=== 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: 2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4


################# ARCHITECTURE FILE ##################
#!/bin/bash
#
# CP2K arch file for Cray-XC50 (Piz Daint, CSCS, GPU partition)
#
# Tested with: GNU 9.3.0, Cray-MPICH 7.7.18, Cray-libsci 20.09.1, Cray-FFTW 3.3.8.10,
#              COSMA 2.6.2, ELPA 2021.11.002, LIBINT 2.6.0, LIBPEXSI 1.2.0,
#              LIBXC 5.2.3, LIBVORI 220621, LIBXSMM 1.17, PLUMED 2.8.0,
#              SIRIUS 7.3.2, SPGLIB 1.16.2
#
# Usage: Source this arch file and then run make as instructed.
#        A full toolchain installation is performed as default.
#        Replace or adapt the "module add" commands below if needed.
#
# Author: Matthias Krack (15.09.2022)
#
# \
   if [ "${0}" = "${BASH_SOURCE}" ]; then \
      echo "ERROR: Script ${0##*/} must be sourced"; \
      echo "Usage: source ${0##*/}"; \
      exit 1; \
   fi; \
   this_file=${BASH_SOURCE##*/}; \
   if [ -n "${1}" ]; then \
      gcc_version="${1}"; \
   else \
      gcc_version="9.3.0"; \
   fi; \
   module add daint-gpu; \
   module rm PrgEnv-cray; \
   module add PrgEnv-gnu; \
   module rm gcc; \
   module add gcc/${gcc_version}; \
   module add cray-fftw/3.3.8.10; \
   module add cudatoolkit; \
   echo "Expected setup:"; \
   echo "   cray-mpich/7.7.18"; \
   echo "   craype-haswell"; \
   echo "   daint-gpu/21.09"; \
   echo "   craype/2.7.10"; \
   echo "   cray-libsci/20.09.1"; \
   echo "   PrgEnv-gnu/6.0.10"; \
   echo "   gcc/${gcc_version}"; \
   echo "   cray-fftw/3.3.8.10"; \
   echo "   cudatoolkit/11.0.2_3.38-8.1__g5b73779"; \
   module list; \
   module -f save cp2k_gpu_gnu_psmp; \
   echo "To load the required modules in your batch job script, use:"; \
   echo "   module restore cp2k_gpu_gnu_psmp"; \
   cd tools/toolchain; \
   ./install_cp2k_toolchain.sh --enable-cuda=yes --gpu-ver=P100 --no-arch-files --with-gcc=system --with-libvdwxc --with-pexsi --with-plumed; \
   cd ../..; \
   printf "Sourcing ${PWD}/tools/toolchain/install/setup ... "; \
   source ${PWD}/tools/toolchain/install/setup; \
   printf "done\n"; \
   echo "Check the output above for error messages and consistency!"; \
   echo "If everything is OK, you can build a CP2K production binary with"; \
   echo "   make -j ARCH=${this_file%.*} VERSION=${this_file##*.}"; \
   echo "Alternatively, you can add further checks, e.g. for regression testing, with"; \
   echo "   make -j ARCH=${this_file%.*} VERSION=${this_file##*.} DO_CHECKS=yes"; \
   echo "or build CP2K as a library with"; \
   echo "   make -j ARCH=${this_file%.*} VERSION=${this_file##*.} libcp2k"; \
   return

# Set options
DO_CHECKS      := no
USE_ACC        := yes
USE_COSMA      := 2.6.2
USE_ELPA       := 2021.11.002
USE_LIBINT     := 2.6.0
USE_LIBPEXSI   := 1.2.0
USE_LIBVORI    := 220621
USE_LIBXC      := 5.2.3
USE_LIBXSMM    := 1.17
USE_PLUMED     := 2.8.0
#USE_QUIP       := b4336484fb65b0e73211a8f920ae4361c7c353fd
USE_SIRIUS     := 7.3.2
USE_SPGLIB     := 1.16.2
# Only needed for SIRIUS
LIBVDWXC_VER   := 0.4.0
SPFFT_VER      := 1.0.6
SPLA_VER       := 1.5.4
HDF5_VER       := 1.12.0
# Only needed for LIBPEXSI
SCOTCH_VER     := 6.0.0
SUPERLU_VER    := 6.1.0

LMAX           := 5
MAX_CONTR      := 4

GPUVER         := P100
OFFLOAD_TARGET := cuda

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

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

DFLAGS         := -D__parallel
DFLAGS         += -D__SCALAPACK
DFLAGS         += -D__FFTW3
DFLAGS         += -D__MPI_VERSION=3
DFLAGS         += -D__MAX_CONTR=$(strip $(MAX_CONTR))

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

CFLAGS         += $(DFLAGS)

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

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

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

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

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

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


===== TESTS (description) =====
 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-32 RI-RPA/RI-MP2 correlation energy
 input file: benchmarks/QS_mp2_rpa/32-H2O/RI-RPA.inp
 required files: ['benchmarks/QS_mp2_rpa/32-H2O/BASIS_H2O', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32.xyz', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32-PBE-TZ.inp', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32-RI-dRPA-TZ.inp']
 output file: result.log
 # nodes = 8
 # ranks/node = 2
 # threads/rank = 6
 nrepeat = 1
 time[min] = 15
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/01
 job id: 41542066
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/02
 job id: 41542102
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/03
 job id: 41542109
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/04
 job id: 41542114
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/05
 job id: 41542117
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/06
 job id: 41542123
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/07
 job id: 41542126
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/08
 job id: 41542131
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/09
 job id: 41542135
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/10
 job id: 41542137
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/11
 job id: 41542144
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/12
 job id: 41542152
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/13
 job id: 41542160
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/14
 job id: 41542166
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/15
 job id: 41542167
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/16
 job id: 41542168
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/17
 job id: 41542169
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/18
 job id: 41542170
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/19
 job id: 41542171
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/20
 job id: 41542172
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/21
 job id: 41542173
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/22
 job id: 41542174
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/23
 job id: 41542175
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/24
 job id: 41542177
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/25
 job id: 41542178
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/26
 job id: 41542180
 --- 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/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/01/result.log


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

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

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               15                 177869.
 MP_Allreduce          344                      9.
 MP_Sync                 3
 MP_comm_split           1
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.022    0.037  136.386  136.386
 farming_run                          1  2.0  135.814  135.815  136.351  136.354
 -------------------------------------------------------------------------------


 @@@@@@@@@@ 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               1.449554E+09
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                    2592
 MPI messages size (bytes):
  total size                         1.140326E+09
  min size                           0.000000E+00
  max size                           1.663488E+06
  average size                     439.940750E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                 132                        0
       128 < size <=     8192                 348                  2850816
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                1536                179306496
    131072 < size <=  4194304                 576                958169088
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         2308                     54.
 MP_Alltoall          4670                 822215.
 MP_ISend             2604                  90577.
 MP_IRecv             2604                  90574.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group               12
 MP_Bcast              228                1113141.
 MP_Allreduce          489                2263609.
 MP_Sync                27
 MP_Alltoall            38                9316958.
 MP_SendRecv            30                 829726.
 MP_ISendRecv          135                 235435.
 MP_Wait               281
 MP_comm_split           8
 MP_ISend              127                3867574.
 MP_IRecv              127                3866554.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.011    0.033  117.780  117.780
 qs_energies                          1  2.0    0.000    0.000  117.562  117.564
 mp2_main                             1  3.0    0.000    0.000  115.354  115.356
 mp2_gpw_main                         1  4.0    0.019    0.027  114.219  114.221
 mp2_ri_gpw_compute_in                1  5.0    0.171    0.173   95.171   95.411
 mp2_ri_gpw_compute_in_loop           1  6.0    0.004    0.004   56.389   56.629
 mp2_eri_3c_integrate_gpw           272  7.0    0.152    0.168   42.716   47.904
 get_2c_integrals                     1  6.0    0.000    0.000   37.878   38.610
 integrate_v_rspace                 273  8.0    0.433    0.447   25.265   30.190
 pw_transfer                       6555 10.6    0.380    0.406   27.699   28.233
 fft_wrap_pw1pw2                   5465 11.4    0.046    0.048   26.350   26.800
 grid_integrate_task_list           273  9.0   21.021   26.474   21.021   26.474
 fft_wrap_pw1pw2_100               2178 12.4    1.192    1.400   23.901   24.335
 compute_2c_integrals                 1  7.0    0.002    0.003   20.445   20.446
 compute_2c_integrals_loop_lm         1  8.0    0.003    0.003   19.690   20.139
 mp2_eri_2c_integrate_gpw             1  9.0    2.376    2.430   19.688   20.136
 rpa_ri_compute_en                    1  5.0    0.000    0.000   18.936   19.121
 cp_fm_cholesky_decompose            12  8.2   17.619   18.368   17.619   18.368
 cholesky_decomp                      1  7.0    0.000    0.000   16.282   17.018
 fft3d_s                           5443 13.4   16.371   16.852   16.393   16.875
 ao_to_mo_and_store_B_mult_1        272  7.0   10.850   15.600   10.850   15.600
 calculate_wavefunction             272  8.0    5.447    5.595   12.664   13.253
 rpa_num_int                          1  6.0    0.000    0.000   10.859   10.860
 rpa_num_int_RPA_matrix_operati       8  7.0    0.000    0.000   10.785   10.846
 calc_potential_gpw                 544  9.5    0.005    0.005    9.708   10.021
 calc_mat_Q                           8  8.0    0.000    0.000    9.406    9.517
 mp2_eri_2c_integrate_gpw_pot_l     272 10.0    0.001    0.002    8.962    9.246
 contract_S_to_Q                      8  9.0    0.000    0.000    8.827    8.937
 parallel_gemm_fm                    14  9.1    0.000    0.000    8.401    8.497
 parallel_gemm_fm_cosma              14 10.1    8.401    8.496    8.401    8.496
 potential_pw2rs                    545 10.0    0.106    0.109    7.749    8.434
 collocate_single_gaussian          272 10.0    0.039    0.042    7.529    7.813
 create_integ_mat                     1  6.0    0.022    0.028    7.742    7.743
 array2fm                             1  7.0    0.000    0.000    6.585    7.102
 pw_scatter_s                      2720 13.7    4.450    4.552    4.450    4.552
 pw_gather_s                       2722 13.2    3.961    4.365    3.961    4.365
 pw_poisson_solve                   545 10.5    2.484    2.534    3.534    3.684
 array2fm_buffer_send                 1  8.0    2.899    3.159    2.899    3.159
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="10", plot="h2o_32_ri_rpa_mp2", label="RI-RPA (8n/2r/6t)", y=114.220487, yerr=0.000000
PlotPoint: name="11", plot="h2o_32_ri_rpa_mp2_mem", label="RI-RPA (8n/2r/6t)", y=2721.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_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    0.036    0.057  400.304  400.308
 farming_run                          1  2.0  399.099  399.109  400.221  400.238
 -------------------------------------------------------------------------------


