142  190.391  190.396
 qs_mol_dyn_low                       1  2.0    0.003    0.005  189.677  189.686
 qs_forces                           11  3.9    0.004    0.004  189.557  189.563
 qs_energies                         11  4.9    0.006    0.041  182.355  182.366
 scf_env_do_scf                      11  5.9    0.001    0.003  164.614  164.621
 velocity_verlet                     10  3.0    0.001    0.002  124.763  124.766
 scf_env_do_scf_inner_loop          116  6.6    0.003    0.009  117.258  117.259
 qs_scf_new_mos                     116  7.6    0.001    0.001   79.534   79.822
 qs_scf_loop_do_ot                  116  8.6    0.001    0.001   79.533   79.821
 dbcsr_multiply_generic            2485 12.5    0.185    0.190   79.020   79.716
 ot_scf_mini                        116  9.6    0.003    0.004   75.067   75.317
 multiply_cannon                   2485 13.5    0.551    0.592   54.623   57.110
 multiply_cannon_loop              2485 14.5    1.168    1.196   50.875   52.498
 init_scf_loop                       11  6.9    0.010    0.081   47.229   47.230
 prepare_preconditioner              11  7.9    0.001    0.005   42.622   42.651
 make_preconditioner                 11  8.9    0.001    0.004   42.621   42.651
 ot_mini                            116 10.6    0.001    0.001   41.875   42.096
 make_full_inverse_cholesky          11  9.9    0.000    0.000   36.214   41.198
 rebuild_ks_matrix                  127  8.3    0.001    0.001   30.486   30.675
 qs_ks_build_kohn_sham_matrix       127  9.3    0.017    0.019   30.486   30.675
 multiply_cannon_multrec          29820 15.5   14.292   19.294   26.101   30.602
 qs_ks_update_qs_env                127  7.6    0.001    0.001   27.493   27.665
 mp_waitall_1                    146592 16.7   17.188   27.027   17.188   27.027
 qs_ot_get_derivative               116 11.6    0.002    0.002   22.544   22.789
 make_m2s                          4970 13.5    0.095    0.101   20.042   21.171
 make_images                       4970 14.5    1.930    2.264   19.737   20.866
 qs_ot_get_p                        127 10.4    0.001    0.001   19.545   19.787
 apply_preconditioner_dbcsr         127 12.6    0.000    0.001   18.765   19.264
 apply_single                       127 13.6    0.001    0.001   18.765   19.264
 ot_diis_step                       116 11.6    0.017    0.018   19.193   19.195
 cp_fm_upper_to_full                104 14.8   11.374   16.766   11.374   16.766
 cp_fm_cholesky_invert               11 10.9   16.306   16.315   16.306   16.315
 qs_ot_p2m_diag                      82 11.4    0.338    0.385   15.427   15.479
 multiply_cannon_metrocomm3       29820 15.5    0.046    0.048    6.238   15.048
 sum_up_and_integrate               127 10.3    0.148    0.161   14.852   14.885
 qs_rho_update_rho_low              127  7.7    0.001    0.001   14.742   14.782
 calculate_rho_elec                 127  8.7    0.174    0.189   14.741   14.782
 integrate_v_rspace                 127 11.3    0.004    0.004   14.703   14.739
 cp_dbcsr_syevd                      82 12.4    0.005    0.005   14.166   14.168
 dbcsr_complete_redistribute        393 12.7    1.520    1.650    9.086   12.872
 make_images_data                  4970 15.5    0.064    0.068   10.898   12.457
 multiply_cannon_sync_h2d         29820 15.5   11.623   12.452   11.623   12.452
 dbcsr_mm_accdrv_process          61748 16.2    7.369    8.067   11.394   11.953
 copy_fm_to_dbcsr                   208 11.6    0.001    0.002    7.706   11.509
 hybrid_alltoall_any               5155 16.4    0.521    2.188    9.655   11.436
 init_scf_run                        11  5.9    0.000    0.001   11.365   11.369
 scf_env_initial_rho_setup           11  6.9    0.004    0.012   11.365   11.368
 cp_fm_diag_elpa                     82 13.4    0.000    0.000   11.077   11.091
 cp_fm_diag_elpa_base                82 14.4   10.117   10.431   11.071   11.083
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    6.383   10.077
 pw_transfer                       1535 11.6    0.087    0.107    9.548    9.606
 qs_ot_get_derivative_diag           76 12.4    0.002    0.002    9.295    9.490
 mp_alltoall_i22                    712 14.1    5.614    9.430    5.614    9.430
 fft_wrap_pw1pw2                   1281 12.7    0.011    0.012    9.320    9.388
 density_rs2pw                      127  9.7    0.006    0.006    7.172    8.402
 fft_wrap_pw1pw2_140                519 13.2    0.480    0.492    8.263    8.341
 wfi_extrapolate                     11  7.9    0.001    0.001    7.824    7.824
 cp_fm_cholesky_decompose            22 10.9    7.734    7.809    7.734    7.809
 grid_integrate_task_list           127 12.3    7.427    7.778    7.427    7.778
 fft3d_ps                          1281 14.7    2.756    2.847    7.557    7.615
 multiply_cannon_metrocomm4       24850 15.5    0.076    0.085    2.671    6.625
 calculate_dm_sparse                127  9.5    0.001    0.001    6.450    6.561
 mp_irecv_dv                      75445 16.2    2.527    6.360    2.527    6.360
 mp_alltoall_d11v                  2401 14.1    5.028    6.256    5.028    6.256
 rs_pw_transfer                    1038 11.9    0.013    0.017    4.707    6.015
 grid_collocate_task_list           127  9.7    5.045    5.700    5.045    5.700
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.549    5.605
 qs_energies_init_hamiltonians       11  5.9    0.371    0.376    4.878    4.879
 potential_pw2rs                    127 12.3    0.022    0.022    4.692    4.707
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.001    4.390    4.466
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    4.368    4.443
 qs_ot_get_orbitals                 116 10.6    0.001    0.001    4.126    4.185
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="406", plot="h2o_256_md", label="(8n/3r/4t)", y=190.396000, yerr=0.000000
PlotPoint: name="407", plot="h2o_256_md_mem", label="(8n/3r/4t)", y=1081.000000, yerr=21.650110
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_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               1.501032E+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               18838186.
