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


Updating 45056593e..454c28448
Fast-forward
 tools/toolchain/scripts/stage3/install_fftw.sh | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)
Current branch master is up to date.


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

 GIT Revision: 454c28448ad2f11fb8d3fa0aeb0a8fa209172190


################# 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 2021.11.002, LIBINT 2.6.0, LIBPEXSI 1.2.0,
#              LIBXC 5.2.3, LIBVORI 220621, LIBXSMM 1.17, PLUMED 2.8.0,
#              SIRIUS 7.3.2, SPGLIB 1.16.2
#
# Usage: Source this arch file and then run make as instructed.
#        A full toolchain installation is performed as default.
#        Replace or adapt the "module add" commands below if needed.
#
# Author: Matthias Krack (15.09.2022)
#
# \
   if [ "${0}" = "${BASH_SOURCE}" ]; then \
      echo "ERROR: Script ${0##*/} must be sourced"; \
      echo "Usage: source ${0##*/}"; \
      exit 1; \
   fi; \
   this_file=${BASH_SOURCE##*/}; \
   if [ -n "${1}" ]; then \
      gcc_version="${1}"; \
   else \
      gcc_version="9.3.0"; \
   fi; \
   module add daint-gpu; \
   module rm PrgEnv-cray; \
   module add PrgEnv-gnu; \
   module rm gcc; \
   module add gcc/${gcc_version}; \
   module add cray-fftw/3.3.8.10; \
   module add cudatoolkit; \
   echo "Expected setup:"; \
   echo "   cray-mpich/7.7.18"; \
   echo "   craype-haswell"; \
   echo "   daint-gpu/21.09"; \
   echo "   craype/2.7.10"; \
   echo "   cray-libsci/20.09.1"; \
   echo "   PrgEnv-gnu/6.0.10"; \
   echo "   gcc/${gcc_version}"; \
   echo "   cray-fftw/3.3.8.10"; \
   echo "   cudatoolkit/11.0.2_3.38-8.1__g5b73779"; \
   module list; \
   module -f save cp2k_gpu_gnu_psmp; \
   echo "To load the required modules in your batch job script, use:"; \
   echo "   module restore cp2k_gpu_gnu_psmp"; \
   cd tools/toolchain; \
   ./install_cp2k_toolchain.sh --enable-cuda=yes --gpu-ver=P100 --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       := 2021.11.002
USE_LIBINT     := 2.6.0
USE_LIBPEXSI   := 1.2.0
USE_LIBVORI    := 220621
USE_LIBXC      := 5.2.3
USE_LIBXSMM    := 1.17
USE_PLUMED     := 2.8.0
#USE_QUIP       := b4336484fb65b0e73211a8f920ae4361c7c353fd
USE_SIRIUS     := 7.3.2
USE_SPGLIB     := 1.16.2
# Only needed for SIRIUS
LIBVDWXC_VER   := 0.4.0
SPFFT_VER      := 1.0.6
SPLA_VER       := 1.5.4
HDF5_VER       := 1.12.0
# Only needed for LIBPEXSI
SCOTCH_VER     := 6.0.0
SUPERLU_VER    := 6.1.0

LMAX           := 5
MAX_CONTR      := 4

GPUVER         := P100
OFFLOAD_TARGET := cuda

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

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

DFLAGS         := -D__parallel
DFLAGS         += -D__SCALAPACK
DFLAGS         += -D__FFTW3
DFLAGS         += -D__MPI_VERSION=3
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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/01
 job id: 41821651
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/02
 job id: 41821652
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/03
 job id: 41821653
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/04
 job id: 41821654
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/05
 job id: 41821655
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/06
 job id: 41821656
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/07
 job id: 41821657
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/08
 job id: 41821658
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/09
 job id: 41821659
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/10
 job id: 41821660
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/11
 job id: 41821661
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/12
 job id: 41821662
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/13
 job id: 41821663
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/14
 job id: 41821664
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/15
 job id: 41821665
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/16
 job id: 41821666
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/17
 job id: 41821667
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/18
 job id: 41821668
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/19
 job id: 41821669
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/20
 job id: 41821670
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/21
 job id: 41821671
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/22
 job id: 41821673
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/23
 job id: 41821674
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/24
 job id: 41821675
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/25
 job id: 41821676
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/26
 job id: 41821677
 --- 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/01/result.log


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

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

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               15                 177869.
 MP_Allreduce          344                      9.
 MP_Sync                 3
 MP_comm_split           1
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.023    0.036  134.207  134.207
 farming_run                          1  2.0  133.612  133.613  134.176  134.179
 -------------------------------------------------------------------------------


 @@@@@@@@@@ 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               1.458545E+09
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                    2592
 MPI messages size (bytes):
  total size                         1.140326E+09
  min size                           0.000000E+00
  max size                           1.663488E+06
  average size                     439.940750E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                 132                        0
       128 < size <=     8192                 348                  2850816
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                1536                179306496
    131072 < size <=  4194304                 576                958169088
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         2308                     54.
 MP_Alltoall          4670                 822215.
 MP_ISend             2604                  90577.
 MP_IRecv             2604                  90574.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group               12
 MP_Bcast              228                1113141.
 MP_Allreduce          489                2263609.
 MP_Sync                27
 MP_Alltoall            38                9316958.
 MP_SendRecv            30                 829726.
 MP_ISendRecv          135                 235435.
 MP_Wait               281
 MP_comm_split           8
 MP_ISend              127                3867574.
 MP_IRecv              127                3866554.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.009    0.030  115.617  115.617
 qs_energies                          1  2.0    0.000    0.000  115.393  115.395
 mp2_main                             1  3.0    0.000    0.000  113.438  113.440
 mp2_gpw_main                         1  4.0    0.020    0.026  112.517  112.519
 mp2_ri_gpw_compute_in                1  5.0    0.171    0.173   93.894   94.024
 mp2_ri_gpw_compute_in_loop           1  6.0    0.004    0.005   55.332   55.463
 mp2_eri_3c_integrate_gpw           272  7.0    0.154    0.170   41.627   46.616
 get_2c_integrals                     1  6.0    0.000    0.000   37.717   38.390
 integrate_v_rspace                 273  8.0    0.434    0.449   25.044   29.714
 pw_transfer                       6555 10.6    0.378    0.388   27.335   27.792
 fft_wrap_pw1pw2                   5465 11.4    0.046    0.048   25.987   26.325
 grid_integrate_task_list           273  9.0   20.871   25.988   20.871   25.988
 fft_wrap_pw1pw2_100               2178 12.4    1.200    1.438   23.546   23.887
 compute_2c_integrals                 1  7.0    0.005    0.006   19.676   19.677
 compute_2c_integrals_loop_lm         1  8.0    0.003    0.003   18.912   19.398
 mp2_eri_2c_integrate_gpw             1  9.0    2.384    2.435   18.910   19.395
 cp_fm_cholesky_decompose            12  8.2   18.046   18.714   18.046   18.714
 rpa_ri_compute_en                    1  5.0    0.000    0.000   18.513   18.681
 cholesky_decomp                      1  7.0    0.000    0.000   16.882   17.537
 fft3d_s                           5443 13.4   16.097   16.246   16.118   16.267
 ao_to_mo_and_store_B_mult_1        272  7.0   10.862   15.592   10.862   15.592
 calculate_wavefunction             272  8.0    5.400    5.490   12.510   13.124
 rpa_num_int                          1  6.0    0.000    0.000   10.643   10.643
 rpa_num_int_RPA_matrix_operati       8  7.0    0.027    0.027   10.604   10.615
 calc_mat_Q                           8  8.0    0.000    0.000    9.367    9.454
 contract_S_to_Q                      8  9.0    0.000    0.000    8.788    8.877
 calc_potential_gpw                 544  9.5    0.005    0.005    8.279    8.709
 mp2_eri_2c_integrate_gpw_pot_l     272 10.0    0.001    0.002    8.248    8.572
 parallel_gemm_fm                    14  9.1    0.000    0.000    8.365    8.453
 parallel_gemm_fm_cosma              14 10.1    8.365    8.453    8.365    8.453
 potential_pw2rs                    545 10.0    0.107    0.109    7.673    8.329
 collocate_single_gaussian          272 10.0    0.040    0.043    7.459    7.724
 create_integ_mat                     1  6.0    0.023    0.027    7.644    7.644
 array2fm                             1  7.0    0.000    0.000    6.660    7.081
 pw_scatter_s                      2720 13.7    4.448    4.606    4.448    4.606
 pw_gather_s                       2722 13.2    3.870    4.229    3.870    4.229
 array2fm_buffer_send                 1  8.0    2.907    3.159    2.907    3.159
 pw_poisson_solve                   545 10.5    1.130    1.175    2.183    2.439
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="10", plot="h2o_32_ri_rpa_mp2", label="RI-RPA (8n/2r/6t)", y=112.518940, 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/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_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    0.029    0.039  397.801  397.803
 farming_run                          1  2.0  396.970  396.978  397.757  397.760
 -------------------------------------------------------------------------------