 @@@@@@@@@@ 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               1.223090E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                   61440
 MPI messages size (bytes):
  total size                         6.073508E+09
  min size                           0.000000E+00
  max size                         642.960000E+03
  average size                      98.852664E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               32004                        0
       128 < size <=     8192                1820                 14909440
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072               18640               1081442304
    131072 < size <=  4194304                8976               4977156096
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         1003                     44.
 MP_Alltoall          1797                 713538.
 MP_ISend             3686                  54943.
 MP_IRecv             3622                  54292.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group               12
 MP_Bcast              703                 408373.
 MP_Allreduce         1825                  23678.
 MP_Sync                38
 MP_Alltoall            77                3645667.
 MP_SendRecv          2171                2843495.
 MP_ISendRecv         1739                 144022.
 MP_Wait              2051
 MP_comm_split           7
 MP_ISend              264                 362227.
 MP_IRecv              264                 362718.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.017    0.048  211.256  211.256
 qs_energies                          1  2.0    0.000    0.000  211.003  211.009
 scf_env_do_scf                       1  3.0    0.000    0.000  107.114  107.115
 qs_ks_update_qs_env                  5  5.0    0.000    0.000  106.184  106.192
 rebuild_ks_matrix                    4  6.0    0.000    0.000  106.183  106.190
 qs_ks_build_kohn_sham_matrix         4  7.0    0.056    0.063  106.183  106.190
 hfx_ks_matrix                        4  8.0    0.001    0.001  105.801  105.804
 integrate_four_center                4  9.0    0.144    0.458  105.800  105.803
 mp2_main                             1  3.0    0.001    0.008  103.596  103.602
 mp2_gpw_main                         1  4.0    0.036    0.063  102.675  102.688
 integrate_four_center_main           4 10.0    0.121    0.602   96.780   99.885
 integrate_four_center_bin          264 11.0   96.660   99.860   96.660   99.860
 init_scf_loop                        1  4.0    0.000    0.000   92.879   92.881
 mp2_ri_gpw_compute_in                1  5.0    0.067    0.095   75.881   76.980
 mp2_ri_gpw_compute_in_loop           1  6.0    0.002    0.014   54.989   56.102
 mp2_eri_3c_integrate_gpw            91  7.0    0.144    0.167   42.592   47.701
 integrate_v_rspace                  95  8.0    0.396    0.574   28.520   33.400
 pw_transfer                       2240 10.6    0.148    0.170   30.144   30.560
 fft_wrap_pw1pw2                   1868 11.4    0.018    0.021   29.145   29.477
 grid_integrate_task_list            95  9.0   23.795   28.892   23.795   28.892
 mp2_ri_gpw_compute_en                1  5.0    0.056    0.064   26.619   28.416
 ao_to_mo_and_store_B_mult_1         91  7.0   10.704   27.381   10.704   27.381
 fft_wrap_pw1pw2_100                730 12.4    1.244    1.414   26.876   27.206
 mp2_ri_gpw_compute_en_RI_loop        1  6.0    1.846    1.896   24.862   24.874
 get_2c_integrals                     1  6.0    0.003    0.028   20.780   20.828
 compute_2c_integrals                 1  7.0    0.007    0.026   19.760   19.773
 compute_2c_integrals_loop_lm         1  8.0    0.002    0.008   19.211   19.616
 mp2_eri_2c_integrate_gpw             1  9.0    1.745    1.831   19.209   19.615
 fft3d_s                           1823 13.4   18.539   18.885   18.552   18.898
 scf_env_do_scf_inner_loop            4  4.0    0.000    0.000   14.232   14.233
 calculate_wavefunction              91  8.0    2.024    2.060    9.811   10.089
 potential_pw2rs                    186 10.0    0.033    0.035    8.692    9.393
 mp2_ri_gpw_compute_en_expansio     172  7.0    0.554    0.587    8.738    9.251
 mp2_eri_2c_integrate_gpw_pot_l      91 10.0    0.001    0.001    8.560    9.063
 calc_potential_gpw                 182  9.5    0.002    0.002    8.570    8.886
 local_gemm                         172  8.0    8.184    8.685    8.184    8.685
 mp2_ri_gpw_compute_en_comm          22  7.0    0.499    0.522    7.888    8.421
 collocate_single_gaussian           91 10.0    0.017    0.020    7.909    8.256
 mp2_ri_gpw_compute_en_ener         172  7.0    6.344    6.441    6.344    6.441
 mp_sendrecv_dm3                   2068  8.0    5.919    6.430    5.919    6.430
 mp_sync                             38 10.4    3.707    5.769    3.707    5.769
 pw_gather_s                        912 13.2    5.034    5.487    5.034    5.487
 pw_scatter_s                       910 13.7    3.956    4.246    3.956    4.246
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="20", plot="h2o_32_ri_rpa_mp2", label="RI-MP2 (8n/6r/2t)", y=102.666572, yerr=0.000000
PlotPoint: name="21", plot="h2o_32_ri_rpa_mp2_mem", label="RI-MP2 (8n/6r/2t)", y=1510.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/03/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                     29.277748E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               5055360       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      29.1
 marketing flops                     2.107592E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             450.510848E+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
 MP_ISendRecv        45220                   5520.
 MP_Wait             60486
 MP_comm_split          50
 MP_ISend            20771                  42672.
 MP_IRecv            20771                  42672.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.014    0.026   53.644   53.645
 qs_mol_dyn_low                       1  2.0    0.003    0.005   53.445   53.461
 qs_forces                           11  3.9    0.014    0.016   53.298   53.300
 qs_energies                         11  4.9    0.002    0.004   51.802   51.822
 scf_env_do_scf                      11  5.9    0.000    0.001   45.781   45.781
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.007   43.600   43.601
 dbcsr_multiply_generic            2286 12.5    0.093    0.098   34.312   34.922
 qs_scf_new_mos                     108  7.5    0.000    0.001   33.104   33.400
 qs_scf_loop_do_ot                  108  8.5    0.000    0.001   33.104   33.400
 ot_scf_mini                        108  9.5    0.002    0.002   31.397   31.623
 multiply_cannon                   2286 13.5    0.184    0.192   26.168   28.035
 multiply_cannon_loop              2286 14.5    1.511    1.597   25.372   27.207
 velocity_verlet                     10  3.0    0.001    0.002   26.780   26.782
 ot_mini                            108 10.5    0.001    0.001   20.214   20.467
 qs_ot_get_derivative               108 11.5    0.001    0.001   17.152   17.374
 mp_waitall_1                    267858 16.1    9.310   15.758    9.310   15.758
 multiply_cannon_metrocomm3       54864 15.5    0.066    0.070    6.173   13.764
 multiply_cannon_multrec          54864 15.5    4.146    6.394    7.416   10.782
 rebuild_ks_matrix                  119  8.3    0.000    0.000    8.180    8.307
 qs_ks_build_kohn_sham_matrix       119  9.3    0.010    0.011    8.179    8.306
 multiply_cannon_sync_h2d         54864 15.5    5.804    8.002    5.804    8.002
 mp_sum_l                          7207 12.9    5.884    7.668    5.884    7.668
 qs_ks_update_qs_env                119  7.6    0.001    0.001    7.229    7.350
 qs_ot_get_p                        119 10.4    0.001    0.001    6.429    6.765
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    5.789    6.246
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    5.866    6.009
 sum_up_and_integrate               119 10.3    0.008    0.010    4.758    4.766
 init_scf_run                        11  5.9    0.000    0.001    4.759    4.759
 scf_env_initial_rho_setup           11  6.9    0.000    0.000    4.759    4.759
 integrate_v_rspace                 119 11.3    0.002    0.002    4.750    4.759
 qs_rho_update_rho_low              119  7.7    0.000    0.001    4.360    4.464
 calculate_rho_elec                 119  8.7    0.011    0.016    4.360    4.464
 dbcsr_mm_accdrv_process          76910 16.1    1.193    1.857    3.193    4.457
 multiply_cannon_metrocomm1       54864 15.5    0.053    0.059    2.022    3.876
 qs_ot_p2m_diag                      50 11.0    0.004    0.006    3.500    3.599
 rs_pw_transfer                     974 11.9    0.012    0.013    3.242    3.345
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.919    3.107
 apply_single                       119 13.6    0.000    0.000    2.918    3.106
 calculate_dm_sparse                119  9.5    0.000    0.000    2.927    3.039
 ot_diis_step                       108 11.5    0.006    0.006    2.749    2.750
 cp_dbcsr_syevd                      50 12.0    0.002    0.003    2.664    2.664
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    2.535    2.618
 density_rs2pw                      119  9.7    0.004    0.004    2.459    2.565
 jit_kernel_multiply                 13 15.8    1.938    2.510    1.938    2.510
 calculate_first_density_matrix       1  7.0    0.000    0.001    2.490    2.500
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    2.405    2.406
 cp_fm_redistribute_end              50 14.0    2.178    2.375    2.182    2.377
 cp_fm_diag_elpa_base                50 14.0    0.192    2.326    0.193    2.339
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.284    2.286
 wfi_extrapolate                     11  7.9    0.001    0.001    2.206    2.206
 acc_transpose_blocks             54864 15.5    0.226    0.245    1.753    2.184
 potential_pw2rs                    119 12.3    0.004    0.004    2.143    2.164
 init_scf_loop                       11  6.9    0.000    0.000    2.158    2.159
 grid_integrate_task_list           119 12.3    2.016    2.107    2.016    2.107
 mp_sum_d                          4129 12.0    1.411    2.058    1.411    2.058
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.964    2.006
 make_m2s                          4572 13.5    0.054    0.056    1.947    2.000
 make_images                       4572 14.5    0.133    0.139    1.864    1.915
 pw_transfer                       1439 11.6    0.051    0.055    1.814    1.888
 fft_wrap_pw1pw2                   1201 12.6    0.007    0.007    1.740    1.815
 fft3d_ps                          1201 14.6    0.358    0.458    1.517    1.587
 mp_alltoall_d11v                  2130 13.8    1.367    1.478    1.367    1.478
 fft_wrap_pw1pw2_140                487 13.2    0.081    0.095    1.338    1.412
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.387    1.409
 grid_collocate_task_list           119  9.7    1.288    1.344    1.288    1.344
 mp_waitany                       12084 13.8    1.181    1.305    1.181    1.305
 dbcsr_dot_sd                      1205 11.9    0.047    0.058    0.795    1.177
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="100", plot="h2o_64_md", label="(8n/12r/1t)", y=53.645000, yerr=0.000000
PlotPoint: name="101", plot="h2o_64_md_mem", label="(8n/12r/1t)", y=429.181818, yerr=1.113404
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_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             486.338560E+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                  73957.
 MP_ISendRecv        33558                  37093.
 MP_Wait             40318
 MP_comm_split          50
 MP_ISend             5720                 128509.
 MP_IRecv             5720                 128509.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.016    0.030   42.308   42.310
 qs_mol_dyn_low                       1  2.0    0.003    0.006   42.119   42.127
 qs_forces                           11  3.9    0.002    0.003   41.541   41.542
 qs_energies                         11  4.9    0.001    0.002   39.741   39.745
 scf_env_do_scf                      11  5.9    0.000    0.001   34.393   34.393
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   31.368   31.369
 dbcsr_multiply_generic            2286 12.5    0.101    0.104   22.348   22.710
 qs_scf_new_mos                     108  7.5    0.001    0.001   21.245   21.473
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   21.245   21.473
 velocity_verlet                     10  3.0    0.002    0.004   20.763   20.775
 ot_scf_mini                        108  9.5    0.002    0.003   20.289   20.461
 multiply_cannon                   2286 13.5    0.208    0.215   16.561   18.449
 multiply_cannon_loop              2286 14.5    0.905    0.982   15.275   16.701
 ot_mini                            108 10.5    0.001    0.001   12.573   12.815
 mp_waitall_1                    217478 16.2    7.119   12.030    7.119   12.030
 qs_ot_get_derivative               108 11.5    0.001    0.001   10.038   10.216
 multiply_cannon_metrocomm3       27432 15.5    0.068    0.071    4.251    9.544
 multiply_cannon_multrec          27432 15.5    1.959    4.332    5.842    8.588
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.882    8.044
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    7.881    8.044
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.968    7.121
 dbcsr_mm_accdrv_process          47894 16.0    3.018    5.180    3.815    5.640
 qs_ot_get_p                        119 10.4    0.001    0.001    4.715    4.948
 sum_up_and_integrate               119 10.3    0.015    0.016    4.811    4.816
 integrate_v_rspace                 119 11.3    0.002    0.002    4.796    4.801
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    3.836    4.689
 qs_rho_update_rho_low              119  7.7    0.001    0.001    4.317    4.347
 calculate_rho_elec                 119  8.7    0.021    0.024    4.316    4.347
 mp_sum_l                          7207 12.9    2.297    4.183    2.297    4.183
 apply_preconditioner_dbcsr         119 12.6    0.000    0.001    3.084    4.162
 apply_single                       119 13.6    0.000    0.000    3.084    4.162
 init_scf_run                        11  5.9    0.000    0.001    4.071    4.072
 scf_env_initial_rho_setup           11  6.9    0.000    0.001    4.071    4.072
 rs_pw_transfer                     974 11.9    0.010    0.011    3.512    3.639
 make_m2s                          4572 13.5    0.052    0.054    3.041    3.286
 make_images                       4572 14.5    0.200    0.237    2.952    3.196
 qs_ot_p2m_diag                      50 11.0    0.009    0.013    3.001    3.020
 init_scf_loop                       11  6.9    0.000    0.000    2.997    2.997
 multiply_cannon_sync_h2d         27432 15.5    2.166    2.827    2.166    2.827
 density_rs2pw                      119  9.7    0.004    0.004    2.661    2.742
 potential_pw2rs                    119 12.3    0.006    0.006    2.515    2.541
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    2.450    2.540
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    2.530    2.530
 ot_diis_step                       108 11.5    0.011    0.013    2.471    2.472
 calculate_first_density_matrix       1  7.0    0.000    0.001    2.334    2.337
 pw_transfer                       1439 11.6    0.063    0.066    2.177    2.220
 calculate_dm_sparse                119  9.5    0.001    0.001    2.109    2.185
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    2.088    2.133
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    2.089    2.089
 cp_fm_redistribute_end              50 14.0    1.716    2.053    1.721    2.054
 cp_fm_diag_elpa_base                50 14.0    0.323    1.972    0.331    2.003
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.992    1.995
 prepare_preconditioner              11  7.9    0.000    0.000    1.958    1.987
 make_preconditioner                 11  8.9    0.000    0.000    1.958    1.987
 grid_integrate_task_list           119 12.3    1.831    1.955    1.831    1.955
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.850    1.910
 fft3d_ps                          1201 14.6    0.503    0.559    1.793    1.835
 make_images_data                  4572 15.5    0.045    0.051    1.301    1.795
 jit_kernel_multiply                  9 16.1    0.743    1.776    0.743    1.776
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.712    1.762
 wfi_extrapolate                     11  7.9    0.001    0.001    1.673    1.673
 hybrid_alltoall_any               4725 16.4    0.050    0.111    1.123    1.624
 mp_alltoall_d11v                  2130 13.8    1.453    1.597    1.453    1.597
 mp_allgather_i34                  2286 14.5    0.728    1.527    0.728    1.527
 fft_wrap_pw1pw2_140                487 13.2    0.077    0.085    1.468    1.515
 acc_transpose_blocks             27432 15.5    0.106    0.111    1.195    1.494
 grid_collocate_task_list           119  9.7    1.240    1.332    1.240    1.332
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.249    1.297
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.275    1.283
 make_images_sizes                 4572 15.5    0.005    0.005    0.924    1.258
 mp_alltoall_i44                   4572 16.5    0.920    1.253    0.920    1.253
 mp_sum_d                          4129 12.0    0.648    1.092    0.648    1.092
 mp_alltoall_z22v                  1201 16.6    0.970    1.062    0.970    1.062
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.976    0.988
 qs_energies_init_hamiltonians       11  5.9    0.000    0.001    0.982    0.983
 rs_pw_transfer_PW2RS_50            119 14.3    0.586    0.604    0.889    0.967
 cp_fm_cholesky_invert               11 10.9    0.877    0.882    0.877    0.882
 acc_transpose_blocks_kernels     27432 16.5    0.183    0.273    0.666    0.878
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="102", plot="h2o_64_md", label="(8n/6r/2t)", y=42.310000, yerr=0.000000
PlotPoint: name="103", plot="h2o_64_md_mem", label="(8n/6r/2t)", y=463.272727, yerr=1.354515
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_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             519.393280E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                  950976
 MPI messages size (bytes):
  total size                       203.844256E+09
  min size                           0.000000E+00
  max size                           1.638400E+06
  average size                     214.352688E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192              253512               2076770304
      8192 < size <=    32768              179424               2939682816
     32768 < size <=   131072              181440              14863564800
    131072 < size <=  4194304              330176             183964913216
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3672                  62660.
 MP_Allreduce        10225                    303.
 MP_Sync               104
 MP_Alltoall          1821                1607811.
 MP_ISendRecv        22134                  57667.
 MP_Wait             33054
 MP_comm_split          50
 MP_ISend             9880                  92618.
 MP_IRecv             9880                  92618.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.013    0.030   32.989   32.989
 qs_mol_dyn_low                       1  2.0    0.003    0.004   32.755   32.762
 qs_forces                           11  3.9    0.002    0.003   32.696   32.697
 qs_energies                         11  4.9    0.001    0.001   31.131   31.134
 scf_env_do_scf                      11  5.9    0.000    0.001   25.973   25.973
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   23.241   23.242
 dbcsr_multiply_generic            2286 12.5    0.096    0.099   17.009   17.087
 velocity_verlet                     10  3.0    0.001    0.002   15.603   15.605
 qs_scf_new_mos                     108  7.5    0.001    0.001   14.951   14.968
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   14.950   14.967
 multiply_cannon                   2286 13.5    0.195    0.205   13.483   14.290
 ot_scf_mini                        108  9.5    0.002    0.002   14.214   14.224
 multiply_cannon_loop              2286 14.5    0.640    0.670   12.652   13.469
 ot_mini                            108 10.5    0.001    0.001    8.903    8.919
 qs_ot_get_derivative               108 11.5    0.001    0.001    7.405    7.414
 multiply_cannon_multrec          18288 15.5    1.918    2.891    6.969    7.288
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.497    6.512
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.012    6.496    6.512
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.757    5.772
 dbcsr_mm_accdrv_process          38222 16.0    4.089    5.239    4.968    5.752
 mp_waitall_1                    169478 16.3    3.316    4.567    3.316    4.567
 sum_up_and_integrate               119 10.3    0.018    0.018    4.103    4.108
 integrate_v_rspace                 119 11.3    0.002    0.003    4.086    4.093
 init_scf_run                        11  5.9    0.000    0.001    3.918    3.918
 scf_env_initial_rho_setup           11  6.9    0.000    0.000    3.917    3.917
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.831    3.460
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.445    3.456
 calculate_rho_elec                 119  8.7    0.030    0.031    3.445    3.455
 qs_ot_get_p                        119 10.4    0.001    0.001    3.114    3.138
 init_scf_loop                       11  6.9    0.000    0.000    2.712    2.712
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.705    2.706
 rs_pw_transfer                     974 11.9    0.009    0.010    2.551    2.661
 multiply_cannon_metrocomm3       18288 15.5    0.044    0.046    1.439    2.489
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.044    2.363
 apply_single                       119 13.6    0.000    0.000    2.044    2.363
 make_m2s                          4572 13.5    0.044    0.046    2.040    2.204
 density_rs2pw                      119  9.7    0.004    0.004    2.013    2.129
 make_images                       4572 14.5    0.190    0.201    1.955    2.118
 jit_kernel_multiply                 10 16.2    0.826    2.086    0.826    2.086
 qs_ot_p2m_diag                      50 11.0    0.012    0.013    2.033    2.038
 calculate_dm_sparse                119  9.5    0.000    0.000    1.983    1.996
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.975    1.977
 grid_integrate_task_list           119 12.3    1.806    1.937    1.806    1.937
 potential_pw2rs                    119 12.3    0.007    0.008    1.891    1.901
 prepare_preconditioner              11  7.9    0.000    0.000    1.887    1.889
 make_preconditioner                 11  8.9    0.000    0.000    1.887    1.889
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.832    1.839
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.735    1.823
 pw_transfer                       1439 11.6    0.063    0.066    1.791    1.800
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.762    1.762
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.701    1.711
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.595    1.600
 multiply_cannon_sync_h2d         18288 15.5    1.392    1.550    1.392    1.550
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.513    1.515
 cp_fm_redistribute_end              50 14.0    1.122    1.490    1.123    1.490
 ot_diis_step                       108 11.5    0.011    0.011    1.477    1.477
 mp_sum_l                          7207 12.9    1.096    1.458    1.096    1.458
 cp_fm_diag_elpa_base                50 14.0    0.350    1.418    0.364    1.458
 acc_transpose_blocks             18288 15.5    0.074    0.075    1.380    1.417
 fft3d_ps                          1201 14.6    0.507    0.525    1.388    1.397
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.339    1.342
 fft_wrap_pw1pw2_140                487 13.2    0.087    0.090    1.317    1.328
 grid_collocate_task_list           119  9.7    1.203    1.285    1.203    1.285
 wfi_extrapolate                     11  7.9    0.001    0.001    1.165    1.165
 make_images_data                  4572 15.5    0.044    0.049    0.934    1.144
