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


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


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

 GIT Revision: f387d9e52db66ef3f179c70ace9df802df4c9cad


################# ARCHITECTURE FILE ##################
#!/bin/bash
#
# CP2K arch file for Cray-XC50 (Piz Daint, CSCS, GPU partition)
#
# Tested with: GNU 9.3.0, Cray-MPICH 7.7.18, Cray-libsci 20.09.1, Cray-FFTW 3.3.8.10,
#              COSMA 2.6.2, ELPA 2022.11.001, LIBINT 2.6.0, LIBPEXSI 1.2.0,
#              LIBXC 6.1.0, LIBVORI 220621, LIBXSMM 1.17, PLUMED 2.8.1,
#              SIRIUS 7.4.3, SPGLIB 1.16.2
#
# Usage: Source this arch file and then run make as instructed.
#        A full toolchain installation is performed as default.
#        Replace or adapt the "module add" commands below if needed.
#
# Author: Matthias Krack (03.02.2023)
#
# \
   if [ "${0}" = "${BASH_SOURCE}" ]; then \
      echo "ERROR: Script ${0##*/} must be sourced"; \
      echo "Usage: source ${0##*/}"; \
      exit 1; \
   fi; \
   this_file=${BASH_SOURCE##*/}; \
   if [ -n "${1}" ]; then \
      gcc_version="${1}"; \
   else \
      gcc_version="9.3.0"; \
   fi; \
   module add daint-gpu; \
   module rm PrgEnv-cray; \
   module add PrgEnv-gnu; \
   module rm gcc; \
   module add gcc/${gcc_version}; \
   module add cray-fftw/3.3.8.10; \
   module add cudatoolkit; \
   echo "Expected setup:"; \
   echo "   cray-mpich/7.7.18"; \
   echo "   craype-haswell"; \
   echo "   daint-gpu/21.09"; \
   echo "   craype/2.7.10"; \
   echo "   cray-libsci/20.09.1"; \
   echo "   PrgEnv-gnu/6.0.10"; \
   echo "   gcc/${gcc_version}"; \
   echo "   cray-fftw/3.3.8.10"; \
   echo "   cudatoolkit/11.0.2_3.38-8.1__g5b73779"; \
   module list; \
   module -f save cp2k_gpu_gnu_psmp; \
   echo "To load the required modules in your batch job script, use:"; \
   echo "   module restore cp2k_gpu_gnu_psmp"; \
   cd tools/toolchain; \
   ./install_cp2k_toolchain.sh --enable-cuda=yes --gpu-ver=P100 -j${maxtasks} --no-arch-files --with-gcc=system --with-libvdwxc --with-pexsi --with-plumed; \
   cd ../..; \
   printf "Sourcing ${PWD}/tools/toolchain/install/setup ... "; \
   source ${PWD}/tools/toolchain/install/setup; \
   printf "done\n"; \
   echo "Check the output above for error messages and consistency!"; \
   echo "If everything is OK, you can build a CP2K production binary with"; \
   echo "   make -j ARCH=${this_file%.*} VERSION=${this_file##*.}"; \
   echo "Alternatively, you can add further checks, e.g. for regression testing, with"; \
   echo "   make -j ARCH=${this_file%.*} VERSION=${this_file##*.} DO_CHECKS=yes"; \
   echo "or build CP2K as a library with"; \
   echo "   make -j ARCH=${this_file%.*} VERSION=${this_file##*.} libcp2k"; \
   return

# Set options
DO_CHECKS      := no
USE_ACC        := yes
USE_COSMA      := 2.6.2
USE_ELPA       := 2022.11.001
USE_LIBINT     := 2.6.0
USE_LIBPEXSI   := 1.2.0
USE_LIBVORI    := 220621
USE_LIBXC      := 6.1.0
USE_LIBXSMM    := 1.17
USE_PLUMED     := 2.8.1
#USE_QUIP       := 0.9.10
USE_SIRIUS     := 7.4.3
USE_SPGLIB     := 1.16.2
# Only needed for SIRIUS
LIBVDWXC_VER   := 0.4.0
SPFFT_VER      := 1.0.6
SPLA_VER       := 1.5.4
HDF5_VER       := 1.12.0
# Only needed for LIBPEXSI
SCOTCH_VER     := 6.0.0
SUPERLU_VER    := 6.1.0

LMAX           := 5
MAX_CONTR      := 4

GPUVER         := P100
OFFLOAD_TARGET := cuda

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

CFLAGS         += $(DFLAGS)

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

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

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

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

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

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


===== TESTS (description) =====
 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-32 RI-RPA/RI-MP2 correlation energy
 input file: benchmarks/QS_mp2_rpa/32-H2O/RI-RPA.inp
 required files: ['benchmarks/QS_mp2_rpa/32-H2O/BASIS_H2O', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32.xyz', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32-PBE-TZ.inp', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32-RI-dRPA-TZ.inp']
 output file: result.log
 # nodes = 8
 # ranks/node = 2
 # threads/rank = 6
 nrepeat = 1
 time[min] = 15
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/01
 job id: 44793999
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/02
 job id: 44794000
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/03
 job id: 44794001
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/04
 job id: 44794002
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/05
 job id: 44794003
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/06
 job id: 44794004
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/07
 job id: 44794005
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/08
 job id: 44794006
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/09
 job id: 44794007
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/10
 job id: 44794008
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/11
 job id: 44794009
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/12
 job id: 44794010
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/13
 job id: 44794011
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/14
 job id: 44794014
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/15
 job id: 44794015
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/16
 job id: 44794017
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/17
 job id: 44794018
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/18
 job id: 44794020
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/19
 job id: 44794023
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/20
 job id: 44794024
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/21
 job id: 44794026
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/22
 job id: 44794027
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/23
 job id: 44794030
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/24
 job id: 44794031
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/25
 job id: 44794033
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/26
 job id: 44794037
 --- 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/f387d9e52db66ef3f179c70ace9df802df4c9cad_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    0.021    0.033  134.369  134.370
 farming_run                          1  2.0  133.736  133.744  134.342  134.344
 -------------------------------------------------------------------------------


 @@@@@@@@@@ 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               1.460187E+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              229                1108280.
 MP_Allreduce          485                2282278.
 MP_Sync                27
 MP_Alltoall            38                9316958.
 MP_SendRecv           120                 384007.
 MP_ISendRecv           45                 235435.
 MP_Wait               191
 MP_comm_split           8
 MP_ISend              127                3867574.
 MP_IRecv              127                3866554.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.010    0.026  115.902  115.902
 qs_energies                          1  2.0    0.000    0.000  115.622  115.625
 mp2_main                             1  3.0    0.000    0.000  113.647  113.649
 mp2_gpw_main                         1  4.0    0.025    0.033  112.814  112.816
 mp2_ri_gpw_compute_in                1  5.0    0.172    0.174   93.899   94.368
 mp2_ri_gpw_compute_in_loop           1  6.0    0.004    0.004   55.450   55.915
 mp2_eri_3c_integrate_gpw           272  7.0    0.154    0.171   41.760   47.205
 get_2c_integrals                     1  6.0    0.000    0.000   37.513   38.273
 integrate_v_rspace                 273  8.0    0.442    0.453   25.127   30.292
 pw_transfer                       6555 10.6    0.372    0.398   27.388   28.205
 fft_wrap_pw1pw2                   5465 11.4    0.045    0.048   26.056   26.726
 grid_integrate_task_list           273  9.0   20.934   26.584   20.934   26.584
 fft_wrap_pw1pw2_100               2178 12.4    1.195    1.441   23.570   24.243
 compute_2c_integrals                 1  7.0    0.002    0.003   19.635   19.641
 compute_2c_integrals_loop_lm         1  8.0    0.004    0.005   18.852   19.344
 mp2_eri_2c_integrate_gpw             1  9.0    2.367    2.418   18.848   19.343
 rpa_ri_compute_en                    1  5.0    0.001    0.002   18.804   18.936
 cp_fm_cholesky_decompose            12  8.2   17.857   18.639   17.857   18.639
 cholesky_decomp                      1  7.0    0.000    0.000   16.723   17.516
 fft3d_s                           5443 13.4   16.136   16.604   16.159   16.625
 ao_to_mo_and_store_B_mult_1        272  7.0   10.857   15.594   10.857   15.594
 calculate_wavefunction             272  8.0    5.425    5.574   12.560   13.192
 rpa_num_int                          1  6.0    0.000    0.001   10.537   10.538
 rpa_num_int_RPA_matrix_operati       8  7.0    0.000    0.000   10.495   10.537
 calc_mat_Q                           8  8.0    0.000    0.000    9.310    9.438
 contract_S_to_Q                      8  9.0    0.000    0.000    8.732    8.856
 calc_potential_gpw                 544  9.5    0.005    0.006    8.256    8.602
 mp2_eri_2c_integrate_gpw_pot_l     272 10.0    0.001    0.002    8.210    8.558
 potential_pw2rs                    545 10.0    0.108    0.110    7.676    8.437
 parallel_gemm_fm                    14  9.1    0.000    0.000    8.313    8.428
 parallel_gemm_fm_cosma              14 10.1    8.313    8.427    8.313    8.427
 collocate_single_gaussian          272 10.0    0.039    0.041    7.448    7.734
 create_integ_mat                     1  6.0    0.022    0.028    7.706    7.707
 array2fm                             1  7.0    0.000    0.000    6.679    7.202
 pw_scatter_s                      2720 13.7    4.441    4.576    4.441    4.576
 pw_gather_s                       2722 13.2    3.868    4.164    3.868    4.164
 array2fm_buffer_send                 1  8.0    2.933    3.080    2.933    3.080
 pw_poisson_solve                   545 10.5    1.120    1.179    2.161    2.342
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="10", plot="h2o_32_ri_rpa_mp2", label="RI-RPA (8n/2r/6t)", y=112.812727, yerr=0.000000
PlotPoint: name="11", plot="h2o_32_ri_rpa_mp2_mem", label="RI-RPA (8n/2r/6t)", y=2731.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/02/result.log


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

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

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               22                 205321.
 MP_Allreduce          344                     10.
 MP_Sync                 4
 MP_comm_split           1
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.027    0.036  396.941  396.943
 farming_run                          1  2.0  396.086  396.090  396.906  396.909
 -------------------------------------------------------------------------------