 @@@@@@@@@@ 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               1.223586E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                   61440
 MPI messages size (bytes):
  total size                         6.073508E+09
  min size                           0.000000E+00
  max size                         642.960000E+03
  average size                      98.852664E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               32004                        0
       128 < size <=     8192                1820                 14909440
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072               18640               1081442304
    131072 < size <=  4194304                8976               4977156096
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         1003                     44.
 MP_Alltoall          1797                 713538.
 MP_ISend             3686                  54943.
 MP_IRecv             3622                  54292.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group               12
 MP_Bcast              703                 408373.
 MP_Allreduce         1825                  23678.
 MP_Sync                38
 MP_Alltoall            77               16747241.
 MP_SendRecv          2171                2843495.
 MP_ISendRecv         1739                 144022.
 MP_Wait              2051
 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    0.014    0.044  210.106  210.106
 qs_energies                          1  2.0    0.000    0.000  209.859  209.867
 scf_env_do_scf                       1  3.0    0.000    0.000  106.022  106.022
 qs_ks_update_qs_env                  5  5.0    0.000    0.000  105.125  105.136
 rebuild_ks_matrix                    4  6.0    0.000    0.000  105.124  105.134
 qs_ks_build_kohn_sham_matrix         4  7.0    0.058    0.068  105.124  105.134
 hfx_ks_matrix                        4  8.0    0.001    0.001  104.740  104.743
 integrate_four_center                4  9.0    0.145    0.449  104.739  104.742
 mp2_main                             1  3.0    0.000    0.000  103.551  103.559
 mp2_gpw_main                         1  4.0    0.033    0.054  102.658  102.666
 integrate_four_center_main           4 10.0    0.103    0.486   96.758   99.004
 integrate_four_center_bin          270 11.0   96.654   98.968   96.654   98.968
 init_scf_loop                        1  4.0    0.000    0.000   91.940   91.940
 mp2_ri_gpw_compute_in                1  5.0    0.067    0.102   75.367   76.752
 mp2_ri_gpw_compute_in_loop           1  6.0    0.002    0.003   54.938   56.320
 mp2_eri_3c_integrate_gpw            91  7.0    0.144    0.156   42.322   47.393
 integrate_v_rspace                  95  8.0    0.397    0.557   28.700   33.599
 pw_transfer                       2240 10.6    0.146    0.164   29.878   30.393
 ao_to_mo_and_store_B_mult_1         91  7.0   10.926   30.109   10.926   30.109
 fft_wrap_pw1pw2                   1868 11.4    0.018    0.022   28.891   29.435
 mp2_ri_gpw_compute_en                1  5.0    0.055    0.064   27.121   29.163
 grid_integrate_task_list            95  9.0   23.978   29.088   23.978   29.088
 fft_wrap_pw1pw2_100                730 12.4    1.271    1.444   26.608   27.032
 mp2_ri_gpw_compute_en_RI_loop        1  6.0    1.836    1.918   25.066   25.076
 get_2c_integrals                     1  6.0    0.001    0.010   20.337   20.366
 compute_2c_integrals                 1  7.0    0.003    0.005   19.327   19.336
 compute_2c_integrals_loop_lm         1  8.0    0.001    0.002   18.851   19.203
 mp2_eri_2c_integrate_gpw             1  9.0    1.758    1.876   18.850   19.201
 fft3d_s                           1823 13.4   18.404   18.721   18.418   18.735
 scf_env_do_scf_inner_loop            4  4.0    0.000    0.000   14.080   14.080
 calculate_wavefunction              91  8.0    2.020    2.054    9.743    9.935
 mp2_ri_gpw_compute_en_expansio     172  7.0    0.555    0.572    8.794    9.456
 potential_pw2rs                    186 10.0    0.033    0.035    8.645    9.264
 local_gemm                         172  8.0    8.239    8.904    8.239    8.904
 mp2_eri_2c_integrate_gpw_pot_l      91 10.0    0.001    0.001    8.229    8.627
 mp2_ri_gpw_compute_en_comm          22  7.0    0.497    0.514    8.045    8.371
 collocate_single_gaussian           91 10.0    0.018    0.027    7.863    8.150
 calc_potential_gpw                 182  9.5    0.002    0.002    7.906    8.092
 mp2_ri_gpw_compute_en_ener         172  7.0    6.345    6.443    6.345    6.443
 mp_sendrecv_dm3                   2068  8.0    6.084    6.407    6.084    6.407
 pw_gather_s                        912 13.2    4.918    5.531    4.918    5.531
 mp_sync                             38 10.4    2.674    4.959    2.674    4.959
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="20", plot="h2o_32_ri_rpa_mp2", label="RI-MP2 (8n/6r/2t)", y=102.663434, yerr=0.000000
PlotPoint: name="21", plot="h2o_32_ri_rpa_mp2_mem", label="RI-MP2 (8n/6r/2t)", y=1511.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_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             450.031616E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 9436608
 MPI messages size (bytes):
  total size                       333.233553E+09
  min size                           0.000000E+00
  max size                         315.840000E+03
  average size                      35.312852E+03
 MPI breakdown and total messages size (bytes):
             size <=      128             4913240                        0
       128 < size <=     8192             1155432               9465298944
      8192 < size <=    32768             1984512              54190407680
     32768 < size <=   131072              551296              42776657920
    131072 < size <=  4194304              832128             226802306368
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3683                  62385.
 MP_Allreduce        10249                    271.
 MP_Sync               580
 MP_Alltoall          2083                 592243.
 MP_ISendRecv        45220                   5520.
 MP_Wait             60486
 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    0.013    0.033   52.223   52.224
 qs_mol_dyn_low                       1  2.0    0.003    0.003   51.948   51.955
 qs_forces                           11  3.9    0.002    0.002   51.795   51.796
 qs_energies                         11  4.9    0.001    0.002   50.331   50.339
 scf_env_do_scf                      11  5.9    0.000    0.001   43.569   43.570
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   41.524   41.526
 dbcsr_multiply_generic            2286 12.5    0.091    0.096   33.787   34.204
 qs_scf_new_mos                     108  7.5    0.000    0.001   31.401   31.671
 qs_scf_loop_do_ot                  108  8.5    0.000    0.001   31.400   31.670
 ot_scf_mini                        108  9.5    0.002    0.002   29.803   29.971
 multiply_cannon                   2286 13.5    0.188    0.197   26.443   27.969
 multiply_cannon_loop              2286 14.5    1.490    1.564   25.713   27.226
 velocity_verlet                     10  3.0    0.002    0.006   25.088   25.089
 ot_mini                            108 10.5    0.001    0.001   18.895   19.120
 qs_ot_get_derivative               108 11.5    0.001    0.001   15.953   16.140
 mp_waitall_1                    267858 16.1    8.448   15.170    8.448   15.170
 multiply_cannon_metrocomm3       54864 15.5    0.066    0.071    5.856   13.431
 multiply_cannon_multrec          54864 15.5    4.218    6.515    7.943   11.532
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.941    8.075
 qs_ks_build_kohn_sham_matrix       119  9.3    0.010    0.011    7.940    8.075
 multiply_cannon_sync_h2d         54864 15.5    5.918    7.643    5.918    7.643
 qs_ks_update_qs_env                119  7.6    0.001    0.001    7.003    7.127
 mp_sum_l                          7207 12.9    5.275    6.930    5.275    6.930
 qs_ot_get_p                        119 10.4    0.001    0.001    6.289    6.618
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    5.191    5.646
 init_scf_run                        11  5.9    0.000    0.001    5.565    5.565
 scf_env_initial_rho_setup           11  6.9    0.000    0.001    5.564    5.565
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    5.436    5.516
 dbcsr_mm_accdrv_process          76910 16.1    1.179    1.835    3.647    5.122
 sum_up_and_integrate               119 10.3    0.013    0.016    4.583    4.591
 integrate_v_rspace                 119 11.3    0.002    0.003    4.570    4.580
 qs_rho_update_rho_low              119  7.7    0.001    0.001    4.106    4.199
 calculate_rho_elec                 119  8.7    0.011    0.016    4.105    4.198
 qs_ot_p2m_diag                      50 11.0    0.004    0.006    3.476    3.552
 calculate_first_density_matrix       1  7.0    0.000    0.000    3.448    3.452
 calculate_dm_sparse                119  9.5    0.000    0.000    3.205    3.323
 jit_kernel_multiply                 13 15.8    2.406    3.214    2.406    3.214
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.880    3.069
 apply_single                       119 13.6    0.000    0.000    2.880    3.069
 multiply_cannon_metrocomm1       54864 15.5    0.053    0.059    1.649    2.995
 rs_pw_transfer                     974 11.9    0.012    0.014    2.846    2.939
 acc_transpose_blocks             54864 15.5    0.230    0.251    2.173    2.714
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.686    2.689
 ot_diis_step                       108 11.5    0.006    0.006    2.671    2.672
 cp_dbcsr_syevd                      50 12.0    0.002    0.003    2.634    2.634
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.432    2.473
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    2.403    2.455
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    2.407    2.407
 cp_fm_redistribute_end              50 14.0    2.186    2.384    2.191    2.387
 cp_fm_diag_elpa_base                50 14.0    0.193    2.336    0.194    2.350
 density_rs2pw                      119  9.7    0.004    0.004    2.204    2.320
 grid_integrate_task_list           119 12.3    2.018    2.127    2.018    2.127
 wfi_extrapolate                     11  7.9    0.001    0.001    2.058    2.058
 init_scf_loop                       11  6.9    0.000    0.000    2.030    2.032
 potential_pw2rs                    119 12.3    0.004    0.005    1.918    1.931
 mp_sum_d                          4129 12.0    1.274    1.901    1.274    1.901
 make_m2s                          4572 13.5    0.053    0.055    1.764    1.816
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.768    1.783
 pw_transfer                       1439 11.6    0.052    0.055    1.679    1.748
 acc_transpose_blocks_kernels     54864 16.5    0.252    0.385    1.174    1.735
 make_images                       4572 14.5    0.133    0.139    1.682    1.734
 fft_wrap_pw1pw2                   1201 12.6    0.007    0.007    1.603    1.675
 mp_alltoall_d11v                  2130 13.8    1.369    1.482    1.369    1.482
 mp_waitany                       12084 13.8    1.286    1.449    1.286    1.449
 fft3d_ps                          1201 14.6    0.355    0.458    1.381    1.444
 jit_kernel_transpose                 5 15.5    0.922    1.417    0.922    1.417
 grid_collocate_task_list           119  9.7    1.288    1.352    1.288    1.352
 fft_wrap_pw1pw2_140                487 13.2    0.080    0.094    1.241    1.311
 dbcsr_dot_sd                      1205 11.9    0.047    0.058    0.708    1.101
 parallel_gemm_fm                    81  9.0    0.000    0.000    1.058    1.062
 parallel_gemm_fm_cosma              81 10.0    1.057    1.062    1.057    1.062
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="100", plot="h2o_64_md", label="(8n/12r/1t)", y=52.224000, yerr=0.000000
PlotPoint: name="101", plot="h2o_64_md_mem", label="(8n/12r/1t)", y=429.090909, yerr=1.239835
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/04/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                     57.173320E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               3066240       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      47.9
 marketing flops                     2.107592E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             487.526400E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 2194560
 MPI messages size (bytes):
  total size                       310.646604E+09
  min size                           0.000000E+00
  max size                           1.145520E+06
  average size                     141.553031E+03
 MPI breakdown and total messages size (bytes):
             size <=      128              724648                        0
       128 < size <=     8192              253512               2076770304
      8192 < size <=    32768              281952               4619501568
     32768 < size <=   131072              494448              39143342080
    131072 < size <=  4194304              440000             264807943488
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3672                  62664.
 MP_Allreduce        10226                    305.
 MP_Sync               104
 MP_Alltoall          2060                 735044.
 MP_ISendRecv        33558                  37093.
 MP_Wait             40318
 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    0.018    0.034   39.604   39.605
 qs_mol_dyn_low                       1  2.0    0.003    0.004   39.381   39.389
 qs_forces                           11  3.9    0.008    0.024   39.318   39.319
 qs_energies                         11  4.9    0.002    0.004   37.594   37.602
 scf_env_do_scf                      11  5.9    0.001    0.001   31.368   31.368
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   28.828   28.828
 dbcsr_multiply_generic            2286 12.5    0.099    0.103   22.421   22.797
 qs_scf_new_mos                     108  7.5    0.001    0.001   19.856   20.103
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   19.855   20.102
 ot_scf_mini                        108  9.5    0.002    0.003   18.970   19.148
 multiply_cannon                   2286 13.5    0.209    0.219   17.390   18.919
 velocity_verlet                     10  3.0    0.001    0.002   18.370   18.371
 multiply_cannon_loop              2286 14.5    0.903    0.987   16.265   17.769
 mp_waitall_1                    217478 16.2    6.480   12.480    6.480   12.480
 ot_mini                            108 10.5    0.001    0.001   11.863   12.104
 multiply_cannon_metrocomm3       27432 15.5    0.068    0.070    4.558   10.620
 qs_ot_get_derivative               108 11.5    0.001    0.001    9.378    9.558
 multiply_cannon_multrec          27432 15.5    1.965    4.267    6.078    8.930
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.163    7.298
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    7.163    7.297
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.298    6.419
 dbcsr_mm_accdrv_process          47894 16.0    3.082    5.286    4.044    6.151
 init_scf_run                        11  5.9    0.000    0.001    4.946    4.946
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    4.946    4.946
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    3.625    4.436
 qs_ot_get_p                        119 10.4    0.001    0.001    4.192    4.420
 sum_up_and_integrate               119 10.3    0.025    0.028    4.173    4.178
 integrate_v_rspace                 119 11.3    0.002    0.002    4.148    4.157
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    3.027    4.137
 apply_single                       119 13.6    0.000    0.000    3.027    4.137
 mp_sum_l                          7207 12.9    2.075    4.077    2.075    4.077
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.641    3.674
 calculate_rho_elec                 119  8.7    0.021    0.024    3.641    3.673
 calculate_first_density_matrix       1  7.0    0.000    0.000    3.380    3.382
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.978    2.980
 multiply_cannon_sync_h2d         27432 15.5    2.186    2.877    2.186    2.877
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.732    2.769
 make_m2s                          4572 13.5    0.052    0.054    2.528    2.766
 rs_pw_transfer                     974 11.9    0.010    0.011    2.635    2.761
 qs_ot_p2m_diag                      50 11.0    0.009    0.013    2.735    2.755
 make_images                       4572 14.5    0.202    0.240    2.442    2.679
 init_scf_loop                       11  6.9    0.000    0.001    2.519    2.519
 jit_kernel_multiply                 11 16.1    0.910    2.465    0.910    2.465
 ot_diis_step                       108 11.5    0.011    0.013    2.433    2.434
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    2.298    2.299
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    2.198    2.295
 acc_transpose_blocks             27432 15.5    0.108    0.112    1.663    2.200
 calculate_dm_sparse                119  9.5    0.000    0.001    2.024    2.101
 density_rs2pw                      119  9.7    0.004    0.004    1.978    2.090
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.951    1.951
 potential_pw2rs                    119 12.3    0.006    0.007    1.919    1.928
 cp_fm_redistribute_end              50 14.0    1.608    1.924    1.612    1.926
 grid_integrate_task_list           119 12.3    1.826    1.920    1.826    1.920
 cp_fm_diag_elpa_base                50 14.0    0.305    1.863    0.312    1.894
 pw_transfer                       1439 11.6    0.063    0.066    1.770    1.807
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.680    1.719
 prepare_preconditioner              11  7.9    0.000    0.000    1.623    1.650
 make_preconditioner                 11  8.9    0.000    0.001    1.623    1.650
 make_images_data                  4572 15.5    0.045    0.051    1.153    1.581
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.519    1.576
 acc_transpose_blocks_kernels     27432 16.5    0.182    0.272    1.126    1.572
 wfi_extrapolate                     11  7.9    0.001    0.001    1.515    1.515
 hybrid_alltoall_any               4725 16.4    0.050    0.112    1.002    1.459
 fft3d_ps                          1201 14.6    0.493    0.545    1.387    1.421
 mp_alltoall_d11v                  2130 13.8    1.251    1.395    1.251    1.395
 mp_allgather_i34                  2286 14.5    0.562    1.330    0.562    1.330
 grid_collocate_task_list           119  9.7    1.242    1.330    1.242    1.330
 fft_wrap_pw1pw2_140                487 13.2    0.076    0.083    1.294    1.330
 jit_kernel_transpose                 5 15.5    0.945    1.305    0.945    1.305
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.245    1.262
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.185    1.232
 mp_sum_d                          4129 12.0    0.601    1.038    0.601    1.038
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    1.012    1.018
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.921    0.935
 rs_pw_transfer_PW2RS_50            119 14.3    0.590    0.610    0.755    0.801
 make_images_sizes                 4572 15.5    0.005    0.005    0.556    0.793
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="102", plot="h2o_64_md", label="(8n/6r/2t)", y=39.605000, yerr=0.000000
PlotPoint: name="103", plot="h2o_64_md_mem", label="(8n/6r/2t)", y=464.000000, yerr=1.477098
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/05/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                     59.051995E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               3143552       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      46.8
 marketing flops                     2.107587E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             520.761344E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                  950976
 MPI messages size (bytes):
  total size                       203.844256E+09
  min size                           0.000000E+00
  max size                           1.638400E+06
  average size                     214.352688E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192              253512               2076770304
      8192 < size <=    32768              179424               2939682816
     32768 < size <=   131072              181440              14863564800
    131072 < size <=  4194304              330176             183964913216
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3672                  62660.
 MP_Allreduce        10225                    303.
 MP_Sync               104
 MP_Alltoall          1821                1607811.
 MP_ISendRecv        22134                  57667.
 MP_Wait             33054
 MP_comm_split          50
 MP_ISend             9880                  92618.
 MP_IRecv             9880                  92618.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.021    0.044   33.533   33.534
 qs_mol_dyn_low                       1  2.0    0.004    0.005   33.226   33.233
 qs_forces                           11  3.9    0.003    0.006   33.160   33.162
 qs_energies                         11  4.9    0.014    0.050   31.598   31.601
 scf_env_do_scf                      11  5.9    0.001    0.001   26.000   26.000
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   23.284   23.286
 dbcsr_multiply_generic            2286 12.5    0.091    0.093   17.410   17.532
 velocity_verlet                     10  3.0    0.002    0.002   15.617   15.619
 qs_scf_new_mos                     108  7.5    0.001    0.001   15.162   15.181
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   15.161   15.180
 multiply_cannon                   2286 13.5    0.195    0.204   13.933   14.753
 ot_scf_mini                        108  9.5    0.002    0.003   14.423   14.436
 multiply_cannon_loop              2286 14.5    0.640    0.668   13.118   13.965
 ot_mini                            108 10.5    0.001    0.001    8.984    8.997
 multiply_cannon_multrec          18288 15.5    1.938    2.915    7.179    7.495
 qs_ot_get_derivative               108 11.5    0.001    0.002    7.462    7.477
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.368    6.390
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.019    6.367    6.389
 dbcsr_mm_accdrv_process          38222 16.0    4.157    5.645    5.155    6.102
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.638    5.660
 mp_waitall_1                    169478 16.3    3.181    4.436    3.181    4.436
 init_scf_run                        11  5.9    0.000    0.001    4.338    4.340
 scf_env_initial_rho_setup           11  6.9    0.011    0.016    4.337    4.339
 sum_up_and_integrate               119 10.3    0.030    0.031    3.983    3.988
 integrate_v_rspace                 119 11.3    0.002    0.003    3.953    3.959
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.849    3.468
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.354    3.361
 calculate_rho_elec                 119  8.7    0.030    0.031    3.353    3.360
 qs_ot_get_p                        119 10.4    0.001    0.001    3.233    3.252
 calculate_first_density_matrix       1  7.0    0.000    0.001    3.068    3.081