 hybrid_alltoall_any               4725 16.4    0.054    0.112    0.803    1.013
 acc_transpose_blocks_kernels     18288 16.5    0.213    0.220    0.941    0.974
 qs_energies_init_hamiltonians       11  5.9    0.000    0.001    0.935    0.936
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.881    0.904
 mp_alltoall_d11v                  2130 13.8    0.734    0.851    0.734    0.851
 cp_fm_cholesky_invert               11 10.9    0.825    0.832    0.825    0.832
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.808    0.809
 mp_alltoall_z22v                  1201 16.6    0.718    0.782    0.718    0.782
 jit_kernel_transpose                 5 15.6    0.728    0.756    0.728    0.756
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.665    0.731
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="104", plot="h2o_64_md", label="(8n/4r/3t)", y=32.989000, yerr=0.000000
PlotPoint: name="105", plot="h2o_64_md_mem", label="(8n/4r/3t)", y=494.727273, yerr=1.542778
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_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             554.102784E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1042416
 MPI messages size (bytes):
  total size                       150.443262E+09
  min size                           0.000000E+00
  max size                           1.188816E+06
  average size                     144.321719E+03
 MPI breakdown and total messages size (bytes):
             size <=      128              228256                        0
       128 < size <=     8192              126888               1039466496
      8192 < size <=    32768              191472               3137077248
     32768 < size <=   131072              295800              25899827200
    131072 < size <=  4194304              200000             120367247040
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3672                  62659.
 MP_Allreduce        10224                    344.
 MP_Sync               104
 MP_Alltoall          1582                2412273.
 MP_ISendRecv        16422                  74133.
 MP_Wait             24482
 MP_comm_split          50
 MP_ISend             7280                 135929.
 MP_IRecv             7280                 135929.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.053    0.159   36.971   36.972
 qs_mol_dyn_low                       1  2.0    0.003    0.005   36.523   36.542
 qs_forces                           11  3.9    0.002    0.004   35.804   35.804
 qs_energies                         11  4.9    0.002    0.003   34.064   34.070
 scf_env_do_scf                      11  5.9    0.000    0.001   28.791   28.792
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   25.169   25.172
 velocity_verlet                     10  3.0    0.001    0.002   19.027   19.056
 dbcsr_multiply_generic            2286 12.5    0.101    0.107   18.465   18.571
 qs_scf_new_mos                     108  7.5    0.001    0.001   16.620   16.666
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   16.619   16.665
 ot_scf_mini                        108  9.5    0.002    0.003   15.671   15.731
 multiply_cannon                   2286 13.5    0.233    0.272   14.586   15.001
 multiply_cannon_loop              2286 14.5    0.937    0.968   13.586   13.954
 ot_mini                            108 10.5    0.001    0.001    9.582    9.660
 multiply_cannon_multrec          27432 15.5    2.336    3.001    8.583    8.958
 qs_ot_get_derivative               108 11.5    0.001    0.001    7.720    7.783
 dbcsr_mm_accdrv_process          47916 15.9    5.190    7.068    6.152    7.299
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.733    6.783
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.016    6.733    6.783
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.998    6.042
 sum_up_and_integrate               119 10.3    0.020    0.024    3.976    3.985
 integrate_v_rspace                 119 11.3    0.002    0.003    3.956    3.965
 init_scf_run                        11  5.9    0.000    0.001    3.858    3.859
 scf_env_initial_rho_setup           11  6.9    0.000    0.001    3.858    3.858
 init_scf_loop                       11  6.9    0.000    0.001    3.595    3.602
 qs_ot_get_p                        119 10.4    0.001    0.001    3.446    3.531
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.472    3.507
 calculate_rho_elec                 119  8.7    0.040    0.046    3.472    3.507
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.879    3.272
 mp_waitall_1                    145218 16.4    2.531    3.105    2.531    3.105
 prepare_preconditioner              11  7.9    0.000    0.000    2.709    2.718
 make_preconditioner                 11  8.9    0.000    0.001    2.709    2.718
 make_full_inverse_cholesky          11  9.9    0.000    0.000    2.281    2.624
 make_m2s                          4572 13.5    0.054    0.056    2.380    2.526
 rs_pw_transfer                     974 11.9    0.009    0.010    2.336    2.477
 calculate_first_density_matrix       1  7.0    0.000    0.002    2.428    2.430
 make_images                       4572 14.5    0.273    0.332    2.271    2.415
 apply_preconditioner_dbcsr         119 12.6    0.000    0.001    2.068    2.194
 apply_single                       119 13.6    0.000    0.000    2.068    2.193
 calculate_dm_sparse                119  9.5    0.001    0.001    2.043    2.092
 qs_ot_p2m_diag                      50 11.0    0.016    0.023    2.080    2.089
 density_rs2pw                      119  9.7    0.003    0.004    1.939    2.072
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.983    2.014
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.900    1.902
 grid_integrate_task_list           119 12.3    1.829    1.891    1.829    1.891
 pw_transfer                       1439 11.6    0.063    0.066    1.859    1.890
 ot_diis_step                       108 11.5    0.012    0.014    1.818    1.818
 jit_kernel_multiply                 10 15.9    0.901    1.815    0.901    1.815
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.770    1.803
 potential_pw2rs                    119 12.3    0.009    0.010    1.756    1.762
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.751    1.751
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.650    1.668
 acc_transpose_blocks             27432 15.5    0.111    0.113    1.462    1.490
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.478    1.479
 fft3d_ps                          1201 14.6    0.534    0.586    1.448    1.475
 multiply_cannon_metrocomm3       27432 15.5    0.038    0.039    0.830    1.468
 cp_fm_redistribute_end              50 14.0    0.973    1.449    0.974    1.450
 fft_wrap_pw1pw2_140                487 13.2    0.087    0.095    1.405    1.439
 mp_sum_l                          7207 12.9    1.113    1.427    1.113    1.427
 cp_fm_diag_elpa_base                50 14.0    0.452    1.384    0.473    1.423
 wfi_extrapolate                     11  7.9    0.001    0.002    1.384    1.384
 grid_collocate_task_list           119  9.7    1.222    1.315    1.222    1.315
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.218    1.227
 dbcsr_complete_redistribute        329 12.2    0.138    0.178    0.917    1.203
 cp_fm_upper_to_full                 72 13.5    0.838    1.163    0.838    1.163
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.140    1.158
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    1.132    1.133
 make_images_data                  4572 15.5    0.045    0.049    0.945    1.121
 multiply_cannon_sync_h2d         27432 15.5    0.990    1.069    0.990    1.069
 hybrid_alltoall_any               4725 16.4    0.062    0.150    0.797    1.010
 mp_alltoall_d11v                  2130 13.8    0.853    0.997    0.853    0.997
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    0.694    0.973
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.798    0.871
 acc_transpose_blocks_kernels     27432 16.5    0.270    0.279    0.836    0.859
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.827    0.834
 cp_fm_cholesky_invert               11 10.9    0.828    0.831    0.828    0.831
 mp_alltoall_z22v                  1201 16.6    0.796    0.819    0.796    0.819
 mp_alltoall_i22                    627 13.8    0.498    0.818    0.498    0.818
 mp_sum_dm                          438  4.9    0.701    0.740    0.701    0.740
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="106", plot="h2o_64_md", label="(8n/3r/4t)", y=36.972000, yerr=0.000000
PlotPoint: name="107", plot="h2o_64_md_mem", label="(8n/3r/4t)", y=525.727273, yerr=4.473984
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_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             599.928832E+06
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  219456
 MPI messages size (bytes):
  total size                        97.042514E+09
  min size                           0.000000E+00
  max size                           3.276800E+06
  average size                     442.195750E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768              101892               3336634368
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304              116112              93705670464
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         8156                     20.
 MP_Alltoall          8655                  64935.
 MP_ISend            36532                 168375.
 MP_IRecv            36532                 168349.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3672                  62658.
 MP_Allreduce        10224                    344.
 MP_Sync               104
 MP_Alltoall          1582                3682667.
 MP_ISendRecv        10710                  94533.
 MP_Wait             16690
 MP_comm_split          50
 MP_ISend             5200                 225425.
 MP_IRecv             5200                 225425.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.058    0.105   28.715   28.716
 qs_mol_dyn_low                       1  2.0    0.003    0.004   28.411   28.419
 qs_forces                           11  3.9    0.002    0.002   28.292   28.293
 qs_energies                         11  4.9    0.004    0.005   26.608   26.610
 scf_env_do_scf                      11  5.9    0.000    0.001   21.688   21.688
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   19.149   19.149
 velocity_verlet                     10  3.0    0.005    0.006   14.628   14.634
 dbcsr_multiply_generic            2286 12.5    0.092    0.095   12.509   12.589
 qs_scf_new_mos                     108  7.5    0.001    0.001   11.345   11.367
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   11.345   11.367
 ot_scf_mini                        108  9.5    0.002    0.002   10.649   10.678
 multiply_cannon                   2286 13.5    0.245    0.260    9.793   10.305
 multiply_cannon_loop              2286 14.5    0.331    0.343    8.822    9.031
 multiply_cannon_multrec           9144 15.5    1.702    1.941    5.857    6.113
 rebuild_ks_matrix                  119  8.3    0.000    0.000    5.933    5.956
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    5.933    5.956
 ot_mini                            108 10.5    0.001    0.001    5.906    5.941
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.308    5.330
 qs_ot_get_derivative               108 11.5    0.001    0.001    4.575    4.605
 dbcsr_mm_accdrv_process          12550 15.8    3.062    3.531    4.054    4.145
 sum_up_and_integrate               119 10.3    0.022    0.023    3.652    3.657
 integrate_v_rspace                 119 11.3    0.003    0.003    3.630    3.635
 init_scf_run                        11  5.9    0.000    0.001    3.426    3.426
 scf_env_initial_rho_setup           11  6.9    0.000    0.000    3.426    3.426
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.330    3.337
 calculate_rho_elec                 119  8.7    0.059    0.061    3.329    3.337
 qs_ot_get_p                        119 10.4    0.001    0.001    2.904    2.951
 init_scf_loop                       11  6.9    0.000    0.000    2.518    2.518
 mp_waitall_1                    121218 16.5    1.893    2.489    1.893    2.489
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.270    2.271
 make_m2s                          4572 13.5    0.035    0.036    1.886    2.071
 make_images                       4572 14.5    0.266    0.298    1.796    1.981
 qs_ot_p2m_diag                      50 11.0    0.022    0.023    1.927    1.931
 grid_integrate_task_list           119 12.3    1.853    1.917    1.853    1.917
 rs_pw_transfer                     974 11.9    0.008    0.009    1.808    1.909
 density_rs2pw                      119  9.7    0.003    0.004    1.717    1.819
 pw_transfer                       1439 11.6    0.064    0.066    1.782    1.789
 prepare_preconditioner              11  7.9    0.000    0.000    1.771    1.776
 make_preconditioner                 11  8.9    0.000    0.000    1.771    1.776
 calculate_dm_sparse                119  9.5    0.000    0.000    1.724    1.744
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.722    1.723
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.692    1.699
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.655    1.681
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.672    1.674
 jit_kernel_multiply                  9 15.8    0.954    1.598    0.954    1.598
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    1.573    1.589
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.488    1.495
 potential_pw2rs                    119 12.3    0.010    0.011    1.433    1.438
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.421    1.422
 cp_fm_redistribute_end              50 14.0    0.709    1.397    0.710    1.398
 cp_fm_diag_elpa_base                50 14.0    0.640    1.314    0.687    1.378
 fft3d_ps                          1201 14.6    0.541    0.553    1.357    1.365
 fft_wrap_pw1pw2_140                487 13.2    0.084    0.087    1.355    1.364
 grid_collocate_task_list           119  9.7    1.274    1.345    1.274    1.345
 ot_diis_step                       108 11.5    0.012    0.013    1.318    1.318
 qs_energies_init_hamiltonians       11  5.9    0.008    0.010    1.241    1.241
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.204    1.219
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    1.193    1.215
 apply_single                       119 13.6    0.000    0.000    1.192    1.214
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.123    1.129
 hybrid_alltoall_any               4725 16.4    0.062    0.177    0.867    1.116
 wfi_extrapolate                     11  7.9    0.001    0.001    1.111    1.111
 make_images_data                  4572 15.5    0.039    0.042    0.887    1.103
 acc_transpose_blocks              9144 15.5    0.038    0.039    0.948    0.967
 mp_alltoall_d11v                  2130 13.8    0.875    0.964    0.875    0.964
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.867    0.916
 cp_fm_cholesky_invert               11 10.9    0.905    0.910    0.905    0.910
 multiply_cannon_metrocomm3        9144 15.5    0.018    0.019    0.343    0.801
 multiply_cannon_sync_h2d          9144 15.5    0.712    0.800    0.712    0.800
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.783    0.793
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.749    0.751
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    0.683    0.734
 mp_allgather_i34                  2286 14.5    0.286    0.729    0.286    0.729
 mp_alltoall_z22v                  1201 16.6    0.690    0.723    0.690    0.723
 acc_transpose_blocks_kernels      9144 16.5    0.118    0.122    0.706    0.721
 jit_kernel_transpose                 5 15.6    0.588    0.601    0.588    0.601
 dbcsr_complete_redistribute        329 12.2    0.167    0.189    0.561    0.589
 qs_create_task_list                 11  7.9    0.001    0.001    0.553    0.578
 generate_qs_task_list               11  8.9    0.190    0.212    0.553    0.577
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="108", plot="h2o_64_md", label="(8n/2r/6t)", y=28.716000, yerr=0.000000
PlotPoint: name="109", plot="h2o_64_md_mem", label="(8n/2r/6t)", y=569.090909, yerr=4.944318
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_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             738.041856E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                   91440
 MPI messages size (bytes):
  total size                        85.748679E+09
  min size                           0.000000E+00
  max size                           6.553600E+06
  average size                     937.758938E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                 572                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768               21148                692256768
     32768 < size <=   131072               19224               1259864064
    131072 < size <=  4194304               41040              21941452800
   4194304 < size <= 16777216                9456              61855174464
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3622                  63729.
 MP_Allreduce        10074                    433.
 MP_Sync                54
 MP_Alltoall          1582                7383731.
 MP_ISendRecv         4998                 189067.
 MP_Wait              8898
 MP_ISend             3120                 546875.
 MP_IRecv             3120                 546875.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.032    0.042   40.790   40.790
 qs_mol_dyn_low                       1  2.0    0.003    0.004   40.466   40.474
 qs_forces                           11  3.9    0.001    0.002   40.403   40.404
 qs_energies                         11  4.9    0.013    0.014   38.452   38.456
 scf_env_do_scf                      11  5.9    0.001    0.001   32.726   32.727
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.006   24.802   24.803
 velocity_verlet                     10  3.0    0.002    0.002   23.045   23.050
 dbcsr_multiply_generic            2286 12.5    0.101    0.103   17.502   17.671
 qs_scf_new_mos                     108  7.5    0.001    0.001   15.862   15.962
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   15.861   15.962
 ot_scf_mini                        108  9.5    0.002    0.002   14.780   14.880
 multiply_cannon                   2286 13.5    0.305    0.312   13.547   14.483
 multiply_cannon_loop              2286 14.5    0.344    0.351   12.289   13.205
 ot_mini                            108 10.5    0.001    0.001    8.825    8.940
 multiply_cannon_multrec           9144 15.5    3.333    4.567    8.527    8.624
 init_scf_loop                       11  6.9    0.000    0.000    7.897    7.899
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.908    7.048
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.013    6.907    7.047
 prepare_preconditioner              11  7.9    0.000    0.000    6.976    6.989
 make_preconditioner                 11  8.9    0.000    0.000    6.976    6.989
 qs_ot_get_derivative               108 11.5    0.001    0.001    6.780    6.877
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.511    6.862
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.239    6.365
 dbcsr_mm_accdrv_process          12550 15.8    3.996    5.604    5.071    6.341
 cp_fm_upper_to_full                 72 14.2    3.177    4.581    3.177    4.581
 sum_up_and_integrate               119 10.3    0.038    0.038    3.691    3.697
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.679    3.683
 calculate_rho_elec                 119  8.7    0.118    0.121    3.678    3.682
 init_scf_run                        11  5.9    0.000    0.001    3.680    3.680
 scf_env_initial_rho_setup           11  6.9    0.000    0.000    3.679    3.680
 integrate_v_rspace                 119 11.3    0.003    0.003    3.653    3.658
 mp_waitall_1                     97218 16.6    2.682    3.575    2.682    3.575
 qs_ot_get_p                        119 10.4    0.001    0.001    3.197    3.338
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.486    2.915
 dbcsr_complete_redistribute        329 12.2    0.290    0.294    2.004    2.853
 make_m2s                          4572 13.5    0.038    0.038    2.383    2.560
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    1.686    2.516
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.204    2.491
 apply_single                       119 13.6    0.000    0.000    2.204    2.491
 make_images                       4572 14.5    0.352    0.383    2.262    2.441
 mp_alltoall_i22                    627 13.8    1.496    2.335    1.496    2.335
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.284    2.287
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.460    2.282
 calculate_dm_sparse                119  9.5    0.000    0.000    2.150    2.168
 multiply_cannon_metrocomm3        9144 15.5    0.019    0.020    1.321    2.160
 pw_transfer                       1439 11.6    0.067    0.068    2.082    2.087
 ot_diis_step                       108 11.5    0.014    0.014    2.015    2.016
 grid_integrate_task_list           119 12.3    2.001    2.014    2.001    2.014
 fft_wrap_pw1pw2                   1201 12.6    0.009    0.009    1.987    1.992
 qs_ot_p2m_diag                      50 11.0    0.043    0.044    1.919    1.920
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.895    1.896
 density_rs2pw                      119  9.7    0.003    0.003    1.834    1.852
 mp_sum_l                          7207 12.9    1.032    1.772    1.032    1.772
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    1.766    1.767
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.691    1.742
 jit_kernel_multiply                 10 15.4    1.047    1.728    1.047    1.728
 fft_wrap_pw1pw2_140                487 13.2    0.086    0.087    1.651    1.658
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.643    1.644
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.609    1.638
 fft3d_ps                          1201 14.6    0.573    0.587    1.621    1.626
 cp_fm_cholesky_invert               11 10.9    1.583    1.586    1.583    1.586
 rs_pw_transfer                     974 11.9    0.009    0.009    1.478    1.517
 grid_collocate_task_list           119  9.7    1.444    1.459    1.444    1.459
 hybrid_alltoall_any               4725 16.4    0.087    0.147    1.151    1.414
 make_images_data                  4572 15.5    0.042    0.045    1.171    1.394
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.367    1.367
 cp_fm_diag_elpa_base                50 14.0    1.222    1.274    1.365    1.366
 wfi_extrapolate                     11  7.9    0.001    0.001    1.338    1.338
 potential_pw2rs                    119 12.3    0.014    0.014    1.270    1.273
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.218    1.226
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.151    1.173
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    1.106    1.123
 multiply_cannon_sync_h2d          9144 15.5    1.040    1.042    1.040    1.042
 mp_alltoall_d11v                  2130 13.8    1.015    1.030    1.015    1.030
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.987    1.022
 qs_create_task_list                 11  7.9    0.001    0.001    0.942    0.955
 generate_qs_task_list               11  8.9    0.372    0.392    0.941    0.954
 mp_alltoall_z22v                  1201 16.6    0.912    0.928    0.912    0.928
 acc_transpose_blocks              9144 15.5    0.038    0.038    0.904    0.908
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.880    0.893
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="110", plot="h2o_64_md", label="(8n/1r/12t)", y=40.790000, yerr=0.000000
PlotPoint: name="111", plot="h2o_64_md_mem", label="(8n/1r/12t)", y=696.636364, yerr=14.169575
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/09/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                    198.287135E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               8410880       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     117.0
 marketing flops                    15.646302E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank             500.166656E+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                 191650.