 @@@@@@@@@@ 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               1.224372E+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              704                 407793.
 MP_Allreduce         1821                  23730.
 MP_Sync                38
 MP_Alltoall            77                2368424.
 MP_SendRecv          2876                2171486.
 MP_ISendRecv         1034                 172620.
 MP_Wait              1346
 MP_comm_split           7
 MP_ISend              264                 362227.
 MP_IRecv              264                 362718.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.013    0.044  210.205  210.206
 qs_energies                          1  2.0    0.000    0.000  209.855  209.863
 scf_env_do_scf                       1  3.0    0.000    0.000  107.239  107.239
 qs_ks_update_qs_env                  5  5.0    0.000    0.000  106.340  106.348
 rebuild_ks_matrix                    4  6.0    0.000    0.000  106.339  106.347
 qs_ks_build_kohn_sham_matrix         4  7.0    0.056    0.064  106.339  106.347
 hfx_ks_matrix                        4  8.0    0.001    0.001  105.954  105.958
 integrate_four_center                4  9.0    0.144    0.452  105.954  105.957
 mp2_main                             1  3.0    0.000    0.000  102.326  102.334
 mp2_gpw_main                         1  4.0    0.032    0.047  101.380  101.389
 integrate_four_center_main           4 10.0    0.089    0.514   97.315  100.068
 integrate_four_center_bin          267 11.0   97.227  100.051   97.227  100.051
 init_scf_loop                        1  4.0    0.000    0.000   93.022   93.022
 mp2_ri_gpw_compute_in                1  5.0    0.064    0.065   74.926   75.950
 mp2_ri_gpw_compute_in_loop           1  6.0    0.002    0.002   54.495   55.517
 mp2_eri_3c_integrate_gpw            91  7.0    0.145    0.160   42.195   47.180
 integrate_v_rspace                  95  8.0    0.402    0.574   28.542   33.362
 pw_transfer                       2240 10.6    0.142    0.160   29.918   30.293
 ao_to_mo_and_store_B_mult_1         91  7.0   10.612   29.363   10.612   29.363
 fft_wrap_pw1pw2                   1868 11.4    0.018    0.021   28.932   29.330
 grid_integrate_task_list            95  9.0   23.829   28.836   23.829   28.836
 mp2_ri_gpw_compute_en                1  5.0    0.055    0.069   26.307   28.003
 fft_wrap_pw1pw2_100                730 12.4    1.266    1.456   26.656   27.051
 mp2_ri_gpw_compute_en_RI_loop        1  6.0    1.846    1.895   24.625   24.634
 get_2c_integrals                     1  6.0    0.000    0.000   20.331   20.367
 compute_2c_integrals                 1  7.0    0.003    0.004   19.307   19.313
 compute_2c_integrals_loop_lm         1  8.0    0.001    0.002   18.847   19.178
 mp2_eri_2c_integrate_gpw             1  9.0    1.734    1.872   18.846   19.177
 fft3d_s                           1823 13.4   18.433   18.744   18.446   18.758
 scf_env_do_scf_inner_loop            4  4.0    0.000    0.000   14.214   14.214
 calculate_wavefunction              91  8.0    2.046    2.094    9.766   10.034
 mp2_ri_gpw_compute_en_expansio     172  7.0    0.555    0.582    8.760    9.278
 potential_pw2rs                    186 10.0    0.034    0.036    8.642    9.185
 local_gemm                         172  8.0    8.205    8.718    8.205    8.718
 mp2_eri_2c_integrate_gpw_pot_l      91 10.0    0.001    0.001    8.225    8.591
 mp2_ri_gpw_compute_en_comm          22  7.0    0.510    0.553    7.627    8.195
 collocate_single_gaussian           91 10.0    0.016    0.019    7.885    8.157
 calc_potential_gpw                 182  9.5    0.002    0.002    7.891    8.138
 mp2_ri_gpw_compute_en_ener         172  7.0    6.346    6.475    6.346    6.475
 mp_sendrecv_dm3                   2068  8.0    5.632    6.201    5.632    6.201
 mp_sync                             38 10.4    3.330    5.561    3.330    5.561
 pw_gather_s                        912 13.2    4.933    5.336    4.933    5.336
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="20", plot="h2o_32_ri_rpa_mp2", label="RI-MP2 (8n/6r/2t)", y=101.376692, yerr=0.000000
PlotPoint: name="21", plot="h2o_32_ri_rpa_mp2_mem", label="RI-MP2 (8n/6r/2t)", y=1512.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/03/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                     29.277748E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               5055360       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      29.1
 marketing flops                     2.107592E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             452.616192E+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                 579374.
 MP_SendRecv         22610                   5520.
 MP_ISendRecv        22610                   5520.
 MP_Wait             37876
 MP_comm_split          50
 MP_ISend            20771                  42672.
 MP_IRecv            20771                  42672.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.020    0.050   52.244   52.247
 qs_mol_dyn_low                       1  2.0    0.004    0.009   51.703   51.890
 qs_forces                           11  3.9    0.003    0.009   51.638   51.639
 qs_energies                         11  4.9    0.005    0.026   50.152   50.162
 scf_env_do_scf                      11  5.9    0.001    0.001   43.687   43.687
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.007   41.629   41.629
 dbcsr_multiply_generic            2286 12.5    0.094    0.097   33.370   33.859
 qs_scf_new_mos                     108  7.5    0.000    0.001   31.602   31.891
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   31.602   31.890
 ot_scf_mini                        108  9.5    0.002    0.002   29.976   30.181
 multiply_cannon                   2286 13.5    0.189    0.200   26.185   27.773
 multiply_cannon_loop              2286 14.5    1.477    1.554   25.505   27.145
 velocity_verlet                     10  3.0    0.001    0.002   25.208   25.208
 ot_mini                            108 10.5    0.001    0.001   19.018   19.265
 qs_ot_get_derivative               108 11.5    0.001    0.001   16.085   16.270
 mp_waitall_1                    245248 16.5    8.304   15.175    8.304   15.175
 multiply_cannon_metrocomm3       54864 15.5    0.069    0.074    5.922   13.378
 multiply_cannon_multrec          54864 15.5    4.276    6.584    7.918   11.526
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.877    8.027
 qs_ks_build_kohn_sham_matrix       119  9.3    0.011    0.015    7.877    8.027
 multiply_cannon_sync_h2d         54864 15.5    5.945    7.514    5.945    7.514
 mp_sum_l                          7207 12.9    5.338    7.096    5.338    7.096
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.946    7.087
 qs_ot_get_p                        119 10.4    0.001    0.001    6.406    6.725
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    5.433    5.889
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    5.342    5.466
 init_scf_run                        11  5.9    0.000    0.001    5.164    5.164
 scf_env_initial_rho_setup           11  6.9    0.000    0.003    5.164    5.164
 dbcsr_mm_accdrv_process          76910 16.1    1.140    1.807    3.563    5.058
 sum_up_and_integrate               119 10.3    0.012    0.015    4.469    4.476
 integrate_v_rspace                 119 11.3    0.002    0.003    4.456    4.465
 qs_rho_update_rho_low              119  7.7    0.001    0.001    4.119    4.214
 calculate_rho_elec                 119  8.7    0.011    0.017    4.119    4.214
 qs_ot_p2m_diag                      50 11.0    0.004    0.006    3.731    3.803
 calculate_dm_sparse                119  9.5    0.000    0.001    3.150    3.308
 jit_kernel_multiply                 13 15.8    2.361    3.161    2.361    3.161
 multiply_cannon_metrocomm1       54864 15.5    0.053    0.058    1.754    3.095
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.864    3.072
 apply_single                       119 13.6    0.000    0.000    2.864    3.072
 calculate_first_density_matrix       1  7.0    0.000    0.003    2.980    2.988
 cp_dbcsr_syevd                      50 12.0    0.002    0.003    2.870    2.870
 rs_pw_transfer                     974 11.9    0.011    0.012    2.665    2.782
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    2.673    2.674
 cp_fm_redistribute_end              50 14.0    2.434    2.652    2.439    2.654
 ot_diis_step                       108 11.5    0.006    0.006    2.651    2.651
 cp_fm_diag_elpa_base                50 14.0    0.213    2.574    0.214    2.583
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.489    2.492
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    2.385    2.458
 density_rs2pw                      119  9.7    0.004    0.004    2.167    2.303
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.193    2.237
 acc_transpose_blocks             54864 15.5    0.227    0.248    1.772    2.232
 wfi_extrapolate                     11  7.9    0.001    0.001    2.117    2.117
 grid_integrate_task_list           119 12.3    2.016    2.113    2.016    2.113
 mp_sum_d                          4127 12.0    1.356    2.046    1.356    2.046
 init_scf_loop                       11  6.9    0.000    0.002    2.040    2.041
 potential_pw2rs                    119 12.3    0.004    0.004    1.821    1.831
 pw_transfer                       1439 11.6    0.053    0.058    1.757    1.826
 fft_wrap_pw1pw2                   1201 12.6    0.007    0.007    1.681    1.754
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.680    1.700
 make_m2s                          4572 13.5    0.054    0.056    1.545    1.590
 fft3d_ps                          1201 14.6    0.369    0.473    1.450    1.516
 make_images                       4572 14.5    0.133    0.138    1.463    1.507
 mp_waitany                       12084 13.8    1.218    1.423    1.218    1.423
 mp_alltoall_d11v                  2130 13.8    1.226    1.369    1.226    1.369
 fft_wrap_pw1pw2_140                487 13.2    0.084    0.097    1.291    1.366
 grid_collocate_task_list           119  9.7    1.291    1.364    1.291    1.364
 dbcsr_dot_sd                      1205 11.9    0.051    0.062    0.731    1.147
 acc_transpose_blocks_kernels     54864 16.5    0.249    0.384    0.800    1.093
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="100", plot="h2o_64_md", label="(8n/12r/1t)", y=52.247000, yerr=0.000000
PlotPoint: name="101", plot="h2o_64_md_mem", label="(8n/12r/1t)", y=431.090909, yerr=1.239835
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_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             487.260160E+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                1031878.
 MP_SendRecv         16779                  37093.
 MP_ISendRecv        16779                  37093.
 MP_Wait             23539
 MP_comm_split          50
 MP_ISend             5720                 128509.
 MP_IRecv             5720                 128509.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.028    0.038   39.765   39.768
 qs_mol_dyn_low                       1  2.0    0.003    0.004   39.471   39.492
 qs_forces                           11  3.9    0.002    0.002   38.547   38.548
 qs_energies                         11  4.9    0.005    0.031   36.869   36.873
 scf_env_do_scf                      11  5.9    0.001    0.003   31.315   31.315
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.008   28.846   28.847
 dbcsr_multiply_generic            2286 12.5    0.101    0.104   21.483   21.872
 qs_scf_new_mos                     108  7.5    0.001    0.001   19.795   20.032
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   19.794   20.032
 ot_scf_mini                        108  9.5    0.002    0.003   18.917   19.088
 velocity_verlet                     10  3.0    0.001    0.002   18.813   18.832
 multiply_cannon                   2286 13.5    0.209    0.215   16.569   18.183
 multiply_cannon_loop              2286 14.5    0.900    0.975   15.487   16.874
 ot_mini                            108 10.5    0.001    0.001   11.686   11.920
 mp_waitall_1                    200699 16.5    5.621   10.842    5.621   10.842
 multiply_cannon_metrocomm3       27432 15.5    0.068    0.071    4.205    9.541
 qs_ot_get_derivative               108 11.5    0.001    0.001    9.243    9.417
 multiply_cannon_multrec          27432 15.5    1.996    4.345    6.127    9.124
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.135    7.275
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.023    7.135    7.275
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.308    6.435
 dbcsr_mm_accdrv_process          47894 16.0    3.241    5.324    4.062    6.038
 qs_ot_get_p                        119 10.4    0.001    0.001    4.374    4.605
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    3.593    4.439
 init_scf_run                        11  5.9    0.000    0.001    4.268    4.269
 scf_env_initial_rho_setup           11  6.9    0.000    0.001    4.268    4.269
 sum_up_and_integrate               119 10.3    0.024    0.026    4.136    4.141
 integrate_v_rspace                 119 11.3    0.002    0.003    4.112    4.119
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    3.037    4.117
 apply_single                       119 13.6    0.000    0.000    3.037    4.117
 mp_sum_l                          7207 12.9    2.045    3.957    2.045    3.957
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.723    3.749
 calculate_rho_elec                 119  8.7    0.021    0.024    3.722    3.749
 qs_ot_p2m_diag                      50 11.0    0.009    0.013    2.950    2.969
 rs_pw_transfer                     974 11.9    0.010    0.012    2.546    2.923
 multiply_cannon_sync_h2d         27432 15.5    2.190    2.836    2.190    2.836
 calculate_first_density_matrix       1  7.0    0.000    0.003    2.753    2.756
 make_m2s                          4572 13.5    0.052    0.054    2.428    2.659
 make_images                       4572 14.5    0.200    0.235    2.339    2.569
 cp_dbcsr_syevd                      50 12.0    0.003    0.004    2.518    2.518
 density_rs2pw                      119  9.7    0.004    0.004    2.058    2.456
 init_scf_loop                       11  6.9    0.002    0.012    2.447    2.448
 ot_diis_step                       108 11.5    0.011    0.011    2.393    2.394
 calculate_dm_sparse                119  9.5    0.000    0.001    2.282    2.354
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    2.112    2.203
 cp_fm_diag_elpa                     50 13.0    0.001    0.008    2.192    2.192
 cp_fm_redistribute_end              50 14.0    1.812    2.166    1.816    2.167
 cp_fm_diag_elpa_base                50 14.0    0.334    2.047    0.347    2.107
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.990    1.993
 jit_kernel_multiply                  9 16.2    0.768    1.967    0.768    1.967
 pw_transfer                       1439 11.6    0.064    0.071    1.901    1.930
 grid_integrate_task_list           119 12.3    1.840    1.908    1.840    1.908
 potential_pw2rs                    119 12.3    0.006    0.006    1.882    1.890
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.810    1.842
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.763    1.804
 prepare_preconditioner              11  7.9    0.001    0.008    1.534    1.561
 make_preconditioner                 11  8.9    0.002    0.018    1.533    1.561
 fft3d_ps                          1201 14.6    0.512    0.563    1.511    1.540
 acc_transpose_blocks             27432 15.5    0.109    0.114    1.210    1.521
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.509    1.517
 make_full_inverse_cholesky          11  9.9    0.000    0.001    1.435    1.496
 make_images_data                  4572 15.5    0.045    0.051    1.106    1.494
 wfi_extrapolate                     11  7.9    0.001    0.001    1.452    1.452
 fft_wrap_pw1pw2_140                487 13.2    0.079    0.086    1.411    1.443
 hybrid_alltoall_any               4725 16.4    0.050    0.110    0.960    1.393
 grid_collocate_task_list           119  9.7    1.231    1.361    1.231    1.361
 mp_allgather_i34                  2286 14.5    0.522    1.260    0.522    1.260
 mp_alltoall_d11v                  2130 13.8    1.123    1.215    1.123    1.215
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.152    1.204
 mp_sum_d                          4127 12.0    0.597    1.042    0.597    1.042
 qs_energies_init_hamiltonians       11  5.9    0.000    0.002    0.981    0.981
 mp_sum_dm                          438  4.9    0.917    0.963    0.917    0.963
 rs_pw_transfer_RS2PW_140           130 11.5    0.140    0.147    0.566    0.944
 mp_waitany                        5720 13.7    0.540    0.942    0.540    0.942
 md_output                           10  3.0    0.000    0.000    0.022    0.923
 md_write_output                     11  3.9    0.019    0.900    0.021    0.913
 update_particle_set                 20  4.0    0.000    0.000    0.890    0.909
 acc_transpose_blocks_kernels     27432 16.5    0.182    0.270    0.679    0.906
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.887    0.900
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="102", plot="h2o_64_md", label="(8n/6r/2t)", y=39.768000, yerr=0.000000
PlotPoint: name="103", plot="h2o_64_md_mem", label="(8n/6r/2t)", y=464.454545, yerr=0.890724
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_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             523.718656E+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                1341229.
 MP_SendRecv         11067                  57667.
 MP_ISendRecv        11067                  57667.
 MP_Wait             21987
 MP_comm_split          50
 MP_ISend             9880                  92618.
 MP_IRecv             9880                  92618.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.018    0.032   33.028   33.030
 qs_mol_dyn_low                       1  2.0    0.003    0.004   32.697   32.705
 qs_forces                           11  3.9    0.002    0.005   31.825   31.826
 qs_energies                         11  4.9    0.002    0.009   30.257   30.260
 scf_env_do_scf                      11  5.9    0.001    0.003   25.419   25.419
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.008   22.895   22.895
 dbcsr_multiply_generic            2286 12.5    0.095    0.097   16.362   16.458
 velocity_verlet                     10  3.0    0.001    0.002   15.958   15.985
 qs_scf_new_mos                     108  7.5    0.001    0.001   14.704   14.724
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   14.703   14.724
 ot_scf_mini                        108  9.5    0.002    0.003   13.988   13.997
 multiply_cannon                   2286 13.5    0.195    0.202   13.121   13.932
 multiply_cannon_loop              2286 14.5    0.632    0.670   12.345   13.191
 ot_mini                            108 10.5    0.001    0.001    8.658    8.672
 qs_ot_get_derivative               108 11.5    0.001    0.001    7.177    7.185
 multiply_cannon_multrec          18288 15.5    1.949    2.911    6.884    7.132
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.374    6.392
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.014    6.374    6.392
 dbcsr_mm_accdrv_process          38222 16.0    4.273    5.425    4.851    5.770
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.630    5.647
 sum_up_and_integrate               119 10.3    0.029    0.031    3.945    3.951
 integrate_v_rspace                 119 11.3    0.002    0.003    3.915    3.925
 init_scf_run                        11  5.9    0.000    0.001    3.651    3.651
 scf_env_initial_rho_setup           11  6.9    0.000    0.001    3.650    3.651
 mp_waitall_1                    158411 16.6    2.494    3.611    2.494    3.611
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.463    3.473
 calculate_rho_elec                 119  8.7    0.030    0.031    3.463    3.472
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.697    3.366
 qs_ot_get_p                        119 10.4    0.001    0.001    3.165    3.186
 init_scf_loop                       11  6.9    0.001    0.004    2.507    2.508
 rs_pw_transfer                     974 11.9    0.009    0.010    2.227    2.497
 calculate_first_density_matrix       1  7.0    0.001    0.004    2.425    2.425
 multiply_cannon_metrocomm3       18288 15.5    0.044    0.047    1.382    2.407
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.081    2.399
 apply_single                       119 13.6    0.000    0.000    2.080    2.399
 density_rs2pw                      119  9.7    0.004    0.004    1.980    2.249
 qs_ot_p2m_diag                      50 11.0    0.012    0.013    2.134    2.140
 pw_transfer                       1439 11.6    0.065    0.071    1.960    1.968
 grid_integrate_task_list           119 12.3    1.802    1.899    1.802    1.899
 calculate_dm_sparse                119  9.5    0.000    0.000    1.881    1.895
 make_m2s                          4572 13.5    0.044    0.045    1.737    1.882
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.867    1.878
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.877    1.877
 make_images                       4572 14.5    0.189    0.200    1.651    1.794
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.735    1.737
 prepare_preconditioner              11  7.9    0.000    0.000    1.717    1.720
 make_preconditioner                 11  8.9    0.000    0.001    1.717    1.720
 potential_pw2rs                    119 12.3    0.007    0.008    1.709    1.716
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.658    1.659
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.568    1.656
 cp_fm_redistribute_end              50 14.0    1.237    1.639    1.238    1.639
 jit_kernel_multiply                  8 16.5    0.526    1.634    0.526    1.634
 multiply_cannon_sync_h2d         18288 15.5    1.418    1.626    1.418    1.626
 cp_fm_diag_elpa_base                50 14.0    0.385    1.561    0.399    1.607
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.580    1.585
 fft3d_ps                          1201 14.6    0.523    0.543    1.546    1.560
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.521    1.528
 fft_wrap_pw1pw2_140                487 13.2    0.090    0.094    1.496    1.507
 mp_sum_l                          7207 12.9    1.120    1.482    1.120    1.482
 ot_diis_step                       108 11.5    0.011    0.011    1.461    1.462
 grid_collocate_task_list           119  9.7    1.213    1.345    1.213    1.345
 acc_transpose_blocks             18288 15.5    0.076    0.077    1.275    1.342
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.257    1.261
 wfi_extrapolate                     11  7.9    0.001    0.001    1.177    1.177
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    0.956    0.957
 make_images_data                  4572 15.5    0.045    0.049    0.784    0.952
 acc_transpose_blocks_kernels     18288 16.5    0.210    0.219    0.836    0.900
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.867    0.890
 hybrid_alltoall_any               4725 16.4    0.055    0.113    0.678    0.876
 mp_sum_dm                          438  4.9    0.846    0.876    0.846    0.876
 md_write_output                     11  3.9    0.026    0.819    0.029    0.861
 md_output                           10  3.0    0.000    0.000    0.029    0.860
 update_particle_set                 20  4.0    0.000    0.000    0.830    0.857
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.815    0.817
 mp_waitany                        9880 13.7    0.512    0.811    0.512    0.811
 rs_pw_transfer_RS2PW_140           130 11.5    0.120    0.128    0.509    0.784
 mp_alltoall_d11v                  2130 13.8    0.647    0.760    0.647    0.760
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.653    0.732
 mp_alltoall_z22v                  1201 16.6    0.624    0.729    0.624    0.729
 cp_fm_cholesky_invert               11 10.9    0.696    0.699    0.696    0.699
 jit_kernel_transpose                 5 15.6    0.627    0.692    0.627    0.692
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="104", plot="h2o_64_md", label="(8n/4r/3t)", y=33.030000, yerr=0.000000
PlotPoint: name="105", plot="h2o_64_md_mem", label="(8n/4r/3t)", y=497.818182, yerr=2.622219
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_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             546.316288E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1042416