 init_scf_loop                       11  6.9    0.000    0.002    2.689    2.691
 multiply_cannon_metrocomm3       18288 15.5    0.045    0.046    1.496    2.677
 calculate_dm_sparse                119  9.5    0.000    0.000    2.626    2.638
 rs_pw_transfer                     974 11.9    0.010    0.010    2.416    2.521
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.046    2.355
 apply_single                       119 13.6    0.000    0.000    2.046    2.355
 jit_kernel_multiply                 10 16.4    0.946    2.304    0.946    2.304
 qs_ot_p2m_diag                      50 11.0    0.012    0.013    2.118    2.123
 density_rs2pw                      119  9.7    0.004    0.004    1.949    2.064
 make_m2s                          4572 13.5    0.045    0.046    1.883    2.020
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.983    1.988
 make_images                       4572 14.5    0.192    0.204    1.798    1.933
 prepare_preconditioner              11  7.9    0.000    0.000    1.876    1.880
 make_preconditioner                 11  8.9    0.000    0.001    1.876    1.880
 grid_integrate_task_list           119 12.3    1.792    1.862    1.792    1.862
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.837    1.838
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.724    1.806
 pw_transfer                       1439 11.6    0.063    0.066    1.759    1.774
 potential_pw2rs                    119 12.3    0.007    0.008    1.765    1.772
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.689    1.691
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.668    1.685
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.631    1.638
 acc_transpose_blocks             18288 15.5    0.074    0.077    1.604    1.625
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.599    1.600
 multiply_cannon_sync_h2d         18288 15.5    1.366    1.582    1.366    1.582
 cp_fm_redistribute_end              50 14.0    1.187    1.577    1.189    1.578
 mp_sum_l                          7207 12.9    1.225    1.554    1.225    1.554
 cp_fm_diag_elpa_base                50 14.0    0.373    1.513    0.388    1.553
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.521    1.528
 ot_diis_step                       108 11.5    0.012    0.014    1.494    1.494
 fft3d_ps                          1201 14.6    0.505    0.523    1.355    1.372
 grid_collocate_task_list           119  9.7    1.203    1.335    1.203    1.335
 fft_wrap_pw1pw2_140                487 13.2    0.086    0.090    1.294    1.310
 wfi_extrapolate                     11  7.9    0.002    0.005    1.213    1.215
 acc_transpose_blocks_kernels     18288 16.5    0.210    0.219    1.161    1.174
 multiply_cannon_metrocomm1       18288 15.5    0.029    0.030    0.436    1.035
 make_images_data                  4572 15.5    0.044    0.049    0.833    0.988
 qs_energies_init_hamiltonians       11  5.9    0.002    0.005    0.982    0.984
 jit_kernel_transpose                 5 15.6    0.950    0.960    0.950    0.960
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.937    0.956
 mp_alltoall_d11v                  2130 13.8    0.746    0.920    0.746    0.920
 hybrid_alltoall_any               4725 16.4    0.054    0.112    0.719    0.899
 cp_fm_cholesky_invert               11 10.9    0.824    0.828    0.824    0.828
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.800    0.802
 mp_alltoall_z22v                  1201 16.6    0.688    0.760    0.688    0.760
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.647    0.716
 mp_waitany                        9880 13.7    0.563    0.693    0.563    0.693
 rs_pw_transfer_RS2PW_140           130 11.5    0.121    0.130    0.559    0.680
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="104", plot="h2o_64_md", label="(8n/4r/3t)", y=33.534000, yerr=0.000000
PlotPoint: name="105", plot="h2o_64_md_mem", label="(8n/4r/3t)", y=495.363636, yerr=1.966664
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_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             543.641600E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1042416
 MPI messages size (bytes):
  total size                       150.443262E+09
  min size                           0.000000E+00
  max size                           1.188816E+06
  average size                     144.321719E+03
 MPI breakdown and total messages size (bytes):
             size <=      128              228256                        0
       128 < size <=     8192              126888               1039466496
      8192 < size <=    32768              191472               3137077248
     32768 < size <=   131072              295800              25899827200
    131072 < size <=  4194304              200000             120367247040
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3672                  62659.
 MP_Allreduce        10224                    344.
 MP_Sync               104
 MP_Alltoall          1582                2412273.
 MP_ISendRecv        16422                  74133.
 MP_Wait             24482
 MP_comm_split          50
 MP_ISend             7280                 135929.
 MP_IRecv             7280                 135929.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.019    0.048   35.939   35.941
 qs_mol_dyn_low                       1  2.0    0.003    0.004   35.701   35.708
 qs_forces                           11  3.9    0.002    0.005   35.620   35.621
 qs_energies                         11  4.9    0.002    0.003   33.898   33.905
 scf_env_do_scf                      11  5.9    0.001    0.001   27.800   27.802
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   24.321   24.325
 dbcsr_multiply_generic            2286 12.5    0.098    0.100   19.195   19.383
 velocity_verlet                     10  3.0    0.001    0.002   17.708   17.711
 qs_scf_new_mos                     108  7.5    0.001    0.001   16.207   16.262
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   16.207   16.261
 multiply_cannon                   2286 13.5    0.228    0.271   15.544   16.089
 ot_scf_mini                        108  9.5    0.002    0.003   15.274   15.327
 multiply_cannon_loop              2286 14.5    0.936    0.969   14.587   15.071
 ot_mini                            108 10.5    0.001    0.001    9.425    9.491
 multiply_cannon_multrec          27432 15.5    2.334    3.148    8.966    9.358
 dbcsr_mm_accdrv_process          47916 15.9    5.581    7.114    6.536    7.708
 qs_ot_get_derivative               108 11.5    0.001    0.001    7.618    7.671
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.497    6.548
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.016    6.497    6.548
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.767    5.811
 init_scf_run                        11  5.9    0.000    0.001    4.681    4.681
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    4.681    4.681
 sum_up_and_integrate               119 10.3    0.035    0.039    3.781    3.790
 integrate_v_rspace                 119 11.3    0.002    0.003    3.746    3.756
 init_scf_loop                       11  6.9    0.000    0.001    3.460    3.478
 qs_ot_get_p                        119 10.4    0.001    0.001    3.249    3.329
 calculate_first_density_matrix       1  7.0    0.000    0.001    3.314    3.315
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.229    3.261
 calculate_rho_elec                 119  8.7    0.040    0.046    3.229    3.261
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.726    3.179
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.855    2.856
 mp_waitall_1                    145218 16.4    2.184    2.793    2.184    2.793
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.668    2.680
 prepare_preconditioner              11  7.9    0.000    0.000    2.612    2.620
 make_preconditioner                 11  8.9    0.000    0.001    2.612    2.620
 make_full_inverse_cholesky          11  9.9    0.000    0.000    2.212    2.541
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.083    2.523
 apply_single                       119 13.6    0.000    0.000    2.083    2.523
 make_m2s                          4572 13.5    0.054    0.056    2.195    2.314
 make_images                       4572 14.5    0.274    0.336    2.088    2.205
 rs_pw_transfer                     974 11.9    0.009    0.010    2.045    2.195
 jit_kernel_multiply                 10 16.0    0.895    2.193    0.895    2.193
 acc_transpose_blocks             27432 15.5    0.111    0.113    2.141    2.165
 calculate_dm_sparse                119  9.5    0.000    0.000    2.023    2.075
 qs_ot_p2m_diag                      50 11.0    0.015    0.023    1.976    1.984
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.916    1.940
 grid_integrate_task_list           119 12.3    1.833    1.906    1.833    1.906
 density_rs2pw                      119  9.7    0.003    0.004    1.734    1.866
 pw_transfer                       1439 11.6    0.063    0.067    1.739    1.767
 ot_diis_step                       108 11.5    0.012    0.016    1.765    1.766
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.649    1.680
 mp_sum_l                          7207 12.9    1.066    1.673    1.066    1.673
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.667    1.668
 potential_pw2rs                    119 12.3    0.009    0.010    1.565    1.569
 acc_transpose_blocks_kernels     27432 16.5    0.269    0.277    1.510    1.529
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.421    1.421
 cp_fm_redistribute_end              50 14.0    0.936    1.396    0.937    1.397
 multiply_cannon_metrocomm3       27432 15.5    0.038    0.039    0.802    1.389
 cp_fm_diag_elpa_base                50 14.0    0.437    1.334    0.457    1.374
 fft_wrap_pw1pw2_140                487 13.2    0.085    0.093    1.338    1.370
 fft3d_ps                          1201 14.6    0.531    0.585    1.328    1.353
 wfi_extrapolate                     11  7.9    0.001    0.001    1.323    1.323
 grid_collocate_task_list           119  9.7    1.221    1.316    1.221    1.316
 jit_kernel_transpose                 5 15.6    1.241    1.254    1.241    1.254
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.208    1.219
 qs_energies_init_hamiltonians       11  5.9    0.003    0.019    1.146    1.161
 cp_fm_upper_to_full                 72 13.5    0.816    1.130    0.816    1.130
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.098    1.116
 dbcsr_complete_redistribute        329 12.2    0.130    0.167    0.795    1.067
 multiply_cannon_sync_h2d         27432 15.5    0.989    1.044    0.989    1.044
 make_images_data                  4572 15.5    0.044    0.048    0.863    0.986
 hybrid_alltoall_any               4725 16.4    0.061    0.149    0.735    0.922
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.797    0.874
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    0.586    0.854
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.820    0.825
 mp_alltoall_d11v                  2130 13.8    0.717    0.816    0.717    0.816
 cp_fm_cholesky_invert               11 10.9    0.762    0.765    0.762    0.765
 mp_alltoall_i22                    627 13.8    0.436    0.726    0.436    0.726
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="106", plot="h2o_64_md", label="(8n/3r/4t)", y=35.941000, yerr=0.000000
PlotPoint: name="107", plot="h2o_64_md_mem", label="(8n/3r/4t)", y=514.636364, yerr=3.226953
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_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             600.805376E+06
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  219456
 MPI messages size (bytes):
  total size                        97.042514E+09
  min size                           0.000000E+00
  max size                           3.276800E+06
  average size                     442.195750E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768              101892               3336634368
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304              116112              93705670464
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         8156                     20.
 MP_Alltoall          8655                  64935.
 MP_ISend            36532                 168375.
 MP_IRecv            36532                 168349.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3672                  62658.
 MP_Allreduce        10224                    344.
 MP_Sync               104
 MP_Alltoall          1582                3682667.
 MP_ISendRecv        10710                  94533.
 MP_Wait             16690
 MP_comm_split          50
 MP_ISend             5200                 225425.
 MP_IRecv             5200                 225425.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.015    0.030   27.920   27.921
 qs_mol_dyn_low                       1  2.0    0.003    0.003   27.742   27.750
 qs_forces                           11  3.9    0.027    0.047   27.663   27.664
 qs_energies                         11  4.9    0.002    0.002   25.958   25.986
 scf_env_do_scf                      11  5.9    0.000    0.001   21.032   21.032
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   18.538   18.539
 velocity_verlet                     10  3.0    0.011    0.028   14.216   14.219
 dbcsr_multiply_generic            2286 12.5    0.090    0.092   12.494   12.599
 qs_scf_new_mos                     108  7.5    0.001    0.001   11.012   11.041
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   11.011   11.040
 ot_scf_mini                        108  9.5    0.002    0.002   10.332   10.371
 multiply_cannon                   2286 13.5    0.231    0.237    9.914   10.331
 multiply_cannon_loop              2286 14.5    0.331    0.342    8.989    9.241
 multiply_cannon_multrec           9144 15.5    1.580    1.844    5.981    6.187
 ot_mini                            108 10.5    0.001    0.001    5.838    5.882
 rebuild_ks_matrix                  119  8.3    0.000    0.000    5.783    5.806
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.014    5.783    5.806
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.166    5.187
 qs_ot_get_derivative               108 11.5    0.001    0.001    4.543    4.581
 dbcsr_mm_accdrv_process          12550 15.8    3.195    3.630    4.299    4.359
 sum_up_and_integrate               119 10.3    0.038    0.041    3.543    3.548
 integrate_v_rspace                 119 11.3    0.003    0.003    3.505    3.511
 init_scf_run                        11  5.9    0.000    0.001    3.492    3.492
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.491    3.492
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.203    3.363
 calculate_rho_elec                 119  8.7    0.059    0.061    3.202    3.362
 qs_ot_get_p                        119 10.4    0.001    0.001    2.726    2.780
 mp_waitall_1                    121218 16.5    1.868    2.475    1.868    2.475
 init_scf_loop                       11  6.9    0.000    0.000    2.474    2.474
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.324    2.347
 jit_kernel_multiply                 10 15.7    1.066    2.006    1.066    2.006
 calculate_dm_sparse                119  9.5    0.000    0.000    1.934    1.974
 make_m2s                          4572 13.5    0.034    0.036    1.778    1.953
 grid_integrate_task_list           119 12.3    1.849    1.935    1.849    1.935
 make_images                       4572 14.5    0.270    0.304    1.690    1.863
 qs_ot_p2m_diag                      50 11.0    0.022    0.023    1.800    1.802
 rs_pw_transfer                     974 11.9    0.008    0.008    1.685    1.801
 prepare_preconditioner              11  7.9    0.000    0.000    1.746    1.750
 make_preconditioner                 11  8.9    0.000    0.000    1.746    1.750
 density_rs2pw                      119  9.7    0.004    0.004    1.595    1.718
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    1.662    1.680
 pw_transfer                       1439 11.6    0.064    0.066    1.671    1.680
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.626    1.661
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.606    1.607
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.580    1.588
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.570    1.571
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.399    1.407
 grid_collocate_task_list           119  9.7    1.272    1.388    1.272    1.388
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.348    1.375
 potential_pw2rs                    119 12.3    0.010    0.011    1.340    1.345
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.337    1.338
 cp_fm_redistribute_end              50 14.0    0.665    1.316    0.666    1.317
 cp_fm_diag_elpa_base                50 14.0    0.605    1.243    0.650    1.302
 fft_wrap_pw1pw2_140                487 13.2    0.082    0.086    1.277    1.287
 ot_diis_step                       108 11.5    0.012    0.013    1.282    1.282
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    1.228    1.255
 fft3d_ps                          1201 14.6    0.536    0.548    1.247    1.254
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    1.160    1.175
 apply_single                       119 13.6    0.000    0.000    1.160    1.175
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.142    1.162
 wfi_extrapolate                     11  7.9    0.001    0.001    1.098    1.098
 hybrid_alltoall_any               4725 16.4    0.062    0.175    0.790    1.055
 make_images_data                  4572 15.5    0.038    0.042    0.843    1.043
 mp_alltoall_d11v                  2130 13.8    0.793    0.923    0.793    0.923
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.871    0.920
 acc_transpose_blocks              9144 15.5    0.039    0.040    0.897    0.908
 cp_fm_cholesky_invert               11 10.9    0.891    0.894    0.891    0.894
 multiply_cannon_sync_h2d          9144 15.5    0.713    0.793    0.713    0.793
 multiply_cannon_metrocomm3        9144 15.5    0.018    0.019    0.455    0.756
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.739    0.741
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.721    0.728
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    0.683    0.728
 mp_allgather_i34                  2286 14.5    0.258    0.700    0.258    0.700
 acc_transpose_blocks_kernels      9144 16.5    0.117    0.120    0.654    0.659
 multiply_cannon_metrocomm1        9144 15.5    0.022    0.023    0.335    0.629
 mp_alltoall_z22v                  1201 16.6    0.585    0.617    0.585    0.617
 qs_create_task_list                 11  7.9    0.000    0.001    0.543    0.568
 generate_qs_task_list               11  8.9    0.190    0.212    0.543    0.567
 mp_waitany                        5200 13.7    0.465    0.564    0.465    0.564
 dbcsr_complete_redistribute        329 12.2    0.163    0.171    0.526    0.561
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="108", plot="h2o_64_md", label="(8n/2r/6t)", y=27.921000, yerr=0.000000
PlotPoint: name="109", plot="h2o_64_md_mem", label="(8n/2r/6t)", y=568.818182, yerr=4.302603
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_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             740.478976E+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_ISendRecv         4998                 189067.
 MP_Wait              8898
 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    0.016    0.034   41.140   41.140
 qs_mol_dyn_low                       1  2.0    0.003    0.003   40.944   40.952
 qs_forces                           11  3.9    0.002    0.002   40.881   40.882
 qs_energies                         11  4.9    0.001    0.001   38.936   38.939
 scf_env_do_scf                      11  5.9    0.001    0.001   32.992   32.993
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.006   25.058   25.059
 velocity_verlet                     10  3.0    0.002    0.002   23.030   23.035
 dbcsr_multiply_generic            2286 12.5    0.099    0.100   18.118   18.363
 qs_scf_new_mos                     108  7.5    0.001    0.001   16.176   16.273
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   16.175   16.272
 multiply_cannon                   2286 13.5    0.304    0.318   14.220   15.275
 ot_scf_mini                        108  9.5    0.002    0.002   15.098   15.201
 multiply_cannon_loop              2286 14.5    0.344    0.349   12.973   14.065
 ot_mini                            108 10.5    0.001    0.001    9.172    9.295
 multiply_cannon_multrec           9144 15.5    3.786    5.217    9.129    9.236
 init_scf_loop                       11  6.9    0.000    0.000    7.907    7.910
 qs_ot_get_derivative               108 11.5    0.001    0.001    7.140    7.245
 prepare_preconditioner              11  7.9    0.000    0.000    6.993    7.007
 make_preconditioner                 11  8.9    0.000    0.000    6.993    7.007
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.816    6.966
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.013    6.816    6.965
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.533    6.882
 dbcsr_mm_accdrv_process          12550 15.8    4.049    5.445    5.219    6.592
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.169    6.304
 cp_fm_upper_to_full                 72 14.2    3.185    4.585    3.185    4.585
 init_scf_run                        11  5.9    0.000    0.001    3.927    3.927
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.927    3.927
 mp_waitall_1                     97218 16.6    2.627    3.727    2.627    3.727
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.698    3.703
 calculate_rho_elec                 119  8.7    0.118    0.121    3.697    3.702
 sum_up_and_integrate               119 10.3    0.064    0.065    3.674    3.680
 integrate_v_rspace                 119 11.3    0.004    0.005    3.610    3.615
 qs_ot_get_p                        119 10.4    0.001    0.001    3.203    3.351
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.435    2.924
 dbcsr_complete_redistribute        329 12.2    0.290    0.296    2.011    2.857
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    1.690    2.515
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.508    2.510
 calculate_dm_sparse                119  9.5    0.000    0.000    2.476    2.494
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.247    2.484
 apply_single                       119 13.6    0.000    0.000    2.247    2.484
 make_m2s                          4572 13.5    0.038    0.038    2.249    2.416
 make_images                       4572 14.5    0.355    0.389    2.130    2.297
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.455    2.275
 mp_alltoall_i22                    627 13.8    1.430    2.268    1.430    2.268
 multiply_cannon_metrocomm3        9144 15.5    0.019    0.020    1.281    2.223
 pw_transfer                       1439 11.6    0.066    0.067    2.053    2.056
 grid_integrate_task_list           119 12.3    2.000    2.005    2.000    2.005
 ot_diis_step                       108 11.5    0.014    0.014    2.005    2.005
 fft_wrap_pw1pw2                   1201 12.6    0.009    0.009    1.957    1.960