 MP_ISendRecv        41800                   9096.
 MP_Wait             58168
 MP_comm_split          48
 MP_ISend            14300                  82312.
 MP_IRecv            14300                  82312.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.042    0.061   83.662   83.663
 qs_mol_dyn_low                       1  2.0    0.003    0.030   83.044   83.368
 qs_forces                           11  3.9    0.014    0.019   82.869   82.870
 qs_energies                         11  4.9    0.011    0.011   79.996   80.012
 scf_env_do_scf                      11  5.9    0.000    0.001   71.132   71.134
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.006   65.427   65.427
 dbcsr_multiply_generic            2055 12.4    0.104    0.107   52.219   52.486
 qs_scf_new_mos                      99  7.5    0.000    0.001   48.226   48.348
 qs_scf_loop_do_ot                   99  8.5    0.000    0.001   48.226   48.348
 ot_scf_mini                         99  9.5    0.002    0.002   45.782   45.881
 multiply_cannon                   2055 13.4    0.179    0.184   42.666   43.376
 velocity_verlet                     10  3.0    0.001    0.002   42.450   42.452
 multiply_cannon_loop              2055 14.4    1.569    1.604   41.642   42.366
 ot_mini                             99 10.5    0.001    0.001   27.728   27.830
 qs_ot_get_derivative                99 11.5    0.001    0.001   20.910   21.018
 multiply_cannon_multrec          49320 15.4   12.050   12.964   17.135   17.800
 rebuild_ks_matrix                  110  8.3    0.000    0.001   14.687   14.799
 qs_ks_build_kohn_sham_matrix       110  9.3    0.011    0.012   14.686   14.798
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.898   13.003
 mp_waitall_1                    241148 16.1   11.857   12.891   11.857   12.891
 multiply_cannon_sync_h2d         49320 15.4    9.947   10.613    9.947   10.613
 qs_ot_get_p                        110 10.4    0.001    0.001    9.480    9.641
 multiply_cannon_metrocomm3       49320 15.4    0.075    0.079    6.967    8.097
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    7.152    7.748
 apply_single                       110 13.6    0.000    0.000    7.152    7.748
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    7.099    7.631
 sum_up_and_integrate               110 10.3    0.023    0.027    7.240    7.256
 integrate_v_rspace                 110 11.3    0.002    0.003    7.217    7.239
 init_scf_run                        11  5.9    0.000    0.001    6.815    6.815
 scf_env_initial_rho_setup           11  6.9    0.000    0.001    6.815    6.815
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    6.757    6.814
 ot_diis_step                        99 11.5    0.006    0.006    6.535    6.536
 qs_rho_update_rho_low              110  7.6    0.000    0.001    6.281    6.418
 calculate_rho_elec                 110  8.6    0.020    0.024    6.281    6.417
 qs_ot_p2m_diag                      48 11.0    0.012    0.019    6.110    6.150
 mp_sum_l                          6514 12.8    5.152    5.874    5.152    5.874
 init_scf_loop                       11  6.9    0.000    0.000    5.677    5.677
 dbcsr_mm_accdrv_process          87628 16.1    2.095    2.192    4.965    5.250
 cp_dbcsr_syevd                      48 12.0    0.002    0.003    5.074    5.074
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    4.577    4.578
 cp_fm_redistribute_end              48 14.0    3.986    4.550    3.990    4.551
 cp_fm_diag_elpa_base                48 14.0    0.554    4.440    0.557    4.466
 rs_pw_transfer                     902 11.9    0.012    0.014    4.120    4.263
 make_m2s                          4110 13.4    0.061    0.065    3.946    4.070
 multiply_cannon_metrocomm1       49320 15.4    0.060    0.065    2.763    4.058
 wfi_extrapolate                     11  7.9    0.001    0.001    4.022    4.022
 make_images                       4110 14.4    0.178    0.191    3.850    3.976
 calculate_dm_sparse                110  9.5    0.000    0.001    3.807    3.891
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    3.655    3.659
 density_rs2pw                      110  9.6    0.004    0.004    3.369    3.541
 prepare_preconditioner              11  7.9    0.000    0.000    3.492    3.511
 make_preconditioner                 11  8.9    0.000    0.000    3.492    3.511
 grid_integrate_task_list           110 12.3    3.258    3.379    3.258    3.379
 qs_ot_get_orbitals                  99 10.5    0.000    0.001    3.323    3.378
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    3.236    3.278
 make_full_inverse_cholesky          11  9.9    0.000    0.000    3.229    3.267
 pw_transfer                       1331 11.6    0.054    0.065    2.879    2.942
 potential_pw2rs                    110 12.3    0.006    0.007    2.850    2.870
 fft_wrap_pw1pw2                   1111 12.6    0.007    0.008    2.788    2.854
 calculate_first_density_matrix       1  7.0    0.000    0.001    2.707    2.712
 jit_kernel_multiply                 13 15.9    2.585    2.620    2.585    2.620
 mp_alltoall_d11v                  2046 13.8    2.138    2.581    2.138    2.581
 fft_wrap_pw1pw2_140                451 13.1    0.168    0.186    2.342    2.412
 fft3d_ps                          1111 14.6    0.753    0.837    2.327    2.382
 acc_transpose_blocks             49320 15.4    0.213    0.224    2.187    2.270
 grid_collocate_task_list           110  9.6    2.085    2.181    2.085    2.181
 mp_sum_d                          3883 11.9    1.512    1.969    1.512    1.969
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.929    1.941
 make_images_data                  4110 15.4    0.043    0.046    1.800    1.933
 mp_waitany                       14300 13.8    1.722    1.912    1.722    1.912
 cp_fm_cholesky_invert               11 10.9    1.886    1.891    1.886    1.891
 hybrid_alltoall_any               4261 16.3    0.081    0.481    1.561    1.821
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="200", plot="h2o_128_md", label="(8n/12r/1t)", y=83.663000, yerr=0.000000
PlotPoint: name="201", plot="h2o_128_md_mem", label="(8n/12r/1t)", y=474.818182, yerr=2.248967
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_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             586.915840E+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                1905003.
 MP_ISendRecv        20680                  26400.
 MP_Wait             32692
 MP_comm_split          48
 MP_ISend            10164                 155761.
 MP_IRecv            10164                 155761.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.019    0.052   69.441   69.442
 qs_mol_dyn_low                       1  2.0    0.003    0.006   69.160   69.170
 qs_forces                           11  3.9    0.003    0.007   68.876   68.878
 qs_energies                         11  4.9    0.001    0.001   65.560   65.564
 scf_env_do_scf                      11  5.9    0.000    0.001   56.793   56.796
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.007   48.891   48.891
 dbcsr_multiply_generic            2055 12.4    0.113    0.117   37.854   38.009
 velocity_verlet                     10  3.0    0.001    0.002   36.580   36.581
 qs_scf_new_mos                      99  7.5    0.001    0.001   32.773   32.926
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   32.772   32.925
 multiply_cannon                   2055 13.4    0.221    0.242   31.076   32.366
 ot_scf_mini                         99  9.5    0.003    0.003   31.092   31.233
 multiply_cannon_loop              2055 14.4    0.932    0.952   29.737   30.768
 ot_mini                             99 10.5    0.001    0.001   18.411   18.560
 multiply_cannon_multrec          24660 15.4    7.614    9.246   13.799   15.619
 rebuild_ks_matrix                  110  8.3    0.000    0.001   13.807   13.945
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.014   13.807   13.944
 qs_ot_get_derivative                99 11.5    0.001    0.002   12.581   12.733
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.186   12.300
 mp_waitall_1                    186928 16.3    7.934   10.336    7.934   10.336
 multiply_cannon_sync_h2d         24660 15.4    7.042    8.006    7.042    8.006
 init_scf_loop                       11  6.9    0.000    0.000    7.866    7.866
 multiply_cannon_metrocomm3       24660 15.4    0.071    0.072    5.199    7.696
 apply_preconditioner_dbcsr         110 12.6    0.000    0.001    6.525    7.298
 apply_single                       110 13.6    0.000    0.001    6.525    7.297
 sum_up_and_integrate               110 10.3    0.028    0.033    6.684    6.695
 integrate_v_rspace                 110 11.3    0.002    0.003    6.655    6.668
 init_scf_run                        11  5.9    0.000    0.001    6.342    6.343
 scf_env_initial_rho_setup           11  6.9    0.000    0.001    6.342    6.343
 dbcsr_mm_accdrv_process          52282 16.1    4.715    5.629    6.025    6.281
 qs_ot_get_p                        110 10.4    0.001    0.001    6.014    6.177
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.883    5.893
 calculate_rho_elec                 110  8.6    0.039    0.047    5.883    5.893
 prepare_preconditioner              11  7.9    0.000    0.000    5.840    5.853
 make_preconditioner                 11  8.9    0.000    0.000    5.840    5.853
 ot_diis_step                        99 11.5    0.010    0.012    5.774    5.774
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.409    5.570
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    4.725    5.437
 make_m2s                          4110 13.4    0.057    0.060    4.269    4.743
 make_images                       4110 14.4    0.396    0.441    4.160    4.631
 qs_ot_p2m_diag                      48 11.0    0.029    0.044    4.100    4.123
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.666    3.667
 wfi_extrapolate                     11  7.9    0.001    0.001    3.554    3.554
 pw_transfer                       1331 11.6    0.066    0.073    3.347    3.487
 rs_pw_transfer                     902 11.9    0.012    0.013    3.231    3.444
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.236    3.379
 grid_integrate_task_list           110 12.3    3.160    3.369    3.160    3.369
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.278    3.354
 density_rs2pw                      110  9.6    0.004    0.004    3.178    3.349
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    3.266    3.267
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.122    3.124
 cp_fm_redistribute_end              48 14.0    2.330    3.098    2.331    3.098
 cp_fm_diag_elpa_base                48 14.0    0.733    2.970    0.764    3.061
 calculate_dm_sparse                110  9.5    0.001    0.001    2.986    3.012
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.918    2.981
 make_images_data                  4110 15.4    0.047    0.051    2.369    2.869
 fft_wrap_pw1pw2_140                451 13.1    0.201    0.221    2.681    2.823
 hybrid_alltoall_any               4261 16.3    0.101    0.439    2.075    2.777
 cp_fm_cholesky_invert               11 10.9    2.744    2.751    2.744    2.751
 fft3d_ps                          1111 14.6    1.070    1.269    2.591    2.720
 calculate_first_density_matrix       1  7.0    0.001    0.008    2.702    2.706
 potential_pw2rs                    110 12.3    0.009    0.009    2.552    2.559
 mp_sum_l                          6514 12.8    1.899    2.454    1.899    2.454
 grid_collocate_task_list           110  9.6    2.118    2.256    2.118    2.256
 mp_alltoall_d11v                  2046 13.8    1.820    2.069    1.820    2.069
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.982    2.004
 qs_energies_init_hamiltonians       11  5.9    0.001    0.003    1.907    1.909
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.784    1.804
 jit_kernel_multiply                  9 16.4    0.955    1.674    0.955    1.674
 mp_allgather_i34                  2055 14.4    0.667    1.633    0.667    1.633
 multiply_cannon_metrocomm4       22605 15.4    0.074    0.079    0.776    1.609
 acc_transpose_blocks             24660 15.4    0.106    0.108    1.537    1.569
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.539    1.549
 mp_irecv_dv                      57340 16.2    0.651    1.488    0.651    1.488
 dbcsr_complete_redistribute        325 12.2    0.237    0.300    1.201    1.479
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.001    1.370    1.478
 cp_fm_cholesky_decompose            22 10.9    1.423    1.431    1.423    1.431
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="202", plot="h2o_128_md", label="(8n/6r/2t)", y=69.442000, yerr=0.000000
PlotPoint: name="203", plot="h2o_128_md_mem", label="(8n/6r/2t)", y=554.818182, yerr=7.940897
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/11/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                    404.681598E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               3346752       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     294.1
 marketing flops                    15.646297E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank             658.567168E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                  854880
 MPI messages size (bytes):
  total size                       708.322787E+09
  min size                           0.000000E+00
  max size                           6.553600E+06
  average size                     828.564000E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768              222984               7302414336
     32768 < size <=   131072              153888              10085203968
    131072 < size <=  4194304              389376             200257044480
   4194304 < size <= 16777216               82208             490679162176
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3521                  65578.
 MP_Allreduce         9838                    559.
 MP_Sync               100
 MP_Alltoall          1496                4511006.
 MP_ISendRecv        13640                  27424.
 MP_Wait             32318
 MP_comm_split          48
 MP_ISend            17072                 115022.
 MP_IRecv            17072                 115022.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.023    0.091   70.746   70.747
 qs_mol_dyn_low                       1  2.0    0.004    0.007   70.279   70.289
 qs_forces                           11  3.9    0.002    0.004   70.207   70.209
 qs_energies                         11  4.9    0.001    0.002   66.992   66.996
 scf_env_do_scf                      11  5.9    0.000    0.001   49.980   49.980
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.012   41.129   41.130
 dbcsr_multiply_generic            2055 12.4    0.109    0.112   37.750   38.075
 velocity_verlet                     10  3.0    0.002    0.002   32.999   33.001
 multiply_cannon                   2055 13.4    0.212    0.224   30.964   32.380
 multiply_cannon_loop              2055 14.4    0.621    0.635   29.681   30.630
 qs_scf_new_mos                      99  7.5    0.001    0.001   26.293   26.380
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   26.293   26.379
 ot_scf_mini                         99  9.5    0.004    0.014   25.049   25.160
 init_scf_run                        11  5.9    0.000    0.001   14.588   14.588
 scf_env_initial_rho_setup           11  6.9    0.000    0.001   14.587   14.588
 ot_mini                             99 10.5    0.008    0.057   13.917   14.160
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.410   12.540
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.013   12.409   12.540
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001   11.605   11.606
 calculate_first_density_matrix       1  7.0    0.000    0.001   11.462   11.463
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000   11.207   11.267
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.952   11.067
 multiply_cannon_multrec          16440 15.4    3.969    5.212    9.737   10.899
 mp_waitall_1                    146766 16.3    7.332   10.543    7.332   10.543
 acc_transpose_blocks             16440 15.4    0.071    0.074    9.953    9.995
 acc_transpose_blocks_kernels     16440 16.4    0.209    0.214    9.531    9.569
 qs_ot_get_derivative                99 11.5    0.001    0.001    9.353    9.468
 jit_kernel_transpose                 5 15.6    9.322    9.359    9.322    9.359
 init_scf_loop                       11  6.9    0.000    0.000    8.814    8.816
 multiply_cannon_metrocomm3       16440 15.4    0.043    0.044    4.232    7.262
 prepare_preconditioner              11  7.9    0.000    0.000    7.021    7.040
 make_preconditioner                 11  8.9    0.000    0.000    7.021    7.040
 make_full_inverse_cholesky          11  9.9    0.000    0.000    6.353    6.697
 sum_up_and_integrate               110 10.3    0.033    0.034    6.608    6.623
 integrate_v_rspace                 110 11.3    0.002    0.003    6.575    6.590
 qs_ot_get_p                        110 10.4    0.001    0.001    6.070    6.191
 dbcsr_mm_accdrv_process          34862 16.1    4.878    5.308    5.622    5.832
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.694    5.705
 calculate_rho_elec                 110  8.6    0.058    0.058    5.694    5.705
 apply_preconditioner_dbcsr         110 12.6    0.000    0.001    5.004    5.437
 apply_single                       110 13.6    0.000    0.000    5.004    5.437
 make_m2s                          4110 13.4    0.050    0.052    4.304    4.692
 ot_diis_step                        99 11.5    0.039    0.235    4.515    4.622
 make_images                       4110 14.4    0.389    0.505    4.189    4.575
 qs_ot_p2m_diag                      48 11.0    0.042    0.044    4.338    4.342
 multiply_cannon_sync_h2d         16440 15.4    3.713    4.288    3.713    4.288
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.989    3.989
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.176    3.795
 grid_integrate_task_list           110 12.3    3.185    3.407    3.185    3.407
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.387    3.390
 cp_fm_redistribute_end              48 14.0    2.108    3.352    2.112    3.354
 cp_fm_diag_elpa_base                48 14.0    1.174    3.187    1.234    3.297
 rs_pw_transfer                     902 11.9    0.010    0.011    3.062    3.296
 density_rs2pw                      110  9.6    0.004    0.004    2.966    3.202
 pw_transfer                       1331 11.6    0.066    0.073    3.174    3.186
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.062    3.075
 wfi_extrapolate                     11  7.9    0.001    0.001    3.041    3.041
 make_images_data                  4110 15.4    0.044    0.047    2.451    2.970
 hybrid_alltoall_any               4261 16.3    0.104    0.374    2.207    2.918
 cp_fm_cholesky_invert               11 10.9    2.860    2.867    2.860    2.867
 calculate_dm_sparse                110  9.5    0.001    0.001    2.563    2.592
 fft_wrap_pw1pw2_140                451 13.1    0.212    0.216    2.557    2.572
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.485    2.542
 mp_sum_l                          6514 12.8    1.869    2.521    1.869    2.521
 potential_pw2rs                    110 12.3    0.011    0.011    2.469    2.475
 fft3d_ps                          1111 14.6    1.062    1.069    2.375    2.388
 grid_collocate_task_list           110  9.6    2.176    2.354    2.176    2.354
 multiply_cannon_metrocomm4       14385 15.4    0.045    0.049    0.858    2.295
 mp_irecv_dv                      48980 15.7    0.788    2.172    0.788    2.172
 mp_alltoall_d11v                  2046 13.8    1.842    2.154    1.842    2.154
 qs_energies_init_hamiltonians       11  5.9    0.030    0.043    1.988    1.989
 dbcsr_complete_redistribute        325 12.2    0.333    0.370    1.512    1.961
 cp_fm_upper_to_full                 70 13.6    1.367    1.845    1.367    1.845
 cp_fm_cholesky_decompose            22 10.9    1.697    1.718    1.697    1.718
 mp_allgather_i34                  2055 14.4    0.607    1.681    0.607    1.681
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.661    1.678
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.499    1.512
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.001    1.378    1.503
 jit_kernel_multiply                  8 16.9    0.352    1.493    0.352    1.493
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    1.032    1.478
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="204", plot="h2o_128_md", label="(8n/4r/3t)", y=70.747000, yerr=0.000000
PlotPoint: name="205", plot="h2o_128_md_mem", label="(8n/4r/3t)", y=622.909091, yerr=7.051171
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_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             734.941184E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                  937080
 MPI messages size (bytes):
  total size                       523.723932E+09
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     558.889250E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6996                        0
       128 < size <=     8192                 264                  2162688
      8192 < size <=    32768              304932               8165326848
     32768 < size <=   131072              110640               6338641920
    131072 < size <=  4194304              489498             400769458320
   4194304 < size <= 16777216               24750             108449092400
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3521                  65576.
 MP_Allreduce         9838                    600.
 MP_Sync               100
 MP_Alltoall          1496                5863162.
 MP_ISendRecv        10120                  43184.
 MP_Wait             25102
 MP_comm_split          48
 MP_ISend            13376                 163145.
 MP_IRecv            13376                 163145.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.084    0.176   74.580   74.581
 qs_mol_dyn_low                       1  2.0    0.004    0.006   74.003   74.012
 qs_forces                           11  3.9    0.002    0.004   73.934   73.935
 qs_energies                         11  4.9    0.005    0.016   70.547   70.551
 scf_env_do_scf                      11  5.9    0.002    0.011   53.348   53.351
 scf_env_do_scf_inner_loop           99  6.5    0.007    0.028   41.242   41.246
 dbcsr_multiply_generic            2055 12.4    0.116    0.119   38.090   38.265
 velocity_verlet                     10  3.0    0.004    0.007   37.023   37.025
 multiply_cannon                   2055 13.4    0.245    0.266   31.054   32.071
 multiply_cannon_loop              2055 14.4    0.885    0.910   29.619   30.189
 qs_scf_new_mos                      99  7.5    0.001    0.001   26.600   26.707
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   26.600   26.706
 ot_scf_mini                         99  9.5    0.003    0.004   24.967   25.079
 ot_mini                             99 10.5    0.001    0.001   14.280   14.416
 init_scf_run                        11  5.9    0.000    0.001   14.343   14.344
 scf_env_initial_rho_setup           11  6.9    0.000    0.001   14.343   14.343
 multiply_cannon_multrec          24660 15.4    4.212    6.673   12.660   13.993
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.037   12.146
 qs_ks_build_kohn_sham_matrix       110  9.3    0.015    0.035   12.037   12.146
 init_scf_loop                       11  6.9    0.007    0.037   12.063   12.073
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001   11.344   11.345
 calculate_first_density_matrix       1  7.0    0.000    0.001   11.238   11.240
 mp_waitall_1                    126806 16.4    5.789   11.150    5.789   11.150
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000   10.965   11.001
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.654   10.747
 qs_ot_get_derivative                99 11.5    0.001    0.001   10.135   10.253
 prepare_preconditioner              11  7.9    0.000    0.000   10.143   10.160
 make_preconditioner                 11  8.9    0.000    0.001   10.143   10.160