 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    0.040    0.081  175.250  175.255
 qs_mol_dyn_low                       1  2.0    0.003    0.003  174.636  174.647
 qs_forces                           11  3.9    0.005    0.012  174.503  174.511
 qs_energies                         11  4.9    0.001    0.001  166.907  166.915
 scf_env_do_scf                      11  5.9    0.001    0.001  149.536  149.539
 velocity_verlet                     10  3.0    0.001    0.001  114.493  114.498
 scf_env_do_scf_inner_loop          117  6.6    0.013    0.158  113.456  113.457
 qs_scf_new_mos                     117  7.6    0.001    0.001   74.600   74.716
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   74.600   74.716
 dbcsr_multiply_generic            2507 12.6    0.181    0.191   73.472   73.772
 ot_scf_mini                        117  9.6    0.003    0.004   70.218   70.261
 multiply_cannon                   2507 13.6    0.587    0.617   54.184   58.146
 multiply_cannon_loop              2507 14.6    0.444    0.455   49.596   50.211
 ot_mini                            117 10.6    0.001    0.001   39.304   39.354
 init_scf_loop                       11  6.9    0.000    0.000   35.932   35.935
 prepare_preconditioner              11  7.9    0.000    0.000   32.005   32.033
 make_preconditioner                 11  8.9    0.000    0.000   32.005   32.033
 mp_waitall_1                    125778 16.7   25.015   32.027   25.015   32.027
 make_full_inverse_cholesky          11  9.9    0.000    0.000   29.930   30.222
 rebuild_ks_matrix                  128  8.3    0.001    0.001   29.909   29.959
 qs_ks_build_kohn_sham_matrix       128  9.3    0.017    0.018   29.908   29.958
 qs_ks_update_qs_env                128  7.6    0.001    0.001   27.164   27.207
 multiply_cannon_multrec          10028 15.6   10.443   14.373   17.988   21.505
 ot_diis_step                       117 11.6    0.020    0.020   19.721   19.722
 qs_ot_get_derivative               117 11.6    0.002    0.002   19.508   19.552
 apply_preconditioner_dbcsr         128 12.6    0.000    0.000   19.357   19.550
 apply_single                       128 13.6    0.001    0.001   19.357   19.549
 multiply_cannon_metrocomm3       10028 15.6    0.022    0.024   12.138   19.061
 cp_fm_cholesky_invert               11 10.9   18.268   18.274   18.268   18.274
 qs_ot_get_p                        128 10.4    0.001    0.001   18.173   18.239
 make_m2s                          5014 13.6    0.066    0.071   15.688   17.949
 make_images                       5014 14.6    2.292    2.773   15.384   17.647
 qs_rho_update_rho_low              128  7.7    0.001    0.001   15.434   15.460
 calculate_rho_elec                 128  8.7    0.259    0.269   15.433   15.459
 sum_up_and_integrate               128 10.3    0.181    0.192   15.165   15.212
 integrate_v_rspace                 128 11.3    0.004    0.005   14.984   15.038
 qs_ot_p2m_diag                      83 11.4    0.499    0.557   14.463   14.512
 cp_dbcsr_syevd                      83 12.4    0.005    0.005   13.320   13.322
 multiply_cannon_sync_h2d         10028 15.6   11.639   12.054   11.639   12.054
 make_images_data                  5014 15.6    0.053    0.060    9.382   11.698
 hybrid_alltoall_any               5200 16.5    0.844    3.812    9.211   11.494
 init_scf_run                        11  5.9    0.000    0.001   10.530   10.531
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   10.530   10.531
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   10.228   10.238
 cp_fm_diag_elpa_base                83 14.4    9.970   10.060   10.220   10.230
 pw_transfer                       1547 11.6    0.085    0.093    9.811    9.850
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.011    9.588    9.631
 fft_wrap_pw1pw2_140                523 13.2    0.497    0.521    8.450    8.495
 cp_fm_cholesky_decompose            22 10.9    8.097    8.197    8.097    8.197
 grid_integrate_task_list           128 12.3    7.768    8.150    7.768    8.150
 density_rs2pw                      128  9.7    0.005    0.006    7.032    7.899
 qs_ot_get_derivative_diag           77 12.4    0.002    0.003    7.799    7.839
 dbcsr_mm_accdrv_process          20762 16.1    2.617    3.490    7.171    7.811
 fft3d_ps                          1291 14.7    2.713    2.803    7.746    7.771
 wfi_extrapolate                     11  7.9    0.001    0.001    7.450    7.450
 multiply_cannon_metrocomm1       10028 15.6    0.028    0.029    4.242    6.756
 mp_allgather_i34                  2507 14.6    2.786    6.576    2.786    6.576
 calculate_dm_sparse                128  9.5    0.001    0.001    6.044    6.118
 grid_collocate_task_list           128  9.7    5.392    6.069    5.392    6.069
 dbcsr_complete_redistribute        395 12.7    2.120    2.176    5.117    5.528
 mp_alltoall_d11v                  2415 14.1    4.825    5.381    4.825    5.381
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    5.334    5.336
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.244    5.254
 rs_pw_transfer                    1046 11.9    0.013    0.013    4.259    5.159
 potential_pw2rs                    128 12.3    0.027    0.028    4.688    4.699
 multiply_cannon_metrocomm4        7521 15.6    0.025    0.028    1.848    4.462
 mp_irecv_dv                      28860 15.9    1.810    4.385    1.810    4.385
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.190    4.232