 qs_ot_p2m_diag                      50 11.0    0.044    0.044    1.919    1.921
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.892    1.893
 mp_sum_l                          7207 12.9    1.112    1.821    1.112    1.821
 density_rs2pw                      119  9.7    0.003    0.003    1.804    1.820
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    1.747    1.748
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.670    1.724
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.642    1.688
 jit_kernel_multiply                  8 15.6    1.143    1.672    1.143    1.672
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.648    1.648
 fft_wrap_pw1pw2_140                487 13.2    0.087    0.089    1.631    1.634
 fft3d_ps                          1201 14.6    0.565    0.575    1.590    1.594
 cp_fm_cholesky_invert               11 10.9    1.568    1.571    1.568    1.571
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.544    1.550
 grid_collocate_task_list           119  9.7    1.440    1.465    1.440    1.465
 rs_pw_transfer                     974 11.9    0.009    0.009    1.414    1.447
 wfi_extrapolate                     11  7.9    0.001    0.001    1.358    1.358
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.354    1.355
 cp_fm_diag_elpa_base                50 14.0    1.208    1.260    1.351    1.353
 hybrid_alltoall_any               4725 16.4    0.087    0.148    1.122    1.351
 make_images_data                  4572 15.5    0.042    0.046    1.051    1.255
 potential_pw2rs                    119 12.3    0.014    0.015    1.230    1.232
 mp_alltoall_d11v                  2130 13.8    1.159    1.174    1.159    1.174
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.136    1.157
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    1.087    1.103
 multiply_cannon_sync_h2d          9144 15.5    1.039    1.041    1.039    1.041
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.989    1.036
 qs_create_task_list                 11  7.9    0.000    0.001    0.944    0.953
 generate_qs_task_list               11  8.9    0.374    0.396    0.943    0.953
 acc_transpose_blocks              9144 15.5    0.039    0.039    0.915    0.925
 mp_alltoall_z22v                  1201 16.6    0.889    0.912    0.889    0.912
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.860    0.875
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="110", plot="h2o_64_md", label="(8n/1r/12t)", y=41.140000, yerr=0.000000
PlotPoint: name="111", plot="h2o_64_md_mem", label="(8n/1r/12t)", y=696.090909, yerr=15.388629
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/09/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                    198.287135E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               8410880       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     117.0
 marketing flops                    15.646302E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank             502.226944E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 8483040
 MPI messages size (bytes):
  total size                         1.160510E+12
  min size                           0.000000E+00
  max size                           1.161504E+06
  average size                     136.803609E+03
 MPI breakdown and total messages size (bytes):
             size <=      128             1836752                        0
       128 < size <=     8192             1040592               8524529664
      8192 < size <=    32768             1486976              24362614784
     32768 < size <=   131072             2491776             216971345920
    131072 < size <=  4194304             1626944             910632720448
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3521                  65372.
 MP_Allreduce         9840                    486.
 MP_Sync               100
 MP_Alltoall          1938                1030913.
 MP_ISendRecv        41800                   9096.
 MP_Wait             58168
 MP_comm_split          48
 MP_ISend            14300                  82312.
 MP_IRecv            14300                  82312.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.016    0.030   82.745   82.746
 qs_mol_dyn_low                       1  2.0    0.003    0.003   82.432   82.442
 qs_forces                           11  3.9    0.002    0.003   82.363   82.365
 qs_energies                         11  4.9    0.030    0.031   79.554   79.574
 scf_env_do_scf                      11  5.9    0.000    0.001   70.519   70.522
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.006   65.029   65.030
 dbcsr_multiply_generic            2055 12.4    0.101    0.104   52.487   52.722
 qs_scf_new_mos                      99  7.5    0.000    0.001   48.070   48.209
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   48.069   48.209
 ot_scf_mini                         99  9.5    0.002    0.002   45.666   45.758
 multiply_cannon                   2055 13.4    0.181    0.187   42.945   43.844
 multiply_cannon_loop              2055 14.4    1.555    1.589   41.983   42.913
 velocity_verlet                     10  3.0    0.001    0.002   41.770   41.771
 ot_mini                             99 10.5    0.001    0.001   27.707   27.805
 qs_ot_get_derivative                99 11.5    0.001    0.001   20.869   20.971
 multiply_cannon_multrec          49320 15.4   12.138   12.893   17.356   18.076
 rebuild_ks_matrix                  110  8.3    0.000    0.001   14.485   14.663
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.013   14.484   14.662
 mp_waitall_1                    241148 16.1   11.971   13.059   11.971   13.059
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.753   12.915
 multiply_cannon_sync_h2d         49320 15.4    9.965   10.489    9.965   10.489
 qs_ot_get_p                        110 10.4    0.001    0.001    9.357    9.530
 multiply_cannon_metrocomm3       49320 15.4    0.079    0.082    7.105    8.389
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    7.215    7.740
 apply_single                       110 13.6    0.000    0.001    7.215    7.740
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    7.147    7.714
 sum_up_and_integrate               110 10.3    0.037    0.044    7.044    7.060
 integrate_v_rspace                 110 11.3    0.003    0.003    7.007    7.028
 init_scf_run                        11  5.9    0.000    0.001    6.973    6.973
 scf_env_initial_rho_setup           11  6.9    0.002    0.002    6.973    6.973
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    6.795    6.859
 ot_diis_step                        99 11.5    0.005    0.005    6.558    6.558
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.169    6.309
 calculate_rho_elec                 110  8.6    0.020    0.024    6.169    6.308
 qs_ot_p2m_diag                      48 11.0    0.012    0.018    6.094    6.133
 mp_sum_l                          6514 12.8    5.164    6.059    5.164    6.059
 dbcsr_mm_accdrv_process          87628 16.1    2.066    2.165    5.097    5.485
 init_scf_loop                       11  6.9    0.000    0.000    5.464    5.464
 cp_dbcsr_syevd                      48 12.0    0.002    0.003    5.079    5.080
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    4.615    4.616
 cp_fm_redistribute_end              48 14.0    4.022    4.593    4.027    4.594
 cp_fm_diag_elpa_base                48 14.0    0.561    4.495    0.564    4.529
 make_m2s                          4110 13.4    0.061    0.066    3.921    4.010
 wfi_extrapolate                     11  7.9    0.001    0.001    3.995    3.995
 rs_pw_transfer                     902 11.9    0.013    0.015    3.789    3.979
 make_images                       4110 14.4    0.179    0.194    3.826    3.919
 calculate_dm_sparse                110  9.5    0.000    0.001    3.792    3.880
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    3.774    3.779
 multiply_cannon_metrocomm1       49320 15.4    0.061    0.065    2.740    3.773
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    3.442    3.517
 density_rs2pw                      110  9.6    0.004    0.004    3.226    3.449
 grid_integrate_task_list           110 12.3    3.247    3.401    3.247    3.401
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    3.337    3.394
 prepare_preconditioner              11  7.9    0.000    0.000    3.307    3.326
 make_preconditioner                 11  8.9    0.000    0.000    3.307    3.326
 make_full_inverse_cholesky          11  9.9    0.000    0.000    3.095    3.137
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.889    2.898
 jit_kernel_multiply                 13 15.9    2.749    2.865    2.749    2.865
 pw_transfer                       1331 11.6    0.054    0.065    2.796    2.850
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    2.709    2.765
 potential_pw2rs                    110 12.3    0.007    0.007    2.612    2.635
 mp_alltoall_d11v                  2046 13.8    2.170    2.541    2.170    2.541
 fft_wrap_pw1pw2_140                451 13.1    0.170    0.189    2.296    2.354
 fft3d_ps                          1111 14.6    0.744    0.827    2.244    2.292
 acc_transpose_blocks             49320 15.4    0.217    0.227    2.195    2.252
 grid_collocate_task_list           110  9.6    2.085    2.217    2.085    2.217
 mp_waitany                       14300 13.8    1.861    2.061    1.861    2.061
 make_images_data                  4110 15.4    0.044    0.046    1.801    1.949
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.871    1.890
 mp_sum_d                          3883 11.9    1.432    1.882    1.432    1.882
 hybrid_alltoall_any               4261 16.3    0.083    0.477    1.583    1.876
 cp_fm_cholesky_invert               11 10.9    1.770    1.774    1.770    1.774
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.670    1.704
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="200", plot="h2o_128_md", label="(8n/12r/1t)", y=82.746000, yerr=0.000000
PlotPoint: name="201", plot="h2o_128_md_mem", label="(8n/12r/1t)", y=476.181818, yerr=2.757409
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_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             588.488704E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1972800
 MPI messages size (bytes):
  total size                         1.077520E+12
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     546.188250E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               14916                        0
       128 < size <=     8192              222984               1826684928
      8192 < size <=    32768              520356              13399818240
     32768 < size <=   131072              372336              35386294272
    131072 < size <=  4194304              787758             788321309808
   4194304 < size <= 16777216               54450             238588003280
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3521                  65587.
 MP_Allreduce         9839                    562.
 MP_Sync               100
 MP_Alltoall          1717                2984769.
 MP_ISendRecv        20680                  26400.
 MP_Wait             32692
 MP_comm_split          48
 MP_ISend            10164                 155761.
 MP_IRecv            10164                 155761.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.041    0.099   69.787   69.789
 qs_mol_dyn_low                       1  2.0    0.003    0.005   69.408   69.431
 qs_forces                           11  3.9    0.003    0.004   69.227   69.228
 qs_energies                         11  4.9    0.036    0.072   65.921   65.925
 scf_env_do_scf                      11  5.9    0.001    0.001   56.216   56.220
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.007   48.514   48.515
 dbcsr_multiply_generic            2055 12.4    0.112    0.117   38.351   38.529
 velocity_verlet                     10  3.0    0.002    0.002   36.154   36.158
 multiply_cannon                   2055 13.4    0.223    0.247   31.653   32.918
 qs_scf_new_mos                      99  7.5    0.001    0.001   32.649   32.775
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   32.648   32.774
 ot_scf_mini                         99  9.5    0.003    0.004   30.995   31.120
 multiply_cannon_loop              2055 14.4    0.932    0.950   30.333   31.078
 ot_mini                             99 10.5    0.001    0.001   18.208   18.336
 multiply_cannon_multrec          24660 15.4    7.663    9.291   14.315   15.868
 rebuild_ks_matrix                  110  8.3    0.000    0.001   13.621   13.709
 qs_ks_build_kohn_sham_matrix       110  9.3    0.014    0.020   13.620   13.709
 qs_ot_get_derivative                99 11.5    0.001    0.001   12.416   12.540
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.013   12.096
 mp_waitall_1                    186928 16.3    7.965   10.529    7.965   10.529
 multiply_cannon_sync_h2d         24660 15.4    7.043    8.321    7.043    8.321
 multiply_cannon_metrocomm3       24660 15.4    0.070    0.073    5.240    8.210
 init_scf_loop                       11  6.9    0.000    0.002    7.666    7.667
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    6.513    7.204
 apply_single                       110 13.6    0.000    0.001    6.513    7.203
 dbcsr_mm_accdrv_process          52282 16.1    5.081    5.975    6.493    6.948
 init_scf_run                        11  5.9    0.000    0.001    6.895    6.896
 scf_env_initial_rho_setup           11  6.9    0.002    0.003    6.895    6.896
 sum_up_and_integrate               110 10.3    0.053    0.061    6.533    6.545
 integrate_v_rspace                 110 11.3    0.002    0.003    6.479    6.494
 qs_ot_get_p                        110 10.4    0.001    0.001    6.148    6.300
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.799    5.811
 calculate_rho_elec                 110  8.6    0.039    0.047    5.798    5.811
 ot_diis_step                        99 11.5    0.010    0.012    5.744    5.744
 prepare_preconditioner              11  7.9    0.000    0.000    5.621    5.638
 make_preconditioner                 11  8.9    0.000    0.001    5.621    5.638
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    4.695    5.394
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.189    5.350
 make_m2s                          4110 13.4    0.057    0.059    4.225    4.717
 make_images                       4110 14.4    0.407    0.450    4.121    4.609
 qs_ot_p2m_diag                      48 11.0    0.029    0.044    4.239    4.258
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.817    3.817
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    3.771    3.773
 wfi_extrapolate                     11  7.9    0.002    0.006    3.508    3.509
 pw_transfer                       1331 11.6    0.066    0.071    3.325    3.465
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.001    3.365    3.404
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.009    3.218    3.361
 grid_integrate_task_list           110 12.3    3.156    3.319    3.156    3.319
 calculate_first_density_matrix       1  7.0    0.000    0.001    3.300    3.302
 rs_pw_transfer                     902 11.9    0.013    0.014    3.120    3.301
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.284    3.287
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.213    3.276
 cp_fm_redistribute_end              48 14.0    2.450    3.259    2.452    3.260
 calculate_dm_sparse                110  9.5    0.001    0.001    3.201    3.239
 cp_fm_diag_elpa_base                48 14.0    0.772    3.134    0.804    3.223
 density_rs2pw                      110  9.6    0.004    0.004    3.067    3.213
 make_images_data                  4110 15.4    0.047    0.052    2.354    2.851
 hybrid_alltoall_any               4261 16.3    0.103    0.445    2.057    2.842
 fft_wrap_pw1pw2_140                451 13.1    0.201    0.219    2.680    2.823
 fft3d_ps                          1111 14.6    1.074    1.268    2.574    2.702
 cp_fm_cholesky_invert               11 10.9    2.603    2.609    2.603    2.609
 mp_sum_l                          6514 12.8    1.853    2.500    1.853    2.500
 potential_pw2rs                    110 12.3    0.009    0.009    2.390    2.404
 jit_kernel_multiply                 11 16.5    1.068    2.368    1.068    2.368
 grid_collocate_task_list           110  9.6    2.121    2.269    2.121    2.269
 qs_energies_init_hamiltonians       11  5.9    0.015    0.043    2.155    2.158
 mp_alltoall_d11v                  2046 13.8    1.816    2.059    1.816    2.059
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.944    1.963
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.780    1.791
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.773    1.791
 mp_allgather_i34                  2055 14.4    0.647    1.672    0.647    1.672
 multiply_cannon_metrocomm4       22605 15.4    0.074    0.079    0.782    1.670
 mp_waitany                       10164 13.8    1.345    1.558    1.345    1.558
 acc_transpose_blocks             24660 15.4    0.108    0.112    1.537    1.557
 mp_irecv_dv                      57340 16.2    0.658    1.552    0.658    1.552
 dbcsr_complete_redistribute        325 12.2    0.267    0.357    1.232    1.499
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.001    1.374    1.484
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="202", plot="h2o_128_md", label="(8n/6r/2t)", y=69.789000, yerr=0.000000
PlotPoint: name="203", plot="h2o_128_md_mem", label="(8n/6r/2t)", y=554.818182, yerr=8.850456
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_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             657.661952E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                  854880
 MPI messages size (bytes):
  total size                       708.322787E+09
  min size                           0.000000E+00
  max size                           6.553600E+06
  average size                     828.564000E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768              222984               7302414336
     32768 < size <=   131072              153888              10085203968
    131072 < size <=  4194304              389376             200257044480
   4194304 < size <= 16777216               82208             490679162176
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3521                  65578.
 MP_Allreduce         9838                    559.
 MP_Sync               100
 MP_Alltoall          1496                4511006.
 MP_ISendRecv        13640                  27424.
 MP_Wait             32318
 MP_comm_split          48
 MP_ISend            17072                 115022.
 MP_IRecv            17072                 115022.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.043    0.160   61.426   61.427
 qs_mol_dyn_low                       1  2.0    0.003    0.006   60.871   60.880
 qs_forces                           11  3.9    0.004    0.021   60.715   60.717
 qs_energies                         11  4.9    0.002    0.004   57.561   57.565
 scf_env_do_scf                      11  5.9    0.001    0.001   48.837   48.838
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.006   40.060   40.061
 velocity_verlet                     10  3.0    0.001    0.002   32.677   32.682
 dbcsr_multiply_generic            2055 12.4    0.106    0.109   29.394   29.658
 qs_scf_new_mos                      99  7.5    0.001    0.001   25.559   25.652
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   25.559   25.652
 ot_scf_mini                         99  9.5    0.003    0.003   24.329   24.428
 multiply_cannon                   2055 13.4    0.213    0.223   23.019   24.126
 multiply_cannon_loop              2055 14.4    0.620    0.635   21.789   22.948
 ot_mini                             99 10.5    0.001    0.001   13.811   13.916
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.191   12.327
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.018   12.191   12.326
 multiply_cannon_multrec          16440 15.4    3.911    5.051   10.262   11.339
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.759   10.882
 mp_waitall_1                    146766 16.3    7.306   10.589    7.306   10.589
 qs_ot_get_derivative                99 11.5    0.001    0.001    9.323    9.425
 init_scf_loop                       11  6.9    0.001    0.007    8.741    8.745
 multiply_cannon_metrocomm3       16440 15.4    0.042    0.044    4.364    7.533
 prepare_preconditioner              11  7.9    0.000    0.000    6.947    6.971
 make_preconditioner                 11  8.9    0.000    0.001    6.947    6.971
 make_full_inverse_cholesky          11  9.9    0.000    0.000    6.247    6.592
 dbcsr_mm_accdrv_process          34862 16.1    4.960    5.873    6.206    6.529
 sum_up_and_integrate               110 10.3    0.061    0.063    6.482    6.498
 integrate_v_rspace                 110 11.3    0.003    0.004    6.421    6.437
 init_scf_run                        11  5.9    0.000    0.001    6.295    6.295
 scf_env_initial_rho_setup           11  6.9    0.001    0.005    6.295    6.295
 qs_ot_get_p                        110 10.4    0.001    0.001    5.735    5.884
 qs_rho_update_rho_low              110  7.6    0.001    0.002    5.550    5.558
 calculate_rho_elec                 110  8.6    0.058    0.058    5.549    5.558
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.984    5.411
 apply_single                       110 13.6    0.000    0.000    4.984    5.411
 make_m2s                          4110 13.4    0.050    0.052    4.146    4.531
 ot_diis_step                        99 11.5    0.011    0.012    4.455    4.455
 make_images                       4110 14.4    0.396    0.516    4.033    4.417
 multiply_cannon_sync_h2d         16440 15.4    3.664    4.338    3.664    4.338
 qs_ot_p2m_diag                      48 11.0    0.042    0.044    4.041    4.045
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.204    3.828
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.694    3.695
 grid_integrate_task_list           110 12.3    3.189    3.376    3.189    3.376
 calculate_first_density_matrix       1  7.0    0.000    0.001    3.237    3.239
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.002    3.183    3.185
 pw_transfer                       1331 11.6    0.065    0.071    3.164    3.173
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.139    3.140
 cp_fm_redistribute_end              48 14.0    1.952    3.112    1.955    3.113
 density_rs2pw                      110  9.6    0.004    0.005    2.835    3.082
 cp_fm_diag_elpa_base                48 14.0    1.092    2.968    1.154    3.081
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.058    3.069
 rs_pw_transfer                     902 11.9    0.011    0.012    2.836    3.040
 wfi_extrapolate                     11  7.9    0.001    0.003    2.965    2.966
 calculate_dm_sparse                110  9.5    0.001    0.001    2.901    2.938
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.841    2.891
 make_images_data                  4110 15.4    0.044    0.048    2.353    2.822
 cp_fm_cholesky_invert               11 10.9    2.799    2.806    2.799    2.806
 hybrid_alltoall_any               4261 16.3    0.105    0.378    2.072    2.715