 MPI messages size (bytes):
  total size                       150.443262E+09
  min size                           0.000000E+00
  max size                           1.188816E+06
  average size                     144.321719E+03
 MPI breakdown and total messages size (bytes):
             size <=      128              228256                        0
       128 < size <=     8192              126888               1039466496
      8192 < size <=    32768              191472               3137077248
     32768 < size <=   131072              295800              25899827200
    131072 < size <=  4194304              200000             120367247040
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3672                  62659.
 MP_Allreduce        10224                    344.
 MP_Sync               104
 MP_Alltoall          1582                2412273.
 MP_SendRecv          8211                  74133.
 MP_ISendRecv         8211                  74133.
 MP_Wait             16271
 MP_comm_split          50
 MP_ISend             7280                 135929.
 MP_IRecv             7280                 135929.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.041    0.076   39.047   39.050
 qs_mol_dyn_low                       1  2.0    0.003    0.004   38.727   38.735
 qs_forces                           11  3.9    0.003    0.012   38.578   38.578
 qs_energies                         11  4.9    0.002    0.004   36.846   36.853
 scf_env_do_scf                      11  5.9    0.001    0.003   31.785   31.786
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.007   28.389   28.390
 dbcsr_multiply_generic            2286 12.5    0.101    0.104   21.985   22.124
 qs_scf_new_mos                     108  7.5    0.001    0.001   19.990   20.039
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   19.990   20.038
 ot_scf_mini                        108  9.5    0.003    0.004   19.066   19.114
 multiply_cannon                   2286 13.5    0.227    0.272   15.610   18.532
 velocity_verlet                     10  3.0    0.018    0.098   17.683   17.685
 multiply_cannon_loop              2286 14.5    0.933    0.965   14.663   17.590
 ot_mini                            108 10.5    0.001    0.001   13.183   13.247
 qs_ot_get_derivative               108 11.5    0.001    0.001   11.382   11.434
 multiply_cannon_multrec          27432 15.5    2.793    3.672    9.412   10.433
 dbcsr_mm_accdrv_process          47916 15.9    5.663    7.785    6.524    8.314
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.556    6.607
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.016    6.556    6.607
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    3.263    6.569
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    4.933    6.006
 apply_single                       119 13.6    0.000    0.000    4.933    6.006
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.813    5.859
 mp_sum_l                          7207 12.9    3.865    5.024    3.865    5.024
 sum_up_and_integrate               119 10.3    0.036    0.038    3.779    3.789
 integrate_v_rspace                 119 11.3    0.002    0.003    3.743    3.754
 init_scf_run                        11  5.9    0.000    0.001    3.694    3.694
 scf_env_initial_rho_setup           11  6.9    0.000    0.000    3.694    3.694
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.510    3.541
 calculate_rho_elec                 119  8.7    0.040    0.046    3.510    3.540
 init_scf_loop                       11  6.9    0.001    0.002    3.375    3.378
 qs_ot_get_p                        119 10.4    0.001    0.001    3.303    3.374
 acc_transpose_blocks             27432 15.5    0.112    0.115    1.570    2.952
 mp_waitall_1                    137007 16.6    1.990    2.920    1.990    2.920
 prepare_preconditioner              11  7.9    0.000    0.001    2.509    2.517
 make_preconditioner                 11  8.9    0.000    0.001    2.509    2.516
 make_full_inverse_cholesky          11  9.9    0.000    0.001    2.122    2.444
 calculate_first_density_matrix       1  7.0    0.002    0.006    2.344    2.345
 acc_transpose_blocks_kernels     27432 16.5    0.268    0.278    0.948    2.324
 make_m2s                          4572 13.5    0.054    0.056    2.107    2.240
 rs_pw_transfer                     974 11.9    0.009    0.009    2.004    2.185
 calculate_dm_sparse                119  9.5    0.000    0.000    2.097    2.158
 make_images                       4572 14.5    0.269    0.330    2.001    2.132
 density_rs2pw                      119  9.7    0.004    0.004    1.936    2.109
 pw_transfer                       1439 11.6    0.065    0.072    2.018    2.054
 qs_ot_p2m_diag                      50 11.0    0.015    0.023    2.038    2.047
 jit_kernel_transpose                 5 15.6    0.680    2.046    0.680    2.046
 multiply_cannon_metrocomm3       27432 15.5    0.038    0.039    0.971    2.004
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.925    1.966
 grid_integrate_task_list           119 12.3    1.814    1.924    1.814    1.924
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.884    1.909
 jit_kernel_multiply                 10 16.0    0.800    1.858    0.800    1.858
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.785    1.787
 ot_diis_step                       108 11.5    0.012    0.012    1.759    1.760
 cp_dbcsr_syevd                      50 12.0    0.004    0.006    1.726    1.726
 fft3d_ps                          1201 14.6    0.556    0.610    1.599    1.637
 fft_wrap_pw1pw2_140                487 13.2    0.089    0.096    1.590    1.634
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.621    1.632
 potential_pw2rs                    119 12.3    0.008    0.010    1.552    1.556
 cp_fm_diag_elpa                     50 13.0    0.001    0.002    1.474    1.475
 cp_fm_redistribute_end              50 14.0    0.974    1.450    0.976    1.450
 cp_fm_diag_elpa_base                50 14.0    0.452    1.384    0.471    1.425
 multiply_cannon_metrocomm1       27432 15.5    0.033    0.034    0.257    1.366
 grid_collocate_task_list           119  9.7    1.221    1.343    1.221    1.343
 wfi_extrapolate                     11  7.9    0.001    0.002    1.301    1.301
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.290    1.300
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    1.114    1.115
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.092    1.110
 cp_fm_upper_to_full                 72 13.5    0.799    1.106    0.799    1.106
 multiply_cannon_sync_h2d         27432 15.5    1.004    1.066    1.004    1.066
 dbcsr_complete_redistribute        329 12.2    0.121    0.147    0.754    1.025
 make_images_data                  4572 15.5    0.045    0.048    0.802    0.937
 hybrid_alltoall_any               4725 16.4    0.062    0.153    0.686    0.890
 mp_alltoall_d11v                  2130 13.8    0.698    0.876    0.698    0.876
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.793    0.872
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.833    0.838
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    0.557    0.821
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="106", plot="h2o_64_md", label="(8n/3r/4t)", y=39.050000, yerr=0.000000
PlotPoint: name="107", plot="h2o_64_md_mem", label="(8n/3r/4t)", y=520.090909, yerr=2.353123
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_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             596.369408E+06
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  219456
 MPI messages size (bytes):
  total size                        97.042514E+09
  min size                           0.000000E+00
  max size                           3.276800E+06
  average size                     442.195750E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768              101892               3336634368
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304              116112              93705670464
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         8156                     20.
 MP_Alltoall          8655                  64935.
 MP_ISend            36532                 168375.
 MP_IRecv            36532                 168349.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3672                  62658.
 MP_Allreduce        10224                    344.
 MP_Sync               104
 MP_Alltoall          1582                3682667.
 MP_SendRecv          5355                  94533.
 MP_ISendRecv         5355                  94533.
 MP_Wait             11335
 MP_comm_split          50
 MP_ISend             5200                 225425.
 MP_IRecv             5200                 225425.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.013    0.031   28.362   28.364
 qs_mol_dyn_low                       1  2.0    0.003    0.003   28.160   28.168
 qs_forces                           11  3.9    0.002    0.002   28.101   28.102
 qs_energies                         11  4.9    0.001    0.002   26.386   26.388
 scf_env_do_scf                      11  5.9    0.000    0.001   21.572   21.572
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.007   19.046   19.047
 velocity_verlet                     10  3.0    0.002    0.002   14.554   14.557
 dbcsr_multiply_generic            2286 12.5    0.101    0.105   12.183   12.261
 qs_scf_new_mos                     108  7.5    0.001    0.001   10.967   10.988
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   10.967   10.988
 ot_scf_mini                        108  9.5    0.002    0.002   10.287   10.313
 multiply_cannon                   2286 13.5    0.231    0.237    9.608   10.058
 multiply_cannon_loop              2286 14.5    0.327    0.339    8.654    8.862
 multiply_cannon_multrec           9144 15.5    1.585    1.834    5.881    6.118
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.028    6.054
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.013    6.027    6.053
 ot_mini                            108 10.5    0.001    0.001    5.648    5.678
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.374    5.397
 qs_ot_get_derivative               108 11.5    0.001    0.001    4.343    4.369
 dbcsr_mm_accdrv_process          12550 15.8    3.003    3.869    4.196    4.279
 sum_up_and_integrate               119 10.3    0.038    0.040    3.695    3.699
 integrate_v_rspace                 119 11.3    0.003    0.003    3.657    3.661
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.567    3.576
 calculate_rho_elec                 119  8.7    0.059    0.061    3.567    3.575
 init_scf_run                        11  5.9    0.000    0.001    3.378    3.378
 scf_env_initial_rho_setup           11  6.9    0.000    0.000    3.378    3.378
 qs_ot_get_p                        119 10.4    0.001    0.001    2.867    2.904
 init_scf_loop                       11  6.9    0.000    0.000    2.504    2.505
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.235    2.237
 pw_transfer                       1439 11.6    0.066    0.069    2.136    2.144
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    2.042    2.053
 density_rs2pw                      119  9.7    0.004    0.004    1.896    2.035
 make_m2s                          4572 13.5    0.034    0.035    1.767    1.967
 grid_integrate_task_list           119 12.3    1.841    1.907    1.841    1.907
 jit_kernel_multiply                 10 15.7    1.155    1.902    1.155    1.902
 qs_ot_p2m_diag                      50 11.0    0.022    0.023    1.887    1.889
 make_images                       4572 14.5    0.268    0.301    1.677    1.876
 mp_waitall_1                    115863 16.7    1.358    1.850    1.358    1.850
 rs_pw_transfer                     974 11.9    0.008    0.008    1.713    1.846
 calculate_dm_sparse                119  9.5    0.000    0.000    1.786    1.806
 prepare_preconditioner              11  7.9    0.000    0.000    1.757    1.762
 make_preconditioner                 11  8.9    0.000    0.000    1.757    1.762
 fft3d_ps                          1201 14.6    0.561    0.570    1.701    1.709
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.691    1.691
 fft_wrap_pw1pw2_140                487 13.2    0.087    0.090    1.673    1.685
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.646    1.673
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.626    1.627
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    1.554    1.567
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.445    1.455
 potential_pw2rs                    119 12.3    0.010    0.011    1.450    1.453
 grid_collocate_task_list           119  9.7    1.267    1.386    1.267    1.386
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.374    1.375
 cp_fm_redistribute_end              50 14.0    0.686    1.349    0.687    1.350
 cp_fm_diag_elpa_base                50 14.0    0.619    1.275    0.662    1.331
 ot_diis_step                       108 11.5    0.013    0.013    1.292    1.292
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    1.224    1.225
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.202    1.207
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    1.160    1.179
 apply_single                       119 13.6    0.000    0.000    1.160    1.179
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.147    1.161
 wfi_extrapolate                     11  7.9    0.001    0.001    1.094    1.094
 hybrid_alltoall_any               4725 16.4    0.062    0.174    0.788    1.066
 make_images_data                  4572 15.5    0.039    0.043    0.807    1.034
 acc_transpose_blocks              9144 15.5    0.038    0.039    0.915    0.921
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.869    0.917
 cp_fm_cholesky_invert               11 10.9    0.902    0.905    0.902    0.905
 mp_alltoall_d11v                  2130 13.8    0.780    0.871    0.780    0.871
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.776    0.779
 multiply_cannon_sync_h2d          9144 15.5    0.707    0.778    0.707    0.778
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.731    0.740
 qs_env_update_s_mstruct             11  6.9    0.000    0.001    0.672    0.718
 mp_allgather_i34                  2286 14.5    0.288    0.697    0.288    0.697
 acc_transpose_blocks_kernels      9144 16.5    0.117    0.120    0.676    0.678
 mp_alltoall_z22v                  1201 16.6    0.589    0.640    0.589    0.640
 multiply_cannon_metrocomm3        9144 15.5    0.019    0.019    0.300    0.598
 yz_to_x                            606 15.1    0.265    0.276    0.566    0.583
 dbcsr_complete_redistribute        329 12.2    0.176    0.188    0.544    0.572
 x_to_yz                            595 16.2    0.275    0.288    0.563    0.569
 qs_create_task_list                 11  7.9    0.000    0.001    0.546    0.569
 generate_qs_task_list               11  8.9    0.188    0.210    0.546    0.568
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="108", plot="h2o_64_md", label="(8n/2r/6t)", y=28.364000, yerr=0.000000
PlotPoint: name="109", plot="h2o_64_md_mem", label="(8n/2r/6t)", y=567.090909, yerr=2.810841
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_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             739.897344E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                   91440
 MPI messages size (bytes):
  total size                        85.748679E+09
  min size                           0.000000E+00
  max size                           6.553600E+06
  average size                     937.758938E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                 572                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768               21148                692256768
     32768 < size <=   131072               19224               1259864064
    131072 < size <=  4194304               41040              21941452800
   4194304 < size <= 16777216                9456              61855174464
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3622                  63729.
 MP_Allreduce        10074                    433.
 MP_Sync                54
 MP_Alltoall          1582                7383731.
 MP_SendRecv          2499                 189067.
 MP_ISendRecv         2499                 189067.
 MP_Wait              6399
 MP_ISend             3120                 546875.
 MP_IRecv             3120                 546875.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.028    0.056   41.302   41.310
 qs_mol_dyn_low                       1  2.0    0.003    0.003   41.025   41.033
 qs_forces                           11  3.9    0.002    0.002   40.965   40.966
 qs_energies                         11  4.9    0.002    0.002   38.973   38.977
 scf_env_do_scf                      11  5.9    0.001    0.001   33.310   33.310
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.007   25.499   25.500
 velocity_verlet                     10  3.0    0.002    0.002   23.287   23.293
 dbcsr_multiply_generic            2286 12.5    0.102    0.104   17.372   17.617
 qs_scf_new_mos                     108  7.5    0.001    0.001   15.676   15.784
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   15.676   15.783
 ot_scf_mini                        108  9.5    0.002    0.002   14.596   14.707
 multiply_cannon                   2286 13.5    0.303    0.308   13.667   14.652
 multiply_cannon_loop              2286 14.5    0.344    0.351   12.439   13.460
 ot_mini                            108 10.5    0.001    0.001    8.812    8.939
 multiply_cannon_multrec           9144 15.5    3.488    4.811    8.663    8.842
 init_scf_loop                       11  6.9    0.000    0.000    7.785    7.788
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.342    7.494
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.013    7.341    7.493
 qs_ot_get_derivative               108 11.5    0.001    0.001    6.813    6.923
 prepare_preconditioner              11  7.9    0.000    0.000    6.811    6.825
 make_preconditioner                 11  8.9    0.000    0.000    6.811    6.825
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.636    6.774
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.376    6.704
 dbcsr_mm_accdrv_process          12550 15.8    4.015    5.326    5.053    6.458
 cp_fm_upper_to_full                 72 14.2    3.182    4.558    3.182    4.558
 qs_rho_update_rho_low              119  7.7    0.001    0.001    4.260    4.269
 calculate_rho_elec                 119  8.7    0.118    0.121    4.260    4.268
 sum_up_and_integrate               119 10.3    0.065    0.066    4.043    4.050
 integrate_v_rspace                 119 11.3    0.003    0.003    3.978    3.985
 init_scf_run                        11  5.9    0.000    0.001    3.638    3.638
 scf_env_initial_rho_setup           11  6.9    0.000    0.001    3.638    3.638
 mp_waitall_1                     94719 16.7    2.232    3.258    2.232    3.258
 qs_ot_get_p                        119 10.4    0.001    0.001    3.099    3.247
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.487    2.893
 pw_transfer                       1439 11.6    0.068    0.069    2.829    2.834
 dbcsr_complete_redistribute        329 12.2    0.291    0.297    1.952    2.769
 fft_wrap_pw1pw2                   1201 12.6    0.009    0.009    2.730    2.736
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    1.653    2.450
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.146    2.414
 apply_single                       119 13.6    0.000    0.000    2.146    2.414
 fft3d_ps                          1201 14.6    0.595    0.603    2.354    2.359
 fft_wrap_pw1pw2_140                487 13.2    0.095    0.097    2.313    2.322
 make_m2s                          4572 13.5    0.038    0.039    2.163    2.315
 multiply_cannon_metrocomm3        9144 15.5    0.020    0.020    1.247    2.238
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.430    2.220
 mp_alltoall_i22                    627 13.8    1.405    2.219    1.405    2.219
 calculate_dm_sparse                119  9.5    0.000    0.000    2.196    2.215
 density_rs2pw                      119  9.7    0.004    0.004    2.195    2.212
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.205    2.206
 make_images                       4572 14.5    0.352    0.384    2.042    2.193
 grid_integrate_task_list           119 12.3    2.055    2.067    2.055    2.067
 ot_diis_step                       108 11.5    0.014    0.015    1.973    1.973
 qs_ot_p2m_diag                      50 11.0    0.043    0.043    1.878    1.878
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.852    1.853
 jit_kernel_multiply                 10 15.7    1.011    1.817    1.011    1.817
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    1.764    1.765
 mp_sum_l                          7207 12.9    0.996    1.751    0.996    1.751
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.649    1.703
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.593    1.640
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.603    1.604
 grid_collocate_task_list           119  9.7    1.488    1.502    1.488    1.502
 potential_pw2rs                    119 12.3    0.014    0.015    1.447    1.450
 rs_pw_transfer                     974 11.9    0.009    0.010    1.430    1.448
 cp_fm_cholesky_invert               11 10.9    1.433    1.436    1.433    1.436
 wfi_extrapolate                     11  7.9    0.001    0.001    1.369    1.369
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.326    1.326
 cp_fm_diag_elpa_base                50 14.0    1.183    1.234    1.324    1.324
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.262    1.272
 hybrid_alltoall_any               4725 16.4    0.087    0.147    1.061    1.236
 make_images_data                  4572 15.5    0.044    0.046    0.981    1.167
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.117    1.135
 qs_env_update_s_mstruct             11  6.9    0.001    0.001    1.099    1.110
 mp_alltoall_d11v                  2130 13.8    1.054    1.078    1.054    1.078
 multiply_cannon_sync_h2d          9144 15.5    1.043    1.050    1.043    1.050
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.990    1.037
 acc_transpose_blocks              9144 15.5    0.038    0.039    0.952    0.962
 yz_to_x                            606 15.1    0.459    0.472    0.942    0.954
 qs_create_task_list                 11  7.9    0.001    0.001    0.937    0.948
 generate_qs_task_list               11  8.9    0.370    0.389    0.936    0.948
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.917    0.931
 mp_alltoall_z22v                  1201 16.6    0.810    0.855    0.810    0.855
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="110", plot="h2o_64_md", label="(8n/1r/12t)", y=41.310000, yerr=0.000000
PlotPoint: name="111", plot="h2o_64_md_mem", label="(8n/1r/12t)", y=696.727273, yerr=12.262959
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_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             502.104064E+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                1379060.
 MP_SendRecv         20900                   9096.
 MP_ISendRecv        20900                   9096.
 MP_Wait             37268
 MP_comm_split          48
 MP_ISend            14300                  82312.
 MP_IRecv            14300                  82312.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.011    0.029   82.492   82.494
 qs_mol_dyn_low                       1  2.0    0.003    0.003   82.229   82.240
 qs_forces                           11  3.9    0.002    0.003   82.149   82.150
 qs_energies                         11  4.9    0.001    0.002   79.338   79.347
 scf_env_do_scf                      11  5.9    0.001    0.002   70.622   70.624
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.008   65.140   65.140
 dbcsr_multiply_generic            2055 12.4    0.108    0.110   51.790   52.096
 qs_scf_new_mos                      99  7.5    0.000    0.001   47.976   48.119
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   47.975   48.118
 ot_scf_mini                         99  9.5    0.002    0.002   45.556   45.652
 multiply_cannon                   2055 13.4    0.179    0.184   42.476   43.639
 multiply_cannon_loop              2055 14.4    1.541    1.597   41.565   42.750
 velocity_verlet                     10  3.0    0.001    0.002   41.698   41.699
 ot_mini                             99 10.5    0.001    0.001   27.498   27.615
 qs_ot_get_derivative                99 11.5    0.001    0.001   20.656   20.768