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    3.551    3.887
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    3.728    3.764
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    3.654    3.661
 copy_fm_to_dbcsr                   209 11.7    0.002    0.002    3.305    3.629
 copy_dbcsr_to_fm                   186 11.8    0.004    0.004    3.562    3.629
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="408", plot="h2o_256_md", label="(8n/2r/6t)", y=175.255000, yerr=0.000000
PlotPoint: name="409", plot="h2o_256_md_mem", label="(8n/2r/6t)", y=1407.272727, yerr=45.992274
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_performance_tests/20/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1430456868864       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1960652570624       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1986252263424       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1992007581696       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2753954734080       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       11613074706432       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15239176888320       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15239176888320       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19911117062144       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        94.230858E+12       0.0%      0.0%    100.0%
 flops max/rank                     11.785799E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6806351296       0.0%      0.0%    100.0%
 number of processed stacks               1979920       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    3437.7
 marketing flops                   145.648783E+12
 -------------------------------------------------------------------------------
 # multiplications                           2528
 max memory usage/rank               3.091214E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                  101120
 MPI messages size (bytes):
  total size                         1.144936E+12
  min size                           0.000000E+00
  max size                         104.857600E+06
  average size                      11.322546E+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               45608              35399925760
   4194304 < size <= 16777216               44720             382939955200
  16777216 < size                           10176             726592330608
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4069                  58204.
 MP_Allreduce        11170                   1510.
 MP_Sync                86
 MP_Alltoall          1724               36993574.
 MP_SendRecv          1806                 218624.
 MP_ISendRecv         1806                 218624.
 MP_Wait              9876
 MP_ISend             6456                1080169.
 MP_IRecv             6456                1080169.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.046    0.083  308.801  308.806
 qs_mol_dyn_low                       1  2.0    0.003    0.003  307.858  307.868
 qs_forces                           11  3.9    0.004    0.005  307.744  307.747
 qs_energies                         11  4.9    0.001    0.001  298.264  298.271
 scf_env_do_scf                      11  5.9    0.001    0.001  275.164  275.177
 velocity_verlet                     10  3.0    0.001    0.001  220.084  220.093
 scf_env_do_scf_inner_loop          118  6.6    0.004    0.009  147.289  147.292
 init_scf_loop                       11  6.9    0.000    0.000  127.610  127.613
 prepare_preconditioner              11  7.9    0.000    0.000  122.394  122.433
 make_preconditioner                 11  8.9    0.000    0.000  122.394  122.433
 make_full_inverse_cholesky          11  9.9    0.000    0.000   98.188  119.500
 qs_scf_new_mos                     118  7.6    0.001    0.001   94.871   94.987
 qs_scf_loop_do_ot                  118  8.6    0.001    0.001   94.870   94.986
 ot_scf_mini                        118  9.6    0.004    0.004   89.951   90.030
 dbcsr_multiply_generic            2528 12.6    0.214    0.225   86.078   86.939
 cp_fm_upper_to_full                104 14.8   54.747   77.899   54.747   77.899
 multiply_cannon                   2528 13.6    0.716    0.772   60.460   61.312
 multiply_cannon_loop              2528 14.6    0.474    0.480   56.570   58.552
 ot_mini                            118 10.6    0.001    0.001   46.164   46.267
 dbcsr_complete_redistribute        393 12.7    4.106    4.149   30.027   43.221
 copy_fm_to_dbcsr                   208 11.6    0.001    0.002   26.631   39.795
 rebuild_ks_matrix                  129  8.3    0.001    0.001   39.501   39.634
 qs_ks_build_kohn_sham_matrix       129  9.3    0.018    0.018   39.500   39.633
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000   24.160   37.209
 qs_ks_update_qs_env                129  7.6    0.001    0.001   36.404   36.532
 mp_alltoall_i22                    716 14.1   21.995   34.959   21.995   34.959
 mp_waitall_1                    104540 16.8   30.006   34.513   30.006   34.513
 cp_fm_cholesky_invert               11 10.9   34.096   34.102   34.096   34.102
 qs_ot_get_p                        129 10.4    0.001    0.001   27.877   27.961
 qs_ot_get_derivative               118 11.6    0.002    0.003   24.852   24.936
 qs_ot_p2m_diag                      82 11.4    0.868    0.873   23.561   23.593