 fft_wrap_pw1pw2_140                451 13.1    0.209    0.214    2.583    2.597
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.376    2.432
 fft3d_ps                          1111 14.6    1.062    1.079    2.372    2.380
 multiply_cannon_metrocomm4       14385 15.4    0.045    0.049    0.887    2.369
 mp_alltoall_d11v                  2046 13.8    1.781    2.338    1.781    2.338
 potential_pw2rs                    110 12.3    0.011    0.011    2.320    2.328
 mp_sum_l                          6514 12.8    1.671    2.315    1.671    2.315
 grid_collocate_task_list           110  9.6    2.177    2.299    2.177    2.299
 mp_irecv_dv                      48980 15.7    0.816    2.244    0.816    2.244
 qs_energies_init_hamiltonians       11  5.9    0.001    0.003    1.992    1.994
 dbcsr_complete_redistribute        325 12.2    0.324    0.355    1.528    1.991
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.858    1.869
 cp_fm_upper_to_full                 70 13.6    1.377    1.850    1.377    1.850
 jit_kernel_multiply                  8 16.5    0.864    1.794    0.864    1.794
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.640    1.658
 cp_fm_cholesky_decompose            22 10.9    1.622    1.640    1.622    1.640
 mp_allgather_i34                  2055 14.4    0.549    1.533    0.549    1.533
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    1.026    1.474
 acc_transpose_blocks             16440 15.4    0.073    0.075    1.435    1.455
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.001    1.360    1.440
 rs_gather_matrices                 110 12.3    0.138    0.151    0.861    1.420
 mp_waitany                       17072 13.8    1.183    1.414    1.183    1.414
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.294    1.302
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="204", plot="h2o_128_md", label="(8n/4r/3t)", y=61.427000, yerr=0.000000
PlotPoint: name="205", plot="h2o_128_md_mem", label="(8n/4r/3t)", y=622.818182, yerr=8.778260
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_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             727.056384E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                  937080
 MPI messages size (bytes):
  total size                       523.723932E+09
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     558.889250E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6996                        0
       128 < size <=     8192                 264                  2162688
      8192 < size <=    32768              304932               8165326848
     32768 < size <=   131072              110640               6338641920
    131072 < size <=  4194304              489498             400769458320
   4194304 < size <= 16777216               24750             108449092400
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3521                  65576.
 MP_Allreduce         9838                    600.
 MP_Sync               100
 MP_Alltoall          1496                5863162.
 MP_ISendRecv        10120                  43184.
 MP_Wait             25102
 MP_comm_split          48
 MP_ISend            13376                 163145.
 MP_IRecv            13376                 163145.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.059    0.161   66.723   66.724
 qs_mol_dyn_low                       1  2.0    0.003    0.005   66.261   66.299
 qs_forces                           11  3.9    0.002    0.004   66.182   66.183
 qs_energies                         11  4.9    0.004    0.015   62.809   62.813
 scf_env_do_scf                      11  5.9    0.001    0.001   53.373   53.376
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.007   41.486   41.487
 velocity_verlet                     10  3.0    0.002    0.002   37.077   37.079
 dbcsr_multiply_generic            2055 12.4    0.114    0.119   30.972   31.202
 qs_scf_new_mos                      99  7.5    0.001    0.001   26.975   27.086
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   26.975   27.085
 ot_scf_mini                         99  9.5    0.003    0.004   25.344   25.451
 multiply_cannon                   2055 13.4    0.245    0.265   23.604   24.808
 multiply_cannon_loop              2055 14.4    0.883    0.910   22.142   22.896
 multiply_cannon_multrec          24660 15.4    4.197    6.785   13.431   14.696
 ot_mini                             99 10.5    0.001    0.001   14.475   14.600
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.016   12.115
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.017   12.016   12.114
 init_scf_loop                       11  6.9    0.001    0.003   11.843   11.848
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.644   10.732
 qs_ot_get_derivative                99 11.5    0.001    0.002   10.303   10.409
 dbcsr_mm_accdrv_process          52304 16.0    7.025    8.759    9.086   10.359
 prepare_preconditioner              11  7.9    0.000    0.000   10.066   10.082
 make_preconditioner                 11  8.9    0.000    0.001   10.066   10.082
 make_full_inverse_cholesky          11  9.9    0.000    0.000    8.269    9.727
 mp_waitall_1                    126806 16.4    4.869    6.811    4.869    6.811
 init_scf_run                        11  5.9    0.000    0.001    6.626    6.627
 scf_env_initial_rho_setup           11  6.9    0.003    0.009    6.625    6.627
 sum_up_and_integrate               110 10.3    0.068    0.071    6.367    6.383
 integrate_v_rspace                 110 11.3    0.003    0.003    6.299    6.315
 make_m2s                          4110 13.4    0.060    0.063    5.605    5.940
 qs_ot_get_p                        110 10.4    0.001    0.001    5.795    5.933
 make_images                       4110 14.4    0.581    0.709    5.464    5.793
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.673    5.680
 calculate_rho_elec                 110  8.6    0.077    0.081    5.672    5.680
 cp_fm_upper_to_full                 70 13.8    3.296    4.686    3.296    4.686
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.133    4.417
 apply_single                       110 13.6    0.000    0.000    4.133    4.417
 ot_diis_step                        99 11.5    0.011    0.013    4.134    4.135
 qs_ot_p2m_diag                      48 11.0    0.055    0.064    3.977    3.992
 dbcsr_complete_redistribute        325 12.2    0.442    0.515    2.782    3.902
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.558    3.721
 calculate_dm_sparse                110  9.5    0.001    0.001    3.561    3.590
 calculate_first_density_matrix       1  7.0    0.000    0.001    3.503    3.507
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.485    3.485
 grid_integrate_task_list           110 12.3    3.275    3.466    3.275    3.466
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    2.246    3.358
 multiply_cannon_sync_h2d         24660 15.4    3.180    3.342    3.180    3.342
 multiply_cannon_metrocomm3       24660 15.4    0.035    0.036    1.548    3.323
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.002    3.292    3.294
 pw_transfer                       1331 11.6    0.065    0.071    3.261    3.288
 hybrid_alltoall_any               4261 16.3    0.121    0.463    2.415    3.280
 make_images_data                  4110 15.4    0.046    0.049    2.876    3.238
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.155    3.184
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.038    3.099
 wfi_extrapolate                     11  7.9    0.001    0.007    3.030    3.032
 jit_kernel_multiply                 12 15.8    1.733    2.956    1.733    2.956
 density_rs2pw                      110  9.6    0.004    0.004    2.801    2.934
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    2.920    2.922
 cp_fm_redistribute_end              48 14.0    1.456    2.891    1.458    2.892
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.787    2.883
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.832    2.874
 cp_fm_diag_elpa_base                48 14.0    1.348    2.750    1.431    2.864
 mp_alltoall_i22                    605 13.7    1.663    2.830    1.663    2.830
 cp_fm_cholesky_invert               11 10.9    2.817    2.827    2.817    2.827
 fft_wrap_pw1pw2_140                451 13.1    0.202    0.216    2.672    2.707
 rs_pw_transfer                     902 11.9    0.011    0.011    2.514    2.674
 fft3d_ps                          1111 14.6    1.067    1.103    2.455    2.470
 grid_collocate_task_list           110  9.6    2.222    2.351    2.222    2.351
 qs_energies_init_hamiltonians       11  5.9    0.002    0.003    2.301    2.302
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    2.167    2.181
 potential_pw2rs                    110 12.3    0.012    0.013    2.133    2.143
 mp_alltoall_d11v                  2046 13.8    1.908    2.131    1.908    2.131
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.733    1.766
 cp_fm_cholesky_decompose            22 10.9    1.688    1.734    1.688    1.734
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.001    1.605    1.708
 acc_transpose_blocks             24660 15.4    0.104    0.106    1.674    1.691
 mp_sum_l                          6514 12.8    1.163    1.673    1.163    1.673
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.619    1.631
 mp_allgather_i34                  2055 14.4    0.560    1.528    0.560    1.528
 multiply_cannon_metrocomm4       20550 15.4    0.057    0.059    0.842    1.502
 mp_irecv_dv                      62702 16.1    0.744    1.425    0.744    1.425
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="206", plot="h2o_128_md", label="(8n/3r/4t)", y=66.724000, yerr=0.000000
PlotPoint: name="207", plot="h2o_128_md_mem", label="(8n/3r/4t)", y=686.363636, yerr=8.875633
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_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             863.166464E+06
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  197280
 MPI messages size (bytes):
  total size                       339.125567E+09
  min size                           0.000000E+00
  max size                          13.107200E+06
  average size                       1.719006E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 132                  4325376
     32768 < size <=   131072               88656              11620319232
    131072 < size <=  4194304               89424             117209825280
   4194304 < size <= 16777216               17616             210291069504
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         7346                     33.
 MP_Alltoall          8043                 263767.
 MP_ISend            32836                 654203.
 MP_IRecv            32836                 654587.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3521                  65574.
 MP_Allreduce         9838                    640.
 MP_Sync               100
 MP_Alltoall          1496                8504061.
 MP_ISendRecv         6600                  54848.
 MP_Wait             17226
 MP_comm_split          48
 MP_ISend             9240                 278857.
 MP_IRecv             9240                 278857.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.016    0.032   55.020   55.021
 qs_mol_dyn_low                       1  2.0    0.003    0.003   54.755   54.764
 qs_forces                           11  3.9    0.002    0.002   54.688   54.689
 qs_energies                         11  4.9    0.002    0.002   51.071   51.077
 scf_env_do_scf                      11  5.9    0.001    0.001   42.785   42.785
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.007   34.861   34.862
 velocity_verlet                     10  3.0    0.003    0.004   30.956   30.959
 dbcsr_multiply_generic            2055 12.4    0.103    0.105   22.829   22.955
 qs_scf_new_mos                      99  7.5    0.001    0.001   20.760   20.805
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   20.760   20.804
 ot_scf_mini                         99  9.5    0.002    0.002   19.526   19.548
 multiply_cannon                   2055 13.4    0.249    0.275   17.233   18.674
 multiply_cannon_loop              2055 14.4    0.323    0.338   15.862   16.211
 rebuild_ks_matrix                  110  8.3    0.000    0.000   11.455   11.503
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.014   11.455   11.503
 ot_mini                             99 10.5    0.001    0.001   10.402   10.422
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.199   10.240
 multiply_cannon_multrec           8220 15.4    3.191    4.469    7.448    8.425
 init_scf_loop                       11  6.9    0.000    0.000    7.870    7.871
 mp_waitall_1                    106626 16.5    6.125    7.771    6.125    7.771
 qs_ot_get_derivative                99 11.5    0.001    0.001    6.591    6.616
 prepare_preconditioner              11  7.9    0.000    0.000    6.249    6.252
 make_preconditioner                 11  8.9    0.000    0.000    6.249    6.252
 sum_up_and_integrate               110 10.3    0.080    0.082    6.169    6.181
 integrate_v_rspace                 110 11.3    0.003    0.003    6.089    6.101
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.823    5.902
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.590    5.605
 calculate_rho_elec                 110  8.6    0.115    0.115    5.589    5.604
 qs_ot_get_p                        110 10.4    0.001    0.001    5.195    5.211
 init_scf_run                        11  5.9    0.000    0.001    5.115    5.115
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.114    5.115
 dbcsr_mm_accdrv_process          17442 15.9    2.802    3.988    4.126    5.053
 make_m2s                          4110 13.4    0.039    0.040    4.272    4.536
 make_images                       4110 14.4    0.640    0.694    4.144    4.405
 multiply_cannon_metrocomm3        8220 15.4    0.017    0.017    2.920    4.212
 qs_ot_p2m_diag                      48 11.0    0.081    0.084    3.817    3.820
 ot_diis_step                        99 11.5    0.012    0.012    3.783    3.784
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    3.686    3.701
 apply_single                       110 13.6    0.000    0.000    3.686    3.701
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.513    3.513
 grid_integrate_task_list           110 12.3    3.372    3.471    3.372    3.471
 pw_transfer                       1331 11.6    0.065    0.071    3.198    3.220
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.009    3.091    3.115
 cp_fm_cholesky_invert               11 10.9    3.075    3.079    3.075    3.079
 multiply_cannon_sync_h2d          8220 15.4    2.916    3.026    2.916    3.026
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    2.968    2.969
 cp_fm_redistribute_end              48 14.0    0.751    2.937    0.756    2.938
 cp_fm_diag_elpa_base                48 14.0    1.997    2.742    2.173    2.903
 make_images_data                  4110 15.4    0.038    0.043    2.430    2.839
 density_rs2pw                      110  9.6    0.004    0.004    2.657    2.778
 hybrid_alltoall_any               4261 16.3    0.201    0.873    2.339    2.764
 wfi_extrapolate                     11  7.9    0.001    0.001    2.722    2.722
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    2.673    2.674
 fft_wrap_pw1pw2_140                451 13.1    0.213    0.216    2.635    2.668
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.596    2.597
 calculate_dm_sparse                110  9.5    0.001    0.001    2.457    2.500
 grid_collocate_task_list           110  9.6    2.332    2.465    2.332    2.465
 rs_pw_transfer                     902 11.9    0.010    0.010    2.242    2.385
 fft3d_ps                          1111 14.6    1.113    1.156    2.346    2.365
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.305    2.305
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.190    2.213
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    2.018    2.030
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.774    1.988
 potential_pw2rs                    110 12.3    0.015    0.016    1.931    1.937
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    1.817    1.829
 mp_alltoall_d11v                  2046 13.8    1.626    1.784    1.626    1.784
 cp_fm_cholesky_decompose            22 10.9    1.702    1.709    1.702    1.709
 mp_allgather_i34                  2055 14.4    0.553    1.647    0.553    1.647
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    1.516    1.636
 jit_kernel_multiply                  9 15.6    1.021    1.628    1.021    1.628
 dbcsr_complete_redistribute        325 12.2    0.595    0.621    1.525    1.615
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.591    1.597
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.439    1.450
 qs_create_task_list                 11  7.9    0.001    0.001    1.243    1.343
 generate_qs_task_list               11  8.9    0.378    0.445    1.242    1.342
 mp_waitany                        9240 13.8    1.084    1.222    1.084    1.222
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.186    1.205
 multiply_cannon_metrocomm1        8220 15.4    0.021    0.022    0.783    1.135
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="208", plot="h2o_128_md", label="(8n/2r/6t)", y=55.021000, yerr=0.000000
PlotPoint: name="209", plot="h2o_128_md_mem", label="(8n/2r/6t)", y=811.454545, yerr=10.823910
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_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               1.365783E+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_ISendRecv         4620                 360267.
 MP_Wait              7524
 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    0.019    0.037   86.616   86.616
 qs_mol_dyn_low                       1  2.0    0.003    0.003   86.247   86.256
 qs_forces                           11  3.9    0.002    0.002   86.179   86.180
 qs_energies                         11  4.9    0.002    0.002   82.147   82.148
 scf_env_do_scf                      11  5.9    0.001    0.001   71.649   71.650
 velocity_verlet                     10  3.0    0.002    0.002   54.809   54.815
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.007   43.307   43.308
 dbcsr_multiply_generic            2055 12.4    0.118    0.120   29.630   29.722
 init_scf_loop                       11  6.9    0.000    0.000   28.267   28.270
 qs_scf_new_mos                      99  7.5    0.001    0.001   26.802   26.862
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   26.802   26.862
 prepare_preconditioner              11  7.9    0.000    0.000   26.323   26.329
 make_preconditioner                 11  8.9    0.000    0.000   26.323   26.329
 make_full_inverse_cholesky          11  9.9    0.000    0.000   20.670   25.794
 ot_scf_mini                         99  9.5    0.002    0.002   25.025   25.072
 multiply_cannon                   2055 13.4    0.346    0.375   22.533   23.284
 multiply_cannon_loop              2055 14.4    0.341    0.343   20.744   21.110
 cp_fm_upper_to_full                 70 14.2   12.673   18.037   12.673   18.037
 ot_mini                             99 10.5    0.001    0.001   13.990   14.038
 rebuild_ks_matrix                  110  8.3    0.001    0.001   13.211   13.256
 qs_ks_build_kohn_sham_matrix       110  9.3    0.014    0.014   13.210   13.255
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.016   12.058
 dbcsr_complete_redistribute        325 12.2    1.022    1.042    7.273   10.409
 multiply_cannon_multrec           8220 15.4    4.367    4.563    9.866   10.232
 qs_ot_get_derivative                99 11.5    0.001    0.001    9.420    9.468
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    6.220    9.350
 mp_waitall_1                     87304 16.6    8.281    9.162    8.281    9.162
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    5.637    8.734
 mp_alltoall_i22                    605 13.7    5.267    8.434    5.267    8.434
 sum_up_and_integrate               110 10.3    0.151    0.152    6.663    6.677
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.510    6.544
 calculate_rho_elec                 110  8.6    0.227    0.227    6.509    6.543
 integrate_v_rspace                 110 11.3    0.004    0.004    6.512    6.527
 init_scf_run                        11  5.9    0.000    0.001    6.259    6.259
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    6.259    6.259
 dbcsr_mm_accdrv_process          11614 15.7    3.328    3.780    5.357    5.890
 qs_ot_get_p                        110 10.4    0.001    0.001    5.810    5.868
 make_m2s                          4110 13.4    0.043    0.043    5.288    5.783
 make_images                       4110 14.4    0.891    0.940    5.100    5.596
 multiply_cannon_metrocomm3        8220 15.4    0.018    0.018    5.171    5.587
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.725    5.500
 apply_single                       110 13.6    0.000    0.000    4.725    5.500
 cp_fm_cholesky_invert               11 10.9    5.347    5.352    5.347    5.352
 ot_diis_step                        99 11.5    0.015    0.016    4.543    4.544
 qs_ot_p2m_diag                      48 11.0    0.151    0.156    4.229    4.237
 multiply_cannon_sync_h2d          8220 15.4    3.947    3.953    3.947    3.953
 pw_transfer                       1331 11.6    0.073    0.073    3.838    3.854
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.785    3.785
 fft_wrap_pw1pw2                   1111 12.6    0.009    0.009    3.721    3.736
 grid_integrate_task_list           110 12.3    3.664    3.712    3.664    3.712
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.170    3.663
 calculate_dm_sparse                110  9.5    0.001    0.001    3.619    3.645
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    3.636    3.638
 hybrid_alltoall_any               4261 16.3    0.261    0.569    2.935    3.618
 make_images_data                  4110 15.4    0.042    0.044    2.868    3.523
 fft_wrap_pw1pw2_140                451 13.1    0.218    0.220    3.221    3.240
 wfi_extrapolate                     11  7.9    0.001    0.001    3.217    3.217
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.183    3.184
 cp_fm_diag_elpa_base                48 14.0    2.647    2.840    3.181    3.181
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    3.069    3.071
 density_rs2pw                      110  9.6    0.004    0.004    3.002    3.022
 fft3d_ps                          1111 14.6    1.283    1.318    2.926    2.943
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.927    2.928
 grid_collocate_task_list           110  9.6    2.627    2.648    2.627    2.648
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.549    2.571
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.424    2.451
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    2.171    2.223
 jit_kernel_multiply                 10 15.3    1.828    2.221    1.828    2.221
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    2.107    2.193
 rs_pw_transfer                     902 11.9    0.011    0.011    2.131    2.188
 mp_alltoall_d11v                  2046 13.8    2.099    2.161    2.099    2.161