 multiply_cannon_multrec          49320 15.4   12.221   12.894   17.241   18.010
 rebuild_ks_matrix                  110  8.3    0.000    0.001   14.408   14.537
 qs_ks_build_kohn_sham_matrix       110  9.3    0.011    0.012   14.407   14.537
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.648   12.766
 mp_waitall_1                    220248 16.4   11.230   12.420   11.230   12.420
 multiply_cannon_sync_h2d         49320 15.4   10.022   10.641   10.022   10.641
 qs_ot_get_p                        110 10.4    0.001    0.001    9.531    9.645
 multiply_cannon_metrocomm3       49320 15.4    0.078    0.083    6.879    8.363
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    7.204    7.701
 apply_single                       110 13.6    0.000    0.000    7.204    7.701
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    6.899    7.490
 sum_up_and_integrate               110 10.3    0.036    0.042    6.970    6.983
 integrate_v_rspace                 110 11.3    0.003    0.003    6.934    6.955
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    6.817    6.863
 init_scf_run                        11  5.9    0.000    0.001    6.714    6.714
 scf_env_initial_rho_setup           11  6.9    0.000    0.001    6.714    6.714
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.494    6.661
 calculate_rho_elec                 110  8.6    0.021    0.026    6.494    6.661
 ot_diis_step                        99 11.5    0.006    0.006    6.524    6.524
 qs_ot_p2m_diag                      48 11.0    0.012    0.019    6.311    6.332
 mp_sum_l                          6514 12.8    5.115    6.079    5.115    6.079
 init_scf_loop                       11  6.9    0.000    0.000    5.456    5.457
 cp_dbcsr_syevd                      48 12.0    0.002    0.003    5.363    5.363
 dbcsr_mm_accdrv_process          87628 16.1    2.045    2.173    4.898    5.262
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    4.899    4.901
 cp_fm_redistribute_end              48 14.0    4.277    4.876    4.281    4.876
 cp_fm_diag_elpa_base                48 14.0    0.589    4.734    0.593    4.757
 rs_pw_transfer                     902 11.9    0.011    0.013    3.558    4.146
 wfi_extrapolate                     11  7.9    0.001    0.001    3.981    3.981
 calculate_dm_sparse                110  9.5    0.000    0.001    3.809    3.934
 density_rs2pw                      110  9.6    0.004    0.005    3.316    3.907
 make_m2s                          4110 13.4    0.061    0.065    3.735    3.830
 make_images                       4110 14.4    0.177    0.190    3.640    3.738
 multiply_cannon_metrocomm1       49320 15.4    0.060    0.064    2.632    3.716
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    3.515    3.518
 grid_integrate_task_list           110 12.3    3.249    3.400    3.249    3.400
 qs_ot_get_orbitals                  99 10.5    0.000    0.001    3.295    3.357
 prepare_preconditioner              11  7.9    0.000    0.000    3.318    3.335
 make_preconditioner                 11  8.9    0.000    0.000    3.318    3.335
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    3.196    3.234
 pw_transfer                       1331 11.6    0.054    0.069    3.135    3.195
 make_full_inverse_cholesky          11  9.9    0.000    0.000    3.100    3.150
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.047    3.108
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.648    2.653
 fft_wrap_pw1pw2_140                451 13.1    0.173    0.194    2.580    2.649
 jit_kernel_multiply                 13 15.9    2.571    2.642    2.571    2.642
 fft3d_ps                          1111 14.6    0.778    0.879    2.572    2.628
 potential_pw2rs                    110 12.3    0.006    0.007    2.576    2.595
 mp_alltoall_d11v                  2046 13.8    1.941    2.395    1.941    2.395
 mp_waitany                       14300 13.8    1.746    2.382    1.746    2.382
 grid_collocate_task_list           110  9.6    2.083    2.290    2.083    2.290
 acc_transpose_blocks             49320 15.4    0.223    0.234    2.172    2.257
 mp_sum_d                          3881 11.9    1.476    1.960    1.476    1.960
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.900    1.918
 make_images_data                  4110 15.4    0.042    0.046    1.684    1.825
 cp_fm_cholesky_invert               11 10.9    1.811    1.815    1.811    1.815
 hybrid_alltoall_any               4261 16.3    0.081    0.475    1.477    1.752
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.656    1.680
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="200", plot="h2o_128_md", label="(8n/12r/1t)", y=82.494000, yerr=0.000000
PlotPoint: name="201", plot="h2o_128_md_mem", label="(8n/12r/1t)", y=477.000000, yerr=2.628515
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_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             585.351168E+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                2462973.
 MP_SendRecv         10340                  26400.
 MP_ISendRecv        10340                  26400.
 MP_Wait             22352
 MP_comm_split          48
 MP_ISend            10164                 155761.
 MP_IRecv            10164                 155761.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.028    0.066   68.373   68.374
 qs_mol_dyn_low                       1  2.0    0.003    0.003   68.091   68.101
 qs_forces                           11  3.9    0.002    0.002   68.015   68.016
 qs_energies                         11  4.9    0.003    0.019   64.663   64.667
 scf_env_do_scf                      11  5.9    0.001    0.001   56.270   56.274
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.007   48.684   48.686
 dbcsr_multiply_generic            2055 12.4    0.114    0.119   37.424   37.588
 velocity_verlet                     10  3.0    0.005    0.018   35.904   35.905
 qs_scf_new_mos                      99  7.5    0.001    0.001   32.508   32.656
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   32.508   32.655
 multiply_cannon                   2055 13.4    0.221    0.240   30.978   31.956
 ot_scf_mini                         99  9.5    0.003    0.004   30.860   31.005
 multiply_cannon_loop              2055 14.4    0.929    0.952   29.709   30.625
 ot_mini                             99 10.5    0.001    0.001   18.106   18.257
 multiply_cannon_multrec          24660 15.4    7.687    9.321   13.884   15.476
 rebuild_ks_matrix                  110  8.3    0.000    0.000   13.743   13.863
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.014   13.743   13.862
 qs_ot_get_derivative                99 11.5    0.001    0.001   12.303   12.448
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.075   12.183
 mp_waitall_1                    176588 16.5    7.352   10.031    7.352   10.031
 multiply_cannon_sync_h2d         24660 15.4    7.086    8.145    7.086    8.145
 multiply_cannon_metrocomm3       24660 15.4    0.070    0.072    5.094    7.793
 init_scf_loop                       11  6.9    0.000    0.002    7.552    7.557
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    6.515    7.171
 apply_single                       110 13.6    0.000    0.001    6.515    7.171
 sum_up_and_integrate               110 10.3    0.051    0.057    6.575    6.589
 integrate_v_rspace                 110 11.3    0.002    0.003    6.523    6.540
 qs_ot_get_p                        110 10.4    0.001    0.001    6.190    6.365
 dbcsr_mm_accdrv_process          52282 16.1    4.646    5.425    6.036    6.313
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.066    6.075
 calculate_rho_elec                 110  8.6    0.039    0.047    6.066    6.074
 init_scf_run                        11  5.9    0.000    0.001    6.025    6.026
 scf_env_initial_rho_setup           11  6.9    0.000    0.001    6.025    6.025
 ot_diis_step                        99 11.5    0.010    0.010    5.757    5.757
 prepare_preconditioner              11  7.9    0.000    0.000    5.501    5.522
 make_preconditioner                 11  8.9    0.000    0.002    5.501    5.522
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    4.629    5.364
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.096    5.243
 make_m2s                          4110 13.4    0.057    0.060    4.008    4.456
 make_images                       4110 14.4    0.396    0.439    3.899    4.345
 qs_ot_p2m_diag                      48 11.0    0.028    0.044    4.291    4.311
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.867    3.867
 pw_transfer                       1331 11.6    0.066    0.073    3.651    3.801
 density_rs2pw                      110  9.6    0.004    0.004    3.239    3.725
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.544    3.698
 wfi_extrapolate                     11  7.9    0.001    0.001    3.479    3.479
 rs_pw_transfer                     902 11.9    0.012    0.013    2.894    3.401
 grid_integrate_task_list           110 12.3    3.154    3.330    3.154    3.330
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.327    3.329
 cp_fm_redistribute_end              48 14.0    2.488    3.301    2.490    3.302
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.157    3.249
 cp_fm_diag_elpa_base                48 14.0    0.777    3.161    0.808    3.247
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    3.192    3.193
 fft_wrap_pw1pw2_140                451 13.1    0.204    0.221    3.030    3.187
 fft3d_ps                          1111 14.6    1.102    1.318    2.890    3.028
 calculate_dm_sparse                110  9.5    0.001    0.001    2.953    2.981
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.859    2.904
 make_images_data                  4110 15.4    0.046    0.050    2.194    2.658
 hybrid_alltoall_any               4261 16.3    0.102    0.444    1.943    2.608
 cp_fm_cholesky_invert               11 10.9    2.540    2.547    2.540    2.547
 grid_collocate_task_list           110  9.6    2.051    2.483    2.051    2.483
 mp_sum_l                          6514 12.8    1.839    2.481    1.839    2.481
 calculate_first_density_matrix       1  7.0    0.000    0.003    2.460    2.462
 potential_pw2rs                    110 12.3    0.008    0.009    2.409    2.424
 jit_kernel_multiply                 11 16.2    1.039    2.142    1.039    2.142
 qs_ot_get_orbitals                  99 10.5    0.000    0.001    1.931    1.957
 mp_alltoall_d11v                  2046 13.8    1.650    1.939    1.650    1.939
 qs_energies_init_hamiltonians       11  5.9    0.000    0.001    1.854    1.855
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.832    1.846
 mp_waitany                       10164 13.8    1.190    1.691    1.190    1.691
 multiply_cannon_metrocomm4       22605 15.4    0.075    0.078    0.770    1.662
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.535    1.548
 mp_irecv_dv                      57340 16.2    0.645    1.547    0.645    1.547
 acc_transpose_blocks             24660 15.4    0.112    0.115    1.521    1.541
 mp_allgather_i34                  2055 14.4    0.601    1.493    0.601    1.493
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.369    1.477
 rs_pw_transfer_RS2PW_140           121 11.5    0.207    0.217    0.949    1.460
 dbcsr_complete_redistribute        325 12.2    0.244    0.297    1.107    1.373
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="202", plot="h2o_128_md", label="(8n/6r/2t)", y=68.374000, yerr=0.000000
PlotPoint: name="203", plot="h2o_128_md_mem", label="(8n/6r/2t)", y=553.454545, yerr=7.088578
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_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             659.910656E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                  854880
 MPI messages size (bytes):
  total size                       708.322787E+09
  min size                           0.000000E+00
  max size                           6.553600E+06
  average size                     828.564000E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768              222984               7302414336
     32768 < size <=   131072              153888              10085203968
    131072 < size <=  4194304              389376             200257044480
   4194304 < size <= 16777216               82208             490679162176
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3521                  65578.
 MP_Allreduce         9838                    559.
 MP_Sync               100
 MP_Alltoall          1496                4511006.
 MP_SendRecv          6820                  27424.
 MP_ISendRecv         6820                  27424.
 MP_Wait             25498
 MP_comm_split          48
 MP_ISend            17072                 115022.
 MP_IRecv            17072                 115022.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.077    0.113   61.323   61.324
 qs_mol_dyn_low                       1  2.0    0.003    0.003   60.634   60.644
 qs_forces                           11  3.9    0.002    0.003   60.549   60.550
 qs_energies                         11  4.9    0.001    0.002   57.325   57.329
 scf_env_do_scf                      11  5.9    0.000    0.001   48.672   48.673
 scf_env_do_scf_inner_loop           99  6.5    0.005    0.021   40.051   40.051
 velocity_verlet                     10  3.0    0.007    0.013   32.709   32.711
 dbcsr_multiply_generic            2055 12.4    0.119    0.122   28.504   28.739
 qs_scf_new_mos                      99  7.5    0.001    0.001   24.989   25.075
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   24.988   25.074
 ot_scf_mini                         99  9.5    0.002    0.003   23.763   23.865
 multiply_cannon                   2055 13.4    0.212    0.224   22.224   23.306
 multiply_cannon_loop              2055 14.4    0.615    0.628   21.038   22.077
 ot_mini                             99 10.5    0.001    0.001   13.615   13.719
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.426   12.540
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.014   12.426   12.539
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.942   11.049
 multiply_cannon_multrec          16440 15.4    3.994    4.988    9.946   10.829
 mp_waitall_1                    139946 16.5    6.797    9.468    6.797    9.468
 qs_ot_get_derivative                99 11.5    0.001    0.001    9.168    9.266
 init_scf_loop                       11  6.9    0.000    0.000    8.586    8.586
 prepare_preconditioner              11  7.9    0.000    0.000    6.799    6.814
 make_preconditioner                 11  8.9    0.000    0.000    6.798    6.813
 multiply_cannon_metrocomm3       16440 15.4    0.043    0.044    4.192    6.785
 sum_up_and_integrate               110 10.3    0.059    0.060    6.618    6.636
 integrate_v_rspace                 110 11.3    0.002    0.003    6.558    6.577
 make_full_inverse_cholesky          11  9.9    0.000    0.000    6.138    6.495
 init_scf_run                        11  5.9    0.000    0.001    6.264    6.264
 scf_env_initial_rho_setup           11  6.9    0.000    0.001    6.263    6.264
 dbcsr_mm_accdrv_process          34862 16.1    4.750    5.510    5.806    6.056
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.951    5.961
 calculate_rho_elec                 110  8.6    0.058    0.059    5.951    5.960
 qs_ot_get_p                        110 10.4    0.001    0.001    5.384    5.505
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.977    5.375
 apply_single                       110 13.6    0.000    0.000    4.977    5.375
 make_m2s                          4110 13.4    0.050    0.053    4.111    4.491
 ot_diis_step                        99 11.5    0.011    0.011    4.418    4.418
 make_images                       4110 14.4    0.390    0.508    3.996    4.375
 density_rs2pw                      110  9.6    0.004    0.005    3.085    4.297
 multiply_cannon_sync_h2d         16440 15.4    3.695    4.199    3.695    4.199
 rs_pw_transfer                     902 11.9    0.010    0.011    2.746    3.943
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.137    3.800
 qs_ot_p2m_diag                      48 11.0    0.042    0.044    3.750    3.754
 pw_transfer                       1331 11.6    0.065    0.073    3.629    3.639
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.523    3.534
 grid_integrate_task_list           110 12.3    3.184    3.416    3.184    3.416
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.410    3.410
 calculate_first_density_matrix       1  7.0    0.000    0.000    3.195    3.196
 fft_wrap_pw1pw2_140                451 13.1    0.213    0.216    3.020    3.032
 wfi_extrapolate                     11  7.9    0.001    0.001    2.983    2.983
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.979    2.980
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    2.887    2.889
 cp_fm_redistribute_end              48 14.0    1.803    2.862    1.805    2.863
 fft3d_ps                          1111 14.6    1.087    1.101    2.822    2.833
 make_images_data                  4110 15.4    0.043    0.047    2.332    2.818
 cp_fm_diag_elpa_base                48 14.0    0.995    2.710    1.054    2.815
 hybrid_alltoall_any               4261 16.3    0.105    0.373    2.080    2.703
 cp_fm_cholesky_invert               11 10.9    2.674    2.680    2.674    2.680
 calculate_dm_sparse                110  9.5    0.001    0.001    2.562    2.602
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.556    2.601
 grid_collocate_task_list           110  9.6    2.083    2.453    2.083    2.453
 mp_waitany                       17072 13.8    1.195    2.448    1.195    2.448
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.345    2.400
 potential_pw2rs                    110 12.3    0.010    0.010    2.378    2.388
 multiply_cannon_metrocomm4       14385 15.4    0.045    0.049    0.867    2.243
 mp_sum_l                          6514 12.8    1.613    2.185    1.613    2.185
 mp_irecv_dv                      48980 15.7    0.797    2.121    0.797    2.121
 rs_pw_transfer_RS2PW_140           121 11.5    0.178    0.182    0.876    2.066
 dbcsr_complete_redistribute        325 12.2    0.345    0.460    1.522    1.999
 qs_energies_init_hamiltonians       11  5.9    0.000    0.001    1.946    1.946
 mp_alltoall_d11v                  2046 13.8    1.659    1.905    1.659    1.905
 cp_fm_upper_to_full                 70 13.6    1.420    1.885    1.420    1.885
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.683    1.697
 cp_fm_cholesky_decompose            22 10.9    1.594    1.613    1.594    1.613
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.518    1.529
 mp_allgather_i34                  2055 14.4    0.515    1.526    0.515    1.526
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    1.045    1.507
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.371    1.498
 make_basis_sm                       11  9.8    0.000    0.000    1.297    1.300
 parallel_gemm_fm                    81  9.0    0.000    0.000    1.298    1.300
 parallel_gemm_fm_cosma              81 10.0    1.298    1.300    1.298    1.300
 jit_kernel_multiply                  6 16.6    0.666    1.298    0.666    1.298
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.268    1.274
 acc_transpose_blocks             16440 15.4    0.072    0.074    1.229    1.255
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="204", plot="h2o_128_md", label="(8n/4r/3t)", y=61.324000, yerr=0.000000
PlotPoint: name="205", plot="h2o_128_md_mem", label="(8n/4r/3t)", y=623.090909, yerr=7.890783
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_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             725.897216E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                  937080
 MPI messages size (bytes):
  total size                       523.723932E+09
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     558.889250E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6996                        0
       128 < size <=     8192                 264                  2162688
      8192 < size <=    32768              304932               8165326848
     32768 < size <=   131072              110640               6338641920
    131072 < size <=  4194304              489498             400769458320
   4194304 < size <= 16777216               24750             108449092400
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3521                  65576.
 MP_Allreduce         9838                    600.
 MP_Sync               100
 MP_Alltoall          1496                5863162.
 MP_SendRecv          5060                  43184.
 MP_ISendRecv         5060                  43184.
 MP_Wait             20042
 MP_comm_split          48
 MP_ISend            13376                 163145.
 MP_IRecv            13376                 163145.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.062    0.134   65.093   65.130
 qs_mol_dyn_low                       1  2.0    0.003    0.004   64.627   64.637
 qs_forces                           11  3.9    0.003    0.006   64.536   64.537
 qs_energies                         11  4.9    0.003    0.008   61.090   61.094
 scf_env_do_scf                      11  5.9    0.001    0.003   52.792   52.795
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.008   41.255   41.257
 velocity_verlet                     10  3.0    0.001    0.002   36.804   36.807
 dbcsr_multiply_generic            2055 12.4    0.115    0.119   29.433   29.695
 qs_scf_new_mos                      99  7.5    0.001    0.001   26.090   26.188
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   26.089   26.187
 ot_scf_mini                         99  9.5    0.003    0.004   24.479   24.577
 multiply_cannon                   2055 13.4    0.243    0.260   22.529   23.800
 multiply_cannon_loop              2055 14.4    0.884    0.909   21.204   21.889
 ot_mini                             99 10.5    0.001    0.001   14.105   14.228
 multiply_cannon_multrec          24660 15.4    4.258    6.964   12.786   13.989
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.322   12.425
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.016   12.322   12.424
 init_scf_loop                       11  6.9    0.001    0.004   11.495   11.501
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.869   10.957
 qs_ot_get_derivative                99 11.5    0.001    0.001    9.986   10.090
 prepare_preconditioner              11  7.9    0.000    0.001    9.720    9.738
 make_preconditioner                 11  8.9    0.000    0.002    9.720    9.738
 make_full_inverse_cholesky          11  9.9    0.000    0.001    7.977    9.405
 dbcsr_mm_accdrv_process          52304 16.0    7.002    8.772    8.381    9.346
 sum_up_and_integrate               110 10.3    0.067    0.070    6.569    6.584
 integrate_v_rspace                 110 11.3    0.003    0.003    6.502    6.516
 mp_waitall_1                    121746 16.5    4.300    6.290    4.300    6.290
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.154    6.163
 calculate_rho_elec                 110  8.6    0.077    0.081    6.154    6.162
 make_m2s                          4110 13.4    0.060    0.061    5.337    5.600
 qs_ot_get_p                        110 10.4    0.001    0.002    5.424    5.558
 init_scf_run                        11  5.9    0.000    0.001    5.543    5.543
 scf_env_initial_rho_setup           11  6.9    0.000    0.001    5.543    5.543
 make_images                       4110 14.4    0.573    0.692    5.199    5.458
 cp_fm_upper_to_full                 70 13.8    3.246    4.602    3.246    4.602
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    3.996    4.084
 ot_diis_step                        99 11.5    0.011    0.011    4.084    4.084
 apply_single                       110 13.6    0.000    0.000    3.996    4.084
 pw_transfer                       1331 11.6    0.065    0.073    3.902    3.935
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.797    3.833
 dbcsr_complete_redistribute        325 12.2    0.422    0.467    2.606    3.741
 qs_ot_p2m_diag                      48 11.0    0.055    0.064    3.682    3.697
 density_rs2pw                      110  9.6    0.004    0.004    3.093    3.599
 grid_integrate_task_list           110 12.3    3.258    3.472    3.258    3.472
 multiply_cannon_sync_h2d         24660 15.4    3.182    3.339    3.182    3.339
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.270    3.322
 fft_wrap_pw1pw2_140                451 13.1    0.203    0.213    3.280    3.322