 cp_dbcsr_syevd                      82 12.4    0.005    0.006   21.825   21.828
 multiply_cannon_metrocomm3       10112 15.6    0.023    0.024   19.948   21.760
 make_m2s                          5056 13.6    0.077    0.081   20.670   21.747
 qs_rho_update_rho_low              129  7.7    0.001    0.001   21.270   21.282
 calculate_rho_elec                 129  8.7    0.487    0.488   21.269   21.281
 make_images                       5056 14.6    3.800    4.027   20.189   21.272
 ot_diis_step                       118 11.6    0.023    0.026   21.268   21.269
 apply_preconditioner_dbcsr         129 12.6    0.000    0.000   20.390   20.746
 apply_single                       129 13.6    0.001    0.001   20.389   20.746
 sum_up_and_integrate               129 10.3    0.326    0.328   20.180   20.260
 integrate_v_rspace                 129 11.3    0.004    0.004   19.854   19.934
 cp_fm_diag_elpa                     82 13.4    0.000    0.000   18.528   18.529
 cp_fm_diag_elpa_base                82 14.4   14.048   15.653   18.524   18.525
 multiply_cannon_multrec          10112 15.6   10.582   12.326   18.059   18.183
 multiply_cannon_sync_h2d         10112 15.6   15.772   15.778   15.772   15.778
 hybrid_alltoall_any               5241 16.5    1.311    3.056   11.418   13.447
 make_images_data                  5056 15.6    0.061    0.065   11.256   13.218
 pw_transfer                       1559 11.6    0.094    0.094   12.869   12.886
 init_scf_run                        11  5.9    0.000    0.001   12.702   12.702
 scf_env_initial_rho_setup           11  6.9    0.003    0.003   12.702   12.702
 fft_wrap_pw1pw2                   1301 12.7    0.012    0.012   12.631   12.644
 fft_wrap_pw1pw2_140                527 13.2    0.549    0.562   11.206   11.224
 fft3d_ps                          1301 14.7    2.778    2.814   10.646   10.659
 qs_ot_get_derivative_diag           76 12.4    0.002    0.002    9.569    9.638
 mp_alltoall_d11v                  2417 14.1    8.563    9.337    8.563    9.337
 wfi_extrapolate                     11  7.9    0.001    0.001    9.196    9.196
 cp_fm_cholesky_decompose            22 10.9    9.172    9.194    9.172    9.194
 dbcsr_mm_accdrv_process          20930 16.1    3.790    5.756    7.234    9.065
 grid_integrate_task_list           129 12.3    8.654    8.847    8.654    8.847
 density_rs2pw                      129  9.7    0.005    0.005    8.705    8.839
 qs_energies_init_hamiltonians       11  5.9    0.285    0.292    8.371    8.372
 calculate_dm_sparse                129  9.5    0.001    0.001    6.991    7.039
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.541    6.608
 grid_collocate_task_list           129  9.7    6.424    6.456    6.424    6.456
 rs_scatter_matrices                140  9.7    3.626    4.560    6.108    6.333
 copy_dbcsr_to_fm                   185 11.7    0.004    0.004    6.122    6.194
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="410", plot="h2o_256_md", label="(8n/1r/12t)", y=308.806000, yerr=0.000000
PlotPoint: name="411", plot="h2o_256_md_mem", label="(8n/1r/12t)", y=2804.272727, yerr=143.084902
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_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               1.261990E+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                6805335.
 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    0.049   85.835   85.837
 qs_energies                          1  2.0    0.000    0.000   84.888   84.901
 ls_scf                               1  3.0    0.000    0.000   83.982   83.995
 dbcsr_multiply_generic             111  6.7    0.014    0.015   72.569   72.748
 multiply_cannon                    111  7.7    0.017    0.020   55.856   56.902
 multiply_cannon_loop               111  8.7    0.212    0.226   52.403   53.726
 ls_scf_main                          1  4.0    0.000    0.000   52.320   52.332
 density_matrix_trs4                  2  5.0    0.002    0.003   46.765   46.836
 ls_scf_init_scf                      1  4.0    0.000    0.000   28.613   28.614
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   27.503   27.549
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   25.410   25.432
 mp_waitall_1                     11031 10.9   22.171   24.720   22.171   24.720
 multiply_cannon_multrec           2664  9.7    8.164    8.973   15.559   17.243
 multiply_cannon_sync_h2d          2664  9.7   13.757   15.207   13.757   15.207
 make_m2s                           222  7.7    0.008    0.011   13.136   13.652
 make_images                        222  8.7    0.099    0.107   13.114   13.632
 multiply_cannon_metrocomm1        2664  9.7    0.010    0.011    9.474   12.430
 multiply_cannon_metrocomm3        2664  9.7    0.009    0.010    5.366    9.247
 make_images_data                   222  9.7    0.004    0.005    7.658    8.243
 hybrid_alltoall_any                227 10.6    0.216    1.839    6.456    8.118
 dbcsr_mm_accdrv_process           4760 10.4    0.513    0.624    7.014    8.040
 dbcsr_mm_accdrv_process_sort      4760 11.4    6.301    7.218    6.301    7.218
 calculate_norms                   4752  9.8    5.577    6.235    5.577    6.235
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.047    5.163
 mp_sum_l                           807  5.4    3.058    4.218    3.058    4.218
 multiply_cannon_metrocomm4        2442  9.7    0.012    0.016    2.073    3.885