 acc_transpose_blocks             24660 15.4    0.104    0.105    8.742   10.084
 make_full_inverse_cholesky          11  9.9    0.000    0.000    8.345    9.819
 acc_transpose_blocks_kernels     24660 16.4    0.306    0.312    8.098    9.425
 dbcsr_mm_accdrv_process          52304 16.0    6.917    8.242    8.301    9.190
 jit_kernel_transpose                 5 15.6    7.792    9.115    7.792    9.115
 sum_up_and_integrate               110 10.3    0.037    0.039    6.440    6.453
 integrate_v_rspace                 110 11.3    0.003    0.009    6.402    6.415
 qs_ot_get_p                        110 10.4    0.001    0.001    5.854    5.993
 multiply_cannon_metrocomm1       24660 15.4    0.034    0.035    1.560    5.862
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.806    5.818
 calculate_rho_elec                 110  8.6    0.077    0.081    5.805    5.817
 make_m2s                          4110 13.4    0.059    0.062    5.344    5.685
 make_images                       4110 14.4    0.574    0.694    5.203    5.541
 cp_fm_upper_to_full                 70 13.8    3.302    4.713    3.302    4.713
 ot_diis_step                        99 11.5    0.012    0.014    4.107    4.107
 apply_preconditioner_dbcsr         110 12.6    0.000    0.001    4.019    4.081
 apply_single                       110 13.6    0.000    0.000    4.019    4.080
 qs_ot_p2m_diag                      48 11.0    0.055    0.064    3.906    3.920
 dbcsr_complete_redistribute        325 12.2    0.414    0.458    2.741    3.896
 grid_integrate_task_list           110 12.3    3.272    3.436    3.272    3.436
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.418    3.418
 multiply_cannon_metrocomm3       24660 15.4    0.035    0.036    1.509    3.373
 multiply_cannon_sync_h2d         24660 15.4    3.183    3.368    3.183    3.368
 pw_transfer                       1331 11.6    0.066    0.073    3.342    3.368
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.312    3.363
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    2.192    3.333
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.232    3.261
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.119    3.179
 density_rs2pw                      110  9.6    0.004    0.004    2.931    3.101
 wfi_extrapolate                     11  7.9    0.001    0.001    2.995    2.995
 hybrid_alltoall_any               4261 16.3    0.119    0.456    2.352    2.989
 make_images_data                  4110 15.4    0.046    0.050    2.626    2.979
 calculate_dm_sparse                110  9.5    0.001    0.001    2.933    2.960
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.789    2.908
 rs_pw_transfer                     902 11.9    0.010    0.011    2.704    2.904
 cp_fm_cholesky_invert               11 10.9    2.869    2.876    2.869    2.876
 mp_alltoall_i22                    605 13.7    1.698    2.875    1.698    2.875
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    2.847    2.849
 cp_fm_redistribute_end              48 14.0    1.416    2.810    1.417    2.811
 cp_fm_diag_elpa_base                48 14.0    1.311    2.677    1.391    2.786
 fft_wrap_pw1pw2_140                451 13.1    0.205    0.214    2.708    2.738
 fft3d_ps                          1111 14.6    1.062    1.094    2.531    2.547
 grid_collocate_task_list           110  9.6    2.220    2.428    2.220    2.428
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    2.330    2.331
 mp_alltoall_d11v                  2046 13.8    1.911    2.270    1.911    2.270
 potential_pw2rs                    110 12.3    0.013    0.013    2.226    2.237
 jit_kernel_multiply                 11 15.9    1.051    2.017    1.051    2.017
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.711    1.745
 cp_fm_cholesky_decompose            22 10.9    1.693    1.740    1.693    1.740
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.001    1.604    1.712
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.628    1.641
 mp_sum_l                          6514 12.8    1.069    1.591    1.069    1.591
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.546    1.564
 multiply_cannon_metrocomm4       20550 15.4    0.056    0.059    0.844    1.535
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="206", plot="h2o_128_md", label="(8n/3r/4t)", y=74.581000, yerr=0.000000
PlotPoint: name="207", plot="h2o_128_md_mem", label="(8n/3r/4t)", y=690.727273, yerr=10.055219
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/13/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                    807.299199E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               1438408       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     684.2
 marketing flops                    15.646297E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank             826.642432E+06
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  197280
 MPI messages size (bytes):
  total size                       339.125567E+09
  min size                           0.000000E+00
  max size                          13.107200E+06
  average size                       1.719006E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 132                  4325376
     32768 < size <=   131072               88656              11620319232
    131072 < size <=  4194304               89424             117209825280
   4194304 < size <= 16777216               17616             210291069504
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         7346                     33.
 MP_Alltoall          8043                 263767.
 MP_ISend            32836                 654203.
 MP_IRecv            32836                 654587.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3521                  65574.
 MP_Allreduce         9838                    640.
 MP_Sync               100
 MP_Alltoall          1496                8504061.
 MP_ISendRecv         6600                  54848.
 MP_Wait             17226
 MP_comm_split          48
 MP_ISend             9240                 278857.
 MP_IRecv             9240                 278857.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.013    0.040   66.084   66.084
 qs_mol_dyn_low                       1  2.0    0.003    0.011   65.804   65.824
 qs_forces                           11  3.9    0.005    0.014   65.695   65.698
 qs_energies                         11  4.9    0.001    0.002   62.009   62.018
 scf_env_do_scf                      11  5.9    0.000    0.001   44.922   44.922
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.006   36.635   36.636
 dbcsr_multiply_generic            2055 12.4    0.105    0.106   31.911   32.026
 velocity_verlet                     10  3.0    0.030    0.044   31.585   31.588
 multiply_cannon                   2055 13.4    0.252    0.281   26.242   27.568
 multiply_cannon_loop              2055 14.4    0.322    0.333   24.823   25.134
 qs_scf_new_mos                      99  7.5    0.001    0.001   21.689   21.724
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   21.688   21.723
 ot_scf_mini                         99  9.5    0.002    0.002   20.425   20.449
 init_scf_run                        11  5.9    0.000    0.001   13.932   13.932
 scf_env_initial_rho_setup           11  6.9    0.000    0.001   13.931   13.932
 mp_waitall_1                    106626 16.5    9.574   13.242    9.574   13.242
 rebuild_ks_matrix                  110  8.3    0.000    0.000   11.601   11.624
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.013   11.601   11.623
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001   11.270   11.272
 calculate_first_density_matrix       1  7.0    0.000    0.000   11.100   11.101
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000   10.871   10.882
 ot_mini                             99 10.5    0.001    0.001   10.774   10.801
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.310   10.329
 acc_transpose_blocks              8220 15.4    0.036    0.037    6.225    9.642
 multiply_cannon_metrocomm3        8220 15.4    0.017    0.017    3.638    9.595
 acc_transpose_blocks_kernels      8220 16.4    0.110    0.114    5.991    9.404
 jit_kernel_transpose                 5 15.6    5.881    9.292    5.881    9.292
 multiply_cannon_multrec           8220 15.4    3.314    4.688    7.652    8.610
 init_scf_loop                       11  6.9    0.000    0.000    8.237    8.239
 qs_ot_get_derivative                99 11.5    0.001    0.001    6.971    6.995
 prepare_preconditioner              11  7.9    0.000    0.000    6.602    6.605
 make_preconditioner                 11  8.9    0.000    0.000    6.602    6.605
 multiply_cannon_metrocomm1        8220 15.4    0.021    0.022    3.496    6.484
 sum_up_and_integrate               110 10.3    0.048    0.049    6.308    6.318
 integrate_v_rspace                 110 11.3    0.003    0.003    6.260    6.271
 make_full_inverse_cholesky          11  9.9    0.000    0.000    6.186    6.263
 qs_ot_get_p                        110 10.4    0.001    0.001    5.702    5.721
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.655    5.668
 calculate_rho_elec                 110  8.6    0.115    0.116    5.654    5.667
 dbcsr_mm_accdrv_process          17442 15.9    2.806    4.163    4.208    5.254
 make_m2s                          4110 13.4    0.039    0.040    4.288    4.562
 make_images                       4110 14.4    0.632    0.688    4.157    4.431
 qs_ot_p2m_diag                      48 11.0    0.081    0.084    4.205    4.209
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.877    3.878
 ot_diis_step                        99 11.5    0.012    0.012    3.778    3.779
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    3.686    3.707
 apply_single                       110 13.6    0.000    0.000    3.686    3.707
 grid_integrate_task_list           110 12.3    3.362    3.515    3.362    3.515
 cp_fm_cholesky_invert               11 10.9    3.300    3.304    3.300    3.304
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.264    3.265
 pw_transfer                       1331 11.6    0.066    0.072    3.226    3.241
 cp_fm_redistribute_end              48 14.0    0.833    3.218    0.840    3.221
 cp_fm_diag_elpa_base                48 14.0    2.192    3.004    2.371    3.167
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.115    3.134
 multiply_cannon_sync_h2d          8220 15.4    2.918    3.034    2.918    3.034
 density_rs2pw                      110  9.6    0.004    0.004    2.734    2.826
 make_images_data                  4110 15.4    0.038    0.043    2.366    2.800
 wfi_extrapolate                     11  7.9    0.001    0.001    2.742    2.742
 qs_energies_init_hamiltonians       11  5.9    0.007    0.021    2.695    2.701
 hybrid_alltoall_any               4261 16.3    0.199    0.862    2.262    2.649
 fft_wrap_pw1pw2_140                451 13.1    0.213    0.217    2.617    2.638
 rs_pw_transfer                     902 11.9    0.010    0.010    2.475    2.599
 calculate_dm_sparse                110  9.5    0.001    0.001    2.545    2.577
 grid_collocate_task_list           110  9.6    2.326    2.504    2.326    2.504
 fft3d_ps                          1111 14.6    1.118    1.142    2.373    2.387
 potential_pw2rs                    110 12.3    0.015    0.016    2.111    2.119
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    2.056    2.073
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.776    1.992
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    1.913    1.927
 cp_fm_cholesky_decompose            22 10.9    1.880    1.898    1.880    1.898
 jit_kernel_multiply                 10 15.8    1.094    1.823    1.094    1.823
 mp_alltoall_d11v                  2046 13.8    1.620    1.753    1.620    1.753
 dbcsr_complete_redistribute        325 12.2    0.568    0.607    1.538    1.641
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    1.518    1.638
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.627    1.630
 mp_allgather_i34                  2055 14.4    0.601    1.627    0.601    1.627
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.483    1.494
 qs_create_task_list                 11  7.9    0.000    0.001    1.232    1.331
 generate_qs_task_list               11  8.9    0.378    0.446    1.232    1.331
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="208", plot="h2o_128_md", label="(8n/2r/6t)", y=66.084000, yerr=0.000000
PlotPoint: name="209", plot="h2o_128_md_mem", label="(8n/2r/6t)", y=774.818182, yerr=12.481391
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_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               1.178763E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                   82200
 MPI messages size (bytes):
  total size                       297.640985E+09
  min size                           0.000000E+00
  max size                          26.214400E+06
  average size                       3.620936E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                 572                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                  44                  1441792
     32768 < size <=   131072               18560               2432696320
    131072 < size <=  4194304               54216              84915781632
   4194304 < size <= 16777216                   0                        0
  16777216 < size                            8808             210291069504
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3462                  67104.
 MP_Allreduce         9672                    819.
 MP_Sync                52
 MP_Alltoall          1474               16505187.
 MP_ISendRecv         4620                 360267.
 MP_Wait              7524
 MP_ISend             2420                1187840.
 MP_IRecv             2420                1187840.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.083    0.149   90.449   90.450
 qs_mol_dyn_low                       1  2.0    0.003    0.004   89.906   89.914
 qs_forces                           11  3.9    0.002    0.002   89.806   89.807
 qs_energies                         11  4.9    0.001    0.001   85.597   85.600
 scf_env_do_scf                      11  5.9    0.001    0.001   74.499   74.500
 velocity_verlet                     10  3.0    0.008    0.010   56.826   56.836
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.007   45.301   45.302
 dbcsr_multiply_generic            2055 12.4    0.128    0.130   30.538   30.623
 init_scf_loop                       11  6.9    0.000    0.000   29.119   29.120
 qs_scf_new_mos                      99  7.5    0.001    0.001   28.272   28.331
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   28.272   28.330
 prepare_preconditioner              11  7.9    0.000    0.000   27.118   27.128
 make_preconditioner                 11  8.9    0.000    0.000   27.118   27.128
 make_full_inverse_cholesky          11  9.9    0.000    0.000   21.383   26.588
 ot_scf_mini                         99  9.5    0.002    0.002   26.513   26.556
 multiply_cannon                   2055 13.4    0.344    0.375   22.821   23.706
 multiply_cannon_loop              2055 14.4    0.341    0.344   20.910   21.238
 cp_fm_upper_to_full                 70 14.2   12.642   18.100   12.642   18.100
 ot_mini                             99 10.5    0.001    0.001   14.523   14.567
 rebuild_ks_matrix                  110  8.3    0.001    0.001   13.702   13.797
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.013   13.701   13.796
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.413   12.498
 dbcsr_complete_redistribute        325 12.2    1.020    1.047    7.418   10.631
 multiply_cannon_multrec           8220 15.4    4.426    4.689   10.122   10.456
 mp_waitall_1                     87304 16.6    8.998   10.148    8.998   10.148
 qs_ot_get_derivative                99 11.5    0.001    0.001    9.742    9.788
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    6.323    9.548
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    5.720    8.919
 mp_alltoall_i22                    605 13.7    5.404    8.650    5.404    8.650
 sum_up_and_integrate               110 10.3    0.089    0.090    6.933    6.948
 integrate_v_rspace                 110 11.3    0.003    0.003    6.843    6.858
 init_scf_run                        11  5.9    0.000    0.001    6.831    6.831
 scf_env_initial_rho_setup           11  6.9    0.000    0.000    6.830    6.831
 qs_ot_get_p                        110 10.4    0.001    0.001    6.686    6.773
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.701    6.736
 calculate_rho_elec                 110  8.6    0.226    0.227    6.701    6.735
 make_m2s                          4110 13.4    0.043    0.043    5.633    6.205
 make_images                       4110 14.4    0.872    0.915    5.446    6.016
 cp_fm_cholesky_invert               11 10.9    5.991    5.996    5.991    5.996
 multiply_cannon_metrocomm3        8220 15.4    0.018    0.018    5.394    5.819
 dbcsr_mm_accdrv_process          11614 15.7    3.242    3.644    5.552    5.804
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.783    5.282
 apply_single                       110 13.6    0.000    0.000    4.783    5.282
 qs_ot_p2m_diag                      48 11.0    0.151    0.156    4.805    4.812
 ot_diis_step                        99 11.5    0.016    0.016    4.740    4.740
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    4.343    4.344
 pw_transfer                       1331 11.6    0.073    0.074    4.038    4.046
 multiply_cannon_sync_h2d          8220 15.4    3.950    3.955    3.950    3.955
 fft_wrap_pw1pw2                   1111 12.6    0.009    0.009    3.914    3.922
 make_images_data                  4110 15.4    0.041    0.044    3.129    3.837
 hybrid_alltoall_any               4261 16.3    0.255    0.553    3.002    3.796
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    3.765    3.767
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.748    3.749
 cp_fm_diag_elpa_base                48 14.0    3.208    3.405    3.746    3.747
 grid_integrate_task_list           110 12.3    3.673    3.736    3.673    3.736
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    3.642    3.643
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.070    3.518
 wfi_extrapolate                     11  7.9    0.001    0.001    3.433    3.433
 fft_wrap_pw1pw2_140                451 13.1    0.217    0.220    3.284    3.296
 density_rs2pw                      110  9.6    0.004    0.004    3.280    3.292
 calculate_first_density_matrix       1  7.0    0.000    0.000    3.291    3.292
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    3.187    3.234
 calculate_dm_sparse                110  9.5    0.001    0.001    3.127    3.143
 fft3d_ps                          1111 14.6    1.265    1.273    3.120    3.128
 grid_collocate_task_list           110  9.6    2.638    2.656    2.638    2.656
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.592    2.634
 rs_pw_transfer                     902 11.9    0.011    0.011    2.478    2.525
 jit_kernel_multiply                 10 15.3    2.109    2.523    2.109    2.523
 potential_pw2rs                    110 12.3    0.021    0.021    2.346    2.350
 cp_fm_cholesky_decompose            22 10.9    2.244    2.259    2.244    2.259
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    2.180    2.241
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    2.098    2.205
 mp_alltoall_d11v                  2046 13.8    2.017    2.075    2.017    2.075
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.825    1.989
 qs_create_task_list                 11  7.9    0.000    0.001    1.901    1.944
 generate_qs_task_list               11  8.9    0.738    0.791    1.900    1.944
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.897    1.907
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="210", plot="h2o_128_md", label="(8n/1r/12t)", y=90.450000, yerr=0.000000
PlotPoint: name="211", plot="h2o_128_md_mem", label="(8n/1r/12t)", y=1108.181818, yerr=21.982713
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/15/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420242647040       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528903135232       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514766E+12       0.0%      0.0%    100.0%
 flops max/rank                      1.094965E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755941440       0.0%      0.0%    100.0%
 number of processed stacks              11950464       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     565.3
 marketing flops                   144.580175E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank             627.064832E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                10348896
 MPI messages size (bytes):
  total size                         4.491514E+12
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     434.009000E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               65736                        0
       128 < size <=     8192                1232                 10092544
      8192 < size <=    32768             3576680              95640223744
     32768 < size <=   131072             1294784              74079797248
    131072 < size <=  4194304             5148576            3175955383376
   4194304 < size <= 16777216              261888            1145794321408
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4085                  56760.
 MP_Allreduce        11253                    785.
 MP_Sync               170
 MP_Alltoall          2226                3123704.
 MP_ISendRecv        48640                  18752.
 MP_Wait             66796
 MP_comm_split          83
 MP_ISend            16020                 108028.
 MP_IRecv            16020                 108028.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.031    0.054  214.504  214.505
 qs_mol_dyn_low                       1  2.0    0.003    0.004  214.047  214.060
 qs_forces                           11  3.9    0.003    0.004  213.950  213.951
 qs_energies                         11  4.9    0.004    0.013  208.344  208.361
 scf_env_do_scf                      11  5.9    0.001    0.002  182.756  182.760
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.008  161.285  161.287
 dbcsr_multiply_generic            2507 12.6    0.175    0.178  133.065  133.824
 velocity_verlet                     10  3.0    0.001    0.002  124.066  124.067
 qs_scf_new_mos                     117  7.6    0.001    0.001  121.579  121.773
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001  121.578  121.772
 ot_scf_mini                        117  9.6    0.003    0.003  115.008  115.210
 multiply_cannon                   2507 13.6    0.238    0.244  109.605  111.997
 multiply_cannon_loop              2507 14.6    2.120    2.195  107.346  109.133
 ot_mini                            117 10.6    0.001    0.001   65.999   66.213
 multiply_cannon_multrec          60168 15.6   33.123   35.066   41.463   43.145
 qs_ot_get_derivative               117 11.6    0.001    0.001   40.964   41.184
 rebuild_ks_matrix                  128  8.3    0.001    0.001   33.962   34.231
 qs_ks_build_kohn_sham_matrix       128  9.3    0.015    0.017   33.961   34.230
 mp_waitall_1                    291448 16.2   28.866   32.004   28.866   32.004
 qs_ks_update_qs_env                128  7.6    0.001    0.001   30.535   30.802
 multiply_cannon_sync_h2d         60168 15.6   27.380   29.964   27.380   29.964
 qs_ot_get_p                        128 10.4    0.001    0.001   27.124   27.366
 apply_preconditioner_dbcsr         128 12.6    0.000    0.001   24.437   24.971
 apply_single                       128 13.6    0.001    0.001   24.437   24.971
 ot_diis_step                       117 11.6    0.007    0.008   24.649   24.650
 init_scf_loop                       11  6.9    0.000    0.002   21.395   21.397
 init_scf_run                        11  5.9    0.000    0.001   21.379   21.380
 scf_env_initial_rho_setup           11  6.9    0.000    0.001   21.379   21.380
 qs_ot_p2m_diag                      83 11.4    0.077    0.091   20.301   20.372
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002   18.992   19.177
 multiply_cannon_metrocomm3       60168 15.6    0.110    0.116   15.788   18.086