 cp_dbcsr_syevd                      48 12.0    0.003    0.005    3.212    3.212
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    2.084    3.207
 multiply_cannon_metrocomm3       24660 15.4    0.035    0.036    1.521    3.206
 fft3d_ps                          1111 14.6    1.092    1.129    3.086    3.110
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.960    3.014
 make_images_data                  4110 15.4    0.047    0.051    2.698    2.994
 calculate_dm_sparse                110  9.5    0.001    0.001    2.946    2.973
 wfi_extrapolate                     11  7.9    0.001    0.002    2.970    2.970
 hybrid_alltoall_any               4261 16.3    0.119    0.454    2.243    2.957
 rs_pw_transfer                     902 11.9    0.010    0.011    2.378    2.883
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.734    2.841
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.811    2.813
 mp_alltoall_i22                    605 13.7    1.617    2.757    1.617    2.757
 cp_fm_diag_elpa                     48 13.0    0.000    0.001    2.688    2.690
 cp_fm_redistribute_end              48 14.0    1.346    2.664    1.347    2.665
 cp_fm_cholesky_invert               11 10.9    2.653    2.661    2.653    2.661
 cp_fm_diag_elpa_base                48 14.0    1.237    2.532    1.315    2.641
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.454    2.498
 calculate_first_density_matrix       1  7.0    0.001    0.005    2.478    2.481
 grid_collocate_task_list           110  9.6    2.182    2.457    2.182    2.457
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    2.262    2.263
 potential_pw2rs                    110 12.3    0.013    0.013    2.217    2.226
 mp_alltoall_d11v                  2046 13.8    1.696    1.980    1.696    1.980
 jit_kernel_multiply                 10 15.7    1.049    1.969    1.049    1.969
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.680    1.713
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.697    1.710
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.600    1.703
 cp_fm_cholesky_decompose            22 10.9    1.627    1.678    1.627    1.678
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.570    1.588
 mp_waitany                       13376 13.8    1.051    1.569    1.051    1.569
 acc_transpose_blocks             24660 15.4    0.106    0.108    1.534    1.567
 mp_sum_l                          6514 12.8    0.922    1.561    0.922    1.561
 mp_allgather_i34                  2055 14.4    0.435    1.535    0.435    1.535
 multiply_cannon_metrocomm4       20550 15.4    0.059    0.061    0.845    1.510
 mp_irecv_dv                      62702 16.1    0.744    1.427    0.744    1.427
 qs_env_update_s_mstruct             11  6.9    0.001    0.001    1.205    1.310
 rs_pw_transfer_RS2PW_140           121 11.5    0.171    0.180    0.804    1.310
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="206", plot="h2o_128_md", label="(8n/3r/4t)", y=65.130000, yerr=0.000000
PlotPoint: name="207", plot="h2o_128_md_mem", label="(8n/3r/4t)", y=684.636364, yerr=6.905501
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_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             829.616128E+06
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  197280
 MPI messages size (bytes):
  total size                       339.125567E+09
  min size                           0.000000E+00
  max size                          13.107200E+06
  average size                       1.719006E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 132                  4325376
     32768 < size <=   131072               88656              11620319232
    131072 < size <=  4194304               89424             117209825280
   4194304 < size <= 16777216               17616             210291069504
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         7346                     33.
 MP_Alltoall          8043                 263767.
 MP_ISend            32836                 654203.
 MP_IRecv            32836                 654587.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3521                  65574.
 MP_Allreduce         9838                    640.
 MP_Sync               100
 MP_Alltoall          1496                8504061.
 MP_SendRecv          3300                  54848.
 MP_ISendRecv         3300                  54848.
 MP_Wait             13926
 MP_comm_split          48
 MP_ISend             9240                 278857.
 MP_IRecv             9240                 278857.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.013    0.029   55.418   55.420
 qs_mol_dyn_low                       1  2.0    0.003    0.003   55.158   55.167
 qs_forces                           11  3.9    0.002    0.002   55.089   55.090
 qs_energies                         11  4.9    0.001    0.001   51.391   51.396
 scf_env_do_scf                      11  5.9    0.001    0.001   42.809   42.810
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.008   35.150   35.150
 velocity_verlet                     10  3.0    0.002    0.002   31.012   31.015
 dbcsr_multiply_generic            2055 12.4    0.106    0.108   22.809   22.972
 qs_scf_new_mos                      99  7.5    0.001    0.001   20.050   20.099
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   20.050   20.099
 ot_scf_mini                         99  9.5    0.002    0.002   18.823   18.844
 multiply_cannon                   2055 13.4    0.247    0.256   17.459   18.626
 multiply_cannon_loop              2055 14.4    0.319    0.332   16.162   16.474
 rebuild_ks_matrix                  110  8.3    0.000    0.000   11.983   12.013
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.013   11.983   12.013
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.641   10.667
 ot_mini                             99 10.5    0.001    0.001   10.170   10.190
 multiply_cannon_multrec           8220 15.4    3.204    4.471    7.669    8.689
 init_scf_loop                       11  6.9    0.000    0.000    7.611    7.613
 mp_waitall_1                    103326 16.6    5.988    7.553    5.988    7.553
 sum_up_and_integrate               110 10.3    0.079    0.081    6.552    6.562
 integrate_v_rspace                 110 11.3    0.003    0.003    6.472    6.483
 qs_ot_get_derivative                99 11.5    0.001    0.001    6.447    6.467
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.281    6.294
 calculate_rho_elec                 110  8.6    0.115    0.116    6.281    6.293
 prepare_preconditioner              11  7.9    0.000    0.000    5.946    5.949
 make_preconditioner                 11  8.9    0.000    0.000    5.946    5.949
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.555    5.630
 init_scf_run                        11  5.9    0.000    0.001    5.440    5.440
 scf_env_initial_rho_setup           11  6.9    0.000    0.001    5.439    5.439
 dbcsr_mm_accdrv_process          17442 15.9    2.813    3.607    4.337    5.395
 qs_ot_get_p                        110 10.4    0.001    0.001    4.769    4.794
 multiply_cannon_metrocomm3        8220 15.4    0.017    0.018    3.000    4.402
 make_m2s                          4110 13.4    0.039    0.040    4.107    4.340
 make_images                       4110 14.4    0.635    0.688    3.977    4.210
 pw_transfer                       1331 11.6    0.066    0.072    4.023    4.040
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.915    3.935
 ot_diis_step                        99 11.5    0.012    0.012    3.700    3.700
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    3.624    3.648
 apply_single                       110 13.6    0.000    0.000    3.624    3.648
 grid_integrate_task_list           110 12.3    3.356    3.526    3.356    3.526
 qs_ot_p2m_diag                      48 11.0    0.081    0.084    3.457    3.461
 density_rs2pw                      110  9.6    0.004    0.004    3.055    3.431
 fft_wrap_pw1pw2_140                451 13.1    0.216    0.219    3.387    3.412
 fft3d_ps                          1111 14.6    1.143    1.174    3.159    3.179
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.158    3.159
 multiply_cannon_sync_h2d          8220 15.4    2.920    3.025    2.920    3.025
 cp_fm_cholesky_invert               11 10.9    2.872    2.876    2.872    2.876
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.857    2.858
 wfi_extrapolate                     11  7.9    0.001    0.001    2.729    2.729
 make_images_data                  4110 15.4    0.038    0.044    2.333    2.703
 hybrid_alltoall_any               4261 16.3    0.200    0.866    2.259    2.683
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    2.677    2.678
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    2.650    2.651
 cp_fm_redistribute_end              48 14.0    0.673    2.623    0.677    2.623
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.616    2.616
 rs_pw_transfer                     902 11.9    0.010    0.010    2.205    2.605
 cp_fm_diag_elpa_base                48 14.0    1.765    2.446    1.939    2.595
 grid_collocate_task_list           110  9.6    2.278    2.540    2.278    2.540
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.522    2.537
 calculate_dm_sparse                110  9.5    0.001    0.001    2.465    2.504
 potential_pw2rs                    110 12.3    0.015    0.016    2.131    2.134
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.777    1.991
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    1.875    1.889
 mp_alltoall_d11v                  2046 13.8    1.517    1.794    1.517    1.794
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    1.749    1.761
 cp_fm_cholesky_decompose            22 10.9    1.683    1.717    1.683    1.717
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.675    1.679
 qs_env_update_s_mstruct             11  6.9    0.001    0.005    1.508    1.638
 jit_kernel_multiply                  7 15.8    1.217    1.599    1.217    1.599
 mp_allgather_i34                  2055 14.4    0.489    1.532    0.489    1.532
 mp_waitany                        9240 13.8    1.073    1.490    1.073    1.490
 dbcsr_complete_redistribute        325 12.2    0.559    0.579    1.379    1.468
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.437    1.449
 qs_create_task_list                 11  7.9    0.001    0.001    1.219    1.327
 generate_qs_task_list               11  8.9    0.378    0.446    1.218    1.326
 multiply_cannon_metrocomm1        8220 15.4    0.021    0.021    0.803    1.230
 rs_pw_transfer_RS2PW_140           121 11.5    0.162    0.165    0.792    1.192
 rs_gather_matrices                 110 12.3    0.325    0.370    0.901    1.153
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.112    1.133
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="208", plot="h2o_128_md", label="(8n/2r/6t)", y=55.420000, yerr=0.000000
PlotPoint: name="209", plot="h2o_128_md_mem", label="(8n/2r/6t)", y=783.727273, yerr=12.439606
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_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               1.357029E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                   82200
 MPI messages size (bytes):
  total size                       297.640985E+09
  min size                           0.000000E+00
  max size                          26.214400E+06
  average size                       3.620936E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                 572                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                  44                  1441792
     32768 < size <=   131072               18560               2432696320
    131072 < size <=  4194304               54216              84915781632
   4194304 < size <= 16777216                   0                        0
  16777216 < size                            8808             210291069504
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3462                  67104.
 MP_Allreduce         9672                    819.
 MP_Sync                52
 MP_Alltoall          1474               16505187.
 MP_SendRecv          2310                 360267.
 MP_ISendRecv         2310                 360267.
 MP_Wait              5214
 MP_ISend             2420                1187840.
 MP_IRecv             2420                1187840.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.018    0.038   87.655   87.656
 qs_mol_dyn_low                       1  2.0    0.003    0.003   87.352   87.361
 qs_forces                           11  3.9    0.002    0.003   86.920   86.921
 qs_energies                         11  4.9    0.002    0.002   82.734   82.735
 scf_env_do_scf                      11  5.9    0.001    0.001   72.596   72.597
 velocity_verlet                     10  3.0    0.002    0.002   56.272   56.324
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.008   43.988   43.990
 dbcsr_multiply_generic            2055 12.4    0.121    0.123   28.368   28.547
 init_scf_loop                       11  6.9    0.000    0.000   28.536   28.541
 prepare_preconditioner              11  7.9    0.000    0.000   26.508   26.520
 make_preconditioner                 11  8.9    0.000    0.000   26.508   26.520
 make_full_inverse_cholesky          11  9.9    0.000    0.000   20.707   25.968
 qs_scf_new_mos                      99  7.5    0.001    0.001   25.824   25.921
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   25.823   25.920
 ot_scf_mini                         99  9.5    0.002    0.002   24.067   24.143
 multiply_cannon                   2055 13.4    0.351    0.370   21.395   21.935
 multiply_cannon_loop              2055 14.4    0.342    0.348   19.623   20.072
 cp_fm_upper_to_full                 70 14.2   12.852   18.365   12.852   18.365
 rebuild_ks_matrix                  110  8.3    0.001    0.001   14.044   14.151
 qs_ks_build_kohn_sham_matrix       110  9.3    0.014    0.014   14.043   14.151
 ot_mini                             99 10.5    0.001    0.001   13.480   13.563
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.724   12.823
 dbcsr_complete_redistribute        325 12.2    1.023    1.040    7.386   10.599
 multiply_cannon_multrec           8220 15.4    4.370    4.571    9.657    9.831
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    6.341    9.559
 qs_ot_get_derivative                99 11.5    0.001    0.001    8.930    9.007
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    5.786    8.971
 mp_alltoall_i22                    605 13.7    5.433    8.680    5.433    8.680
 mp_waitall_1                     84994 16.7    7.235    8.354    7.235    8.354
 qs_rho_update_rho_low              110  7.6    0.001    0.001    7.688    7.723
 calculate_rho_elec                 110  8.6    0.227    0.227    7.687    7.722
 sum_up_and_integrate               110 10.3    0.150    0.152    7.297    7.310
 integrate_v_rspace                 110 11.3    0.004    0.004    7.147    7.160
 init_scf_run                        11  5.9    0.000    0.001    5.871    5.871
 scf_env_initial_rho_setup           11  6.9    0.000    0.000    5.870    5.871
 make_m2s                          4110 13.4    0.044    0.044    5.106    5.626
 qs_ot_get_p                        110 10.4    0.001    0.001    5.512    5.608
 dbcsr_mm_accdrv_process          11614 15.7    3.297    3.594    5.145    5.498
 make_images                       4110 14.4    0.881    0.939    4.917    5.436
 cp_fm_cholesky_invert               11 10.9    5.310    5.314    5.310    5.314
 pw_transfer                       1331 11.6    0.075    0.075    5.214    5.219
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.605    5.160
 apply_single                       110 13.6    0.000    0.000    4.605    5.160
 fft_wrap_pw1pw2                   1111 12.6    0.009    0.009    5.098    5.102
 multiply_cannon_metrocomm3        8220 15.4    0.018    0.018    4.614    5.076
 ot_diis_step                        99 11.5    0.016    0.016    4.521    4.521
 fft_wrap_pw1pw2_140                451 13.1    0.222    0.227    4.435    4.444
 fft3d_ps                          1111 14.6    1.299    1.305    4.291    4.299
 qs_ot_p2m_diag                      48 11.0    0.151    0.155    3.954    3.961
 multiply_cannon_sync_h2d          8220 15.4    3.950    3.957    3.950    3.957
 density_rs2pw                      110  9.6    0.004    0.004    3.751    3.783
 grid_integrate_task_list           110 12.3    3.662    3.710    3.662    3.710
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    3.675    3.676
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.517    3.517
 hybrid_alltoall_any               4261 16.3    0.257    0.558    2.841    3.502
 make_images_data                  4110 15.4    0.042    0.046    2.749    3.374
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    2.835    3.329
 wfi_extrapolate                     11  7.9    0.001    0.001    3.287    3.287
 calculate_dm_sparse                110  9.5    0.001    0.001    3.113    3.137
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    3.065    3.067
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    2.933    2.934
 cp_fm_diag_elpa_base                48 14.0    2.396    2.598    2.932    2.932
 grid_collocate_task_list           110  9.6    2.634    2.666    2.634    2.666
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.555    2.583
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.463    2.463
 potential_pw2rs                    110 12.3    0.021    0.022    2.456    2.460
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.372    2.415
 qs_env_update_s_mstruct             11  6.9    0.002    0.004    2.195    2.263
 rs_pw_transfer                     902 11.9    0.011    0.011    2.206    2.234
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    2.113    2.192
 jit_kernel_multiply                 10 15.3    1.647    1.991    1.647    1.991
 cp_fm_cholesky_decompose            22 10.9    1.979    1.989    1.979    1.989
 mp_alltoall_d11v                  2046 13.8    1.866    1.946    1.866    1.946
 qs_create_task_list                 11  7.9    0.001    0.001    1.891    1.935
 generate_qs_task_list               11  8.9    0.733    0.787    1.890    1.935
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.921    1.930
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.813    1.854
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="210", plot="h2o_128_md", label="(8n/1r/12t)", y=87.656000, yerr=0.000000
PlotPoint: name="211", plot="h2o_128_md_mem", label="(8n/1r/12t)", y=1215.272727, yerr=56.215641
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/15/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1410023282688       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1924145348608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1957871443968       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1963544850432       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2714615709696       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4377645416448       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5350455508992       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5395653328896       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6594687401984       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11444707676160       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15019188129792       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15019188129792       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19624853225472       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        92.796579E+12       0.0%      0.0%    100.0%
 flops max/rank                      1.086553E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6705500928       0.0%      0.0%    100.0%
 number of processed stacks              11851392       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     565.8
 marketing flops                   143.508480E+12
 -------------------------------------------------------------------------------
 # multiplications                           2485
 max memory usage/rank             634.286080E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                10258080
 MPI messages size (bytes):
  total size                         4.456716E+12
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     434.459062E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               65736                        0
       128 < size <=     8192                1232                 10092544
      8192 < size <=    32768             3542056              94711185408
     32768 < size <=   131072             1282176              73356279808
    131072 < size <=  4194304             5107038            3151762635464
   4194304 < size <= 16777216              259842            1136842803272
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4083                  56784.
 MP_Allreduce        11248                    786.
 MP_Sync               168
 MP_Alltoall          2210                2522944.
 MP_SendRecv         24130                  18752.
 MP_ISendRecv        24130                  18752.
 MP_Wait             42150
 MP_comm_split          82
 MP_ISend            15900                 108037.
 MP_IRecv            15900                 108037.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.023    0.032  200.968  200.969
 qs_mol_dyn_low                       1  2.0    0.003    0.003  200.572  200.587
 qs_forces                           11  3.9    0.003    0.004  200.484  200.485
 qs_energies                         11  4.9    0.001    0.002  194.922  194.938
 scf_env_do_scf                      11  5.9    0.001    0.001  178.610  178.614
 scf_env_do_scf_inner_loop          116  6.6    0.003    0.008  157.985  157.987
 dbcsr_multiply_generic            2485 12.5    0.178    0.181  121.830  122.665
 velocity_verlet                     10  3.0    0.001    0.002  120.785  120.786
 qs_scf_new_mos                     116  7.6    0.001    0.001  118.451  118.743
 qs_scf_loop_do_ot                  116  8.6    0.001    0.001  118.450  118.743
 ot_scf_mini                        116  9.6    0.003    0.003  111.943  112.214
 multiply_cannon                   2485 13.5    0.234    0.244   99.717  101.495
 multiply_cannon_loop              2485 14.5    2.074    2.153   97.593   99.488
 ot_mini                            116 10.6    0.001    0.001   64.062   64.334
 multiply_cannon_multrec          59640 15.5   33.093   35.348   41.292   43.086
 qs_ot_get_derivative               116 11.6    0.001    0.001   39.351   39.641
 rebuild_ks_matrix                  127  8.3    0.001    0.001   33.465   33.739
 qs_ks_build_kohn_sham_matrix       127  9.3    0.015    0.017   33.464   33.738
 mp_waitall_1                    264810 16.5   27.328   31.060   27.328   31.060
 qs_ks_update_qs_env                127  7.6    0.001    0.001   30.056   30.306
 multiply_cannon_sync_h2d         59640 15.5   27.327   29.006   27.327   29.006
 qs_ot_get_p                        127 10.4    0.001    0.001   26.273   26.570
 apply_preconditioner_dbcsr         127 12.6    0.000    0.001   24.186   25.026
 apply_single                       127 13.6    0.001    0.001   24.185   25.026
 ot_diis_step                       116 11.6    0.007    0.008   24.395   24.397
 init_scf_loop                       11  6.9    0.000    0.001   20.550   20.551
 qs_ot_p2m_diag                      82 11.4    0.076    0.090   19.794   19.839
 qs_ot_get_derivative_diag           76 12.4    0.002    0.002   18.047   18.247
 multiply_cannon_metrocomm3       59640 15.5    0.114    0.120   15.176   17.689
 cp_dbcsr_syevd                      82 12.4    0.004    0.005   17.402   17.403
 prepare_preconditioner              11  7.9    0.000    0.000   15.935   15.995
 make_preconditioner                 11  8.9    0.000    0.000   15.935   15.995
 make_full_inverse_cholesky          11  9.9    0.000    0.000   15.202   15.349
 cp_fm_diag_elpa                     82 13.4    0.000    0.001   14.596   14.601
 cp_fm_redistribute_end              82 14.4   11.542   14.529   11.554   14.533
 cp_fm_diag_elpa_base                82 14.4    2.935   14.168    2.968   14.292
 sum_up_and_integrate               127 10.3    0.089    0.107   14.071   14.084
 integrate_v_rspace                 127 11.3    0.003    0.004   13.981   13.998
 make_m2s                          4970 13.5    0.105    0.116   13.400   13.856
 make_images                       4970 14.5    0.397    0.416   13.218   13.683