 mp_irecv_dv                       6231 10.9    2.055    3.857    2.055    3.857
 arnoldi_extremal                     4  6.8    0.000    0.000    3.296    3.335
 arnoldi_normal_ev                    4  7.8    0.001    0.003    3.296    3.335
 make_images_sizes                  222  9.7    0.000    0.000    0.864    3.219
 mp_alltoall_i44                    222 10.7    0.863    3.218    0.863    3.218
 build_subspace                      16  8.4    0.009    0.012    3.196    3.198
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    2.245    3.069
 ls_scf_post                          1  4.0    0.000    0.000    3.049    3.062
 ls_scf_store_result                  1  5.0    0.000    0.000    2.878    2.912
 dbcsr_special_finalize             555  9.7    0.005    0.006    2.264    2.830
 dbcsr_merge_single_wm              555 10.7    0.456    0.600    2.256    2.820
 make_images_pack                   222  9.7    2.205    2.624    2.206    2.625
 dbcsr_matrix_vector_mult           304  9.0    0.006    0.013    2.333    2.575
 dbcsr_sort_data                    658 11.4    2.059    2.557    2.059    2.557
 dbcsr_matrix_vector_mult_local     304 10.0    2.069    2.460    2.071    2.462
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.313    2.390
 buffer_matrices_ensure_size        222  8.7    1.753    2.120    1.753    2.120
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.795    1.797
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.786    1.787
 qs_ks_build_kohn_sham_matrix         3  8.3    0.000    0.001    1.786    1.787
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="500", plot="h2o_32_nrep3_ls", label="(8n/12r/1t)", y=85.837000, 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/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_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               2.110857E+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    0.045    0.078   92.184   92.185
 qs_energies                          1  2.0    0.000    0.000   91.147   91.153
 ls_scf                               1  3.0    0.002    0.020   89.834   89.839
 dbcsr_multiply_generic             111  6.7    0.015    0.016   75.416   75.796
 multiply_cannon                    111  7.7    0.029    0.046   53.185   57.552
 ls_scf_main                          1  4.0    0.025    0.230   55.417   55.425
 multiply_cannon_loop               111  8.7    0.116    0.125   49.923   53.570
 density_matrix_trs4                  2  5.0    0.003    0.015   49.383   49.618
 ls_scf_init_scf                      1  4.0    0.000    0.001   30.832   30.833
 mp_waitall_1                      9105 10.9   21.113   30.028   21.113   30.028
 ls_scf_init_matrix_S                 1  5.0    0.000    0.001   29.618   29.718
 multiply_cannon_multrec           1332  9.7   13.131   16.910   22.423   27.353
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.208   27.221
 multiply_cannon_metrocomm3        1332  9.7    0.006    0.007   11.682   20.468
 make_m2s                           222  7.7    0.006    0.007   15.370   16.010
 make_images                        222  8.7    1.583    1.983   15.340   15.982
 dbcsr_mm_accdrv_process           4041 10.4    0.288    0.445    8.891   10.445
 dbcsr_mm_accdrv_process_sort      4041 11.4    8.483   10.000    8.483   10.000
 make_images_data                   222  9.7    0.004    0.004    8.804    9.718
 hybrid_alltoall_any                227 10.6    0.524    2.479    8.203    9.228
 mp_sum_l                           807  5.4    5.558    8.803    5.558    8.803
 multiply_cannon_metrocomm4        1221  9.7    0.007    0.008    3.208    7.816
 mp_irecv_dv                       3311 11.0    3.187    7.747    3.187    7.747
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    4.290    6.981
 calculate_norms                   2376  9.8    6.005    6.694    6.005    6.694
 multiply_cannon_sync_h2d          1332  9.7    4.780    5.872    4.780    5.872
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.140    5.344
 arnoldi_extremal                     4  6.8    0.000    0.000    4.690    4.712
 arnoldi_normal_ev                    4  7.8    0.006    0.015    4.690    4.712
 build_subspace                      16  8.4    0.014    0.021    4.420    4.424
 ls_scf_post                          1  4.0    0.000    0.003    3.583    3.589
 ls_scf_store_result                  1  5.0    0.000    0.000    3.305    3.404
 dbcsr_matrix_vector_mult           304  9.0    0.010    0.021    3.185    3.386
 dbcsr_matrix_vector_mult_local     304 10.0    2.742    3.222    2.744    3.224
 ls_scf_dm_to_ks                      2  5.0    0.002    0.017    2.811    2.924
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.004    1.260    2.667
 make_images_pack                   222  9.7    2.027    2.424    2.029    2.426
 mp_allgather_i34                   111  8.7    0.953    2.303    0.953    2.303
 dbcsr_sort_data                    436 11.2    1.814    2.042    1.814    2.042
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.914    1.916
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.900    1.903
 qs_ks_build_kohn_sham_matrix         3  8.3    0.000    0.001    1.900    1.903
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="502", plot="h2o_32_nrep3_ls", label="(8n/6r/2t)", y=92.185000, yerr=0.000000