 cp_dbcsr_syevd                      83 12.4    0.004    0.005   17.702   17.703
 prepare_preconditioner              11  7.9    0.000    0.000   16.745   16.799
 make_preconditioner                 11  8.9    0.000    0.001   16.745   16.799
 make_full_inverse_cholesky          11  9.9    0.000    0.000   15.973   16.148
 cp_dbcsr_sm_fm_multiply             37  9.5    0.003    0.003   15.449   15.459
 cp_fm_diag_elpa                     83 13.4    0.000    0.001   14.742   14.748
 cp_fm_redistribute_end              83 14.4   11.633   14.654   11.645   14.657
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000   14.546   14.639
 sum_up_and_integrate               128 10.3    0.052    0.063   14.525   14.540
 integrate_v_rspace                 128 11.3    0.003    0.004   14.472   14.490
 make_m2s                          5014 13.6    0.104    0.112   14.040   14.450
 cp_fm_diag_elpa_base                83 14.4    2.968   14.341    2.999   14.446
 make_images                       5014 14.6    0.405    0.421   13.858   14.284
 qs_rho_update_rho_low              128  7.7    0.001    0.001   13.079   13.161
 calculate_rho_elec                 128  8.7    0.045    0.063   13.079   13.160
 calculate_first_density_matrix       1  7.0    0.000    0.001   12.125   12.129
 acc_transpose_blocks             60168 15.6    0.297    0.316   11.681   11.826
 acc_transpose_blocks_kernels     60168 16.6    0.726    0.759   10.062   10.125
 cp_fm_cholesky_invert               11 10.9    9.638    9.646    9.638    9.646
 jit_kernel_transpose                 5 15.6    9.336    9.393    9.336    9.393
 mp_sum_l                          7870 13.0    8.171    9.163    8.171    9.163
 wfi_extrapolate                     11  7.9    0.001    0.001    9.087    9.087
 calculate_dm_sparse                128  9.5    0.001    0.001    8.378    8.487
 dbcsr_mm_accdrv_process         124484 16.2    3.301    3.452    7.907    8.442
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    7.934    8.057
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    7.808    7.917
 multiply_cannon_metrocomm1       60168 15.6    0.086    0.092    5.977    7.787
 make_images_data                  5014 15.6    0.069    0.078    6.815    7.678
 grid_integrate_task_list           128 12.3    7.084    7.600    7.084    7.600
 density_rs2pw                      128  9.7    0.006    0.007    6.888    7.407
 hybrid_alltoall_any               5200 16.5    0.288    2.246    5.950    7.261
 pw_transfer                       1547 11.6    0.075    0.104    6.961    7.238
 rs_pw_transfer                    1046 11.9    0.017    0.019    6.583    7.137
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.013    6.747    6.998
 fft_wrap_pw1pw2_140                523 13.2    0.436    0.485    5.668    5.861
 fft3d_ps                          1291 14.7    2.093    2.586    5.547    5.754
 mp_alltoall_d11v                  2415 14.1    4.255    5.352    4.255    5.352
 potential_pw2rs                    128 12.3    0.009    0.011    5.041    5.075
 grid_collocate_task_list           128  9.7    4.719    5.051    4.719    5.051
 cp_fm_cholesky_decompose            22 10.9    4.899    4.913    4.899    4.913
 mp_sum_d                          4464 12.1    3.677    4.437    3.677    4.437
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="400", plot="h2o_256_md", label="(8n/12r/1t)", y=214.505000, yerr=0.000000
PlotPoint: name="401", plot="h2o_256_md_mem", label="(8n/12r/1t)", y=592.818182, yerr=6.899515
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/16/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1410022121472       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1924145348608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1957871443968       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1963544850432       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2714615709696       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4377645416448       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5350455508992       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5395653328896       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6594687401984       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11444702699520       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15019188129792       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15019188129792       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19624853225472       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        92.796573E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.166472E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6705499744       0.0%      0.0%    100.0%
 number of processed stacks               5925696       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1131.6
 marketing flops                   143.508480E+12
 -------------------------------------------------------------------------------
 # multiplications                           2485
 max memory usage/rank             828.645376E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 2385600
 MPI messages size (bytes):
  total size                         4.069300E+12
  min size                           0.000000E+00
  max size                          17.653760E+06
  average size                       1.705776E+06
 MPI breakdown and total messages size (bytes):
             size <=      128               14916                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768               70188               2295595008
     32768 < size <=   131072              716032              54973693952
    131072 < size <=  4194304             1363760            1386318135296
   4194304 < size <= 16777216              153648            1453842923456
  16777216 < size                           67056            1171888537600
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4089                  57145.
 MP_Allreduce        11262                    946.
 MP_Sync               168
 MP_Alltoall          1955                6381427.
 MP_ISendRecv        23876                  47072.
 MP_Wait             37656
 MP_comm_split          82
 MP_ISend            11660                 212488.
 MP_IRecv            11660                 212488.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.079    0.157  192.956  192.959
 qs_mol_dyn_low                       1  2.0    0.011    0.029  192.126  192.138
 qs_forces                           11  3.9    0.013    0.024  191.574  191.582
 qs_energies                         11  4.9    0.012    0.017  184.731  184.745
 scf_env_do_scf                      11  5.9    0.001    0.001  167.648  167.657
 scf_env_do_scf_inner_loop          116  6.6    0.023    0.079  133.523  133.527
 velocity_verlet                     10  3.0    0.006    0.011  120.119  120.137
 dbcsr_multiply_generic            2485 12.5    0.185    0.206   97.056   98.280
 qs_scf_new_mos                     116  7.6    0.001    0.001   94.625   95.139
 qs_scf_loop_do_ot                  116  8.6    0.001    0.002   94.624   95.138
 ot_scf_mini                        116  9.6    0.006    0.014   89.830   90.412
 multiply_cannon                   2485 13.5    0.472    0.528   76.975   81.294
 multiply_cannon_loop              2485 14.5    1.248    1.283   73.860   76.312
 ot_mini                            116 10.6    0.004    0.008   49.910   50.404
 mp_waitall_1                    224796 16.4   24.977   38.326   24.977   38.326
 multiply_cannon_multrec          29820 15.5   21.765   25.893   31.483   36.117
 init_scf_loop                       11  6.9    0.018    0.141   34.031   34.041
 rebuild_ks_matrix                  127  8.3    0.001    0.001   32.806   33.380
 qs_ks_build_kohn_sham_matrix       127  9.3    0.022    0.060   32.806   33.380
 qs_ks_update_qs_env                127  7.6    0.001    0.001   29.494   30.037
 prepare_preconditioner              11  7.9    0.000    0.000   29.508   29.598
 make_preconditioner                 11  8.9    0.006    0.048   29.508   29.598
 make_full_inverse_cholesky          11  9.9    0.000    0.000   28.165   28.714
 qs_ot_get_derivative               116 11.6    0.003    0.017   28.080   28.635
 multiply_cannon_metrocomm3       29820 15.5    0.094    0.098   15.787   27.758
 apply_preconditioner_dbcsr         127 12.6    0.000    0.001   21.897   23.066
 apply_single                       127 13.6    0.001    0.001   21.897   23.066
 qs_ot_get_p                        127 10.4    0.005    0.023   21.925   22.510
 ot_diis_step                       116 11.6    0.015    0.017   21.649   21.655
 multiply_cannon_sync_h2d         29820 15.5   19.095   21.452   19.095   21.452
 cp_fm_cholesky_invert               11 10.9   17.299   17.311   17.299   17.311
 qs_ot_p2m_diag                      82 11.4    0.187    0.226   16.989   17.027
 cp_dbcsr_syevd                      82 12.4    0.005    0.005   15.830   15.833
 make_m2s                          4970 13.5    0.088    0.093   14.213   15.563
 make_images                       4970 14.5    1.138    1.318   14.005   15.353
 sum_up_and_integrate               127 10.3    0.061    0.072   14.506   14.553
 integrate_v_rspace                 127 11.3    0.003    0.003   14.445   14.494
 qs_rho_update_rho_low              127  7.7    0.001    0.002   13.310   13.399
 calculate_rho_elec                 127  8.7    0.087    0.104   13.309   13.398
 cp_fm_diag_elpa                     82 13.4    0.000    0.000   12.602   12.611
 cp_fm_redistribute_end              82 14.4    7.352   12.525    7.362   12.526
 cp_fm_diag_elpa_base                82 14.4    4.929   12.055    5.144   12.415
 init_scf_run                        11  5.9    0.000    0.001   12.051   12.053
 scf_env_initial_rho_setup           11  6.9    0.000    0.002   12.051   12.053
 qs_ot_get_derivative_diag           76 12.4    0.002    0.002   11.059   11.498
 multiply_cannon_metrocomm4       27335 15.5    0.095    0.111    3.741   10.436
 make_images_data                  4970 15.5    0.066    0.072    8.553   10.114
 mp_irecv_dv                      68888 16.3    3.549   10.056    3.549   10.056
 dbcsr_mm_accdrv_process          61726 16.2    4.721    5.336    9.190    9.760
 hybrid_alltoall_any               5155 16.4    0.340    1.497    7.453    9.585
 wfi_extrapolate                     11  7.9    0.001    0.003    8.467    8.467
 pw_transfer                       1535 11.6    0.082    0.099    7.849    7.926
 fft_wrap_pw1pw2                   1281 12.7    0.010    0.011    7.622    7.692
 grid_integrate_task_list           127 12.3    7.135    7.546    7.135    7.546
 density_rs2pw                      127  9.7    0.006    0.006    6.936    7.418
 cp_fm_cholesky_decompose            22 10.9    7.134    7.208    7.134    7.208
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    6.217    6.965
 fft_wrap_pw1pw2_140                519 13.2    0.456    0.493    6.622    6.687
 calculate_dm_sparse                127  9.5    0.005    0.010    6.514    6.669
 rs_pw_transfer                    1038 11.9    0.014    0.015    6.028    6.535
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.003    6.397    6.406
 fft3d_ps                          1281 14.7    2.751    2.920    6.011    6.060
 mp_sum_l                          7804 13.0    4.122    5.974    4.122    5.974
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.385    5.539
 qs_ot_get_orbitals                 116 10.6    0.001    0.001    5.366    5.444
 grid_collocate_task_list           127  9.7    4.867    5.189    4.867    5.189
 mp_alltoall_d11v                  2401 14.1    4.648    5.103    4.648    5.103
 potential_pw2rs                    127 12.3    0.016    0.018    5.030    5.070
 mp_allgather_i34                  2485 14.5    1.699    4.651    1.699    4.651
 mp_sum_d                          4448 12.1    2.799    4.345    2.799    4.345
 dbcsr_complete_redistribute        393 12.7    0.782    0.919    3.333    4.192
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="402", plot="h2o_256_md", label="(8n/6r/2t)", y=192.959000, yerr=0.000000
PlotPoint: name="403", plot="h2o_256_md_mem", label="(8n/6r/2t)", y=789.272727, yerr=4.594283
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/17/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420242647040       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528903135232       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514766E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.928533E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755941440       0.0%      0.0%    100.0%
 number of processed stacks               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             944.648192E+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             931531265168
  16777216 < size                           28672             751619276800
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4085                  57197.
 MP_Allreduce        11251                    985.
 MP_Sync               170
 MP_Alltoall          1712                9388896.
 MP_ISendRecv        15872                  75008.
 MP_Wait             29756
 MP_comm_split          83
 MP_ISend            11748                 275205.
 MP_IRecv            11748                 275205.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.063    0.148  188.176  188.176
 qs_mol_dyn_low                       1  2.0    0.003    0.006  187.487  187.500
 qs_forces                           11  3.9    0.017    0.041  187.333  187.338
 qs_energies                         11  4.9    0.005    0.031  180.755  180.777
 scf_env_do_scf                      11  5.9    0.001    0.001  156.155  156.160
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.009  119.945  119.946
 velocity_verlet                     10  3.0    0.011    0.022  114.876  114.882
 dbcsr_multiply_generic            2507 12.6    0.182    0.187   90.978   92.025
 qs_scf_new_mos                     117  7.6    0.001    0.001   82.745   83.030
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   82.744   83.029
 ot_scf_mini                        117  9.6    0.004    0.005   78.563   78.883
 multiply_cannon                   2507 13.6    0.498    0.527   70.756   75.384
 multiply_cannon_loop              2507 14.6    0.862    0.890   67.461   70.173
 ot_mini                            117 10.6    0.001    0.002   42.911   43.242
 mp_waitall_1                    178456 16.5   26.645   36.435   26.645   36.435
 init_scf_loop                       11  6.9    0.001    0.010   36.110   36.113
 prepare_preconditioner              11  7.9    0.000    0.000   32.019   32.065
 make_preconditioner                 11  8.9    0.000    0.002   32.019   32.065
 rebuild_ks_matrix                  128  8.3    0.001    0.001   30.619   31.089
 qs_ks_build_kohn_sham_matrix       128  9.3    0.015    0.016   30.618   31.089
 make_full_inverse_cholesky          11  9.9    0.000    0.000   29.653   31.030
 multiply_cannon_metrocomm3       20056 15.6    0.058    0.062   15.813   29.393
 qs_ks_update_qs_env                128  7.6    0.001    0.001   27.686   28.121
 multiply_cannon_multrec          20056 15.6   13.416   16.463   22.199   25.299
 qs_ot_get_derivative               117 11.6    0.002    0.003   23.151   23.472
 qs_ot_get_p                        128 10.4    0.001    0.001   20.855   21.295
 apply_preconditioner_dbcsr         128 12.6    0.000    0.001   19.865   20.878
 apply_single                       128 13.6    0.001    0.001   19.864   20.878
 ot_diis_step                       117 11.6    0.018    0.021   19.644   19.644
 init_scf_run                        11  5.9    0.000    0.001   19.369   19.369
 scf_env_initial_rho_setup           11  6.9    0.001    0.007   19.368   19.369
 qs_ot_p2m_diag                      83 11.4    0.266    0.273   16.485   16.496
 make_m2s                          5014 13.6    0.081    0.086   14.998   16.066
 make_images                       5014 14.6    1.164    1.251   14.764   15.833
 multiply_cannon_sync_h2d         20056 15.6   14.327   15.753   14.327   15.753
 cp_dbcsr_syevd                      83 12.4    0.005    0.005   15.437   15.438
 cp_fm_cholesky_invert               11 10.9   15.135   15.146   15.135   15.146
 sum_up_and_integrate               128 10.3    0.070    0.076   14.382   14.407
 integrate_v_rspace                 128 11.3    0.003    0.003   14.311   14.339
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002   13.965   13.971
 qs_rho_update_rho_low              128  7.7    0.001    0.001   13.236   13.283
 calculate_rho_elec                 128  8.7    0.132    0.146   13.235   13.282
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000   13.006   13.119
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   12.346   12.346
 cp_fm_redistribute_end              83 14.4    4.648   12.273    4.665   12.276
 cp_fm_diag_elpa_base                83 14.4    7.168   11.656    7.585   12.154
 calculate_first_density_matrix       1  7.0    0.002    0.018   11.718   11.722
 make_images_data                  5014 15.6    0.060    0.067    9.332   10.818
 hybrid_alltoall_any               5200 16.5    0.431    1.969    7.989   10.017
 acc_transpose_blocks             20056 15.6    0.090    0.093    9.158    9.902
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002    9.135    9.374
 acc_transpose_blocks_kernels     20056 16.6    0.268    0.275    8.589    9.329
 multiply_cannon_metrocomm4       17549 15.6    0.062    0.072    3.452    9.220
 jit_kernel_transpose                 5 15.6    8.321    9.058    8.321    9.058
 mp_irecv_dv                      50230 16.2    3.329    8.972    3.329    8.972
 dbcsr_mm_accdrv_process          41502 16.2    4.624    5.403    8.248    8.371
 pw_transfer                       1547 11.6    0.083    0.101    7.844    7.958
 cp_fm_cholesky_decompose            22 10.9    7.691    7.754    7.691    7.754
 grid_integrate_task_list           128 12.3    7.357    7.740    7.357    7.740
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.011    7.618    7.739
 cp_fm_upper_to_full                105 14.5    5.777    7.582    5.777    7.582
 wfi_extrapolate                     11  7.9    0.001    0.001    7.456    7.456
 multiply_cannon_metrocomm1       20056 15.6    0.038    0.040    1.400    7.429
 density_rs2pw                      128  9.7    0.005    0.006    6.679    7.101
 fft_wrap_pw1pw2_140                523 13.2    0.470    0.514    6.668    6.799
 dbcsr_complete_redistribute        395 12.7    1.170    1.260    4.604    6.395
 calculate_dm_sparse                128  9.5    0.001    0.002    6.023    6.102
 fft3d_ps                          1291 14.7    2.700    2.928    5.896    5.981
 rs_pw_transfer                    1046 11.9    0.013    0.014    5.511    5.860
 grid_collocate_task_list           128  9.7    5.077    5.397    5.077    5.397
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    4.612    5.337
 copy_fm_to_dbcsr                   209 11.7    0.002    0.002    3.402    5.193
 mp_allgather_i34                  2507 14.6    1.822    5.050    1.822    5.050
 mp_sum_l                          7870 13.0    3.444    4.943    3.444    4.943
 potential_pw2rs                    128 12.3    0.021    0.023    4.777    4.788
 mp_alltoall_d11v                  2415 14.1    4.238    4.738    4.238    4.738
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    4.120    4.156
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    2.346    4.119
 qs_energies_init_hamiltonians       11  5.9    0.003    0.010    3.808    3.820
 mp_alltoall_i22                    716 14.1    1.948    3.818    1.948    3.818
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="404", plot="h2o_256_md", label="(8n/4r/3t)", y=188.176000, yerr=0.000000
PlotPoint: name="405", plot="h2o_256_md_mem", label="(8n/4r/3t)", y=897.636364, yerr=7.713892
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/18/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420242647040       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528903135232       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514766E+12       0.0%      0.0%    100.0%
 flops max/rank                      4.353791E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755941440       0.0%      0.0%    100.0%
 number of processed stacks               5977344       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1130.3
 marketing flops                   144.580175E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank               1.143034E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1143192
 MPI messages size (bytes):
  total size                         2.023815E+12
  min size                           0.000000E+00
  max size                          17.653760E+06
  average size                       1.770320E+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              319024              36042702848
    131072 < size <=  4194304              715736             785529176064
   4194304 < size <= 16777216               70320             665379475120
  16777216 < size                           30720             536870912000
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4093                  57084.
 MP_Allreduce        11271                   1067.
 MP_Sync               170
 MP_Alltoall          1712               12503107.
 MP_ISendRecv        11776                  75008.
 MP_Wait             28330
 MP_comm_split          83
 MP_ISend            14952                 244818.
 MP_IRecv            14952                 244818.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.079    0.180  193.375  193.377
 qs_mol_dyn_low                       1  2.0    0.050    0.195  192.004  192.017
 qs_forces                           11  3.9    0.023    0.033  191.800  191.881
 qs_energies                         11  4.9    0.006    0.016  184.626  184.714
 scf_env_do_scf                      11  5.9    0.004    0.012  166.689  166.702
 velocity_verlet                     10  3.0    0.013    0.015  126.528  126.531
 scf_env_do_scf_inner_loop          117  6.6    0.009    0.037  118.813  118.818
 qs_scf_new_mos                     117  7.6    0.001    0.001   82.580   82.845
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   82.579   82.844
 dbcsr_multiply_generic            2507 12.6    0.197    0.219   80.385   81.172
 ot_scf_mini                        117  9.6    0.003    0.004   78.062   78.335
 multiply_cannon                   2507 13.6    0.556    0.586   55.223   57.415
 multiply_cannon_loop              2507 14.6    1.179    1.210   51.389   53.096
 init_scf_loop                       11  6.9    0.001    0.002   47.739   47.744
 prepare_preconditioner              11  7.9    0.000    0.000   43.384   43.399
 make_preconditioner                 11  8.9    0.000    0.002   43.384   43.398
 ot_mini                            117 10.6    0.001    0.001   42.877   43.149
 make_full_inverse_cholesky          11  9.9    0.000    0.000   36.814   41.939
 multiply_cannon_multrec          30084 15.6   14.245   19.374   26.516   31.307
 rebuild_ks_matrix                  128  8.3    0.001    0.001   29.467   29.653
 qs_ks_build_kohn_sham_matrix       128  9.3    0.016    0.018   29.466   29.653
 mp_waitall_1                    153770 16.5   17.854   29.111   17.854   29.111
 qs_ks_update_qs_env                128  7.6    0.001    0.001   26.665   26.824
 qs_ot_get_derivative               117 11.6    0.002    0.006   23.229   23.494
 qs_ot_get_p                        128 10.4    0.001    0.001   21.560   21.838
 make_m2s                          5014 13.6    0.094    0.100   20.637   21.638
 make_images                       5014 14.6    1.956    2.303   20.332   21.339
 apply_preconditioner_dbcsr         128 12.6    0.000    0.001   19.071   19.538
 apply_single                       128 13.6    0.001    0.001   19.071   19.538
 ot_diis_step                       117 11.6    0.017    0.018   19.514   19.516
 qs_ot_p2m_diag                      83 11.4    0.343    0.391   17.105   17.158
 cp_fm_cholesky_invert               11 10.9   16.752   16.761   16.752   16.761
 cp_fm_upper_to_full                105 14.7   11.208   16.671   11.208   16.671