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    2.137    2.153
 cp_fm_cholesky_decompose            22 10.9    2.098    2.122    2.098    2.122
 potential_pw2rs                    110 12.3    0.021    0.022    2.085    2.090
 qs_create_task_list                 11  7.9    0.001    0.001    1.905    1.951
 generate_qs_task_list               11  8.9    0.740    0.795    1.904    1.950
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.821    1.869
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.802    1.807
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="210", plot="h2o_128_md", label="(8n/1r/12t)", y=86.616000, yerr=0.000000
PlotPoint: name="211", plot="h2o_128_md_mem", label="(8n/1r/12t)", y=1219.636364, yerr=65.216106
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/15/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420242647040       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528903135232       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514766E+12       0.0%      0.0%    100.0%
 flops max/rank                      1.094965E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755941440       0.0%      0.0%    100.0%
 number of processed stacks              11950464       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     565.3
 marketing flops                   144.580175E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank             626.143232E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                10348896
 MPI messages size (bytes):
  total size                         4.491514E+12
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     434.009000E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               65736                        0
       128 < size <=     8192                1232                 10092544
      8192 < size <=    32768             3576680              95640223744
     32768 < size <=   131072             1294784              74079797248
    131072 < size <=  4194304             5148576            3175955383376
   4194304 < size <= 16777216              261888            1145794321408
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4085                  56760.
 MP_Allreduce        11253                    785.
 MP_Sync               170
 MP_Alltoall          2226                2194719.
 MP_ISendRecv        48640                  18752.
 MP_Wait             66796
 MP_comm_split          83
 MP_ISend            16020                 108028.
 MP_IRecv            16020                 108028.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.021    0.057  204.018  204.020
 qs_mol_dyn_low                       1  2.0    0.007    0.035  203.530  203.543
 qs_forces                           11  3.9    0.003    0.004  203.393  203.394
 qs_energies                         11  4.9    0.003    0.007  197.859  197.879
 scf_env_do_scf                      11  5.9    0.001    0.001  181.261  181.265
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.009  160.597  160.599
 dbcsr_multiply_generic            2507 12.6    0.172    0.176  124.690  125.509
 velocity_verlet                     10  3.0    0.011    0.020  122.494  122.495
 qs_scf_new_mos                     117  7.6    0.001    0.001  121.709  122.017
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001  121.708  122.016
 ot_scf_mini                        117  9.6    0.003    0.004  115.097  115.393
 multiply_cannon                   2507 13.6    0.240    0.248  100.817  102.980
 multiply_cannon_loop              2507 14.6    2.104    2.175   98.534  100.441
 ot_mini                            117 10.6    0.001    0.002   66.178   66.468
 multiply_cannon_multrec          60168 15.6   33.109   35.654   41.417   43.398
 qs_ot_get_derivative               117 11.6    0.001    0.002   41.204   41.503
 rebuild_ks_matrix                  128  8.3    0.001    0.001   33.315   33.673
 qs_ks_build_kohn_sham_matrix       128  9.3    0.016    0.021   33.314   33.673
 mp_waitall_1                    291448 16.2   29.007   32.440   29.007   32.440
 qs_ks_update_qs_env                128  7.6    0.001    0.001   29.984   30.289
 multiply_cannon_sync_h2d         60168 15.6   27.249   29.601   27.249   29.601
 qs_ot_get_p                        128 10.4    0.001    0.001   26.886   27.214
 apply_preconditioner_dbcsr         128 12.6    0.000    0.001   24.385   25.152
 apply_single                       128 13.6    0.001    0.001   24.385   25.152
 ot_diis_step                       117 11.6    0.008    0.011   24.610   24.612
 init_scf_loop                       11  6.9    0.000    0.000   20.584   20.586
 qs_ot_p2m_diag                      83 11.4    0.077    0.092   20.142   20.258
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002   19.281   19.510
 multiply_cannon_metrocomm3       60168 15.6    0.114    0.120   15.614   18.161
 cp_dbcsr_syevd                      83 12.4    0.004    0.005   17.564   17.564
 prepare_preconditioner              11  7.9    0.000    0.000   15.997   16.038
 make_preconditioner                 11  8.9    0.000    0.000   15.997   16.038
 make_full_inverse_cholesky          11  9.9    0.000    0.000   15.227   15.421
 cp_fm_diag_elpa                     83 13.4    0.000    0.001   14.720   14.725
 cp_fm_redistribute_end              83 14.4   11.625   14.646   11.637   14.650
 make_m2s                          5014 13.6    0.102    0.113   14.171   14.543
 cp_fm_diag_elpa_base                83 14.4    2.967   14.340    2.999   14.449
 make_images                       5014 14.6    0.410    0.430   13.998   14.383
 sum_up_and_integrate               128 10.3    0.091    0.110   13.976   13.995
 integrate_v_rspace                 128 11.3    0.004    0.004   13.884   13.903
 qs_rho_update_rho_low              128  7.7    0.001    0.001   12.798   12.928
 calculate_rho_elec                 128  8.7    0.045    0.063   12.797   12.928
 init_scf_run                        11  5.9    0.000    0.001   12.301   12.302
 scf_env_initial_rho_setup           11  6.9    0.001    0.003   12.301   12.301
 mp_sum_l                          7870 13.0    8.464    9.804    8.464    9.804
 cp_fm_cholesky_invert               11 10.9    9.075    9.082    9.075    9.082
 wfi_extrapolate                     11  7.9    0.001    0.003    9.048    9.049
 calculate_dm_sparse                128  9.5    0.001    0.001    8.417    8.522
 dbcsr_mm_accdrv_process         124484 16.2    3.284    3.450    7.875    8.460
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    7.921    8.087
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    7.926    8.027
 make_images_data                  5014 15.6    0.072    0.079    6.991    8.007
 multiply_cannon_metrocomm1       60168 15.6    0.088    0.095    6.163    8.003
 grid_integrate_task_list           128 12.3    7.066    7.575    7.066    7.575
 hybrid_alltoall_any               5200 16.5    0.293    2.261    6.102    7.492
 density_rs2pw                      128  9.7    0.006    0.007    6.568    7.202
 pw_transfer                       1547 11.6    0.075    0.103    6.865    7.144
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.014    6.661    6.912
 cp_dbcsr_sm_fm_multiply             37  9.5    0.003    0.004    6.668    6.676
 rs_pw_transfer                    1046 11.9    0.018    0.020    5.849    6.454
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.828    5.943
 fft_wrap_pw1pw2_140                523 13.2    0.446    0.509    5.708    5.895
 fft3d_ps                          1291 14.7    2.092    2.577    5.451    5.647
 mp_alltoall_d11v                  2415 14.1    4.306    5.425    4.306    5.425
 grid_collocate_task_list           128  9.7    4.720    5.074    4.720    5.074
 cp_fm_cholesky_decompose            22 10.9    4.719    4.732    4.719    4.732
 mp_sum_d                          4464 12.1    3.699    4.582    3.699    4.582
 potential_pw2rs                    128 12.3    0.010    0.011    4.488    4.514
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="400", plot="h2o_256_md", label="(8n/12r/1t)", y=204.020000, yerr=0.000000
PlotPoint: name="401", plot="h2o_256_md_mem", label="(8n/12r/1t)", y=593.000000, yerr=6.915069
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/16/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420241154048       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528896499712       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514757E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.183246E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755939872       0.0%      0.0%    100.0%
 number of processed stacks               5975232       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1130.7
 marketing flops                   144.580175E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank             826.298368E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 2406720
 MPI messages size (bytes):
  total size                         4.100942E+12
  min size                           0.000000E+00
  max size                          17.653760E+06
  average size                       1.703955E+06
 MPI breakdown and total messages size (bytes):
             size <=      128               14916                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768               70860               2317615104
     32768 < size <=   131072              722992              55511613440
    131072 < size <=  4194304             1375664            1398181724160
   4194304 < size <= 16777216              154704            1463834560144
  16777216 < size                           67584            1181116006400
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4075                  57341.
 MP_Allreduce        11227                    947.
 MP_Sync               170
 MP_Alltoall          1969                6435542.
 MP_ISendRecv        24064                  47072.
 MP_Wait             37948
 MP_comm_split          83
 MP_ISend            11748                 212467.
 MP_IRecv            11748                 212467.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.017    0.032  191.161  191.162
 qs_mol_dyn_low                       1  2.0    0.004    0.009  190.810  190.824
 qs_forces                           11  3.9    0.003    0.005  190.714  190.715
 qs_energies                         11  4.9    0.002    0.003  183.991  184.004
 scf_env_do_scf                      11  5.9    0.001    0.001  167.369  167.380
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.008  134.053  134.057
 velocity_verlet                     10  3.0    0.002    0.010  119.620  119.622
 dbcsr_multiply_generic            2507 12.6    0.182    0.187   98.400   99.702
 qs_scf_new_mos                     117  7.6    0.001    0.001   95.283   95.728
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   95.282   95.727
 ot_scf_mini                        117  9.6    0.004    0.005   90.470   90.975
 multiply_cannon                   2507 13.6    0.478    0.533   78.317   82.931
 multiply_cannon_loop              2507 14.6    1.256    1.295   75.051   77.594
 ot_mini                            117 10.6    0.001    0.001   50.110   50.617
 mp_waitall_1                    226760 16.4   25.220   38.255   25.220   38.255
 multiply_cannon_multrec          30084 15.6   22.148   26.296   32.040   36.652
 rebuild_ks_matrix                  128  8.3    0.001    0.001   32.897   33.438
 qs_ks_build_kohn_sham_matrix       128  9.3    0.018    0.024   32.896   33.438
 init_scf_loop                       11  6.9    0.000    0.000   33.223   33.225
 qs_ks_update_qs_env                128  7.6    0.001    0.001   29.663   30.149
 prepare_preconditioner              11  7.9    0.000    0.000   28.835   28.909
 make_preconditioner                 11  8.9    0.000    0.000   28.835   28.909
 multiply_cannon_metrocomm3       30084 15.6    0.095    0.102   15.915   28.818
 qs_ot_get_derivative               117 11.6    0.001    0.002   28.199   28.692
 make_full_inverse_cholesky          11  9.9    0.000    0.000   27.534   28.114
 apply_preconditioner_dbcsr         128 12.6    0.000    0.000   21.999   23.136
 apply_single                       128 13.6    0.001    0.001   21.999   23.136
 qs_ot_get_p                        128 10.4    0.001    0.001   22.082   22.856
 ot_diis_step                       117 11.6    0.015    0.018   21.746   21.750
 multiply_cannon_sync_h2d         30084 15.6   19.406   21.734   19.406   21.734
 qs_ot_p2m_diag                      83 11.4    0.188    0.217   17.273   17.307
 cp_fm_cholesky_invert               11 10.9   16.875   16.887   16.875   16.887
 cp_dbcsr_syevd                      83 12.4    0.005    0.006   16.131   16.133
 make_m2s                          5014 13.6    0.090    0.098   14.455   16.000
 make_images                       5014 14.6    1.170    1.358   14.256   15.803
 sum_up_and_integrate               128 10.3    0.115    0.134   14.378   14.412
 integrate_v_rspace                 128 11.3    0.004    0.004   14.263   14.303
 cp_fm_diag_elpa                     83 13.4    0.000    0.001   13.018   13.025
 qs_rho_update_rho_low              128  7.7    0.001    0.001   12.957   12.991
 calculate_rho_elec                 128  8.7    0.088    0.105   12.956   12.991
 cp_fm_redistribute_end              83 14.4    7.609   12.952    7.622   12.954
 cp_fm_diag_elpa_base                83 14.4    5.095   12.394    5.315   12.853
 init_scf_run                        11  5.9    0.000    0.001   11.877   11.879
 scf_env_initial_rho_setup           11  6.9    0.001    0.002   11.877   11.878
 qs_ot_get_derivative_diag           77 12.4    0.002    0.003   10.870   11.231
 make_images_data                  5014 15.6    0.067    0.073    8.798   10.585
 multiply_cannon_metrocomm4       27577 15.6    0.097    0.112    3.750   10.410
 dbcsr_mm_accdrv_process          62242 16.2    4.577    5.519    9.349   10.109
 mp_irecv_dv                      69486 16.3    3.558   10.030    3.558   10.030
 hybrid_alltoall_any               5200 16.5    0.344    1.522    7.533   10.026
 wfi_extrapolate                     11  7.9    0.001    0.003    8.351    8.352
 pw_transfer                       1547 11.6    0.085    0.102    7.785    7.839
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.011    7.560    7.610
 grid_integrate_task_list           128 12.3    7.155    7.592    7.155    7.592
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    6.734    7.567
 density_rs2pw                      128  9.7    0.006    0.006    6.731    7.185
 cp_fm_cholesky_decompose            22 10.9    7.040    7.123    7.040    7.123
 calculate_dm_sparse                128  9.5    0.001    0.001    6.697    6.825
 fft_wrap_pw1pw2_140                523 13.2    0.469    0.519    6.596    6.654
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.003    6.364    6.374
 rs_pw_transfer                    1046 11.9    0.015    0.017    5.605    6.053
 fft3d_ps                          1291 14.7    2.773    2.919    5.930    5.987
 mp_sum_l                          7870 13.0    3.838    5.694    3.838    5.694
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.498    5.666
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    5.304    5.386
 grid_collocate_task_list           128  9.7    4.909    5.287    4.909    5.287
 mp_allgather_i34                  2507 14.6    1.836    5.109    1.836    5.109
 potential_pw2rs                    128 12.3    0.015    0.018    4.854    4.876
 mp_alltoall_d11v                  2415 14.1    4.162    4.589    4.162    4.589
 dbcsr_complete_redistribute        395 12.7    0.772    0.850    3.144    4.012
 mp_sum_d                          4459 12.1    2.590    3.851    2.590    3.851
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="402", plot="h2o_256_md", label="(8n/6r/2t)", y=191.162000, yerr=0.000000
PlotPoint: name="403", plot="h2o_256_md_mem", label="(8n/6r/2t)", y=788.272727, yerr=1.212879
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/17/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420239992832       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528891191296       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514751E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.928533E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755938624       0.0%      0.0%    100.0%
 number of processed stacks               3984192       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1695.7
 marketing flops                   144.579337E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank             930.947072E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                 1042912
 MPI messages size (bytes):
  total size                         2.716210E+12
  min size                           0.000000E+00
  max size                          26.214400E+06
  average size                       2.604448E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 264                  8650752
     32768 < size <=   131072              281856              36943429632
    131072 < size <=  4194304              660064             996105256960
   4194304 < size <= 16777216               65632             931530938576
  16777216 < size                           28672             751619276800
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4075                  57335.
 MP_Allreduce        11226                    986.
 MP_Sync               170
 MP_Alltoall          1712                9388896.
 MP_ISendRecv        15872                  75008.
 MP_Wait             29756
 MP_comm_split          83
 MP_ISend            11748                 275205.
 MP_IRecv            11748                 275205.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.032    0.115  177.111  177.112
 qs_mol_dyn_low                       1  2.0    0.003    0.005  176.534  176.547
 qs_forces                           11  3.9    0.003    0.004  176.437  176.440
 qs_energies                         11  4.9    0.002    0.004  169.948  169.958
 scf_env_do_scf                      11  5.9    0.001    0.002  154.088  154.092
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.009  118.632  118.634
 velocity_verlet                     10  3.0    0.001    0.002  112.977  112.980
 dbcsr_multiply_generic            2507 12.6    0.179    0.184   81.969   82.953
 qs_scf_new_mos                     117  7.6    0.001    0.001   82.268   82.601
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   82.267   82.600
 ot_scf_mini                        117  9.6    0.004    0.005   78.134   78.484
 multiply_cannon                   2507 13.6    0.500    0.520   62.120   66.315
 multiply_cannon_loop              2507 14.6    0.860    0.885   58.986   61.250
 ot_mini                            117 10.6    0.001    0.001   42.572   42.934
 init_scf_loop                       11  6.9    0.000    0.002   35.351   35.360
 mp_waitall_1                    178456 16.5   25.345   35.146   25.345   35.146
 prepare_preconditioner              11  7.9    0.000    0.000   31.353   31.398
 make_preconditioner                 11  8.9    0.000    0.001   31.353   31.398
 make_full_inverse_cholesky          11  9.9    0.000    0.000   29.050   30.429
 rebuild_ks_matrix                  128  8.3    0.001    0.001   29.909   30.331
 qs_ks_build_kohn_sham_matrix       128  9.3    0.017    0.023   29.908   30.330
 qs_ks_update_qs_env                128  7.6    0.001    0.001   27.023   27.409
 multiply_cannon_multrec          20056 15.6   13.582   16.379   22.485   25.250
 multiply_cannon_metrocomm3       20056 15.6    0.058    0.062   15.067   24.440
 qs_ot_get_derivative               117 11.6    0.002    0.002   22.857   23.207
 qs_ot_get_p                        128 10.4    0.001    0.001   20.966   21.405
 apply_preconditioner_dbcsr         128 12.6    0.000    0.000   19.825   20.859
 apply_single                       128 13.6    0.001    0.001   19.825   20.858
 ot_diis_step                       117 11.6    0.018    0.020   19.603   19.603
 qs_ot_p2m_diag                      83 11.4    0.266    0.273   16.617   16.631
 multiply_cannon_sync_h2d         20056 15.6   14.244   16.033   14.244   16.033
 make_m2s                          5014 13.6    0.082    0.087   14.791   15.695
 cp_dbcsr_syevd                      83 12.4    0.005    0.005   15.594   15.596
 make_images                       5014 14.6    1.185    1.292   14.564   15.465
 cp_fm_cholesky_invert               11 10.9   14.816   14.825   14.816   14.825
 sum_up_and_integrate               128 10.3    0.132    0.144   14.102   14.130
 integrate_v_rspace                 128 11.3    0.004    0.004   13.970   13.994
 qs_rho_update_rho_low              128  7.7    0.001    0.001   12.927   12.966
 calculate_rho_elec                 128  8.7    0.132    0.147   12.926   12.966
 cp_fm_diag_elpa                     83 13.4    0.000    0.001   12.511   12.512
 cp_fm_redistribute_end              83 14.4    4.704   12.426    4.720   12.428
 cp_fm_diag_elpa_base                83 14.4    7.257   11.810    7.682   12.331
 init_scf_run                        11  5.9    0.000    0.001   10.873   10.873
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   10.873   10.873
 make_images_data                  5014 15.6    0.062    0.069    9.086   10.318
 hybrid_alltoall_any               5200 16.5    0.433    1.970    7.912    9.547
 qs_ot_get_derivative_diag           77 12.4    0.002    0.003    8.973    9.227
 multiply_cannon_metrocomm4       17549 15.6    0.063    0.072    3.444    9.120
 mp_irecv_dv                      50230 16.2    3.321    8.868    3.321    8.868
 dbcsr_mm_accdrv_process          41502 16.2    4.467    5.483    8.362    8.464
 grid_integrate_task_list           128 12.3    7.256    7.737    7.256    7.737
 pw_transfer                       1547 11.6    0.085    0.103    7.537    7.645
 cp_fm_cholesky_decompose            22 10.9    7.565    7.588    7.565    7.588
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.011    7.314    7.427
 wfi_extrapolate                     11  7.9    0.001    0.003    7.381    7.382
 cp_fm_upper_to_full                105 14.5    5.655    7.358    5.655    7.358
 density_rs2pw                      128  9.7    0.006    0.006    6.425    7.072
 fft_wrap_pw1pw2_140                523 13.2    0.478    0.531    6.404    6.523
 dbcsr_complete_redistribute        395 12.7    1.173    1.203    4.468    6.174
 calculate_dm_sparse                128  9.5    0.001    0.001    5.942    6.046
 rs_pw_transfer                    1046 11.9    0.014    0.015    5.152    5.838
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.727    5.731
 fft3d_ps                          1291 14.7    2.694    2.897    5.579    5.643
 grid_collocate_task_list           128  9.7    5.071    5.445    5.071    5.445
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    4.567    5.246
 copy_fm_to_dbcsr                   209 11.7    0.002    0.002    3.266    4.965
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.824    4.946
 mp_alltoall_d11v                  2415 14.1    4.135    4.918    4.135    4.918
 mp_sum_l                          7870 13.0    3.317    4.810    3.317    4.810
 potential_pw2rs                    128 12.3    0.020    0.023    4.515    4.529