PlotPoint: name="503", plot="h2o_32_nrep3_ls_mem", label="(8n/6r/2t)", y=1709.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_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               2.722660E+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    0.034    0.050   94.943   94.945
 qs_energies                          1  2.0    0.000    0.000   93.809   93.812
 ls_scf                               1  3.0    0.000    0.000   92.328   92.331
 dbcsr_multiply_generic             111  6.7    0.016    0.016   76.546   76.808
 ls_scf_main                          1  4.0    0.000    0.000   57.571   57.575
 multiply_cannon                    111  7.7    0.040    0.097   52.780   57.089
 multiply_cannon_loop               111  8.7    0.099    0.104   49.211   52.878
 density_matrix_trs4                  2  5.0    0.002    0.003   51.489   51.651
 mp_waitall_1                      7281 11.0   23.867   33.563   23.867   33.563
 ls_scf_init_scf                      1  4.0    0.000    0.000   31.232   31.235
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   29.762   29.821
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.343   27.358
 multiply_cannon_multrec            888  9.7   12.624   15.310   21.223   24.517
 multiply_cannon_metrocomm3         888  9.7    0.004    0.004   11.070   22.534
 make_m2s                           222  7.7    0.006    0.007   17.164   18.424
 make_images                        222  8.7    1.978    2.284   17.126   18.384
 make_images_data                   222  9.7    0.003    0.004    9.831   10.875
 hybrid_alltoall_any                227 10.6    0.616    2.851    9.514   10.806
 dbcsr_mm_accdrv_process           3754 10.4    0.242    0.417    8.134    9.325
 dbcsr_mm_accdrv_process_sort      3754 11.4    7.762    8.908    7.762    8.908
 mp_sum_l                           807  5.4    5.044    8.325    5.044    8.325
 multiply_cannon_sync_h2d           888  9.7    6.024    7.589    6.024    7.589
 multiply_cannon_metrocomm1         888  9.7    0.003    0.003    3.580    7.098
 multiply_cannon_metrocomm4         777  9.7    0.004    0.005    2.433    6.901
 mp_irecv_dv                       2335 11.1    2.417    6.859    2.417    6.859
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.945    6.477
 arnoldi_extremal                     4  6.8    0.000    0.000    5.248    5.269
 arnoldi_normal_ev                    4  7.8    0.001    0.005    5.248    5.269
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.991    5.177
 build_subspace                      16  8.4    0.014    0.020    4.933    4.938
 calculate_norms                   1584  9.8    4.277    4.581    4.277    4.581
 mp_allgather_i34                   111  8.7    1.410    3.937    1.410    3.937
 dbcsr_matrix_vector_mult           304  9.0    0.009    0.021    3.523    3.861
 dbcsr_matrix_vector_mult_local     304 10.0    3.016    3.584    3.018    3.586
 ls_scf_post                          1  4.0    0.000    0.000    3.525    3.528
 ls_scf_store_result                  1  5.0    0.000    0.000    3.273    3.344
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.931    3.034
 make_images_sizes                  222  9.7    0.000    0.000    0.987    2.292
 mp_alltoall_i44                    222 10.7    0.986    2.292    0.986    2.292
 dbcsr_sort_data                    325 11.1    1.888    2.172    1.888    2.172
 make_images_pack                   222  9.7    1.830    2.137    1.832    2.139
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.983    1.985
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.965    1.967
 qs_ks_build_kohn_sham_matrix         3  8.3    0.002    0.012    1.965    1.967
 dbcsr_data_release                9322 10.9    1.298    1.923    1.298    1.923
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="504", plot="h2o_32_nrep3_ls", label="(8n/4r/3t)", y=94.945000, yerr=0.000000
PlotPoint: name="505", plot="h2o_32_nrep3_ls_mem", label="(8n/4r/3t)", y=2183.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_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               3.372274E+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    0.039    0.077   97.963   97.964
 qs_energies                          1  2.0    0.000    0.000   97.198   97.234
 ls_scf                               1  3.0    0.000    0.001   95.304   95.340
 dbcsr_multiply_generic             111  6.7    0.017    0.019   78.456   78.679
 ls_scf_main                          1  4.0    0.000    0.002   58.932   58.933
 multiply_cannon                    111  7.7    0.055    0.134   51.594   57.045
 density_matrix_trs4                  2  5.0    0.009    0.056   52.673   52.799
 multiply_cannon_loop               111  8.7    0.115    0.128   46.420   49.621
 ls_scf_init_scf                      1  4.0    0.001    0.011   32.827   32.829
 ls_scf_init_matrix_S                 1  5.0    0.000    0.002   31.495   31.568
 mp_waitall_1                      6369 11.0   22.493   30.340   22.493   30.340
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.003   29.009   29.022
 multiply_cannon_multrec           1332  9.7   14.209   17.607   22.134   25.357
 make_m2s                           222  7.7    0.006    0.007   21.017   22.485
 make_images                        222  8.7    3.148    3.603   20.967   22.437
 multiply_cannon_metrocomm3        1332  9.7    0.003    0.003    8.989   17.621
 make_images_data                   222  9.7    0.004    0.004   11.728   13.443