 multiply_cannon_metrocomm3       30084 15.6    0.046    0.048    6.307   15.812
 cp_dbcsr_syevd                      83 12.4    0.005    0.005   15.808   15.810
 sum_up_and_integrate               128 10.3    0.079    0.087   14.271   14.292
 integrate_v_rspace                 128 11.3    0.003    0.004   14.192   14.215
 qs_rho_update_rho_low              128  7.7    0.001    0.001   13.482   13.552
 calculate_rho_elec                 128  8.7    0.174    0.190   13.481   13.552
 dbcsr_complete_redistribute        395 12.7    1.626    1.747    9.573   13.363
 make_images_data                  5014 15.6    0.066    0.090   11.163   12.967
 multiply_cannon_sync_h2d         30084 15.6   11.789   12.590   11.789   12.590
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   12.536   12.540
 cp_fm_redistribute_end              83 14.4    2.175   12.441    2.192   12.446
 dbcsr_mm_accdrv_process          62264 16.2    7.560    8.505   11.847   12.390
 cp_fm_diag_elpa_base                83 14.4    9.629   11.785   10.219   12.307
 hybrid_alltoall_any               5200 16.5    0.523    2.189    9.886   12.099
 copy_fm_to_dbcsr                   209 11.7    0.002    0.002    8.143   11.947
 init_scf_run                        11  5.9    0.000    0.001   11.645   11.646
 scf_env_initial_rho_setup           11  6.9    0.000    0.001   11.645   11.646
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    6.548   10.230
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002    9.601    9.792
 mp_alltoall_i22                    716 14.1    5.748    9.486    5.748    9.486
 pw_transfer                       1547 11.6    0.083    0.096    8.029    8.098
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.011    7.801    7.876
 cp_fm_cholesky_decompose            22 10.9    7.762    7.854    7.762    7.854
 grid_integrate_task_list           128 12.3    7.565    7.847    7.565    7.847
 wfi_extrapolate                     11  7.9    0.001    0.001    7.691    7.691
 multiply_cannon_metrocomm4       25070 15.6    0.075    0.085    2.704    7.317
 density_rs2pw                      128  9.7    0.005    0.006    6.543    7.212
 mp_irecv_dv                      76098 16.2    2.561    7.050    2.561    7.050
 fft_wrap_pw1pw2_140                523 13.2    0.471    0.477    6.843    6.936
 calculate_dm_sparse                128  9.5    0.005    0.019    6.345    6.442
 fft3d_ps                          1291 14.7    2.803    2.901    6.041    6.098
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.003    5.937    6.008
 rs_pw_transfer                    1046 11.9    0.013    0.014    5.183    5.971
 grid_collocate_task_list           128  9.7    5.212    5.578    5.212    5.578
 mp_alltoall_d11v                  2415 14.1    5.069    5.419    5.069    5.419
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    4.726    4.807
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.667    4.748
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    4.520    4.605
 potential_pw2rs                    128 12.3    0.024    0.024    4.533    4.553
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    4.222    4.275
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="406", plot="h2o_256_md", label="(8n/3r/4t)", y=193.377000, yerr=0.000000
PlotPoint: name="407", plot="h2o_256_md_mem", label="(8n/3r/4t)", y=1079.909091, yerr=17.737759
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/19/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                      5.820059E+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               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               1.466327E+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             716108638608
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      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             3997                  58279.
 MP_Allreduce        10990                   1175.
 MP_Sync                86
 MP_Alltoall          1700               18828160.
 MP_ISendRecv         7620                 122880.
 MP_Wait             19810
 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    0.048    0.080  187.197  187.198
 qs_mol_dyn_low                       1  2.0    0.003    0.003  186.496  186.508
 qs_forces                           11  3.9    0.013    0.017  186.226  186.231
 qs_energies                         11  4.9    0.006    0.008  178.844  178.861
 scf_env_do_scf                      11  5.9    0.001    0.001  152.672  152.686
 velocity_verlet                     10  3.0    0.032    0.054  115.602  115.613
 scf_env_do_scf_inner_loop          116  6.6    0.003    0.008  115.477  115.479
 dbcsr_multiply_generic            2485 12.5    0.180    0.184   83.427   83.746
 qs_scf_new_mos                     116  7.6    0.001    0.001   79.013   79.111
 qs_scf_loop_do_ot                  116  8.6    0.001    0.001   79.013   79.110
 ot_scf_mini                        116  9.6    0.003    0.004   74.540   74.602
 multiply_cannon                   2485 13.5    0.578    0.621   62.852   67.852
 multiply_cannon_loop              2485 14.5    0.444    0.453   58.240   58.769
 ot_mini                            116 10.6    0.001    0.001   40.072   40.121
 init_scf_loop                       11  6.9    0.000    0.000   37.026   37.028
 mp_waitall_1                    128490 16.6   26.890   33.655   26.890   33.655
 prepare_preconditioner              11  7.9    0.000    0.000   33.078   33.105
 make_preconditioner                 11  8.9    0.000    0.000   33.078   33.105
 make_full_inverse_cholesky          11  9.9    0.000    0.000   30.837   31.120
 rebuild_ks_matrix                  127  8.3    0.001    0.001   29.121   29.255
 qs_ks_build_kohn_sham_matrix       127  9.3    0.016    0.017   29.120   29.254
 qs_ks_update_qs_env                127  7.6    0.001    0.001   26.554   26.680
 qs_ot_get_p                        127 10.4    0.001    0.001   21.549   21.610
 multiply_cannon_multrec           9940 15.5   10.301   14.043   17.643   20.723
 qs_ot_get_derivative               116 11.6    0.002    0.002   20.420   20.490
 ot_diis_step                       116 11.6    0.019    0.020   19.567   19.568
 apply_preconditioner_dbcsr         127 12.6    0.000    0.000   19.168   19.351
 apply_single                       127 13.6    0.001    0.001   19.168   19.350
 init_scf_run                        11  5.9    0.000    0.001   19.313   19.313
 scf_env_initial_rho_setup           11  6.9    0.000    0.001   19.312   19.313
 make_m2s                          4970 13.5    0.066    0.074   16.755   18.997
 cp_fm_cholesky_invert               11 10.9   18.923   18.931   18.923   18.931
 make_images                       4970 14.5    2.269    2.618   16.451   18.688
 multiply_cannon_metrocomm3        9940 15.5    0.022    0.023   12.025   18.600
 qs_ot_p2m_diag                      82 11.4    0.490    0.496   17.429   17.448
 cp_dbcsr_syevd                      82 12.4    0.005    0.005   16.224   16.227
 sum_up_and_integrate               127 10.3    0.102    0.108   14.328   14.378
 integrate_v_rspace                 127 11.3    0.004    0.004   14.226   14.278
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002   13.938   13.948
 qs_rho_update_rho_low              127  7.7    0.001    0.001   13.605   13.637
 calculate_rho_elec                 127  8.7    0.255    0.266   13.604   13.636
 cp_fm_diag_elpa                     82 13.4    0.000    0.000   13.047   13.052
 cp_fm_diag_elpa_base                82 14.4   12.771   12.874   13.033   13.038
 make_images_data                  4970 15.5    0.051    0.060   10.183   13.034
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000   12.781   12.800
 hybrid_alltoall_any               5155 16.4    0.800    3.755    9.898   12.413
 multiply_cannon_sync_h2d          9940 15.5   11.513   11.997   11.513   11.997
 calculate_first_density_matrix       1  7.0    0.000    0.000   11.613   11.614
 acc_transpose_blocks              9940 15.5    0.046    0.047    9.579    9.587
 acc_transpose_blocks_kernels      9940 16.5    0.135    0.137    9.241    9.245
 jit_kernel_transpose                 5 15.6    9.105    9.110    9.105    9.110
 cp_fm_cholesky_decompose            22 10.9    8.340    8.484    8.340    8.484
 qs_ot_get_derivative_diag           76 12.4    0.002    0.002    8.259    8.317
 pw_transfer                       1535 11.6    0.082    0.089    8.097    8.117
 grid_integrate_task_list           127 12.3    7.687    8.113    7.687    8.113
 fft_wrap_pw1pw2                   1281 12.7    0.010    0.010    7.872    7.899
 multiply_cannon_metrocomm1        9940 15.5    0.029    0.030    4.892    7.792
 dbcsr_mm_accdrv_process          20590 16.1    2.690    3.487    6.975    7.631
 mp_allgather_i34                  2485 14.5    2.833    7.610    2.833    7.610
 wfi_extrapolate                     11  7.9    0.001    0.001    7.499    7.499
 fft_wrap_pw1pw2_140                519 13.2    0.490    0.506    6.843    6.878
 density_rs2pw                      127  9.7    0.005    0.005    6.325    6.596
 calculate_dm_sparse                127  9.5    0.001    0.001    6.138    6.229
 mp_alltoall_d11v                  2401 14.1    5.281    6.156    5.281    6.156
 fft3d_ps                          1281 14.7    2.712    2.783    6.056    6.094
 dbcsr_complete_redistribute        393 12.7    2.118    2.163    5.578    5.972
 grid_collocate_task_list           127  9.7    5.450    5.649    5.450    5.649
 qs_energies_init_hamiltonians       11  5.9    0.011    0.017    5.244    5.254
 rs_pw_transfer                    1038 11.9    0.012    0.013    4.542    4.809
 potential_pw2rs                    127 12.3    0.026    0.027    4.412    4.433
 multiply_cannon_metrocomm4        7455 15.5    0.023    0.026    1.854    4.065
 mp_irecv_dv                      28618 15.9    1.820    3.993    1.820    3.993
 copy_fm_to_dbcsr                   208 11.6    0.001    0.002    3.612    3.950
 copy_dbcsr_to_fm                   185 11.7    0.004    0.004    3.782    3.851
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    3.552    3.851
 qs_ot_get_orbitals                 116 10.6    0.001    0.001    3.712    3.755
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="408", plot="h2o_256_md", label="(8n/2r/6t)", y=187.198000, yerr=0.000000
PlotPoint: name="409", plot="h2o_256_md_mem", label="(8n/2r/6t)", y=1374.727273, yerr=46.236725
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_performance_tests/20/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1430460020736       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1958505086976       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1986244964352       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1992000282624       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2753956716544       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4454954827776       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5444944789504       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5492290093056       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6712799002624       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11613089636352       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15239146475520       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15239146475520       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19911124992000       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        94.228663E+12       0.0%      0.0%    100.0%
 flops max/rank                     11.785520E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6806316384       0.0%      0.0%    100.0%
 number of processed stacks               1979552       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    3438.3
 marketing flops                   145.646636E+12
 -------------------------------------------------------------------------------
 # multiplications                           2527
 max memory usage/rank               2.296971E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                  101080
 MPI messages size (bytes):
  total size                         1.144901E+12
  min size                           0.000000E+00
  max size                         104.857600E+06
  average size                      11.326685E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                 572                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                  44                  2883584
    131072 < size <=  4194304               45568              35366371328
   4194304 < size <= 16777216               44720             382939955200
  16777216 < size                           10176             726591885696
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4024                  58831.
 MP_Allreduce        11057                   1512.
 MP_Sync                87
 MP_Alltoall          1724               36993716.
 MP_ISendRecv         3612                 218624.
 MP_Wait             11682
 MP_ISend             6456                1080169.
 MP_IRecv             6456                1080169.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.030    0.069  297.800  297.800
 qs_mol_dyn_low                       1  2.0    0.003    0.004  297.050  297.062
 qs_forces                           11  3.9    0.020    0.030  296.958  296.961
 qs_energies                         11  4.9    0.002    0.002  288.290  288.309
 scf_env_do_scf                      11  5.9    0.001    0.001  257.997  258.013
 velocity_verlet                     10  3.0    0.002    0.002  209.236  209.243
 scf_env_do_scf_inner_loop          118  6.6    0.003    0.008  133.887  133.889
 init_scf_loop                       11  6.9    0.000    0.000  123.857  123.861
 prepare_preconditioner              11  7.9    0.000    0.000  119.171  119.200
 make_preconditioner                 11  8.9    0.000    0.000  119.171  119.199
 make_full_inverse_cholesky          11  9.9    0.000    0.000   95.516  116.272
 dbcsr_multiply_generic            2527 12.6    0.215    0.222   91.895   92.452
 qs_scf_new_mos                     118  7.6    0.001    0.001   91.122   91.217
 qs_scf_loop_do_ot                  118  8.6    0.001    0.001   91.121   91.216
 ot_scf_mini                        118  9.6    0.004    0.004   86.347   86.381
 cp_fm_upper_to_full                105 14.8   52.690   75.278   52.690   75.278
 multiply_cannon                   2527 13.6    0.686    0.739   67.416   68.016
 multiply_cannon_loop              2527 14.6    0.476    0.486   63.846   65.139
 ot_mini                            118 10.6    0.001    0.001   44.539   44.567
 dbcsr_complete_redistribute        395 12.7    3.991    4.029   29.302   42.073
 copy_fm_to_dbcsr                   209 11.7    0.001    0.001   25.928   38.660
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000   23.610   36.150
 mp_waitall_1                    106306 16.7   28.980   36.025   28.980   36.025
 mp_alltoall_i22                    718 14.1   21.368   34.253   21.368   34.253
 rebuild_ks_matrix                  129  8.3    0.001    0.001   34.161   34.192
 qs_ks_build_kohn_sham_matrix       129  9.3    0.017    0.018   34.160   34.191
 cp_fm_cholesky_invert               11 10.9   33.589   33.596   33.589   33.596
 qs_ks_update_qs_env                129  7.6    0.001    0.001   31.909   31.941
 qs_ot_get_p                        129 10.4    0.001    0.001   26.305   26.318
 multiply_cannon_metrocomm3       10108 15.6    0.023    0.023   19.490   25.652
 qs_ot_get_derivative               118 11.6    0.002    0.002   24.528   24.560
 qs_ot_p2m_diag                      83 11.4    0.879    0.885   22.191   22.217
 make_m2s                          5054 13.6    0.077    0.080   19.917   20.781
 cp_dbcsr_syevd                      83 12.4    0.005    0.006   20.471   20.472
 init_scf_run                        11  5.9    0.000    0.001   20.377   20.377
 scf_env_initial_rho_setup           11  6.9    0.000    0.001   20.376   20.377
 make_images                       5054 14.6    3.785    3.874   19.440   20.306
 ot_diis_step                       118 11.6    0.022    0.022   19.985   19.986
 apply_preconditioner_dbcsr         129 12.6    0.000    0.000   19.187   19.385
 apply_single                       129 13.6    0.001    0.001   19.187   19.385
 multiply_cannon_multrec          10108 15.6   10.584   12.422   18.034   18.085
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   17.278   17.279
 cp_fm_diag_elpa_base                83 14.4   12.874   14.512   17.273   17.274
 sum_up_and_integrate               129 10.3    0.195    0.196   15.919   16.014
 integrate_v_rspace                 129 11.3    0.004    0.004   15.724   15.818
 multiply_cannon_sync_h2d         10108 15.6   15.774   15.787   15.774   15.787
 qs_rho_update_rho_low              129  7.7    0.001    0.001   15.165   15.182
 calculate_rho_elec                 129  8.7    0.486    0.487   15.164   15.181
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002   14.946   14.999
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000   13.194   13.225
 hybrid_alltoall_any               5240 16.5    1.312    3.064   10.661   12.449
 make_images_data                  5054 15.6    0.059    0.065   10.556   12.259
 calculate_first_density_matrix       1  7.0    0.000    0.000   11.538   11.539
 acc_transpose_blocks             10108 15.6    0.044    0.045    8.986    9.716
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002    9.489    9.517
 acc_transpose_blocks_kernels     10108 16.6    0.138    0.140    8.631    9.358
 jit_kernel_transpose                 5 15.6    8.493    9.220    8.493    9.220
 dbcsr_mm_accdrv_process          20926 16.1    3.862    5.801    7.211    9.057
 cp_fm_cholesky_decompose            22 10.9    9.012    9.042    9.012    9.042
 grid_integrate_task_list           129 12.3    8.603    8.780    8.603    8.780
 wfi_extrapolate                     11  7.9    0.001    0.001    8.591    8.591
 pw_transfer                       1559 11.6    0.094    0.094    8.530    8.536
 fft_wrap_pw1pw2                   1301 12.7    0.011    0.011    8.288    8.293
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    7.924    7.932
 fft_wrap_pw1pw2_140                527 13.2    0.528    0.532    7.302    7.313
 mp_alltoall_d11v                  2423 14.1    7.059    7.187    7.059    7.187
 calculate_dm_sparse                129  9.5    0.001    0.001    6.599    6.681
 grid_collocate_task_list           129  9.7    6.387    6.426    6.387    6.426
 fft3d_ps                          1301 14.7    2.783    2.789    6.333    6.347
 density_rs2pw                      129  9.7    0.005    0.005    6.160    6.187
 copy_dbcsr_to_fm                   186 11.8    0.004    0.004    5.964    6.043
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="410", plot="h2o_256_md", label="(8n/1r/12t)", y=297.800000, yerr=0.000000
PlotPoint: name="411", plot="h2o_256_md_mem", label="(8n/1r/12t)", y=2160.363636, yerr=53.583024
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_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               1.260524E+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               19627572.
 MP_ISendRecv          570                  19200.
 MP_Wait              1302
 MP_ISend              642                 197829.
 MP_IRecv              642                 197607.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.021    0.067  101.059  101.059
 qs_energies                          1  2.0    0.000    0.000  100.436  100.450
 ls_scf                               1  3.0    0.000    0.000   99.537   99.551
 dbcsr_multiply_generic             111  6.7    0.014    0.015   88.459   88.614
 multiply_cannon                    111  7.7    0.028    0.035   65.007   72.468
 multiply_cannon_loop               111  8.7    0.211    0.225   61.557   69.175
 ls_scf_main                          1  4.0    0.000    0.000   52.306   52.307
 density_matrix_trs4                  2  5.0    0.002    0.003   46.826   46.928
 ls_scf_init_scf                      1  4.0    0.000    0.000   44.189   44.190
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   43.092   43.137
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   40.924   40.942
 mp_waitall_1                     11316 10.9   27.054   31.143   27.054   31.143
 multiply_cannon_metrocomm1        2664  9.7    0.009    0.010   13.150   17.707
 multiply_cannon_multrec           2664  9.7    8.185    9.008   15.494   17.330
 compute_matrix_preconditioner        1  6.0    0.000    0.001   16.859   16.863
 multiply_cannon_sync_h2d          2664  9.7   13.850   15.708   13.850   15.708
 multiply_cannon_metrocomm3        2664  9.7    0.009    0.010    6.345   15.093
 make_m2s                           222  7.7    0.008    0.011   13.313   13.790
 make_images                        222  8.7    0.099    0.109   13.291   13.769
 mp_sum_l                           807  5.4    9.611   11.669    9.611   11.669
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    8.789   10.484
 acc_transpose_blocks              2664  9.7    0.019    0.021    4.798    9.035
 acc_transpose_blocks_kernels      2664 10.7    0.037    0.041    4.690    8.927
 jit_kernel_transpose                 1 13.0    4.653    8.892    4.653    8.892
 make_images_data                   222  9.7    0.004    0.005    7.880    8.472
 hybrid_alltoall_any                227 10.6    0.215    1.851    6.828    8.253
 dbcsr_mm_accdrv_process           4760 10.4    0.512    0.610    6.931    7.895
 dbcsr_mm_accdrv_process_sort      4760 11.4    6.215    7.103    6.215    7.103
 calculate_norms                   4752  9.8    5.571    6.214    5.571    6.214
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.978    5.131
 make_images_sizes                  222  9.7    0.000    0.000    0.735    3.868
 mp_alltoall_i44                    222 10.7    0.735    3.868    0.735    3.868
 multiply_cannon_metrocomm4        2442  9.7    0.012    0.014    2.055    3.329
 arnoldi_extremal                     4  6.8    0.000    0.000    3.283    3.307
 arnoldi_normal_ev                    4  7.8    0.001    0.003    3.283    3.307
 mp_irecv_dv                       6231 10.9    2.037    3.301    2.037    3.301
 build_subspace                      16  8.4    0.009    0.012    3.184    3.186
 ls_scf_post                          1  4.0    0.000    0.000    3.041    3.055
 ls_scf_store_result                  1  5.0    0.000    0.000    2.856    2.893
 dbcsr_special_finalize             555  9.7    0.005    0.006    2.348    2.724
 dbcsr_merge_single_wm              555 10.7    0.458    0.589    2.340    2.716
 make_images_pack                   222  9.7    2.204    2.626    2.206    2.628
 dbcsr_matrix_vector_mult           304  9.0    0.003    0.010    2.351    2.587
 dbcsr_sort_data                    658 11.4    2.140    2.467    2.140    2.467
 dbcsr_matrix_vector_mult_local     304 10.0    2.069    2.459    2.071    2.461
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.275    2.355
 buffer_matrices_ensure_size        222  8.7    1.765    2.123    1.765    2.123
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="500", plot="h2o_32_nrep3_ls", label="(8n/12r/1t)", y=101.059000, yerr=0.000000
PlotPoint: name="501", plot="h2o_32_nrep3_ls_mem", label="(8n/12r/1t)", y=1140.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_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               2.103775E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                  106560
 MPI messages size (bytes):
  total size                         2.699093E+12
  min size                           0.000000E+00
  max size                          72.286792E+06
  average size                      25.329324E+06
 MPI breakdown and total messages size (bytes):
             size <=      128               23040                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                3264                325830144
    131072 < size <=  4194304                5280               3328561104
   4194304 < size <= 16777216               12709             156766962056
  16777216 < size                           62267            2538670978840
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 266696.