 mp_allgather_i34                  2507 14.6    1.651    4.462    1.651    4.462
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    4.038    4.077
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    2.283    3.944
 mp_alltoall_i22                    716 14.1    1.887    3.732    1.887    3.732
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    3.708    3.709
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="404", plot="h2o_256_md", label="(8n/4r/3t)", y=177.112000, yerr=0.000000
PlotPoint: name="405", plot="h2o_256_md_mem", label="(8n/4r/3t)", y=883.272727, yerr=9.381712
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_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               1.139261E+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             4073                  57357.
 MP_Allreduce        11221                   1069.
 MP_Sync               168
 MP_Alltoall          1700               12496361.
 MP_ISendRecv        11684                  75008.
 MP_Wait             28114
 MP_comm_split          82
 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    0.064    0.082  187.878  187.880
 qs_mol_dyn_low                       1  2.0    0.006    0.026  187.322  187.335
 qs_forces                           11  3.9    0.009    0.023  186.447  186.454
 qs_energies                         11  4.9    0.004    0.021  179.410  179.424
 scf_env_do_scf                      11  5.9    0.001    0.001  161.976  161.985
 velocity_verlet                     10  3.0    0.003    0.009  123.751  123.787
 scf_env_do_scf_inner_loop          116  6.6    0.003    0.009  115.042  115.044
 dbcsr_multiply_generic            2485 12.5    0.186    0.189   79.722   80.495
 qs_scf_new_mos                     116  7.6    0.001    0.001   80.024   80.327
 qs_scf_loop_do_ot                  116  8.6    0.001    0.001   80.023   80.326
 ot_scf_mini                        116  9.6    0.003    0.004   75.571   75.859
 multiply_cannon                   2485 13.5    0.553    0.594   55.100   58.687
 multiply_cannon_loop              2485 14.5    1.166    1.197   51.385   53.221
 init_scf_loop                       11  6.9    0.000    0.000   46.807   46.808
 prepare_preconditioner              11  7.9    0.000    0.000   42.739   42.762
 make_preconditioner                 11  8.9    0.000    0.000   42.739   42.762
 ot_mini                            116 10.6    0.001    0.001   42.079   42.360
 make_full_inverse_cholesky          11  9.9    0.000    0.000   36.124   41.223
 multiply_cannon_multrec          29820 15.5   14.027   19.315   26.089   30.853
 rebuild_ks_matrix                  127  8.3    0.001    0.001   28.689   29.026
 qs_ks_build_kohn_sham_matrix       127  9.3    0.017    0.021   28.688   29.025
 mp_waitall_1                    152434 16.5   17.658   27.057   17.658   27.057
 qs_ks_update_qs_env                127  7.6    0.001    0.001   25.903   26.210
 qs_ot_get_derivative               116 11.6    0.002    0.002   22.590   22.881
 make_m2s                          4970 13.5    0.096    0.100   20.296   21.434
 make_images                       4970 14.5    1.953    2.286   19.996   21.136
 qs_ot_get_p                        127 10.4    0.001    0.001   19.770   20.067
 apply_preconditioner_dbcsr         127 12.6    0.000    0.001   18.864   19.450
 apply_single                       127 13.6    0.001    0.001   18.863   19.450
 ot_diis_step                       116 11.6    0.018    0.021   19.374   19.376
 cp_fm_upper_to_full                104 14.7   11.238   16.671   11.238   16.671
 cp_fm_cholesky_invert               11 10.9   16.229   16.238   16.229   16.238
 qs_ot_p2m_diag                      82 11.4    0.339    0.386   15.680   15.731
 multiply_cannon_metrocomm3       29820 15.5    0.046    0.048    6.444   14.867
 cp_dbcsr_syevd                      82 12.4    0.005    0.005   14.409   14.410
 sum_up_and_integrate               127 10.3    0.140    0.154   13.861   13.892
 integrate_v_rspace                 127 11.3    0.004    0.004   13.721   13.757
 dbcsr_complete_redistribute        393 12.7    1.513    1.629    9.239   13.031
 qs_rho_update_rho_low              127  7.7    0.001    0.001   12.911   12.942
 calculate_rho_elec                 127  8.7    0.174    0.189   12.910   12.941
 multiply_cannon_sync_h2d         29820 15.5   11.663   12.666   11.663   12.666
 make_images_data                  4970 15.5    0.064    0.068   11.016   12.600
 dbcsr_mm_accdrv_process          61748 16.2    7.399    8.229   11.634   12.176
 hybrid_alltoall_any               5155 16.4    0.524    2.195    9.826   11.710
 copy_fm_to_dbcsr                   208 11.6    0.001    0.002    7.839   11.627
 init_scf_run                        11  5.9    0.000    0.001   11.441   11.442
 scf_env_initial_rho_setup           11  6.9    0.001    0.002   11.440   11.441
 cp_fm_diag_elpa                     82 13.4    0.000    0.001   11.364   11.367
 cp_fm_redistribute_end              82 14.4    1.961   11.287    1.977   11.291
 cp_fm_diag_elpa_base                82 14.4    8.697   10.666    9.281   11.145
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    6.593   10.299
 mp_alltoall_i22                    712 14.1    5.691    9.596    5.691    9.596
 qs_ot_get_derivative_diag           76 12.4    0.002    0.002    9.234    9.439
 grid_integrate_task_list           127 12.3    7.434    7.848    7.434    7.848
 pw_transfer                       1535 11.6    0.084    0.096    7.647    7.724
 cp_fm_cholesky_decompose            22 10.9    7.575    7.681    7.575    7.681
 wfi_extrapolate                     11  7.9    0.001    0.004    7.582    7.584
 fft_wrap_pw1pw2                   1281 12.7    0.010    0.011    7.424    7.506
 density_rs2pw                      127  9.7    0.005    0.006    6.122    6.663
 fft_wrap_pw1pw2_140                519 13.2    0.478    0.490    6.561    6.661
 multiply_cannon_metrocomm4       24850 15.5    0.074    0.083    2.763    6.597
 mp_irecv_dv                      75445 16.2    2.620    6.331    2.620    6.331
 calculate_dm_sparse                127  9.5    0.001    0.001    6.206    6.277
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.155    6.199
 fft3d_ps                          1281 14.7    2.774    2.840    5.668    5.732
 mp_alltoall_d11v                  2401 14.1    4.891    5.510    4.891    5.510
 grid_collocate_task_list           127  9.7    5.160    5.490    5.160    5.490
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.096    5.175
 rs_pw_transfer                    1038 11.9    0.013    0.015    4.538    5.011
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    4.491    4.574
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    4.400    4.405
 qs_ot_get_orbitals                 116 10.6    0.001    0.001    4.164    4.212
 potential_pw2rs                    127 12.3    0.023    0.023    4.182    4.201
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="406", plot="h2o_256_md", label="(8n/3r/4t)", y=187.880000, yerr=0.000000
PlotPoint: name="407", plot="h2o_256_md_mem", label="(8n/3r/4t)", y=1072.818182, yerr=19.784375
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/19/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1430454546432       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1973537472512       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1986255912960       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1992006770688       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2753958699008       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4454954827776       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5444944789504       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5492290093056       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6712799002624       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11613065416704       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15239182565376       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15239182565376       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19911132921856       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        94.243766E+12       0.0%      0.0%    100.0%
 flops max/rank                      5.910792E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6806547424       0.0%      0.0%    100.0%
 number of processed stacks               1978768       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    3439.8
 marketing flops                   145.661668E+12
 -------------------------------------------------------------------------------
 # multiplications                           2534
 max memory usage/rank               1.510232E+09
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  243264
 MPI messages size (bytes):
  total size                         1.342058E+12
  min size                           0.000000E+00
  max size                          52.428800E+06
  average size                       5.516879E+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              115488              60548972544
   4194304 < size <= 16777216              105840             554906419200
  16777216 < size                           20352             726592540656
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         9025                     51.
 MP_Alltoall          9734                 793691.
 MP_ISend            40500                2096702.
 MP_IRecv            40500                2095807.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4041                  57658.
 MP_Allreduce        11099                   1171.
 MP_Sync                88
 MP_Alltoall          1724               18848005.
 MP_ISendRecv         7740                 122880.
 MP_Wait             20114
 MP_ISend            10760                 423501.
 MP_IRecv            10760                 423501.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.017    0.031  172.718  172.719
 qs_mol_dyn_low                       1  2.0    0.003    0.003  171.968  171.980
 qs_forces                           11  3.9    0.003    0.003  170.026  170.035
 qs_energies                         11  4.9    0.002    0.002  162.732  162.742
 scf_env_do_scf                      11  5.9    0.001    0.001  145.514  145.526
 velocity_verlet                     10  3.0    0.010    0.012  113.627  113.746
 scf_env_do_scf_inner_loop          118  6.6    0.003    0.008  110.061  110.062
 dbcsr_multiply_generic            2534 12.6    0.180    0.186   74.442   74.850
 qs_scf_new_mos                     118  7.6    0.001    0.001   74.351   74.424
 qs_scf_loop_do_ot                  118  8.6    0.001    0.001   74.351   74.424
 ot_scf_mini                        118  9.6    0.004    0.004   69.912   69.984
 multiply_cannon                   2534 13.6    0.590    0.627   54.835   59.075
 multiply_cannon_loop              2534 14.6    0.454    0.463   50.204   51.035
 ot_mini                            118 10.6    0.001    0.001   39.672   39.739
 init_scf_loop                       11  6.9    0.000    0.000   35.301   35.302
 mp_waitall_1                    130986 16.6   25.753   33.452   25.753   33.452
 prepare_preconditioner              11  7.9    0.000    0.000   31.485   31.517
 make_preconditioner                 11  8.9    0.000    0.000   31.485   31.516
 make_full_inverse_cholesky          11  9.9    0.000    0.000   29.328   29.625
 rebuild_ks_matrix                  129  8.3    0.001    0.001   28.599   28.700
 qs_ks_build_kohn_sham_matrix       129  9.3    0.018    0.018   28.599   28.700
 qs_ks_update_qs_env                129  7.6    0.001    0.001   26.139   26.231
 multiply_cannon_multrec          10136 15.6   10.515   14.710   17.960   22.190
 ot_diis_step                       118 11.6    0.020    0.021   19.911   19.912
 qs_ot_get_derivative               118 11.6    0.002    0.002   19.692   19.763
 apply_preconditioner_dbcsr         129 12.6    0.000    0.000   19.461   19.750
 apply_single                       129 13.6    0.001    0.001   19.460   19.750
 multiply_cannon_metrocomm3       10136 15.6    0.022    0.023   12.371   19.573
 make_m2s                          5068 13.6    0.068    0.072   16.009   18.001
 cp_fm_cholesky_invert               11 10.9   17.872   17.878   17.872   17.878
 make_images                       5068 14.6    2.344    2.928   15.703   17.696
 qs_ot_get_p                        129 10.4    0.001    0.001   17.355   17.455
 sum_up_and_integrate               129 10.3    0.182    0.192   14.107   14.155
 integrate_v_rspace                 129 11.3    0.004    0.004   13.924   13.982
 qs_ot_p2m_diag                      84 11.4    0.502    0.508   13.652   13.666
 qs_rho_update_rho_low              129  7.7    0.001    0.001   13.129   13.154
 calculate_rho_elec                 129  8.7    0.260    0.271   13.129   13.154
 multiply_cannon_sync_h2d         10136 15.6   11.740   12.601   11.740   12.601
 cp_dbcsr_syevd                      84 12.4    0.005    0.005   12.499   12.500
 make_images_data                  5068 15.6    0.054    0.061    9.638   12.239
 hybrid_alltoall_any               5255 16.5    0.815    3.543    9.424   11.900
 init_scf_run                        11  5.9    0.000    0.001   10.448   10.448
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   10.447   10.448
 cp_fm_diag_elpa                     84 13.4    0.000    0.000    9.477    9.484
 cp_fm_diag_elpa_base                84 14.4    9.223    9.298    9.468    9.475
 grid_integrate_task_list           129 12.3    7.821    8.145    7.821    8.145
 cp_fm_cholesky_decompose            22 10.9    7.944    8.088    7.944    8.088
 qs_ot_get_derivative_diag           78 12.4    0.002    0.003    7.933    7.983
 pw_transfer                       1559 11.6    0.084    0.090    7.763    7.776
 dbcsr_mm_accdrv_process          20954 16.1    2.617    3.428    7.067    7.695
 fft_wrap_pw1pw2                   1301 12.7    0.010    0.011    7.541    7.559
 multiply_cannon_metrocomm1       10136 15.6    0.030    0.030    4.302    7.483
 wfi_extrapolate                     11  7.9    0.001    0.001    7.217    7.217
 mp_allgather_i34                  2534 14.6    2.810    6.824    2.810    6.824
 fft_wrap_pw1pw2_140                527 13.2    0.508    0.526    6.642    6.663
 calculate_dm_sparse                129  9.5    0.001    0.001    6.319    6.410
 density_rs2pw                      129  9.7    0.005    0.006    5.907    6.168
 grid_collocate_task_list           129  9.7    5.525    5.865    5.525    5.865
 fft3d_ps                          1301 14.7    2.746    2.818    5.679    5.715
 dbcsr_complete_redistribute        397 12.7    2.120    2.221    5.268    5.614
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.235    5.251
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    5.218    5.219
 mp_alltoall_d11v                  2429 14.1    4.765    5.104    4.765    5.104
 multiply_cannon_metrocomm4        7602 15.6    0.024    0.027    1.861    4.929
 mp_irecv_dv                      29142 15.9    1.824    4.849    1.824    4.849
 rs_pw_transfer                    1054 12.0    0.013    0.013    4.030    4.305
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.158    4.197
 potential_pw2rs                    129 12.3    0.026    0.027    4.068    4.080
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    3.575    3.869
 copy_fm_to_dbcsr                   210 11.7    0.002    0.002    3.454    3.783
 qs_ot_get_orbitals                 118 10.6    0.001    0.001    3.705    3.736
 copy_dbcsr_to_fm                   187 11.8    0.004    0.004    3.544    3.596
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    3.450    3.470
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="408", plot="h2o_256_md", label="(8n/2r/6t)", y=172.719000, yerr=0.000000
PlotPoint: name="409", plot="h2o_256_md_mem", label="(8n/2r/6t)", y=1415.636364, yerr=44.926754
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_performance_tests/20/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                     11.785520E+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               1979552       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    3438.3
 marketing flops                   145.646636E+12
 -------------------------------------------------------------------------------
 # multiplications                           2527
 max memory usage/rank               3.043049E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                  101080
 MPI messages size (bytes):
  total size                         1.144901E+12
  min size                           0.000000E+00
  max size                         104.857600E+06
  average size                      11.326685E+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               45568              35366371328
   4194304 < size <= 16777216               44720             382939955200
  16777216 < size                           10176             726591885696
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4024                  58831.
 MP_Allreduce        11057                   1512.
 MP_Sync                87
 MP_Alltoall          1724               36993717.
 MP_ISendRecv         3612                 218624.
 MP_Wait             11682
 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    0.029    0.083  290.748  290.749
 qs_mol_dyn_low                       1  2.0    0.003    0.003  290.172  290.184
 qs_forces                           11  3.9    0.003    0.003  290.076  290.079
 qs_energies                         11  4.9    0.002    0.002  281.447  281.454
 scf_env_do_scf                      11  5.9    0.001    0.001  259.218  259.233
 velocity_verlet                     10  3.0    0.004    0.005  209.704  209.711
 scf_env_do_scf_inner_loop          118  6.6    0.003    0.008  134.144  134.145
 init_scf_loop                       11  6.9    0.000    0.000  124.824  124.827
 prepare_preconditioner              11  7.9    0.000    0.000  120.189  120.223
 make_preconditioner                 11  8.9    0.000    0.000  120.189  120.223
 make_full_inverse_cholesky          11  9.9    0.000    0.000   95.885  117.339
 qs_scf_new_mos                     118  7.6    0.001    0.001   91.867   92.037
 qs_scf_loop_do_ot                  118  8.6    0.001    0.001   91.866   92.036
 ot_scf_mini                        118  9.6    0.004    0.004   86.987   87.086
 dbcsr_multiply_generic            2527 12.6    0.212    0.218   84.702   85.498
 cp_fm_upper_to_full                105 14.8   53.092   76.343   53.092   76.343
 multiply_cannon                   2527 13.6    0.701    0.735   59.818   60.580
 multiply_cannon_loop              2527 14.6    0.478    0.488   56.056   57.874
 ot_mini                            118 10.6    0.001    0.001   45.020   45.142
 dbcsr_complete_redistribute        395 12.7    4.006    4.058   29.917   43.094
 copy_fm_to_dbcsr                   209 11.7    0.001    0.002   26.552   39.697
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000   24.256   37.247
 mp_alltoall_i22                    718 14.1   22.085   35.059   22.085   35.059
 rebuild_ks_matrix                  129  8.3    0.001    0.001   33.740   33.871
 qs_ks_build_kohn_sham_matrix       129  9.3    0.018    0.018   33.740   33.870
 cp_fm_cholesky_invert               11 10.9   33.609   33.615   33.609   33.615
 mp_waitall_1                    106306 16.7   28.781   32.908   28.781   32.908
 qs_ks_update_qs_env                129  7.6    0.001    0.001   31.516   31.638
 qs_ot_get_p                        129 10.4    0.001    0.001   26.290   26.402
 qs_ot_get_derivative               118 11.6    0.002    0.002   24.401   24.509
 qs_ot_p2m_diag                      83 11.4    0.878    0.884   22.124   22.156
 multiply_cannon_metrocomm3       10108 15.6    0.023    0.023   19.205   21.108
 make_m2s                          5054 13.6    0.078    0.082   20.001   20.999
 ot_diis_step                       118 11.6    0.023    0.023   20.584   20.584
 make_images                       5054 14.6    3.790    3.917   19.521   20.523
 cp_dbcsr_syevd                      83 12.4    0.006    0.006   20.383   20.384
 apply_preconditioner_dbcsr         129 12.6    0.000    0.000   19.661   20.017
 apply_single                       129 13.6    0.001    0.001   19.661   20.017
 multiply_cannon_multrec          10108 15.6   10.542   12.363   18.354   18.515
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   17.184   17.186
 cp_fm_diag_elpa_base                83 14.4   12.827   14.399   17.180   17.182
 sum_up_and_integrate               129 10.3    0.324    0.326   15.826   15.925
 multiply_cannon_sync_h2d         10108 15.6   15.773   15.790   15.773   15.790
 integrate_v_rspace                 129 11.3    0.004    0.004   15.501   15.600
 qs_rho_update_rho_low              129  7.7    0.001    0.001   14.980   14.994
 calculate_rho_elec                 129  8.7    0.487    0.487   14.980   14.993
 hybrid_alltoall_any               5240 16.5    1.316    3.076   10.827   12.541
 make_images_data                  5054 15.6    0.061    0.065   10.677   12.454
 init_scf_run                        11  5.9    0.000    0.001   12.278   12.279
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   12.278   12.278
 qs_ot_get_derivative_diag           77 12.4    0.002    0.003    9.504    9.589
 dbcsr_mm_accdrv_process          20926 16.1    3.853    5.567    7.574    9.492
 cp_fm_cholesky_decompose            22 10.9    8.900    8.929    8.900    8.929
 grid_integrate_task_list           129 12.3    8.620    8.795    8.620    8.795
 wfi_extrapolate                     11  7.9    0.001    0.001    8.588    8.588
 pw_transfer                       1559 11.6    0.091    0.092    8.298    8.306
 fft_wrap_pw1pw2                   1301 12.7    0.011    0.011    8.063    8.072
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    7.990    7.991
 calculate_dm_sparse                129  9.5    0.001    0.001    7.131    7.219
 fft_wrap_pw1pw2_140                527 13.2    0.544    0.546    7.121    7.132
 mp_alltoall_d11v                  2423 14.1    6.897    7.036    6.897    7.036
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.448    6.508
 grid_collocate_task_list           129  9.7    6.386    6.419    6.386    6.419
 fft3d_ps                          1301 14.7    2.777    2.784    6.086    6.097
 copy_dbcsr_to_fm                   186 11.8    0.004    0.004    6.022    6.071
 density_rs2pw                      129  9.7    0.005    0.005    6.001    6.038
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="410", plot="h2o_256_md", label="(8n/1r/12t)", y=290.749000, yerr=0.000000
PlotPoint: name="411", plot="h2o_256_md_mem", label="(8n/1r/12t)", y=2689.818182, yerr=182.829189
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_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               1.260171E+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                6799628.
 MP_ISendRecv          570                  19200.
 MP_Wait              1302
 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    0.017    0.032   84.774   84.775