 qs_rho_update_rho_low              127  7.7    0.001    0.001   13.410   13.488
 calculate_rho_elec                 127  8.7    0.045    0.064   13.410   13.487
 init_scf_run                        11  5.9    0.000    0.001   12.202   12.202
 scf_env_initial_rho_setup           11  6.9    0.000    0.001   12.202   12.202
 density_rs2pw                      127  9.7    0.006    0.007    6.927   10.124
 cp_fm_cholesky_invert               11 10.9    9.177    9.185    9.177    9.185
 wfi_extrapolate                     11  7.9    0.001    0.001    9.032    9.032
 rs_pw_transfer                    1038 11.9    0.016    0.018    5.597    8.807
 mp_sum_l                          7804 13.0    7.454    8.461    7.454    8.461
 calculate_dm_sparse                127  9.5    0.001    0.001    8.314    8.418
 dbcsr_mm_accdrv_process         123452 16.2    3.196    3.403    7.765    8.270
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    7.825    7.966
 pw_transfer                       1535 11.6    0.075    0.091    7.693    7.943
 fft_wrap_pw1pw2                   1281 12.7    0.010    0.012    7.488    7.743
 qs_ot_get_orbitals                 116 10.6    0.001    0.001    7.609    7.715
 grid_integrate_task_list           127 12.3    7.012    7.455    7.012    7.455
 make_images_data                  4970 15.5    0.065    0.073    6.546    7.332
 multiply_cannon_metrocomm1       59640 15.5    0.088    0.093    5.904    7.291
 fft_wrap_pw1pw2_140                519 13.2    0.444    0.513    6.503    6.829
 hybrid_alltoall_any               5155 16.4    0.288    2.239    5.738    6.816
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.003    6.592    6.603
 fft3d_ps                          1281 14.7    2.087    2.876    6.279    6.454
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.773    5.945
 mp_waitany                       15900 13.9    2.644    5.824    2.644    5.824
 grid_collocate_task_list           127  9.7    4.517    5.751    4.517    5.751
 mp_alltoall_d11v                  2401 14.1    3.927    5.344    3.927    5.344
 rs_pw_transfer_RS2PW_140           138 11.5    0.276    0.288    2.093    5.326
 cp_fm_cholesky_decompose            22 10.9    4.642    4.654    4.642    4.654
 potential_pw2rs                    127 12.3    0.009    0.011    4.579    4.599
 mp_sum_d                          4443 12.1    3.559    4.481    3.559    4.481
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="400", plot="h2o_256_md", label="(8n/12r/1t)", y=200.969000, yerr=0.000000
PlotPoint: name="401", plot="h2o_256_md_mem", label="(8n/12r/1t)", y=597.000000, yerr=8.581163
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_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             827.965440E+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                5222471.
 MP_SendRecv         12032                  47072.
 MP_ISendRecv        12032                  47072.
 MP_Wait             25916
 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    0.043    0.079  189.621  189.624
 qs_mol_dyn_low                       1  2.0    0.005    0.019  189.121  189.135
 qs_forces                           11  3.9    0.004    0.012  189.005  189.006
 qs_energies                         11  4.9    0.006    0.025  182.201  182.216
 scf_env_do_scf                      11  5.9    0.001    0.001  165.780  165.790
 scf_env_do_scf_inner_loop          117  6.6    0.018    0.066  133.082  133.084
 velocity_verlet                     10  3.0    0.003    0.005  119.162  119.163
 dbcsr_multiply_generic            2507 12.6    0.188    0.194   97.018   98.121
 qs_scf_new_mos                     117  7.6    0.001    0.001   92.956   93.354
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   92.955   93.354
 ot_scf_mini                        117  9.6    0.004    0.005   88.174   88.634
 multiply_cannon                   2507 13.6    0.477    0.532   77.516   81.518
 multiply_cannon_loop              2507 14.6    1.253    1.293   74.280   76.476
 ot_mini                            117 10.6    0.002    0.009   49.331   49.724
 mp_waitall_1                    214728 16.6   23.795   37.279   23.795   37.279
 multiply_cannon_multrec          30084 15.6   22.345   26.587   31.962   36.644
 rebuild_ks_matrix                  128  8.3    0.001    0.001   33.410   33.900
 qs_ks_build_kohn_sham_matrix       128  9.3    0.017    0.022   33.410   33.900
 init_scf_loop                       11  6.9    0.001    0.002   32.611   32.612
 qs_ks_update_qs_env                128  7.6    0.001    0.001   30.065   30.512
 multiply_cannon_metrocomm3       30084 15.6    0.095    0.099   15.271   28.377
 prepare_preconditioner              11  7.9    0.000    0.001   28.211   28.295
 make_preconditioner                 11  8.9    0.000    0.002   28.211   28.295
 qs_ot_get_derivative               117 11.6    0.001    0.002   27.403   27.870
 make_full_inverse_cholesky          11  9.9    0.000    0.000   26.913   27.439
 apply_preconditioner_dbcsr         128 12.6    0.000    0.001   21.963   23.087
 apply_single                       128 13.6    0.001    0.001   21.963   23.086
 multiply_cannon_sync_h2d         30084 15.6   19.668   21.810   19.668   21.810
 ot_diis_step                       117 11.6    0.019    0.056   21.758   21.761
 qs_ot_get_p                        128 10.4    0.001    0.001   20.530   21.156
 cp_fm_cholesky_invert               11 10.9   16.466   16.479   16.466   16.479
 qs_ot_p2m_diag                      83 11.4    0.187    0.215   15.895   15.929
 make_m2s                          5014 13.6    0.091    0.101   14.030   15.596
 make_images                       5014 14.6    1.148    1.330   13.817   15.378
 cp_dbcsr_syevd                      83 12.4    0.005    0.006   14.762   14.764
 sum_up_and_integrate               128 10.3    0.115    0.132   14.689   14.718
 integrate_v_rspace                 128 11.3    0.003    0.004   14.574   14.608
 qs_rho_update_rho_low              128  7.7    0.001    0.002   14.016   14.067
 calculate_rho_elec                 128  8.7    0.088    0.106   14.015   14.066
 cp_fm_diag_elpa                     83 13.4    0.000    0.001   11.793   11.802
 cp_fm_redistribute_end              83 14.4    6.889   11.735    6.898   11.736
 cp_fm_diag_elpa_base                83 14.4    4.604   11.233    4.820   11.598
 init_scf_run                        11  5.9    0.000    0.001   11.577   11.579
 scf_env_initial_rho_setup           11  6.9    0.000    0.002   11.577   11.579
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002   10.740   11.048
 make_images_data                  5014 15.6    0.064    0.072    8.480   10.319
 multiply_cannon_metrocomm4       27577 15.6    0.097    0.112    3.658   10.267
 density_rs2pw                      128  9.7    0.006    0.007    7.429    9.899
 mp_irecv_dv                      69486 16.3    3.463    9.870    3.463    9.870
 dbcsr_mm_accdrv_process          62242 16.2    4.450    5.201    9.069    9.653
 hybrid_alltoall_any               5200 16.5    0.343    1.527    7.218    9.434
 pw_transfer                       1547 11.6    0.086    0.103    8.789    8.875
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.011    8.563    8.643
 wfi_extrapolate                     11  7.9    0.001    0.001    8.367    8.367
 rs_pw_transfer                    1046 11.9    0.014    0.016    5.694    8.198
 fft_wrap_pw1pw2_140                523 13.2    0.473    0.526    7.575    7.674
 grid_integrate_task_list           128 12.3    7.194    7.586    7.194    7.586
 fft3d_ps                          1291 14.7    2.750    2.918    6.928    6.982
 cp_fm_cholesky_decompose            22 10.9    6.894    6.960    6.894    6.960
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    6.112    6.922
 calculate_dm_sparse                128  9.5    0.001    0.001    6.478    6.612
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.090    6.099
 grid_collocate_task_list           128  9.7    4.699    5.868    4.699    5.868
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.297    5.417
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    5.288    5.351
 mp_sum_l                          7870 13.0    3.699    5.109    3.699    5.109
 potential_pw2rs                    128 12.3    0.014    0.016    4.990    5.012
 mp_waitany                       11748 13.9    2.477    4.987    2.477    4.987
 mp_allgather_i34                  2507 14.6    1.816    4.721    1.816    4.721
 rs_pw_transfer_RS2PW_140           139 11.5    0.354    0.381    2.077    4.563
 mp_alltoall_d11v                  2415 14.1    3.776    4.490    3.776    4.490
 mp_sum_d                          4457 12.1    2.690    4.104    2.690    4.104
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    3.754    3.794
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="402", plot="h2o_256_md", label="(8n/6r/2t)", y=189.624000, yerr=0.000000
PlotPoint: name="403", plot="h2o_256_md_mem", label="(8n/6r/2t)", y=789.636364, yerr=0.771389
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_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             973.766656E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                 1042912
 MPI messages size (bytes):
  total size                         2.716210E+12
  min size                           0.000000E+00
  max size                          26.214400E+06
  average size                       2.604448E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 264                  8650752
     32768 < size <=   131072              281856              36943429632
    131072 < size <=  4194304              660064             996105256960
   4194304 < size <= 16777216               65632             931530938576
  16777216 < size                           28672             751619276800
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4075                  57335.
 MP_Allreduce        11226                    986.
 MP_Sync               170
 MP_Alltoall          1712                9388896.
 MP_SendRecv          7936                  75008.
 MP_ISendRecv         7936                  75008.
 MP_Wait             21820
 MP_comm_split          83
 MP_ISend            11748                 275205.
 MP_IRecv            11748                 275205.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.063    0.267  178.093  178.113
 qs_mol_dyn_low                       1  2.0    0.006    0.029  177.414  177.427
 qs_forces                           11  3.9    0.004    0.018  177.263  177.270
 qs_energies                         11  4.9    0.006    0.019  170.602  170.617
 scf_env_do_scf                      11  5.9    0.001    0.004  154.708  154.708
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.009  119.597  119.597
 velocity_verlet                     10  3.0    0.003    0.008  113.989  113.994
 dbcsr_multiply_generic            2507 12.6    0.183    0.188   82.107   83.671
 qs_scf_new_mos                     117  7.6    0.001    0.001   81.096   81.484
 qs_scf_loop_do_ot                  117  8.6    0.001    0.002   81.095   81.483
 ot_scf_mini                        117  9.6    0.004    0.005   76.994   77.453
 multiply_cannon                   2507 13.6    0.500    0.519   62.088   66.501
 multiply_cannon_loop              2507 14.6    0.853    0.888   58.904   62.524
 ot_mini                            117 10.6    0.001    0.002   42.782   43.227
 init_scf_loop                       11  6.9    0.001    0.005   35.013   35.015
 mp_waitall_1                    170520 16.6   24.713   34.981   24.713   34.981
 rebuild_ks_matrix                  128  8.3    0.001    0.001   30.987   31.577
 qs_ks_build_kohn_sham_matrix       128  9.3    0.016    0.019   30.987   31.577
 prepare_preconditioner              11  7.9    0.000    0.001   30.958   31.012
 make_preconditioner                 11  8.9    0.000    0.002   30.958   31.012
 make_full_inverse_cholesky          11  9.9    0.000    0.001   28.514   29.991
 qs_ks_update_qs_env                128  7.6    0.001    0.001   27.917   28.451
 multiply_cannon_multrec          20056 15.6   13.516   17.667   22.426   26.491
 multiply_cannon_metrocomm3       20056 15.6    0.059    0.062   14.965   25.320
 qs_ot_get_derivative               117 11.6    0.002    0.003   23.104   23.540
 apply_preconditioner_dbcsr         128 12.6    0.000    0.001   19.809   20.753
 apply_single                       128 13.6    0.001    0.001   19.808   20.752
 qs_ot_get_p                        128 10.4    0.001    0.001   19.538   20.071
 ot_diis_step                       117 11.6    0.026    0.088   19.582   19.582
 multiply_cannon_sync_h2d         20056 15.6   14.570   16.147   14.570   16.147
 make_m2s                          5014 13.6    0.082    0.085   14.681   15.779
 make_images                       5014 14.6    1.173    1.260   14.446   15.538
 qs_ot_p2m_diag                      83 11.4    0.265    0.272   15.215   15.222
 sum_up_and_integrate               128 10.3    0.132    0.143   14.722   14.748
 integrate_v_rspace                 128 11.3    0.004    0.004   14.590   14.618
 qs_rho_update_rho_low              128  7.7    0.001    0.003   14.425   14.473
 calculate_rho_elec                 128  8.7    0.132    0.147   14.424   14.472
 cp_fm_cholesky_invert               11 10.9   14.353   14.362   14.353   14.362
 cp_dbcsr_syevd                      83 12.4    0.006    0.008   14.220   14.220
 cp_fm_diag_elpa                     83 13.4    0.001    0.002   11.099   11.100
 cp_fm_redistribute_end              83 14.4    4.195   11.038    4.208   11.041
 cp_fm_diag_elpa_base                83 14.4    6.410   10.459    6.815   10.925
 init_scf_run                        11  5.9    0.000    0.001   10.754   10.754
 scf_env_initial_rho_setup           11  6.9    0.000    0.002   10.753   10.754
 make_images_data                  5014 15.6    0.060    0.068    9.100   10.608
 hybrid_alltoall_any               5200 16.5    0.432    1.986    7.966    9.891
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002    9.063    9.417
 multiply_cannon_metrocomm4       17549 15.6    0.062    0.074    3.380    9.315
 pw_transfer                       1547 11.6    0.086    0.107    9.177    9.292
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.011    8.953    9.073
 mp_irecv_dv                      50230 16.2    3.258    9.060    3.258    9.060
 density_rs2pw                      128  9.7    0.006    0.006    7.296    8.985
 dbcsr_mm_accdrv_process          41502 16.2    4.526    5.412    8.357    8.516
 fft_wrap_pw1pw2_140                523 13.2    0.478    0.523    7.924    8.047
 grid_integrate_task_list           128 12.3    7.330    7.904    7.330    7.904
 cp_fm_upper_to_full                105 14.5    5.814    7.508    5.814    7.508
 wfi_extrapolate                     11  7.9    0.001    0.002    7.484    7.484
 cp_fm_cholesky_decompose            22 10.9    7.311    7.368    7.311    7.368
 fft3d_ps                          1291 14.7    2.666    2.906    7.217    7.304
 rs_pw_transfer                    1046 11.9    0.014    0.014    5.119    6.790
 dbcsr_complete_redistribute        395 12.7    1.182    1.215    4.654    6.493
 calculate_dm_sparse                128  9.5    0.001    0.001    5.868    6.042
 grid_collocate_task_list           128  9.7    4.889    5.830    4.889    5.830
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.572    5.579
 mp_alltoall_d11v                  2415 14.1    4.276    5.359    4.276    5.359
 copy_fm_to_dbcsr                   209 11.7    0.002    0.002    3.490    5.328
 mp_sum_l                          7870 13.0    3.615    5.296    3.615    5.296
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    4.636    5.292
 mp_allgather_i34                  2507 14.6    1.720    5.046    1.720    5.046
 potential_pw2rs                    128 12.3    0.020    0.023    4.827    4.842
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.664    4.788
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    2.424    4.176
 mp_waitany                       11748 13.9    2.334    4.077    2.334    4.077
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    4.009    4.043
 mp_alltoall_i22                    716 14.1    2.069    3.968    2.069    3.968
 qs_energies_init_hamiltonians       11  5.9    0.001    0.003    3.811    3.812
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    3.582    3.637
 rs_pw_transfer_RS2PW_140           139 11.5    0.337    0.354    1.940    3.605
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="404", plot="h2o_256_md", label="(8n/4r/3t)", y=178.113000, yerr=0.000000
PlotPoint: name="405", plot="h2o_256_md_mem", label="(8n/4r/3t)", y=912.363636, yerr=26.735311
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/18/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1430457200640       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1962800054272       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1986252263424       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1992001093632       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2753958699008       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4454954827776       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5444944789504       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5492290093056       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6712799002624       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11613077360640       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15239162695680       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15239162695680       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                        94.232994E+12       0.0%      0.0%    100.0%
 flops max/rank                      4.387242E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6806382528       0.0%      0.0%    100.0%
 number of processed stacks               6026880       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1129.3
 marketing flops                   145.651870E+12
 -------------------------------------------------------------------------------
 # multiplications                           2529
 max memory usage/rank               1.141248E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1153224
 MPI messages size (bytes):
  total size                         2.039489E+12
  min size                           0.000000E+00
  max size                          17.653760E+06
  average size                       1.768511E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                6996                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 396                  8650752
     32768 < size <=   131072              322096              36390305792
    131072 < size <=  4194304              721976             792118951936
   4194304 < size <= 16777216               70800             669921808880
  16777216 < size                           30960             541065216000
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4127                  56626.
 MP_Allreduce        11356                   1063.
 MP_Sync               172
 MP_Alltoall          1724               12509633.
 MP_SendRecv          5934                  75008.
 MP_ISendRecv         5934                  75008.
 MP_Wait             22612
 MP_comm_split          84
 MP_ISend            15064                 244788.
 MP_IRecv            15064                 244788.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.053    0.190  187.466  187.467
 qs_mol_dyn_low                       1  2.0    0.003    0.004  186.925  186.939
 qs_forces                           11  3.9    0.003    0.003  186.808  186.812
 qs_energies                         11  4.9    0.003    0.011  179.573  179.581
 scf_env_do_scf                      11  5.9    0.004    0.017  162.931  162.940
 velocity_verlet                     10  3.0    0.002    0.003  124.699  124.702
 scf_env_do_scf_inner_loop          118  6.6    0.003    0.009  116.731  116.733
 dbcsr_multiply_generic            2529 12.6    0.193    0.200   79.081   79.825
 qs_scf_new_mos                     118  7.6    0.001    0.001   79.116   79.388
 qs_scf_loop_do_ot                  118  8.6    0.001    0.001   79.115   79.387
 ot_scf_mini                        118  9.6    0.004    0.005   74.611   74.892
 multiply_cannon                   2529 13.6    0.556    0.603   54.769   57.596
 multiply_cannon_loop              2529 14.6    1.189    1.219   51.119   53.055
 init_scf_loop                       11  6.9    0.001    0.006   46.069   46.072
 ot_mini                            118 10.6    0.001    0.001   42.153   42.427
 prepare_preconditioner              11  7.9    0.000    0.001   41.928   41.964
 make_preconditioner                 11  8.9    0.000    0.003   41.928   41.964
 make_full_inverse_cholesky          11  9.9    0.000    0.001   35.560   40.490
 multiply_cannon_multrec          30348 15.6   14.371   19.527   26.304   30.903
 rebuild_ks_matrix                  129  8.3    0.001    0.001   30.055   30.337
 qs_ks_build_kohn_sham_matrix       129  9.3    0.017    0.019   30.055   30.337
 qs_ks_update_qs_env                129  7.6    0.001    0.001   27.054   27.302
 mp_waitall_1                    149172 16.7   16.788   26.723   16.788   26.723
 qs_ot_get_derivative               118 11.6    0.001    0.002   22.434   22.715
 make_m2s                          5058 13.6    0.098    0.103   20.025   21.145
 make_images                       5058 14.6    1.963    2.267   19.724   20.845
 apply_preconditioner_dbcsr         129 12.6    0.000    0.001   19.150   19.694
 apply_single                       129 13.6    0.001    0.001   19.150   19.694
 ot_diis_step                       118 11.6    0.018    0.021   19.591   19.594
 qs_ot_get_p                        129 10.4    0.001    0.002   18.716   19.011
 cp_fm_upper_to_full                106 14.7   11.029   16.269   11.029   16.269
 cp_fm_cholesky_invert               11 10.9   15.952   15.961   15.952   15.961
 multiply_cannon_metrocomm3       30348 15.6    0.046    0.049    6.327   15.357
 sum_up_and_integrate               129 10.3    0.142    0.154   14.840   14.870
 integrate_v_rspace                 129 11.3    0.004    0.004   14.698   14.733
 qs_ot_p2m_diag                      84 11.4    0.346    0.394   14.676   14.729
 qs_rho_update_rho_low              129  7.7    0.001    0.001   14.573   14.604
 calculate_rho_elec                 129  8.7    0.176    0.192   14.573   14.604
 cp_dbcsr_syevd                      84 12.4    0.006    0.008   13.397   13.398
 multiply_cannon_sync_h2d         30348 15.6   11.810   12.742   11.810   12.742
 dbcsr_complete_redistribute        397 12.7    1.521    1.630    8.868   12.659
 make_images_data                  5058 15.6    0.065    0.071   10.624   12.183
 dbcsr_mm_accdrv_process          62780 16.2    7.347    8.181   11.505   12.005
 copy_fm_to_dbcsr                   210 11.7    0.002    0.002    7.547   11.302
 hybrid_alltoall_any               5245 16.5    0.531    2.235    9.564   11.191
 init_scf_run                        11  5.9    0.000    0.001   10.713   10.714
 scf_env_initial_rho_setup           11  6.9    0.000    0.001   10.713   10.714
 cp_fm_diag_elpa                     84 13.4    0.001    0.002   10.293   10.295
 cp_fm_redistribute_end              84 14.4    1.777   10.219    1.790   10.224
 cp_fm_diag_elpa_base                84 14.4    7.814    9.597    8.399   10.099
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    6.345   10.036
 qs_ot_get_derivative_diag           78 12.4    0.002    0.002    9.328    9.531
 pw_transfer                       1559 11.6    0.088    0.108    9.341    9.409
 mp_alltoall_i22                    720 14.1    5.443    9.233    5.443    9.233
 fft_wrap_pw1pw2                   1301 12.7    0.010    0.012    9.111    9.188
 density_rs2pw                      129  9.7    0.006    0.006    7.057    8.645
 fft_wrap_pw1pw2_140                527 13.2    0.488    0.499    8.094    8.192
 grid_integrate_task_list           129 12.3    7.561    7.903    7.561    7.903
 cp_fm_cholesky_decompose            22 10.9    7.519    7.619    7.519    7.619
 wfi_extrapolate                     11  7.9    0.001    0.002    7.565    7.565
 fft3d_ps                          1301 14.7    2.796    2.895    7.320    7.383
 multiply_cannon_metrocomm4       25290 15.6    0.078    0.087    2.756    7.197
 mp_irecv_dv                      76751 16.2    2.609    6.936    2.609    6.936