 MP_Allreduce         3058                  10339.
 MP_Sync                 4
 MP_Alltoall            47               15335933.
 MP_ISendRecv          282                  57600.
 MP_Wait               828
 MP_ISend              462                 414589.
 MP_IRecv              462                 413870.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.033    0.067   93.569   93.570
 qs_energies                          1  2.0    0.000    0.000   92.936   92.940
 ls_scf                               1  3.0    0.002    0.017   91.621   91.625
 dbcsr_multiply_generic             111  6.7    0.015    0.016   77.298   77.657
 multiply_cannon                    111  7.7    0.030    0.041   55.200   58.821
 ls_scf_main                          1  4.0    0.000    0.001   55.171   55.183
 multiply_cannon_loop               111  8.7    0.115    0.122   51.906   55.168
 density_matrix_trs4                  2  5.0    0.002    0.003   49.379   49.593
 ls_scf_init_scf                      1  4.0    0.000    0.001   32.859   32.878
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   31.603   31.714
 mp_waitall_1                      9246 10.9   22.014   30.271   22.014   30.271
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   29.174   29.185
 multiply_cannon_multrec           1332  9.7   13.016   16.950   22.193   27.230
 multiply_cannon_metrocomm3        1332  9.7    0.006    0.007   12.307   21.031
 make_m2s                           222  7.7    0.006    0.007   15.474   16.089
 make_images                        222  8.7    1.565    1.968   15.443   16.060
 dbcsr_mm_accdrv_process           4041 10.4    0.263    0.447    8.783   10.320
 make_images_data                   222  9.7    0.004    0.004    8.957    9.878
 dbcsr_mm_accdrv_process_sort      4041 11.4    8.381    9.873    8.381    9.873
 hybrid_alltoall_any                227 10.6    0.522    2.478    8.369    9.352
 mp_sum_l                           807  5.4    5.354    8.624    5.354    8.624
 multiply_cannon_metrocomm4        1221  9.7    0.006    0.008    3.200    7.653
 mp_irecv_dv                       3311 11.0    3.180    7.601    3.180    7.601
 calculate_norms                   2376  9.8    5.979    6.797    5.979    6.797
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    4.083    6.713
 multiply_cannon_sync_h2d          1332  9.7    4.734    6.006    4.734    6.006
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.103    5.329
 arnoldi_extremal                     4  6.8    0.000    0.000    4.792    4.812
 arnoldi_normal_ev                    4  7.8    0.001    0.005    4.792    4.812
 build_subspace                      16  8.4    0.014    0.021    4.534    4.538
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.003    1.371    3.872
 ls_scf_post                          1  4.0    0.000    0.001    3.589    3.592
 dbcsr_matrix_vector_mult           304  9.0    0.005    0.016    3.193    3.453
 ls_scf_store_result                  1  5.0    0.000    0.000    3.283    3.408
 dbcsr_matrix_vector_mult_local     304 10.0    2.733    3.210    2.735    3.212
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.576    2.688
 compute_matrix_preconditioner        1  6.0    0.000    0.002    2.555    2.562
 make_images_pack                   222  9.7    2.025    2.436    2.027    2.438
 mp_allgather_i34                   111  8.7    0.996    2.379    0.996    2.379
 dbcsr_sort_data                    436 11.2    1.789    2.014    1.789    2.014
 acc_transpose_blocks              1332  9.7    0.007    0.007    1.759    1.997
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.938    1.959
 acc_transpose_blocks_kernels      1332 10.7    0.018    0.019    1.713    1.949
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.925    1.947
 qs_ks_build_kohn_sham_matrix         3  8.3    0.004    0.025    1.925    1.947
 jit_kernel_transpose                 1 13.0    1.695    1.931    1.695    1.931
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="502", plot="h2o_32_nrep3_ls", label="(8n/6r/2t)", y=93.570000, yerr=0.000000
PlotPoint: name="503", plot="h2o_32_nrep3_ls_mem", label="(8n/6r/2t)", y=1761.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_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               2.701636E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                   46176
 MPI messages size (bytes):
  total size                         1.924064E+12
  min size                           0.000000E+00
  max size                         108.059888E+06
  average size                      41.668048E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                9984                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304                3328               1170063360
   4194304 < size <= 16777216                1870              19378539600
  16777216 < size                           30994            1903514987232
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 265470.
 MP_Allreduce         3058                  11181.
 MP_Sync                 4
 MP_Alltoall            47               23526250.
 MP_ISendRecv          186                  57600.
 MP_Wait               732
 MP_ISend              462                 560046.
 MP_IRecv              462                 560662.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.081    0.153   95.231   95.233
 qs_energies                          1  2.0    0.000    0.000   94.354   94.374
 ls_scf                               1  3.0    0.004    0.011   92.930   92.949
 dbcsr_multiply_generic             111  6.7    0.019    0.047   77.040   77.355
 multiply_cannon                    111  7.7    0.040    0.110   53.691   57.795
 ls_scf_main                          1  4.0    0.000    0.005   57.055   57.060
 multiply_cannon_loop               111  8.7    0.099    0.105   50.062   53.558
 density_matrix_trs4                  2  5.0    0.002    0.003   51.096   51.283
 mp_waitall_1                      7374 11.0   23.708   33.393   23.708   33.393
 ls_scf_init_scf                      1  4.0    0.006    0.020   32.267   32.274
 ls_scf_init_matrix_S                 1  5.0    0.000    0.001   31.006   31.076
 matrix_sqrt_Newton_Schulz            2  6.5    0.005    0.037   28.345   28.369
 multiply_cannon_multrec            888  9.7   12.624   15.265   21.115   24.357
 multiply_cannon_metrocomm3         888  9.7    0.004    0.004   11.109   22.471
 make_m2s                           222  7.7    0.007    0.012   16.838   18.093
 make_images                        222  8.7    1.973    2.284   16.799   18.053
 make_images_data                   222  9.7    0.003    0.004    9.675   10.827
 hybrid_alltoall_any                227 10.6    0.626    2.854    9.491   10.708
 dbcsr_mm_accdrv_process           3754 10.4    0.226    0.411    8.032    9.219
 dbcsr_mm_accdrv_process_sort      3754 11.4    7.663    8.808    7.663    8.808
 mp_sum_l                           807  5.4    4.955    8.329    4.955    8.329
 multiply_cannon_sync_h2d           888  9.7    5.982    7.326    5.982    7.326
 multiply_cannon_metrocomm1         888  9.7    0.002    0.003    3.542    7.037
 multiply_cannon_metrocomm4         777  9.7    0.004    0.005    2.475    6.922
 mp_irecv_dv                       2335 11.1    2.459    6.857    2.459    6.857
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.787    6.630
 arnoldi_extremal                     4  6.8    0.003    0.023    5.324    5.367
 arnoldi_normal_ev                    4  7.8    0.041    0.084    5.320    5.347
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.957    5.160
 build_subspace                      16  8.4    0.015    0.021    4.811    4.830
 calculate_norms                   1584  9.8    4.266    4.610    4.266    4.610
 dbcsr_matrix_vector_mult           304  9.0    0.005    0.016    3.445    3.751
 mp_allgather_i34                   111  8.7    1.472    3.731    1.472    3.731
 ls_scf_post                          1  4.0    0.009    0.024    3.605    3.626
 dbcsr_matrix_vector_mult_local     304 10.0    3.003    3.571    3.005    3.573
 ls_scf_store_result                  1  5.0    0.000    0.000    3.322    3.419
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.799    2.921
 make_images_pack                   222  9.7    1.812    2.139    1.815    2.142
 dbcsr_sort_data                    325 11.1    1.868    2.131    1.868    2.131
 make_images_sizes                  222  9.7    0.000    0.000    0.852    2.083
 mp_alltoall_i44                    222 10.7    0.852    2.083    0.852    2.083
 dbcsr_data_release                9322 10.9    1.300    2.036    1.300    2.036
 compute_matrix_preconditioner        1  6.0    0.000    0.001    2.010    2.025
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.920    1.921
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="504", plot="h2o_32_nrep3_ls", label="(8n/4r/3t)", y=95.233000, yerr=0.000000
PlotPoint: name="505", plot="h2o_32_nrep3_ls_mem", label="(8n/4r/3t)", y=2184.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_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               3.333075E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                   50616
 MPI messages size (bytes):
  total size                         1.536549E+12
  min size                           0.000000E+00
  max size                          72.286792E+06
  average size                      30.356986E+06
 MPI breakdown and total messages size (bytes):
             size <=      128               10368                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                1056                104411904
    131072 < size <=  4194304                3168                831638784
   4194304 < size <= 16777216                3103              33613273640
  16777216 < size                           32921            1501999894888
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 266696.
 MP_Allreduce         3058                  13371.
 MP_Sync                 4
 MP_Alltoall            47               30278988.
 MP_ISendRecv          138                  86400.
 MP_Wait               600
 MP_ISend              378                 823502.
 MP_IRecv              378                 823753.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.213    0.391  113.266  113.269
 qs_energies                          1  2.0    0.000    0.000  111.919  112.015
 ls_scf                               1  3.0    0.001    0.007  110.274  110.361
 dbcsr_multiply_generic             111  6.7    0.017    0.017   93.943   94.158
 multiply_cannon                    111  7.7    0.050    0.095   61.177   68.632
 multiply_cannon_loop               111  8.7    0.114    0.125   56.141   64.274
 ls_scf_main                          1  4.0    0.001    0.027   58.700   58.701
 density_matrix_trs4                  2  5.0    0.002    0.003   52.647   52.753
 ls_scf_init_scf                      1  4.0    0.000    0.002   48.329   48.332
 ls_scf_init_matrix_S                 1  5.0    0.000    0.001   47.034   47.116
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   44.557   44.573
 mp_waitall_1                      6438 11.0   26.727   38.395   26.727   38.395
 multiply_cannon_multrec           1332  9.7   14.141   17.890   21.965   25.395
 multiply_cannon_metrocomm3        1332  9.7    0.003    0.003   11.740   24.697
 make_m2s                           222  7.7    0.007    0.008   21.144   22.597
 make_images                        222  8.7    3.133    3.595   21.094   22.548
 compute_matrix_preconditioner        1  6.0    0.001    0.001   16.502   16.509
 mp_sum_l                           807  5.4   10.178   14.457   10.178   14.457
 make_images_data                   222  9.7    0.004    0.005   11.790   13.574
 hybrid_alltoall_any                227 10.6    0.800    3.833   11.086   12.884
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    9.156   12.710
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.003    4.028    9.005
 dbcsr_mm_accdrv_process           3641 10.4    0.211    0.405    7.463    8.994
 acc_transpose_blocks              1332  9.7    0.007    0.007    5.899    8.774
 acc_transpose_blocks_kernels      1332 10.7    0.017    0.018    5.839    8.714
 jit_kernel_transpose                 1 13.0    5.823    8.696    5.823    8.696
 dbcsr_mm_accdrv_process_sort      3641 11.4    7.091    8.567    7.091    8.567
 multiply_cannon_metrocomm4        1110  9.7    0.004    0.006    2.074    6.075
 multiply_cannon_sync_h2d          1332  9.7    5.512    6.058    5.512    6.058
 mp_irecv_dv                       3229 10.9    2.051    6.006    2.051    6.006
 arnoldi_extremal                     4  6.8    0.000    0.003    5.301    5.321
 arnoldi_normal_ev                    4  7.8    0.002    0.005    5.301    5.321
 build_subspace                      16  8.4    0.015    0.021    4.921    4.932
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.566    4.782
 calculate_norms                   2376  9.8    4.190    4.611    4.190    4.611
 mp_allgather_i34                   111  8.7    2.161    4.463    2.161    4.463
 dbcsr_matrix_vector_mult           304  9.0    0.006    0.016    3.585    3.903
 dbcsr_matrix_vector_mult_local     304 10.0    3.170    3.685    3.172    3.687
 dbcsr_sort_data                    658 11.4    3.023    3.373    3.023    3.373
 ls_scf_post                          1  4.0    0.012    0.097    3.244    3.328
 dbcsr_special_finalize             555  9.7    0.006    0.007    2.755    3.186
 dbcsr_merge_single_wm              555 10.7    0.527    0.643    2.747    3.178
 ls_scf_store_result                  1  5.0    0.000    0.000    2.974    3.031
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.926    2.977
 dbcsr_data_release               10477 10.7    1.580    2.499    1.580    2.499
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="506", plot="h2o_32_nrep3_ls", label="(8n/3r/4t)", y=113.269000, yerr=0.000000
PlotPoint: name="507", plot="h2o_32_nrep3_ls_mem", label="(8n/3r/4t)", y=2723.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_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               4.631540E+09
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                   10656
 MPI messages size (bytes):
  total size                         1.149035E+12
  min size                           0.000000E+00
  max size                         203.538048E+06
  average size                     107.829832E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                2304                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304                 768                702038016
   4194304 < size <= 16777216                   0                        0
  16777216 < size                            7584            1148332810224
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast                2                     12.
 MP_Allreduce          705                    128.
 MP_Alltoall           310               12920694.
 MP_ISend             1776               40180424.
 MP_IRecv             1776               40465030.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 265558.
 MP_Allreduce         3049                  15663.
 MP_Sync                 4
 MP_Alltoall            47               46208988.
 MP_ISendRecv           90                 115200.
 MP_Wait               573
 MP_ISend              420                 924980.
 MP_IRecv              420                 924528.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.061    0.070   99.650   99.651
 qs_energies                          1  2.0    0.000    0.000   98.471   98.477
 ls_scf                               1  3.0    0.000    0.000   96.541   96.546
 dbcsr_multiply_generic             111  6.7    0.017    0.018   78.030   78.268
 ls_scf_main                          1  4.0    0.000    0.000   61.956   61.956
 multiply_cannon                    111  7.7    0.085    0.144   55.508   60.500
 density_matrix_trs4                  2  5.0    0.002    0.003   54.906   54.996
 multiply_cannon_loop               111  8.7    0.069    0.077   50.937   52.665
 mp_waitall_1                      5481 11.0   26.636   32.626   26.636   32.626
 ls_scf_init_scf                      1  4.0    0.000    0.000   30.974   30.981
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   29.792   29.831
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.523   27.539
 multiply_cannon_multrec            444  9.7   14.006   16.533   21.007   23.103
 make_m2s                           222  7.7    0.004    0.005   17.659   20.193
 make_images                        222  8.7    3.707    4.409   17.597   20.132
 multiply_cannon_metrocomm1         444  9.7    0.002    0.002   11.243   16.418
 multiply_cannon_metrocomm3         444  9.7    0.001    0.001    6.270   15.281
 make_images_data                   222  9.7    0.003    0.004    9.919   12.397
 hybrid_alltoall_any                227 10.6    0.786    3.751    9.813   12.303
 dbcsr_mm_accdrv_process           3003 10.4    0.176    0.344    6.704    7.816
 multiply_cannon_sync_h2d           444  9.7    6.527    7.731    6.527    7.731
 dbcsr_mm_accdrv_process_sort      3003 11.4    6.389    7.474    6.389    7.474
 mp_allgather_i34                   111  8.7    2.775    6.982    2.775    6.982
 arnoldi_extremal                     4  6.8    0.000    0.000    5.905    5.938
 arnoldi_normal_ev                    4  7.8    0.050    0.068    5.905    5.938
 build_subspace                      16  8.4    0.015    0.019    5.457    5.466
 mp_sum_l                           807  5.4    2.908    5.236    2.908    5.236
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.629    4.756
 dbcsr_matrix_vector_mult           304  9.0    0.007    0.016    4.170    4.346
 dbcsr_matrix_vector_mult_local     304 10.0    3.651    4.125    3.653    4.128
 multiply_cannon_metrocomm4         333  9.7    0.001    0.002    1.680    4.099
 mp_irecv_dv                       1241 11.2    1.662    4.073    1.662    4.073
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    2.044    3.991
 calculate_norms                    792  9.8    3.561    3.765    3.561    3.765
 ls_scf_post                          1  4.0    0.000    0.000    3.611    3.616
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    3.410    3.517
 make_images_sizes                  222  9.7    0.000    0.000    1.113    3.484
 mp_alltoall_i44                    222 10.7    1.113    3.483    1.113    3.483
 ls_scf_store_result                  1  5.0    0.000    0.000    3.391    3.434
 dbcsr_finalize                     304  7.8    0.062    0.078    2.195    2.268
 dbcsr_merge_all                    275  8.9    0.473    0.525    2.045    2.105
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.994    1.995
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="508", plot="h2o_32_nrep3_ls", label="(8n/2r/6t)", y=99.651000, yerr=0.000000
PlotPoint: name="509", plot="h2o_32_nrep3_ls_mem", label="(8n/2r/6t)", y=3659.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4_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               8.727740E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                    4440
 MPI messages size (bytes):
  total size                       770.525954E+09
  min size                           0.000000E+00
  max size                         399.069120E+06
  average size                     173.541888E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                 640                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304                 640                468025344
   4194304 < size <= 16777216                   0                        0
  16777216 < size                            3160             770057961712
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 284111.
 MP_Allreduce         3043                  21950.
 MP_Sync                 4
 MP_Alltoall            47               88727262.
 MP_ISendRecv           84                 732600.
 MP_Wait               309
 MP_ISend              180                3337386.
 MP_IRecv              180                3339494.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.112    0.117  122.200  122.201
 qs_energies                          1  2.0    0.000    0.000  120.698  120.713
 ls_scf                               1  3.0    0.000    0.000  117.817  117.832
 dbcsr_multiply_generic             111  6.7    0.024    0.026   91.834   91.964
 ls_scf_main                          1  4.0    0.000    0.000   65.172   65.173
 multiply_cannon                    111  7.7    0.147    0.226   57.950   64.015
 multiply_cannon_loop               111  8.7    0.069    0.075   54.607   61.715
 density_matrix_trs4                  2  5.0    0.002    0.003   56.346   56.390
 ls_scf_init_scf                      1  4.0    0.000    0.000   48.972   48.973
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   47.607   47.621
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   44.765   44.775
 mp_waitall_1                      4569 11.1   23.275   28.802   23.275   28.802
 make_m2s                           222  7.7    0.005    0.005   23.541   24.384
 make_images                        222  8.7    4.579    4.961   23.435   24.276
 multiply_cannon_multrec            444  9.7   17.814   18.445   22.395   22.872
 multiply_cannon_metrocomm3         444  9.7    0.001    0.001   11.895   18.011
 compute_matrix_preconditioner        1  6.0    0.002    0.002   15.877   15.889
 hybrid_alltoall_any                227 10.6    1.659    3.618   12.665   15.208
 make_images_data                   222  9.7    0.003    0.003   12.782   15.036
 mp_sum_l                           807  5.4    8.023    9.547    8.023    9.547
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    7.435    8.926
 multiply_cannon_sync_h2d           444  9.7    8.847    8.899    8.847    8.899
 acc_transpose_blocks               444  9.7    0.002    0.002    7.031    7.936
 acc_transpose_blocks_kernels       444 10.7    0.005    0.005    6.996    7.901
 jit_kernel_transpose                 1 13.0    6.991    7.896    6.991    7.896
 arnoldi_extremal                     4  6.8    0.000    0.000    7.476    7.484
 arnoldi_normal_ev                    4  7.8    0.025    0.036    7.476    7.484
 build_subspace                      16  8.4    0.025    0.036    6.901    6.917
 dbcsr_matrix_vector_mult           304  9.0    0.009    0.024    5.495    5.662
 dbcsr_matrix_vector_mult_local     304 10.0    4.972    5.273    4.974    5.275
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.991    5.212
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    4.810    4.903
 dbcsr_mm_accdrv_process           1814 10.4    0.255    0.318    4.414    4.547
 dbcsr_mm_accdrv_process_sort      1814 11.4    4.113    4.241    4.113    4.241
 ls_scf_post                          1  4.0    0.000    0.000    3.673    3.687
 make_images_sizes                  222  9.7    0.000    0.000    1.442    3.459
 mp_alltoall_i44                    222 10.7    1.441    3.459    1.441    3.459
 ls_scf_store_result                  1  5.0    0.000    0.000    3.424    3.434
 calculate_norms                    792  9.8    3.243    3.285    3.243    3.285
 dbcsr_finalize                     304  7.8    0.082    0.089    3.085    3.134
 mp_allgather_i34                   111  8.7    0.964    3.098    0.964    3.098
 dbcsr_merge_all                    275  8.9    0.891    0.920    2.871    2.913
 dbcsr_complete_redistribute          5  7.6    1.441    1.478    2.792    2.886
 dbcsr_data_release               12724 10.6    2.323    2.858    2.323    2.858
 qs_energies_init_hamiltonians        1  3.0    0.001    0.005    2.851    2.851
 matrix_ls_to_qs                      2  6.0    0.000    0.000    2.432    2.541
 dbcsr_sort_data                    325 11.1    2.446    2.496    2.446    2.496
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="510", plot="h2o_32_nrep3_ls", label="(8n/1r/12t)", y=122.201000, yerr=0.000000
PlotPoint: name="511", plot="h2o_32_nrep3_ls_mem", label="(8n/1r/12t)", y=6804.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


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

CommitSHA: 2a8b4f8b6e28c5e9192b960573eb6cb2bc3debf4
Summary: empty
Status: OK