 hybrid_alltoall_any                227 10.6    0.795    3.797   10.988   12.972
 dbcsr_mm_accdrv_process           3641 10.4    0.238    0.409    7.562    9.059
 dbcsr_mm_accdrv_process_sort      3641 11.4    7.187    8.644    7.187    8.644
 mp_sum_l                           807  5.4    4.286    7.747    4.286    7.747
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.003    2.603    6.524
 multiply_cannon_sync_h2d          1332  9.7    5.477    6.304    5.477    6.304
 multiply_cannon_metrocomm4        1110  9.7    0.004    0.006    2.084    6.033
 mp_irecv_dv                       3229 10.9    2.061    5.969    2.061    5.969
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.249    5.930
 arnoldi_extremal                     4  6.8    0.000    0.000    5.395    5.412
 arnoldi_normal_ev                    4  7.8    0.001    0.005    5.395    5.412
 build_subspace                      16  8.4    0.014    0.021    5.058    5.064
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.637    4.827
 mp_allgather_i34                   111  8.7    2.267    4.677    2.267    4.677
 calculate_norms                   2376  9.8    4.199    4.579    4.199    4.579
 dbcsr_matrix_vector_mult           304  9.0    0.010    0.020    3.690    3.996
 dbcsr_matrix_vector_mult_local     304 10.0    3.182    3.681    3.184    3.683
 ls_scf_post                          1  4.0    0.000    0.001    3.545    3.583
 dbcsr_sort_data                    658 11.4    3.071    3.378    3.071    3.378
 ls_scf_dm_to_ks                      2  5.0    0.000    0.001    3.075    3.139
 dbcsr_special_finalize             555  9.7    0.006    0.007    2.821    3.114
 dbcsr_merge_single_wm              555 10.7    0.534    0.648    2.813    3.107
 ls_scf_store_result                  1  5.0    0.000    0.000    2.994    3.043
 dbcsr_data_release               10477 10.7    1.579    2.403    1.579    2.403
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.063    2.064
 rebuild_ks_matrix                    3  7.3    0.000    0.000    2.039    2.041
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.002    2.039    2.041
 dbcsr_finalize                     304  7.8    0.049    0.061    1.794    1.979
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="506", plot="h2o_32_nrep3_ls", label="(8n/3r/4t)", y=97.964000, yerr=0.000000
PlotPoint: name="507", plot="h2o_32_nrep3_ls_mem", label="(8n/3r/4t)", y=2718.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_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               4.636922E+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    0.042    0.059   98.358   98.359
 qs_energies                          1  2.0    0.000    0.000   97.582   97.586
 ls_scf                               1  3.0    0.000    0.000   95.641   95.651
 dbcsr_multiply_generic             111  6.7    0.017    0.018   76.674   76.840
 ls_scf_main                          1  4.0    0.000    0.000   61.556   61.557
 multiply_cannon                    111  7.7    0.084    0.179   54.543   59.833
 density_matrix_trs4                  2  5.0    0.002    0.003   54.261   54.364
 multiply_cannon_loop               111  8.7    0.069    0.077   49.924   51.417
 mp_waitall_1                      5436 11.0   25.301   31.157   25.301   31.157
 ls_scf_init_scf                      1  4.0    0.000    0.000   30.536   30.541
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   29.177   29.215
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.005   27.013
 multiply_cannon_multrec            444  9.7   13.981   16.364   21.084   23.951
 make_m2s                           222  7.7    0.004    0.005   17.415   19.993
 make_images                        222  8.7    3.733    4.438   17.353   19.933
 multiply_cannon_metrocomm1         444  9.7    0.002    0.002   10.560   15.147
 multiply_cannon_metrocomm3         444  9.7    0.001    0.001    5.929   14.034
 make_images_data                   222  9.7    0.003    0.004    9.616   12.180
 hybrid_alltoall_any                227 10.6    0.790    3.765    9.399   11.893
 multiply_cannon_sync_h2d           444  9.7    6.519    8.340    6.519    8.340
 dbcsr_mm_accdrv_process           3003 10.4    0.164    0.341    6.810    7.956
 dbcsr_mm_accdrv_process_sort      3003 11.4    6.495    7.609    6.495    7.609
 mp_allgather_i34                   111  8.7    2.847    7.038    2.847    7.038
 arnoldi_extremal                     4  6.8    0.000    0.000    6.001    6.009
 arnoldi_normal_ev                    4  7.8    0.002    0.005    6.001    6.009
 build_subspace                      16  8.4    0.015    0.019    5.610    5.619
 mp_sum_l                           807  5.4    2.756    4.899    2.756    4.899
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.509    4.658
 dbcsr_matrix_vector_mult           304  9.0    0.011    0.020    4.284    4.482
 multiply_cannon_metrocomm4         333  9.7    0.001    0.002    1.607    4.390
 mp_irecv_dv                       1241 11.2    1.588    4.363    1.588    4.363
 dbcsr_matrix_vector_mult_local     304 10.0    3.686    4.153    3.688    4.156
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    3.734    3.835
 calculate_norms                    792  9.8    3.586    3.711    3.586    3.711
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    1.870    3.704
 ls_scf_post                          1  4.0    0.000    0.000    3.550    3.554