 rs_pw_transfer                    1054 12.0    0.013    0.015    4.676    6.324
 calculate_dm_sparse                129  9.5    0.001    0.001    6.157    6.242
 grid_collocate_task_list           129  9.7    5.101    5.883    5.101    5.883
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.439    5.470
 mp_alltoall_d11v                  2429 14.1    4.727    5.285    4.727    5.285
 potential_pw2rs                    129 12.3    0.023    0.023    4.636    4.656
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    4.478    4.479
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.401    4.476
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    4.269    4.355
 qs_ot_get_orbitals                 118 10.6    0.001    0.001    4.176    4.235
 mp_waitany                       15064 13.9    2.243    3.822    2.243    3.822
 dbcsr_special_finalize           12645 15.6    0.067    0.070    3.548    3.756
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="406", plot="h2o_256_md", label="(8n/3r/4t)", y=187.467000, yerr=0.000000
PlotPoint: name="407", plot="h2o_256_md_mem", label="(8n/3r/4t)", y=1076.909091, yerr=18.656973
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/19/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        1963544850432       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2714615709696       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4377645416448       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5350455508992       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5395653328896       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6594687401984       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11444706349056       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15019188129792       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15019188129792       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19624853225472       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        92.796578E+12       0.0%      0.0%    100.0%
 flops max/rank                      5.820059E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6705500608       0.0%      0.0%    100.0%
 number of processed stacks               1944496       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    3448.5
 marketing flops                   143.507742E+12
 -------------------------------------------------------------------------------
 # multiplications                           2485
 max memory usage/rank               1.467650E+09
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  238560
 MPI messages size (bytes):
  total size                         1.321104E+12
  min size                           0.000000E+00
  max size                          52.428800E+06
  average size                       5.537828E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                 132                  8650752
    131072 < size <=  4194304              112800              59139686400
   4194304 < size <= 16777216              104112             545846722560
  16777216 < size                           20064             716108623056
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         8852                     52.
 MP_Alltoall          9584                 804353.
 MP_ISend            39716                2104723.
 MP_IRecv            39716                2103824.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4003                  58193.
 MP_Allreduce        11005                   1175.
 MP_Sync                86
 MP_Alltoall          1700               18828162.
 MP_SendRecv          3810                 122880.
 MP_ISendRecv         3810                 122880.
 MP_Wait             16000
 MP_ISend            10600                 423612.
 MP_IRecv            10600                 423612.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.023    0.041  172.007  172.012
 qs_mol_dyn_low                       1  2.0    0.003    0.003  171.590  171.602
 qs_forces                           11  3.9    0.003    0.003  171.258  171.264
 qs_energies                         11  4.9    0.002    0.002  163.730  163.738
 scf_env_do_scf                      11  5.9    0.001    0.001  146.466  146.469
 velocity_verlet                     10  3.0    0.002    0.002  112.534  112.552
 scf_env_do_scf_inner_loop          116  6.6    0.003    0.009  110.874  110.876
 dbcsr_multiply_generic            2485 12.5    0.183    0.188   72.816   73.336
 qs_scf_new_mos                     116  7.6    0.001    0.001   72.761   72.879
 qs_scf_loop_do_ot                  116  8.6    0.001    0.001   72.760   72.878
 ot_scf_mini                        116  9.6    0.003    0.004   68.422   68.548
 multiply_cannon                   2485 13.5    0.578    0.624   53.578   57.477
 multiply_cannon_loop              2485 14.5    0.438    0.448   48.993   49.975
 ot_mini                            116 10.6    0.001    0.001   38.788   38.909
 init_scf_loop                       11  6.9    0.000    0.000   35.448   35.450
 mp_waitall_1                    124680 16.7   25.023   32.271   25.023   32.271
 prepare_preconditioner              11  7.9    0.000    0.000   31.521   31.550
 make_preconditioner                 11  8.9    0.000    0.000   31.521   31.550
 make_full_inverse_cholesky          11  9.9    0.000    0.000   29.428   29.675
 rebuild_ks_matrix                  127  8.3    0.001    0.001   29.554   29.658
 qs_ks_build_kohn_sham_matrix       127  9.3    0.017    0.018   29.553   29.657
 qs_ks_update_qs_env                127  7.6    0.001    0.001   26.855   26.949
 multiply_cannon_multrec           9940 15.5   10.334   14.179   17.675   20.846
 ot_diis_step                       116 11.6    0.019    0.021   19.507   19.507
 apply_preconditioner_dbcsr         127 12.6    0.000    0.000   19.135   19.449
 apply_single                       127 13.6    0.001    0.001   19.134   19.448
 qs_ot_get_derivative               116 11.6    0.001    0.002   19.213   19.347
 multiply_cannon_metrocomm3        9940 15.5    0.023    0.024   11.943   18.910
 cp_fm_cholesky_invert               11 10.9   18.013   18.019   18.013   18.019
 make_m2s                          4970 13.5    0.066    0.069   15.683   17.988
 make_images                       4970 14.5    2.259    2.774   15.378   17.682
 qs_ot_get_p                        127 10.4    0.001    0.001   16.959   17.097
 qs_rho_update_rho_low              127  7.7    0.001    0.001   15.159   15.210
 calculate_rho_elec                 127  8.7    0.256    0.266   15.158   15.209
 sum_up_and_integrate               127 10.3    0.180    0.189   14.870   14.918
 integrate_v_rspace                 127 11.3    0.004    0.004   14.690   14.741
 qs_ot_p2m_diag                      82 11.4    0.489    0.495   13.362   13.380
 cp_dbcsr_syevd                      82 12.4    0.005    0.005   12.261   12.261
 multiply_cannon_sync_h2d          9940 15.5   11.511   11.902   11.511   11.902
 make_images_data                  4970 15.5    0.051    0.060    9.590   11.886
 hybrid_alltoall_any               5155 16.4    0.804    3.540    9.404   11.782
 init_scf_run                        11  5.9    0.000    0.001   10.473   10.473
 scf_env_initial_rho_setup           11  6.9    0.000    0.001   10.472   10.473
 pw_transfer                       1535 11.6    0.084    0.092    9.560    9.598
 fft_wrap_pw1pw2                   1281 12.7    0.010    0.010    9.340    9.384
 cp_fm_diag_elpa                     82 13.4    0.000    0.000    9.304    9.315
 cp_fm_diag_elpa_base                82 14.4    9.064    9.139    9.295    9.305
 fft_wrap_pw1pw2_140                519 13.2    0.493    0.511    8.247    8.289
 grid_integrate_task_list           127 12.3    7.651    8.252    7.651    8.252
 cp_fm_cholesky_decompose            22 10.9    7.924    8.034    7.924    8.034
 qs_ot_get_derivative_diag           76 12.4    0.002    0.002    7.668    7.757
 density_rs2pw                      127  9.7    0.005    0.005    6.849    7.726
 dbcsr_mm_accdrv_process          20590 16.1    2.754    3.462    6.976    7.587
 fft3d_ps                          1281 14.7    2.689    2.765    7.511    7.532
 wfi_extrapolate                     11  7.9    0.001    0.001    7.367    7.367
 multiply_cannon_metrocomm1        9940 15.5    0.028    0.029    4.238    7.218
 mp_allgather_i34                  2485 14.5    2.820    7.096    2.820    7.096
 calculate_dm_sparse                127  9.5    0.001    0.001    6.081    6.179
 grid_collocate_task_list           127  9.7    5.349    6.041    5.349    6.041
 mp_alltoall_d11v                  2401 14.1    4.804    5.818    4.804    5.818
 dbcsr_complete_redistribute        393 12.7    2.140    2.217    5.072    5.439
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    5.314    5.315
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.127    5.133
 rs_pw_transfer                    1038 11.9    0.012    0.013    4.055    4.966
 potential_pw2rs                    127 12.3    0.026    0.027    4.460    4.472
 multiply_cannon_metrocomm4        7455 15.5    0.024    0.027    1.849    4.335
 mp_irecv_dv                      28618 15.9    1.811    4.260    1.811    4.260
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.048    4.076
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    3.574    3.889
 qs_ot_get_orbitals                 116 10.6    0.001    0.001    3.648    3.682
 copy_fm_to_dbcsr                   208 11.6    0.002    0.002    3.345    3.658
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    3.598    3.609
 copy_dbcsr_to_fm                   185 11.7    0.004    0.004    3.445    3.549
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    3.420    3.456
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="408", plot="h2o_256_md", label="(8n/2r/6t)", y=172.012000, yerr=0.000000
PlotPoint: name="409", plot="h2o_256_md_mem", label="(8n/2r/6t)", y=1378.454545, yerr=34.399692
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_performance_tests/20/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1410022950912       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1924145348608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1957871443968       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1963542011904       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2714615709696       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4377645416448       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5350455508992       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5395653328896       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6594687401984       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11444706349056       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15019182452736       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15019182452736       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19624853225472       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        92.796564E+12       0.0%      0.0%    100.0%
 flops max/rank                     11.606412E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6705499488       0.0%      0.0%    100.0%
 number of processed stacks               1947808       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    3442.6
 marketing flops                   143.507742E+12
 -------------------------------------------------------------------------------
 # multiplications                           2485
 max memory usage/rank               2.976780E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                   99400
 MPI messages size (bytes):
  total size                         1.127422E+12
  min size                           0.000000E+00
  max size                         104.857600E+06
  average size                      11.342272E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                 572                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                  44                  2883584
    131072 < size <=  4194304               44768              34745614336
   4194304 < size <= 16777216               43984             376564613120
  16777216 < size                           10032             716108490000
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3991                  59299.
 MP_Allreduce        10975                   1515.
 MP_Sync                86
 MP_Alltoall          1700               36954339.
 MP_SendRecv          1778                 218624.
 MP_ISendRecv         1778                 218624.
 MP_Wait              9728
 MP_ISend             6360                1080477.
 MP_IRecv             6360                1080477.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.049    0.064  294.753  294.761
 qs_mol_dyn_low                       1  2.0    0.003    0.003  294.152  294.166
 qs_forces                           11  3.9    0.003    0.003  294.060  294.063
 qs_energies                         11  4.9    0.002    0.002  284.665  284.681
 scf_env_do_scf                      11  5.9    0.001    0.001  262.310  262.321
 velocity_verlet                     10  3.0    0.002    0.002  212.688  212.696
 scf_env_do_scf_inner_loop          116  6.6    0.004    0.009  136.971  136.974
 init_scf_loop                       11  6.9    0.000    0.000  125.079  125.083
 prepare_preconditioner              11  7.9    0.000    0.000  120.010  120.046
 make_preconditioner                 11  8.9    0.000    0.000  120.010  120.046
 make_full_inverse_cholesky          11  9.9    0.000    0.000   96.138  117.263
 qs_scf_new_mos                     116  7.6    0.001    0.001   87.373   87.489
 qs_scf_loop_do_ot                  116  8.6    0.001    0.001   87.372   87.488
 ot_scf_mini                        116  9.6    0.004    0.004   82.783   82.811
 dbcsr_multiply_generic            2485 12.5    0.214    0.220   79.960   80.552
 cp_fm_upper_to_full                104 14.8   53.238   76.195   53.238   76.195
 multiply_cannon                   2485 13.5    0.703    0.758   56.277   56.784
 multiply_cannon_loop              2485 14.5    0.471    0.477   52.826   54.098
 ot_mini                            116 10.6    0.001    0.001   42.831   42.856
 dbcsr_complete_redistribute        393 12.7    3.993    4.031   29.568   42.524
 copy_fm_to_dbcsr                   208 11.6    0.002    0.002   26.144   39.042
 rebuild_ks_matrix                  127  8.3    0.001    0.001   37.334   37.369
 qs_ks_build_kohn_sham_matrix       127  9.3    0.017    0.018   37.333   37.368
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000   23.827   36.581
 mp_alltoall_i22                    712 14.1   21.637   34.663   21.637   34.663
 qs_ks_update_qs_env                127  7.6    0.001    0.001   34.332   34.366
 cp_fm_cholesky_invert               11 10.9   33.707   33.714   33.707   33.714
 mp_waitall_1                    102768 16.8   25.479   29.034   25.479   29.034
 qs_ot_get_p                        127 10.4    0.001    0.001   25.196   25.223
 qs_ot_get_derivative               116 11.6    0.002    0.002   23.454   23.488
 qs_ot_p2m_diag                      82 11.4    0.868    0.873   21.381   21.410
 qs_rho_update_rho_low              127  7.7    0.001    0.001   20.409   20.431
 calculate_rho_elec                 127  8.7    0.479    0.480   20.409   20.430
 make_m2s                          4970 13.5    0.077    0.079   19.059   19.773
 cp_dbcsr_syevd                      82 12.4    0.005    0.006   19.673   19.676
 ot_diis_step                       116 11.6    0.022    0.022   19.344   19.345
 sum_up_and_integrate               127 10.3    0.318    0.320   19.255   19.332
 make_images                       4970 14.5    3.721    3.878   18.582   19.301
 integrate_v_rspace                 127 11.3    0.004    0.004   18.936   19.012
 apply_preconditioner_dbcsr         127 12.6    0.000    0.000   18.604   18.843
 apply_single                       127 13.6    0.001    0.001   18.603   18.843
 multiply_cannon_multrec           9940 15.5   10.360   12.171   17.971   18.058
 multiply_cannon_metrocomm3        9940 15.5    0.023    0.024   16.765   17.854
 cp_fm_diag_elpa                     82 13.4    0.000    0.000   16.494   16.494
 cp_fm_diag_elpa_base                82 14.4   12.114   13.714   16.488   16.489
 multiply_cannon_sync_h2d          9940 15.5   15.535   15.560   15.535   15.560
 init_scf_run                        11  5.9    0.000    0.001   12.363   12.363
 scf_env_initial_rho_setup           11  6.9    0.000    0.000   12.362   12.363
 pw_transfer                       1535 11.6    0.092    0.092   11.948   11.952
 fft_wrap_pw1pw2                   1281 12.7    0.011    0.011   11.715   11.719
 hybrid_alltoall_any               5155 16.4    1.288    2.999   10.117   11.672
 make_images_data                  4970 15.5    0.060    0.065    9.947   11.461
 fft_wrap_pw1pw2_140                519 13.2    0.538    0.541   10.394   10.404
 fft3d_ps                          1281 14.7    2.718    2.724    9.763    9.772
 dbcsr_mm_accdrv_process          20590 16.0    3.712    5.384    7.376    9.157
 cp_fm_cholesky_decompose            22 10.9    9.009    9.074    9.009    9.074
 wfi_extrapolate                     11  7.9    0.001    0.001    9.046    9.046
 qs_ot_get_derivative_diag           76 12.4    0.002    0.002    8.952    8.985
 mp_alltoall_d11v                  2401 14.1    7.859    8.891    7.859    8.891
 grid_integrate_task_list           127 12.3    8.507    8.682    8.507    8.682
 density_rs2pw                      127  9.7    0.005    0.005    8.133    8.275
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    8.022    8.023
 calculate_dm_sparse                127  9.5    0.001    0.001    6.533    6.639
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.366    6.401
 grid_collocate_task_list           127  9.7    6.311    6.346    6.311    6.346
 rs_scatter_matrices                138  9.7    3.576    4.606    5.937    6.175
 copy_dbcsr_to_fm                   185 11.7    0.004    0.005    6.056    6.113
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="410", plot="h2o_256_md", label="(8n/1r/12t)", y=294.761000, yerr=0.000000
PlotPoint: name="411", plot="h2o_256_md_mem", label="(8n/1r/12t)", y=2632.454545, yerr=173.318605
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_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               1.261580E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                  458208
 MPI messages size (bytes):
  total size                         3.456111E+12
  min size                           0.000000E+00
  max size                          18.735064E+06
  average size                       7.542668E+06
 MPI breakdown and total messages size (bytes):
             size <=      128              112896                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 224                  5687808
     32768 < size <=   131072               10528                813356544
    131072 < size <=  4194304               36422              76284728544
   4194304 < size <= 16777216              294266            3312457683808
  16777216 < size                            3872              66548597808
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 255669.
 MP_Allreduce         3059                   6274.
 MP_Sync                 4
 MP_Alltoall            54                6805335.
 MP_SendRecv           285                  19200.
 MP_ISendRecv          285                  19200.
 MP_Wait              1017
 MP_ISend              642                 197829.
 MP_IRecv              642                 197607.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.018    0.036   84.671   84.672
 qs_energies                          1  2.0    0.000    0.000   84.224   84.237
 ls_scf                               1  3.0    0.000    0.000   83.316   83.329
 dbcsr_multiply_generic             111  6.7    0.014    0.015   72.428   72.573
 multiply_cannon                    111  7.7    0.017    0.020   55.921   57.091
 multiply_cannon_loop               111  8.7    0.207    0.225   52.496   53.869
 ls_scf_main                          1  4.0    0.000    0.000   52.075   52.080
 density_matrix_trs4                  2  5.0    0.002    0.003   46.624   46.714
 ls_scf_init_scf                      1  4.0    0.000    0.000   28.242   28.243
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   27.141   27.196
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   25.029   25.045
 mp_waitall_1                     11031 10.9   22.222   24.934   22.222   24.934
 multiply_cannon_multrec           2664  9.7    8.168    8.892   15.489   17.181
 multiply_cannon_sync_h2d          2664  9.7   13.629   15.186   13.629   15.186
 make_m2s                           222  7.7    0.008    0.011   12.848   13.404
 make_images                        222  8.7    0.099    0.109   12.826   13.384
 multiply_cannon_metrocomm1        2664  9.7    0.009    0.010    9.603   13.199
 multiply_cannon_metrocomm3        2664  9.7    0.009    0.010    5.496    8.198
 make_images_data                   222  9.7    0.004    0.005    7.452    7.981
 dbcsr_mm_accdrv_process           4760 10.4    0.507    0.637    6.938    7.895
 hybrid_alltoall_any                227 10.6    0.215    1.839    6.407    7.604
 dbcsr_mm_accdrv_process_sort      4760 11.4    6.232    7.123    6.232    7.123
 calculate_norms                   4752  9.8    5.519    6.172    5.519    6.172
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.974    5.080
 mp_sum_l                           807  5.4    3.134    4.949    3.134    4.949
 multiply_cannon_metrocomm4        2442  9.7    0.012    0.016    2.096    3.828
 mp_irecv_dv                       6231 10.9    2.077    3.797    2.077    3.797
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    2.334    3.671
 make_images_sizes                  222  9.7    0.000    0.000    0.623    3.346
 mp_alltoall_i44                    222 10.7    0.622    3.345    0.622    3.345
 arnoldi_extremal                     4  6.8    0.000    0.000    3.233    3.251
 arnoldi_normal_ev                    4  7.8    0.001    0.002    3.233    3.251
 build_subspace                      16  8.4    0.009    0.012    3.142    3.144
 ls_scf_post                          1  4.0    0.000    0.000    2.999    3.013
 ls_scf_store_result                  1  5.0    0.000    0.000    2.813    2.860
 dbcsr_special_finalize             555  9.7    0.005    0.006    2.419    2.790
 dbcsr_merge_single_wm              555 10.7    0.465    0.610    2.411    2.782
 make_images_pack                   222  9.7    2.208    2.636    2.210    2.637
 dbcsr_matrix_vector_mult           304  9.0    0.005    0.013    2.328    2.556
 dbcsr_sort_data                    658 11.4    2.205    2.511    2.205    2.511
 dbcsr_matrix_vector_mult_local     304 10.0    2.069    2.460    2.071    2.461
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.254    2.323
 buffer_matrices_ensure_size        222  8.7    1.782    2.204    1.782    2.204
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.774    1.779
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.764    1.770
 qs_ks_build_kohn_sham_matrix         3  8.3    0.000    0.001    1.764    1.770
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="500", plot="h2o_32_nrep3_ls", label="(8n/12r/1t)", y=84.672000, yerr=0.000000
PlotPoint: name="501", plot="h2o_32_nrep3_ls_mem", label="(8n/12r/1t)", y=1133.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_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               2.107445E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                  106560
 MPI messages size (bytes):
  total size                         2.699093E+12
  min size                           0.000000E+00
  max size                          72.286792E+06
  average size                      25.329324E+06
 MPI breakdown and total messages size (bytes):
             size <=      128               23040                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                3264                325830144
    131072 < size <=  4194304                5280               3328561104
   4194304 < size <= 16777216               12709             156766962056
  16777216 < size                           62267            2538670978840
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 266696.
 MP_Allreduce         3058                  10339.