 qs_energies                          1  2.0    0.000    0.000   84.360   84.374
 ls_scf                               1  3.0    0.000    0.000   83.452   83.466
 dbcsr_multiply_generic             111  6.7    0.015    0.016   72.535   72.666
 multiply_cannon                    111  7.7    0.017    0.020   55.936   57.108
 multiply_cannon_loop               111  8.7    0.212    0.228   52.560   53.652
 ls_scf_main                          1  4.0    0.000    0.000   52.207   52.219
 density_matrix_trs4                  2  5.0    0.002    0.003   46.696   46.753
 ls_scf_init_scf                      1  4.0    0.000    0.000   28.188   28.200
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   27.079   27.136
 mp_waitall_1                     11316 10.9   22.567   25.215   22.567   25.215
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   24.994   25.007
 multiply_cannon_multrec           2664  9.7    8.201    8.991   15.529   17.311
 multiply_cannon_sync_h2d          2664  9.7   13.544   15.471   13.544   15.471
 make_m2s                           222  7.7    0.009    0.012   13.056   13.509
 make_images                        222  8.7    0.102    0.112   13.034   13.488
 multiply_cannon_metrocomm1        2664  9.7    0.010    0.011    9.781   12.515
 multiply_cannon_metrocomm3        2664  9.7    0.010    0.011    5.492    8.488
 make_images_data                   222  9.7    0.005    0.006    7.617    8.164
 dbcsr_mm_accdrv_process           4760 10.4    0.508    0.613    6.946    7.978
 hybrid_alltoall_any                227 10.6    0.219    1.856    6.558    7.659
 dbcsr_mm_accdrv_process_sort      4760 11.4    6.238    7.203    6.238    7.203
 calculate_norms                   4752  9.8    5.530    6.321    5.530    6.321
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.068    5.224
 mp_sum_l                           807  5.4    2.996    4.733    2.996    4.733
 make_images_sizes                  222  9.7    0.000    0.000    0.693    3.854
 mp_alltoall_i44                    222 10.7    0.692    3.854    0.692    3.854
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    2.215    3.381
 arnoldi_extremal                     4  6.8    0.000    0.000    3.239    3.266
 arnoldi_normal_ev                    4  7.8    0.001    0.002    3.239    3.266
 multiply_cannon_metrocomm4        2442  9.7    0.012    0.014    2.077    3.233
 mp_irecv_dv                       6231 10.9    2.060    3.212    2.060    3.212
 build_subspace                      16  8.4    0.009    0.012    3.142    3.144
 ls_scf_post                          1  4.0    0.000    0.000    3.056    3.070
 ls_scf_store_result                  1  5.0    0.000    0.000    2.883    2.917
 dbcsr_special_finalize             555  9.7    0.005    0.006    2.380    2.756
 dbcsr_merge_single_wm              555 10.7    0.447    0.596    2.371    2.747
 make_images_pack                   222  9.7    2.216    2.646    2.218    2.647
 dbcsr_matrix_vector_mult           304  9.0    0.004    0.010    2.309    2.547
 dbcsr_sort_data                    658 11.4    2.181    2.511    2.181    2.511
 dbcsr_matrix_vector_mult_local     304 10.0    2.061    2.448    2.063    2.450
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.239    2.299
 buffer_matrices_ensure_size        222  8.7    1.752    2.128    1.752    2.128
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.777    1.789
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.767    1.779
 qs_ks_build_kohn_sham_matrix         3  8.3    0.012    0.023    1.767    1.779
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="500", plot="h2o_32_nrep3_ls", label="(8n/12r/1t)", y=84.775000, yerr=0.000000
PlotPoint: name="501", plot="h2o_32_nrep3_ls_mem", label="(8n/12r/1t)", y=1140.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_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               2.097799E+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_ISendRecv          282                  57600.
 MP_Wait               828
 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    0.033    0.075   91.224   91.225
 qs_energies                          1  2.0    0.000    0.000   90.337   90.343
 ls_scf                               1  3.0    0.002    0.019   89.030   89.036
 dbcsr_multiply_generic             111  6.7    0.016    0.016   75.178   75.508
 multiply_cannon                    111  7.7    0.029    0.042   53.292   57.128
 ls_scf_main                          1  4.0    0.000    0.001   54.658   54.668
 multiply_cannon_loop               111  8.7    0.117    0.124   50.044   53.513
 density_matrix_trs4                  2  5.0    0.002    0.003   49.012   49.229
 ls_scf_init_scf                      1  4.0    0.000    0.001   30.783   30.784
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   29.667   29.747
 mp_waitall_1                      9246 10.9   20.765   29.700   20.765   29.700
 multiply_cannon_multrec           1332  9.7   13.254   16.906   22.526   27.290
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.263   27.276
 multiply_cannon_metrocomm3        1332  9.7    0.007    0.008   11.630   20.628
 make_m2s                           222  7.7    0.008    0.009   15.133   15.792
 make_images                        222  8.7    1.587    1.987   15.103   15.762
 dbcsr_mm_accdrv_process           4041 10.4    0.277    0.455    8.874   10.484
 dbcsr_mm_accdrv_process_sort      4041 11.4    8.464   10.030    8.464   10.030
 make_images_data                   222  9.7    0.004    0.005    8.557    9.427
 hybrid_alltoall_any                227 10.6    0.526    2.502    8.002    8.873
 mp_sum_l                           807  5.4    5.467    8.664    5.467    8.664
 multiply_cannon_metrocomm4        1221  9.7    0.006    0.008    3.229    7.706
 mp_irecv_dv                       3311 11.0    3.208    7.654    3.208    7.654
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    4.194    6.868
 calculate_norms                   2376  9.8    6.017    6.784    6.017    6.784
 multiply_cannon_sync_h2d          1332  9.7    4.834    6.168    4.834    6.168
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.085    5.270
 arnoldi_extremal                     4  6.8    0.000    0.002    4.618    4.640
 arnoldi_normal_ev                    4  7.8    0.001    0.005    4.618    4.640
 build_subspace                      16  8.4    0.014    0.021    4.365    4.369
 ls_scf_post                          1  4.0    0.001    0.008    3.586    3.594
 ls_scf_store_result                  1  5.0    0.000    0.000    3.261    3.412
 dbcsr_matrix_vector_mult           304  9.0    0.005    0.018    3.121    3.346
 dbcsr_matrix_vector_mult_local     304 10.0    2.733    3.214    2.735    3.216
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.004    1.216    2.785
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.487    2.576
 make_images_pack                   222  9.7    2.041    2.423    2.044    2.426
 mp_allgather_i34                   111  8.7    0.938    2.280    0.938    2.280
 dbcsr_sort_data                    436 11.2    1.845    2.081    1.845    2.081
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="502", plot="h2o_32_nrep3_ls", label="(8n/6r/2t)", y=91.225000, yerr=0.000000
PlotPoint: name="503", plot="h2o_32_nrep3_ls_mem", label="(8n/6r/2t)", y=1733.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_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               2.701586E+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_ISendRecv          186                  57600.
 MP_Wait               732
 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    0.085    0.282   94.923   94.938
 qs_energies                          1  2.0    0.000    0.000   93.914   93.948
 ls_scf                               1  3.0    0.003    0.023   92.507   92.529
 dbcsr_multiply_generic             111  6.7    0.016    0.017   77.190   77.528
 ls_scf_main                          1  4.0    0.001    0.012   57.549   57.564
 multiply_cannon                    111  7.7    0.044    0.117   53.430   57.184
 multiply_cannon_loop               111  8.7    0.101    0.108   49.880   54.109
 density_matrix_trs4                  2  5.0    0.002    0.003   51.626   51.835
 mp_waitall_1                      7374 11.0   23.832   34.248   23.832   34.248
 ls_scf_init_scf                      1  4.0    0.000    0.001   31.375   31.380
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   30.091   30.207
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.486   27.499
 multiply_cannon_multrec            888  9.7   12.670   15.365   21.306   24.692
 multiply_cannon_metrocomm3         888  9.7    0.004    0.005   10.973   23.564
 make_m2s                           222  7.7    0.007    0.008   16.963   18.164
 make_images                        222  8.7    1.977    2.293   16.925   18.124
 hybrid_alltoall_any                227 10.6    0.624    2.872    9.230   10.644
 make_images_data                   222  9.7    0.004    0.005    9.601   10.620
 dbcsr_mm_accdrv_process           3754 10.4    0.278    0.499    8.158    9.331
 mp_sum_l                           807  5.4    5.415    8.919    5.415    8.919
 dbcsr_mm_accdrv_process_sort      3754 11.4    7.717    8.879    7.717    8.879
 multiply_cannon_sync_h2d           888  9.7    6.094    7.996    6.094    7.996
 multiply_cannon_metrocomm4         777  9.7    0.004    0.005    2.503    6.972
 mp_irecv_dv                       2335 11.1    2.487    6.908    2.487    6.908
 multiply_cannon_metrocomm1         888  9.7    0.003    0.003    3.879    6.866
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    4.053    6.786
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.138    5.335
 arnoldi_extremal                     4  6.8    0.000    0.002    5.090    5.107
 arnoldi_normal_ev                    4  7.8    0.001    0.005    5.089    5.107
 build_subspace                      16  8.4    0.014    0.021    4.775    4.786
 calculate_norms                   1584  9.8    4.272    4.601    4.272    4.601
 dbcsr_matrix_vector_mult           304  9.0    0.005    0.017    3.440    3.753
 mp_allgather_i34                   111  8.7    1.382    3.721    1.382    3.721
 ls_scf_post                          1  4.0    0.003    0.023    3.580    3.599
 dbcsr_matrix_vector_mult_local     304 10.0    3.010    3.575    3.012    3.577
 ls_scf_store_result                  1  5.0    0.000    0.000    3.301    3.404
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.737    2.835
 make_images_sizes                  222  9.7    0.000    0.000    1.028    2.234
 mp_alltoall_i44                    222 10.7    1.027    2.233    1.027    2.233
 make_images_pack                   222  9.7    1.816    2.141    1.819    2.144
 dbcsr_sort_data                    325 11.1    1.882    2.136    1.882    2.136
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.947    1.952
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.928    1.933
 qs_ks_build_kohn_sham_matrix         3  8.3    0.010    0.022    1.928    1.933
 dbcsr_data_release                9322 10.9    1.317    1.916    1.317    1.916
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="504", plot="h2o_32_nrep3_ls", label="(8n/4r/3t)", y=94.938000, yerr=0.000000
PlotPoint: name="505", plot="h2o_32_nrep3_ls_mem", label="(8n/4r/3t)", y=2195.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_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               3.319771E+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_ISendRecv          138                  86400.
 MP_Wait               600
 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    0.037    0.054   97.396   97.398
 qs_energies                          1  2.0    0.000    0.000   96.777   96.782
 ls_scf                               1  3.0    0.000    0.003   95.113   95.118
 dbcsr_multiply_generic             111  6.7    0.018    0.019   78.808   79.064
 ls_scf_main                          1  4.0    0.000    0.002   58.462   58.464
 multiply_cannon                    111  7.7    0.067    0.154   52.130   57.031
 density_matrix_trs4                  2  5.0    0.002    0.003   52.456   52.577
 multiply_cannon_loop               111  8.7    0.115    0.127   46.998   50.300
 ls_scf_init_scf                      1  4.0    0.000    0.001   33.397   33.399
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   32.235   32.316
 mp_waitall_1                      6438 11.0   22.457   29.458   22.457   29.458
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.005   29.295   29.308
 multiply_cannon_multrec           1332  9.7   14.357   17.703   22.478   25.974
 make_m2s                           222  7.7    0.008    0.009   20.892   22.352
 make_images                        222  8.7    3.159    3.630   20.840   22.303
 multiply_cannon_metrocomm3        1332  9.7    0.003    0.004    9.238   16.995
 make_images_data                   222  9.7    0.004    0.005   11.551   13.132
 hybrid_alltoall_any                227 10.6    0.805    3.804   10.871   12.898
 dbcsr_mm_accdrv_process           3641 10.4    0.256    0.786    7.756    9.199
 dbcsr_mm_accdrv_process_sort      3641 11.4    7.164    8.636    7.164    8.636
 mp_sum_l                           807  5.4    4.186    7.628    4.186    7.628
 multiply_cannon_sync_h2d          1332  9.7    5.547    6.140    5.547    6.140
 multiply_cannon_metrocomm4        1110  9.7    0.004    0.006    2.096    5.987
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.160    5.985
 mp_irecv_dv                       3229 10.9    2.073    5.914    2.073    5.914
 arnoldi_extremal                     4  6.8    0.004    0.024    5.343    5.357
 arnoldi_normal_ev                    4  7.8    0.006    0.021    5.339    5.357
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.959    5.127
 build_subspace                      16  8.4    0.015    0.021    4.927    4.950
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.003    2.505    4.876
 mp_allgather_i34                   111  8.7    2.239    4.635    2.239    4.635
 calculate_norms                   2376  9.8    4.184    4.557    4.184    4.557
 dbcsr_matrix_vector_mult           304  9.0    0.006    0.017    3.613    3.913
 dbcsr_matrix_vector_mult_local     304 10.0    3.175    3.676    3.177    3.677
 dbcsr_sort_data                    658 11.4    3.047    3.381    3.047    3.381
 ls_scf_post                          1  4.0    0.000    0.002    3.254    3.260
 dbcsr_special_finalize             555  9.7    0.006    0.007    2.785    3.193
 dbcsr_merge_single_wm              555 10.7    0.533    0.664    2.776    3.185
 ls_scf_store_result                  1  5.0    0.000    0.000    2.993    3.059
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.867    2.926
 dbcsr_data_release               10477 10.7    1.611    2.442    1.611    2.442
 dbcsr_finalize                     304  7.8    0.050    0.062    1.818    1.997
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="506", plot="h2o_32_nrep3_ls", label="(8n/3r/4t)", y=97.398000, yerr=0.000000
PlotPoint: name="507", plot="h2o_32_nrep3_ls_mem", label="(8n/3r/4t)", y=2771.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_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               4.630655E+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_ISendRecv           90                 115200.
 MP_Wait               573
 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    0.057  101.957  101.958
 qs_energies                          1  2.0    0.000    0.000  101.196  101.203
 ls_scf                               1  3.0    0.000    0.000   99.294   99.299
 dbcsr_multiply_generic             111  6.7    0.018    0.019   81.032   81.253
 multiply_cannon                    111  7.7    0.085    0.135   57.779   63.258
 ls_scf_main                          1  4.0    0.000    0.000   61.899   61.899
 multiply_cannon_loop               111  8.7    0.069    0.076   53.204   55.827
 density_matrix_trs4                  2  5.0    0.002    0.003   54.917   55.011
 ls_scf_init_scf                      1  4.0    0.000    0.000   33.835   33.839
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   32.678   32.709
 mp_waitall_1                      5481 11.0   27.315   32.538   27.315   32.538
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   28.068   28.082
 multiply_cannon_multrec            444  9.7   14.036   17.321   22.443   24.335
 make_m2s                           222  7.7    0.006    0.007   17.640   20.170
 make_images                        222  8.7    3.747    4.450   17.576   20.108
 multiply_cannon_metrocomm1         444  9.7    0.002    0.002   11.592   18.501
 multiply_cannon_metrocomm3         444  9.7    0.001    0.001    6.753   15.812
 make_images_data                   222  9.7    0.003    0.004    9.774   12.295
 hybrid_alltoall_any                227 10.6    0.793    3.772    9.481   12.165
 dbcsr_mm_accdrv_process           3003 10.4    0.326    1.202    8.101   10.259
 mp_sum_l                           807  5.4    3.634    7.993    3.634    7.993
 multiply_cannon_sync_h2d           444  9.7    6.553    7.691    6.553    7.691
 dbcsr_mm_accdrv_process_sort      3003 11.4    6.426    7.537    6.426    7.537
 apply_matrix_preconditioner          6  5.3    0.000    0.000    7.018    7.129
 mp_allgather_i34                   111  8.7    2.779    7.021    2.779    7.021
 arnoldi_extremal                     4  6.8    0.000    0.000    5.851    5.868
 arnoldi_normal_ev                    4  7.8    0.001    0.004    5.851    5.868
 build_subspace                      16  8.4    0.015    0.020    5.462    5.471
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    2.438    4.588
 dbcsr_matrix_vector_mult           304  9.0    0.007    0.017    4.175    4.366
 dbcsr_matrix_vector_mult_local     304 10.0    3.686    4.158    3.688    4.160
 multiply_cannon_metrocomm4         333  9.7    0.001    0.002    1.659    3.815
 mp_irecv_dv                       1241 11.2    1.639    3.772    1.639    3.772
 calculate_norms                    792  9.8    3.560    3.733    3.560    3.733
 ls_scf_post                          1  4.0    0.000    0.000    3.560    3.567
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    3.388    3.483
 ls_scf_store_result                  1  5.0    0.000    0.000    3.351    3.383
 make_images_sizes                  222  9.7    0.000    0.000    1.178    3.339
 mp_alltoall_i44                    222 10.7    1.178    3.339    1.178    3.339
 jit_kernel_multiply                  1 12.1    1.350    2.646    1.350    2.646
 dbcsr_finalize                     304  7.8    0.062    0.078    2.209    2.273
 dbcsr_merge_all                    275  8.9    0.477    0.537    2.057    2.100
 dbcsr_data_release               10123 10.8    1.349    2.052    1.349    2.052
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="508", plot="h2o_32_nrep3_ls", label="(8n/2r/6t)", y=101.958000, yerr=0.000000
PlotPoint: name="509", plot="h2o_32_nrep3_ls_mem", label="(8n/2r/6t)", y=3680.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/454c28448ad2f11fb8d3fa0aeb0a8fa209172190_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               8.777654E+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_ISendRecv           84                 732600.
 MP_Wait               309
 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    0.081    0.123  111.515  111.516
 qs_energies                          1  2.0    0.000    0.000  109.956  109.971
 ls_scf                               1  3.0    0.000    0.000  107.044  107.058
 dbcsr_multiply_generic             111  6.7    0.023    0.028   81.200   81.314
 ls_scf_main                          1  4.0    0.000    0.000   66.150   66.151
 density_matrix_trs4                  2  5.0    0.002    0.003   57.283   57.334
 multiply_cannon                    111  7.7    0.146    0.177   53.564   55.557
 multiply_cannon_loop               111  8.7    0.067    0.070   50.043   50.883
 ls_scf_init_scf                      1  4.0    0.000    0.000   37.200   37.202
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   35.804   35.823
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   30.639   30.653
 mp_waitall_1                      4569 11.1   24.475   28.684   24.475   28.684
 multiply_cannon_multrec            444  9.7   17.967   18.783   23.898   25.153
 make_m2s                           222  7.7    0.007    0.007   23.991   25.009
 make_images                        222  8.7    4.608    4.988   23.882   24.898
 hybrid_alltoall_any                227 10.6    1.663    3.625   12.979   15.687
 make_images_data                   222  9.7    0.003    0.004   13.193   15.610
 multiply_cannon_metrocomm3         444  9.7    0.001    0.001   12.167   14.257
 multiply_cannon_sync_h2d           444  9.7    8.848    8.897    8.848    8.897
 apply_matrix_preconditioner          6  5.3    0.000    0.000    7.359    7.610
 arnoldi_extremal                     4  6.8    0.000    0.000    7.375    7.392
 arnoldi_normal_ev                    4  7.8    0.002    0.009    7.374    7.392
 dbcsr_mm_accdrv_process           1814 10.4    0.266    1.160    5.758    6.952
 build_subspace                      16  8.4    0.026    0.036    6.819    6.835
 dbcsr_matrix_vector_mult           304  9.0    0.009    0.026    5.446    5.615
 dbcsr_matrix_vector_mult_local     304 10.0    5.030    5.336    5.032    5.339
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    4.823    4.911
 dbcsr_mm_accdrv_process_sort      1814 11.4    4.146    4.274    4.146    4.274
 ls_scf_post                          1  4.0    0.000    0.000    3.694    3.708
 mp_allgather_i34                   111  8.7    1.138    3.586    1.138    3.586
 make_images_sizes                  222  9.7    0.000    0.000    1.426    3.482
 mp_alltoall_i44                    222 10.7    1.426    3.481    1.426    3.481
 ls_scf_store_result                  1  5.0    0.000    0.000    3.444    3.456
 calculate_norms                    792  9.8    3.239    3.284    3.239    3.284
 dbcsr_finalize                     304  7.8    0.082    0.090    3.093    3.148
 dbcsr_complete_redistribute          5  7.6    1.442    1.478    2.791    2.923
 dbcsr_merge_all                    275  8.9    0.894    0.921    2.877    2.920
 qs_energies_init_hamiltonians        1  3.0    0.001    0.002    2.882    2.882
 dbcsr_data_release               12724 10.6    2.325    2.843    2.325    2.843
 multiply_cannon_metrocomm1         444  9.7    0.001    0.001    0.819    2.801
 jit_kernel_multiply                  1 12.5    1.345    2.585    1.345    2.585
 matrix_ls_to_qs                      2  6.0    0.000    0.000    2.428    2.577
 dbcsr_sort_data                    325 11.1    2.443    2.501    2.443    2.501
 dbcsr_new_transposed                 4  7.5    0.243    0.251    2.272    2.288
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="510", plot="h2o_32_nrep3_ls", label="(8n/1r/12t)", y=111.516000, yerr=0.000000
PlotPoint: name="511", plot="h2o_32_nrep3_ls_mem", label="(8n/1r/12t)", y=6881.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


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

CommitSHA: 454c28448ad2f11fb8d3fa0aeb0a8fa209172190
Summary: empty
Status: OK