 ls_scf_store_result                  1  5.0    0.000    0.000    3.329    3.374
 make_images_sizes                  222  9.7    0.000    0.000    1.139    3.261
 mp_alltoall_i44                    222 10.7    1.139    3.260    1.139    3.260
 dbcsr_finalize                     304  7.8    0.062    0.078    2.201    2.279
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.232    2.233
 rebuild_ks_matrix                    3  7.3    0.000    0.000    2.199    2.201
 qs_ks_build_kohn_sham_matrix         3  8.3    0.000    0.001    2.199    2.201
 dbcsr_merge_all                    275  8.9    0.474    0.534    2.052    2.117
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="508", plot="h2o_32_nrep3_ls", label="(8n/2r/6t)", y=98.359000, yerr=0.000000
PlotPoint: name="509", plot="h2o_32_nrep3_ls_mem", label="(8n/2r/6t)", y=3627.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/eddef23af3f7f6c41d23d0ba171cfc643ffab15a_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               8.772551E+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    0.082    0.101  109.831  109.832
 qs_energies                          1  2.0    0.000    0.000  108.055  108.070
 ls_scf                               1  3.0    0.000    0.000  105.089  105.103
 dbcsr_multiply_generic             111  6.7    0.023    0.028   77.999   78.187
 ls_scf_main                          1  4.0    0.000    0.000   66.090   66.091
 density_matrix_trs4                  2  5.0    0.002    0.003   56.746   56.826
 multiply_cannon                    111  7.7    0.133    0.178   49.304   50.271
 multiply_cannon_loop               111  8.7    0.068    0.069   45.875   47.509
 ls_scf_init_scf                      1  4.0    0.000    0.000   34.989   34.990
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   33.317   33.343
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   30.131   30.140
 mp_waitall_1                      4527 11.1   21.442   25.760   21.442   25.760
 make_m2s                           222  7.7    0.005    0.005   23.879   24.801
 make_images                        222  8.7    4.615    4.981   23.773   24.693
 multiply_cannon_multrec            444  9.7   17.868   18.702   22.571   23.141
 hybrid_alltoall_any                227 10.6    1.668    3.655   12.855   15.711
 make_images_data                   222  9.7    0.003    0.003   13.059   15.425
 multiply_cannon_metrocomm3         444  9.7    0.001    0.001    9.830   10.670
 multiply_cannon_sync_h2d           444  9.7    8.820    8.878    8.820    8.878
 arnoldi_extremal                     4  6.8    0.000    0.000    7.467    7.476
 arnoldi_normal_ev                    4  7.8    0.004    0.011    7.466    7.476
 build_subspace                      16  8.4    0.026    0.036    6.909    6.922
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.420    5.697
 dbcsr_matrix_vector_mult           304  9.0    0.017    0.033    5.538    5.673
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    5.277    5.371
 dbcsr_matrix_vector_mult_local     304 10.0    5.021    5.325    5.024    5.328
 dbcsr_mm_accdrv_process           1814 10.4    0.302    0.669    4.526    4.781
 dbcsr_mm_accdrv_process_sort      1814 11.4    4.178    4.310    4.178    4.310
 ls_scf_post                          1  4.0    0.000    0.000    4.011    4.025
 mp_sum_l                           807  5.4    2.497    3.912    2.497    3.912
 make_images_sizes                  222  9.7    0.000    0.000    1.453    3.617
 mp_alltoall_i44                    222 10.7    1.453    3.616    1.453    3.616
 ls_scf_store_result                  1  5.0    0.000    0.000    3.411    3.433
 calculate_norms                    792  9.8    3.269    3.327    3.269    3.327
 mp_allgather_i34                   111  8.7    1.064    3.265    1.064    3.265
 dbcsr_finalize                     304  7.8    0.082    0.089    3.099    3.165
 dbcsr_merge_all                    275  8.9    0.892    0.918    2.885    2.944
 qs_energies_init_hamiltonians        1  3.0    0.001    0.001    2.935    2.935
 dbcsr_complete_redistribute          5  7.6    1.439    1.492    2.783    2.894
 dbcsr_data_release               12724 10.6    2.340    2.860    2.340    2.860
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.587    2.588
 matrix_ls_to_qs                      2  6.0    0.000    0.000    2.442    2.561
 rebuild_ks_matrix                    3  7.3    0.000    0.000    2.521    2.522
 qs_ks_build_kohn_sham_matrix         3  8.3    0.000    0.001    2.521    2.522
 dbcsr_sort_data                    325 11.1    2.452    2.499    2.452    2.499
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    1.571    2.449
 dbcsr_new_transposed                 4  7.5    0.243    0.252    2.312    2.324
 dbcsr_frobenius_norm                74  6.6    2.056    2.130    2.195    2.247
 dbcsr_add_d                        103  6.2    0.000    0.000    2.134    2.204
 dbcsr_add_anytype                  103  7.2    0.860    0.891    2.133    2.203
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="510", plot="h2o_32_nrep3_ls", label="(8n/1r/12t)", y=109.832000, yerr=0.000000
PlotPoint: name="511", plot="h2o_32_nrep3_ls_mem", label="(8n/1r/12t)", y=6809.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


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

CommitSHA: eddef23af3f7f6c41d23d0ba171cfc643ffab15a
Summary: empty
Status: OK