 MP_Sync                 4
 MP_Alltoall            47               15335933.
 MP_SendRecv           141                  57600.
 MP_ISendRecv          141                  57600.
 MP_Wait               687
 MP_ISend              462                 414589.
 MP_IRecv              462                 413870.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.044    0.082   91.239   91.239
 qs_energies                          1  2.0    0.000    0.000   90.769   90.773
 ls_scf                               1  3.0    0.000    0.000   89.457   89.461
 dbcsr_multiply_generic             111  6.7    0.015    0.016   75.527   75.894
 multiply_cannon                    111  7.7    0.029    0.042   53.469   57.582
 ls_scf_main                          1  4.0    0.000    0.000   55.134   55.140
 multiply_cannon_loop               111  8.7    0.116    0.122   50.185   53.552
 density_matrix_trs4                  2  5.0    0.002    0.003   49.386   49.637
 ls_scf_init_scf                      1  4.0    0.000    0.000   30.758   30.759
 mp_waitall_1                      9105 10.9   21.253   30.410   21.253   30.410
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   29.573   29.653
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.165   27.182
 multiply_cannon_multrec           1332  9.7   13.082   16.523   22.309   26.848
 multiply_cannon_metrocomm3        1332  9.7    0.006    0.007   12.076   21.121
 make_m2s                           222  7.7    0.006    0.007   15.172   15.894
 make_images                        222  8.7    1.570    1.952   15.142   15.866
 dbcsr_mm_accdrv_process           4041 10.4    0.291    0.442    8.821   10.395
 dbcsr_mm_accdrv_process_sort      4041 11.4    8.412    9.953    8.412    9.953
 make_images_data                   222  9.7    0.004    0.004    8.626    9.618
 hybrid_alltoall_any                227 10.6    0.523    2.473    8.018    9.200
 mp_sum_l                           807  5.4    5.574    8.878    5.574    8.878
 multiply_cannon_metrocomm4        1221  9.7    0.007    0.008    3.233    7.913
 mp_irecv_dv                       3311 11.0    3.213    7.864    3.213    7.864
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    4.289    7.108
 calculate_norms                   2376  9.8    5.980    6.693    5.980    6.693
 multiply_cannon_sync_h2d          1332  9.7    4.802    6.103    4.802    6.103
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.073    5.269
 arnoldi_extremal                     4  6.8    0.000    0.000    4.634    4.660
 arnoldi_normal_ev                    4  7.8    0.001    0.005    4.634    4.660
 build_subspace                      16  8.4    0.014    0.021    4.376    4.379
 ls_scf_post                          1  4.0    0.000    0.000    3.566    3.571
 ls_scf_store_result                  1  5.0    0.000    0.000    3.241    3.388
 dbcsr_matrix_vector_mult           304  9.0    0.009    0.021    3.117    3.350
 dbcsr_matrix_vector_mult_local     304 10.0    2.729    3.212    2.731    3.213
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.003    1.185    2.804
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.601    2.700
 make_images_pack                   222  9.7    2.028    2.400    2.030    2.402
 mp_allgather_i34                   111  8.7    0.988    2.377    0.988    2.377
 dbcsr_sort_data                    436 11.2    1.821    2.100    1.821    2.100
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.895    1.897
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.882    1.885
 qs_ks_build_kohn_sham_matrix         3  8.3    0.000    0.001    1.882    1.885
 dbcsr_data_new                    4174 10.1    1.617    1.844    1.617    1.844
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="502", plot="h2o_32_nrep3_ls", label="(8n/6r/2t)", y=91.239000, yerr=0.000000
PlotPoint: name="503", plot="h2o_32_nrep3_ls_mem", label="(8n/6r/2t)", y=1725.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_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               2.699071E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                   46176
 MPI messages size (bytes):
  total size                         1.924064E+12
  min size                           0.000000E+00
  max size                         108.059888E+06
  average size                      41.668048E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                9984                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304                3328               1170063360
   4194304 < size <= 16777216                1870              19378539600
  16777216 < size                           30994            1903514987232
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 265470.
 MP_Allreduce         3058                  11181.
 MP_Sync                 4
 MP_Alltoall            47               23526250.
 MP_SendRecv            93                  57600.
 MP_ISendRecv           93                  57600.
 MP_Wait               639
 MP_ISend              462                 560046.
 MP_IRecv              462                 560662.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.032    0.047   94.669   94.671
 qs_energies                          1  2.0    0.000    0.000   94.042   94.048
 ls_scf                               1  3.0    0.000    0.000   92.645   92.650
 dbcsr_multiply_generic             111  6.7    0.015    0.016   77.339   77.688
 ls_scf_main                          1  4.0    0.000    0.000   58.139   58.145
 multiply_cannon                    111  7.7    0.042    0.121   53.181   56.796
 multiply_cannon_loop               111  8.7    0.100    0.111   49.597   53.929
 density_matrix_trs4                  2  5.0    0.002    0.003   52.172   52.307
 mp_waitall_1                      7281 11.0   24.213   34.323   24.213   34.323
 ls_scf_init_scf                      1  4.0    0.000    0.000   30.913   30.915
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   29.627   29.724
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.185   27.197
 multiply_cannon_multrec            888  9.7   12.603   15.221   21.165   24.340
 multiply_cannon_metrocomm3         888  9.7    0.004    0.004   11.205   23.559
 make_m2s                           222  7.7    0.006    0.007   17.196   18.451
 make_images                        222  8.7    1.968    2.295   17.158   18.409
 hybrid_alltoall_any                227 10.6    0.620    2.855    9.427   10.897
 make_images_data                   222  9.7    0.003    0.004    9.781   10.844
 mp_sum_l                           807  5.4    5.401    9.357    5.401    9.357
 dbcsr_mm_accdrv_process           3754 10.4    0.246    0.415    8.057    9.283
 dbcsr_mm_accdrv_process_sort      3754 11.4    7.688    8.868    7.688    8.868
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    4.220    7.496
 multiply_cannon_sync_h2d           888  9.7    6.060    7.481    6.060    7.481
 multiply_cannon_metrocomm1         888  9.7    0.003    0.003    3.842    7.071
 multiply_cannon_metrocomm4         777  9.7    0.004    0.005    2.450    6.690
 mp_irecv_dv                       2335 11.1    2.434    6.636    2.434    6.636
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.893    5.107
 arnoldi_extremal                     4  6.8    0.000    0.000    5.036    5.054
 arnoldi_normal_ev                    4  7.8    0.001    0.005    5.036    5.054
 build_subspace                      16  8.4    0.014    0.020    4.726    4.732
 calculate_norms                   1584  9.8    4.250    4.593    4.250    4.593
 mp_allgather_i34                   111  8.7    1.435    3.917    1.435    3.917
 dbcsr_matrix_vector_mult           304  9.0    0.009    0.020    3.395    3.725
 ls_scf_post                          1  4.0    0.000    0.000    3.593    3.602
 dbcsr_matrix_vector_mult_local     304 10.0    3.007    3.574    3.009    3.576
 ls_scf_store_result                  1  5.0    0.000    0.000    3.323    3.417
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.867    2.976
 make_images_sizes                  222  9.7    0.000    0.000    1.116    2.271
 mp_alltoall_i44                    222 10.7    1.116    2.270    1.116    2.270
 make_images_pack                   222  9.7    1.821    2.146    1.824    2.149
 dbcsr_sort_data                    325 11.1    1.869    2.145    1.869    2.145
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.990    1.992
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.972    1.974
 qs_ks_build_kohn_sham_matrix         3  8.3    0.003    0.014    1.972    1.974
 dbcsr_data_release                9322 10.9    1.332    1.918    1.332    1.918
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="504", plot="h2o_32_nrep3_ls", label="(8n/4r/3t)", y=94.671000, yerr=0.000000
PlotPoint: name="505", plot="h2o_32_nrep3_ls_mem", label="(8n/4r/3t)", y=2157.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_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               3.349234E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                   50616
 MPI messages size (bytes):
  total size                         1.536549E+12
  min size                           0.000000E+00
  max size                          72.286792E+06
  average size                      30.356986E+06
 MPI breakdown and total messages size (bytes):
             size <=      128               10368                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                1056                104411904
    131072 < size <=  4194304                3168                831638784
   4194304 < size <= 16777216                3103              33613273640
  16777216 < size                           32921            1501999894888
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 266696.
 MP_Allreduce         3058                  13371.
 MP_Sync                 4
 MP_Alltoall            47               30278988.
 MP_SendRecv            69                  86400.
 MP_ISendRecv           69                  86400.
 MP_Wait               531
 MP_ISend              378                 823502.
 MP_IRecv              378                 823753.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.040    0.063   96.209   96.211
 qs_energies                          1  2.0    0.000    0.000   95.470   95.476
 ls_scf                               1  3.0    0.001    0.008   93.820   93.825
 dbcsr_multiply_generic             111  6.7    0.016    0.018   77.496   77.770
 ls_scf_main                          1  4.0    0.000    0.000   58.088   58.090
 multiply_cannon                    111  7.7    0.043    0.107   51.101   55.776
 density_matrix_trs4                  2  5.0    0.002    0.003   51.983   52.087
 multiply_cannon_loop               111  8.7    0.115    0.128   46.067   49.092
 ls_scf_init_scf                      1  4.0    0.000    0.001   32.536   32.538
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   31.199   31.268
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.002   28.751   28.762
 mp_waitall_1                      6369 11.0   21.809   28.187   21.809   28.187
 multiply_cannon_multrec           1332  9.7   14.242   17.759   22.124   25.376
 make_m2s                           222  7.7    0.006    0.008   20.788   22.250
 make_images                        222  8.7    3.140    3.590   20.738   22.202
 multiply_cannon_metrocomm3        1332  9.7    0.003    0.003    8.710   16.854
 make_images_data                   222  9.7    0.004    0.004   11.482   13.097
 hybrid_alltoall_any                227 10.6    0.797    3.777   10.814   12.685
 dbcsr_mm_accdrv_process           3641 10.4    0.211    0.397    7.510    9.016
 dbcsr_mm_accdrv_process_sort      3641 11.4    7.139    8.600    7.139    8.600
 mp_sum_l                           807  5.4    4.036    7.343    4.036    7.343
 multiply_cannon_metrocomm4        1110  9.7    0.004    0.006    2.100    6.124
 mp_irecv_dv                       3229 10.9    2.077    6.045    2.077    6.045
 multiply_cannon_sync_h2d          1332  9.7    5.524    6.021    5.524    6.021
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.144    5.797
 arnoldi_extremal                     4  6.8    0.000    0.002    5.201    5.216
 arnoldi_normal_ev                    4  7.8    0.002    0.005    5.201    5.214
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.003    2.448    4.972
 build_subspace                      16  8.4    0.015    0.021    4.863    4.874
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.520    4.740
 calculate_norms                   2376  9.8    4.203    4.524    4.203    4.524
 mp_allgather_i34                   111  8.7    2.163    4.508    2.163    4.508
 dbcsr_matrix_vector_mult           304  9.0    0.010    0.020    3.556    3.863
 dbcsr_matrix_vector_mult_local     304 10.0    3.169    3.672    3.171    3.674
 dbcsr_sort_data                    658 11.4    3.100    3.406    3.100    3.406
 ls_scf_post                          1  4.0    0.000    0.001    3.195    3.200
 dbcsr_special_finalize             555  9.7    0.006    0.008    2.854    3.146
 dbcsr_merge_single_wm              555 10.7    0.541    0.653    2.846    3.138
 ls_scf_dm_to_ks                      2  5.0    0.000    0.001    3.006    3.057
 ls_scf_store_result                  1  5.0    0.000    0.000    2.934    2.984
 dbcsr_data_release               10477 10.7    1.595    2.497    1.595    2.497
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.036    2.037
 rebuild_ks_matrix                    3  7.3    0.000    0.000    2.012    2.014
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.004    2.012    2.014
 dbcsr_finalize                     304  7.8    0.049    0.061    1.799    1.993
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="506", plot="h2o_32_nrep3_ls", label="(8n/3r/4t)", y=96.211000, yerr=0.000000
PlotPoint: name="507", plot="h2o_32_nrep3_ls_mem", label="(8n/3r/4t)", y=2698.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_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               4.627685E+09
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                   10656
 MPI messages size (bytes):
  total size                         1.149035E+12
  min size                           0.000000E+00
  max size                         203.538048E+06
  average size                     107.829832E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                2304                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304                 768                702038016
   4194304 < size <= 16777216                   0                        0
  16777216 < size                            7584            1148332810224
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast                2                     12.
 MP_Allreduce          705                    128.
 MP_Alltoall           310               12920694.
 MP_ISend             1776               40180424.
 MP_IRecv             1776               40465030.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 265558.
 MP_Allreduce         3049                  15663.
 MP_Sync                 4
 MP_Alltoall            47               46208988.
 MP_SendRecv            45                 115200.
 MP_ISendRecv           45                 115200.
 MP_Wait               528
 MP_ISend              420                 924980.
 MP_IRecv              420                 924528.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.046    0.062   98.718   98.718
 qs_energies                          1  2.0    0.000    0.000   97.909   97.911
 ls_scf                               1  3.0    0.000    0.000   95.958   95.961
 dbcsr_multiply_generic             111  6.7    0.017    0.019   77.223   77.482
 ls_scf_main                          1  4.0    0.000    0.000   61.548   61.549
 multiply_cannon                    111  7.7    0.080    0.132   54.630   59.206
 density_matrix_trs4                  2  5.0    0.002    0.003   54.294   54.380
 multiply_cannon_loop               111  8.7    0.070    0.078   50.238   52.781
 mp_waitall_1                      5436 11.0   25.692   31.406   25.692   31.406
 ls_scf_init_scf                      1  4.0    0.000    0.000   30.786   30.792
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   29.415   29.458
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.288   27.297
 multiply_cannon_multrec            444  9.7   14.062   16.825   21.094   23.470
 make_m2s                           222  7.7    0.004    0.005   17.501   19.925
 make_images                        222  8.7    3.731    4.421   17.439   19.865
 multiply_cannon_metrocomm1         444  9.7    0.002    0.002   10.701   15.670
 multiply_cannon_metrocomm3         444  9.7    0.001    0.001    6.053   14.805
 make_images_data                   222  9.7    0.003    0.004    9.743   12.094
 hybrid_alltoall_any                227 10.6    0.792    3.785    9.508   11.918
 multiply_cannon_sync_h2d           444  9.7    6.532    7.956    6.532    7.956
 dbcsr_mm_accdrv_process           3003 10.4    0.190    0.355    6.738    7.863
 dbcsr_mm_accdrv_process_sort      3003 11.4    6.420    7.519    6.420    7.519
 mp_allgather_i34                   111  8.7    2.644    6.958    2.644    6.958
 arnoldi_extremal                     4  6.8    0.000    0.000    5.783    5.792
 arnoldi_normal_ev                    4  7.8    0.001    0.004    5.783    5.792
 build_subspace                      16  8.4    0.015    0.020    5.394    5.402
 mp_sum_l                           807  5.4    3.131    5.004    3.131    5.004
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.556    4.703
 dbcsr_matrix_vector_mult           304  9.0    0.011    0.020    4.149    4.342
 dbcsr_matrix_vector_mult_local     304 10.0    3.678    4.143    3.680    4.145
 multiply_cannon_metrocomm4         333  9.7    0.001    0.002    1.670    3.943
 mp_irecv_dv                       1241 11.2    1.650    3.917    1.650    3.917
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    2.219    3.868
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    3.678    3.779
 calculate_norms                    792  9.8    3.529    3.646    3.529    3.646
 ls_scf_post                          1  4.0    0.000    0.000    3.623    3.625
 ls_scf_store_result                  1  5.0    0.000    0.000    3.376    3.418
 make_images_sizes                  222  9.7    0.000    0.000    1.101    3.163
 mp_alltoall_i44                    222 10.7    1.101    3.163    1.101    3.163
 dbcsr_finalize                     304  7.8    0.062    0.078    2.201    2.257
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.217    2.218
 rebuild_ks_matrix                    3  7.3    0.000    0.000    2.184    2.185
 qs_ks_build_kohn_sham_matrix         3  8.3    0.000    0.001    2.184    2.185
 dbcsr_merge_all                    275  8.9    0.475    0.523    2.053    2.095
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="508", plot="h2o_32_nrep3_ls", label="(8n/2r/6t)", y=98.718000, yerr=0.000000
PlotPoint: name="509", plot="h2o_32_nrep3_ls_mem", label="(8n/2r/6t)", y=3633.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/f387d9e52db66ef3f179c70ace9df802df4c9cad_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               8.760795E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                    4440
 MPI messages size (bytes):
  total size                       770.525954E+09
  min size                           0.000000E+00
  max size                         399.069120E+06
  average size                     173.541888E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                 640                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304                 640                468025344
   4194304 < size <= 16777216                   0                        0
  16777216 < size                            3160             770057961712
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 284111.
 MP_Allreduce         3043                  21950.
 MP_Sync                 4
 MP_Alltoall            47               88727262.
 MP_SendRecv            42                 732600.
 MP_ISendRecv           42                 732600.
 MP_Wait               267
 MP_ISend              180                3337386.
 MP_IRecv              180                3339494.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.088    0.142  108.381  108.381
 qs_energies                          1  2.0    0.000    0.000  106.887  106.900
 ls_scf                               1  3.0    0.000    0.000  103.877  103.889
 dbcsr_multiply_generic             111  6.7    0.023    0.026   77.299   77.429
 ls_scf_main                          1  4.0    0.000    0.000   65.992   65.993
 density_matrix_trs4                  2  5.0    0.002    0.003   56.668   56.723
 multiply_cannon                    111  7.7    0.158    0.335   49.971   52.088
 multiply_cannon_loop               111  8.7    0.068    0.072   46.494   47.333
 ls_scf_init_scf                      1  4.0    0.000    0.000   34.199   34.200
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   32.529   32.541
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   29.711   29.718
 mp_waitall_1                      4527 11.1   22.188   25.776   22.188   25.776
 make_m2s                           222  7.7    0.005    0.005   23.782   24.784
 make_images                        222  8.7    4.595    4.999   23.676   24.676
 multiply_cannon_multrec            444  9.7   17.832   18.591   22.446   23.209
 hybrid_alltoall_any                227 10.6    1.658    3.609   12.858   15.645
 make_images_data                   222  9.7    0.003    0.003   13.016   15.447
 multiply_cannon_metrocomm3         444  9.7    0.001    0.001   10.567   11.190
 multiply_cannon_sync_h2d           444  9.7    8.844    8.908    8.844    8.908
 arnoldi_extremal                     4  6.8    0.000    0.000    7.311    7.320
 arnoldi_normal_ev                    4  7.8    0.002    0.008    7.311    7.320
 build_subspace                      16  8.4    0.026    0.037    6.757    6.768
 dbcsr_matrix_vector_mult           304  9.0    0.016    0.032    5.409    5.564
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    5.296    5.382
 dbcsr_matrix_vector_mult_local     304 10.0    4.991    5.293    4.993    5.296
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.010    5.243
 dbcsr_mm_accdrv_process           1814 10.4    0.187    0.328    4.439    4.553
 dbcsr_mm_accdrv_process_sort      1814 11.4    4.132    4.266    4.132    4.266
 ls_scf_post                          1  4.0    0.000    0.000    3.686    3.698
 mp_allgather_i34                   111  8.7    1.136    3.552    1.136    3.552
 make_images_sizes                  222  9.7    0.000    0.000    1.425    3.539
 mp_alltoall_i44                    222 10.7    1.425    3.538    1.425    3.538
 ls_scf_store_result                  1  5.0    0.000    0.000    3.405    3.414
 calculate_norms                    792  9.8    3.244    3.288    3.244    3.288
 dbcsr_finalize                     304  7.8    0.082    0.089    3.075    3.137
 qs_energies_init_hamiltonians        1  3.0    0.001    0.001    2.980    2.980
 dbcsr_merge_all                    275  8.9    0.891    0.922    2.861    2.916
 dbcsr_complete_redistribute          5  7.6    1.459    1.493    2.786    2.903
 dbcsr_data_release               12724 10.6    2.335    2.821    2.335    2.821
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.590    2.592
 matrix_ls_to_qs                      2  6.0    0.000    0.000    2.454    2.588
 rebuild_ks_matrix                    3  7.3    0.000    0.000    2.524    2.526
 qs_ks_build_kohn_sham_matrix         3  8.3    0.000    0.001    2.524    2.526
 dbcsr_sort_data                    325 11.1    2.441    2.504    2.441    2.504
 dbcsr_new_transposed                 4  7.5    0.243    0.253    2.298    2.312
 dbcsr_frobenius_norm                74  6.6    2.061    2.134    2.192    2.233
 dbcsr_add_d                        103  6.2    0.000    0.000    2.131    2.205
 dbcsr_add_anytype                  103  7.2    0.859    0.891    2.130    2.205
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="510", plot="h2o_32_nrep3_ls", label="(8n/1r/12t)", y=108.381000, yerr=0.000000
PlotPoint: name="511", plot="h2o_32_nrep3_ls_mem", label="(8n/1r/12t)", y=6869.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


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

CommitSHA: f387d9e52db66ef3f179c70ace9df802df4c9cad
Summary: empty
Status: OK