=== 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: 0ea91c6b73893ebcd66acc6836a089d1c601130e


################# ARCHITECTURE FILE ##################
#!/bin/bash
#
# CP2K arch file for Cray-XC50 (Piz Daint, CSCS, GPU partition)
#
# Tested with: GNU 9.3.0, Cray-MPICH 7.7.18, Cray-libsci 20.09.1, Cray-FFTW 3.3.8.10,
#              COSMA 2.6.2, ELPA 2022.11.001, LIBINT 2.6.0, LIBPEXSI 1.2.0,
#              LIBXC 6.1.0, LIBVORI 220621, LIBXSMM 1.17, PLUMED 2.8.1,
#              SIRIUS 7.3.2, 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 (12.01.2023)
#
# \
   if [ "${0}" = "${BASH_SOURCE}" ]; then \
      echo "ERROR: Script ${0##*/} must be sourced"; \
      echo "Usage: source ${0##*/}"; \
      exit 1; \
   fi; \
   this_file=${BASH_SOURCE##*/}; \
   if [ -n "${1}" ]; then \
      gcc_version="${1}"; \
   else \
      gcc_version="9.3.0"; \
   fi; \
   module add daint-gpu; \
   module rm PrgEnv-cray; \
   module add PrgEnv-gnu; \
   module rm gcc; \
   module add gcc/${gcc_version}; \
   module add cray-fftw/3.3.8.10; \
   module add cudatoolkit; \
   echo "Expected setup:"; \
   echo "   cray-mpich/7.7.18"; \
   echo "   craype-haswell"; \
   echo "   daint-gpu/21.09"; \
   echo "   craype/2.7.10"; \
   echo "   cray-libsci/20.09.1"; \
   echo "   PrgEnv-gnu/6.0.10"; \
   echo "   gcc/${gcc_version}"; \
   echo "   cray-fftw/3.3.8.10"; \
   echo "   cudatoolkit/11.0.2_3.38-8.1__g5b73779"; \
   module list; \
   module -f save cp2k_gpu_gnu_psmp; \
   echo "To load the required modules in your batch job script, use:"; \
   echo "   module restore cp2k_gpu_gnu_psmp"; \
   cd tools/toolchain; \
   ./install_cp2k_toolchain.sh --enable-cuda=yes --gpu-ver=P100 -j${maxtasks} --no-arch-files --with-gcc=system --with-libvdwxc --with-pexsi --with-plumed; \
   cd ../..; \
   printf "Sourcing ${PWD}/tools/toolchain/install/setup ... "; \
   source ${PWD}/tools/toolchain/install/setup; \
   printf "done\n"; \
   echo "Check the output above for error messages and consistency!"; \
   echo "If everything is OK, you can build a CP2K production binary with"; \
   echo "   make -j ARCH=${this_file%.*} VERSION=${this_file##*.}"; \
   echo "Alternatively, you can add further checks, e.g. for regression testing, with"; \
   echo "   make -j ARCH=${this_file%.*} VERSION=${this_file##*.} DO_CHECKS=yes"; \
   echo "or build CP2K as a library with"; \
   echo "   make -j ARCH=${this_file%.*} VERSION=${this_file##*.} libcp2k"; \
   return

# Set options
DO_CHECKS      := no
USE_ACC        := yes
USE_COSMA      := 2.6.2
USE_ELPA       := 2022.11.001
USE_LIBINT     := 2.6.0
USE_LIBPEXSI   := 1.2.0
USE_LIBVORI    := 220621
USE_LIBXC      := 6.1.0
USE_LIBXSMM    := 1.17
USE_PLUMED     := 2.8.1
#USE_QUIP       := 0.9.10
USE_SIRIUS     := 7.3.2
USE_SPGLIB     := 1.16.2
# Only needed for SIRIUS
LIBVDWXC_VER   := 0.4.0
SPFFT_VER      := 1.0.6
SPLA_VER       := 1.5.4
HDF5_VER       := 1.12.0
# Only needed for LIBPEXSI
SCOTCH_VER     := 6.0.0
SUPERLU_VER    := 6.1.0

LMAX           := 5
MAX_CONTR      := 4

GPUVER         := P100
OFFLOAD_TARGET := cuda

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

CFLAGS         += $(DFLAGS)

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

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

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

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

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

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


===== TESTS (description) =====
 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-32 RI-RPA/RI-MP2 correlation energy
 input file: benchmarks/QS_mp2_rpa/32-H2O/RI-RPA.inp
 required files: ['benchmarks/QS_mp2_rpa/32-H2O/BASIS_H2O', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32.xyz', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32-PBE-TZ.inp', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32-RI-dRPA-TZ.inp']
 output file: result.log
 # nodes = 8
 # ranks/node = 2
 # threads/rank = 6
 nrepeat = 1
 time[min] = 15
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/01
 job id: 44334442
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/02
 job id: 44334443
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/03
 job id: 44334444
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/04
 job id: 44334446
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/05
 job id: 44334447
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/06
 job id: 44334448
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/07
 job id: 44334449
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/08
 job id: 44334450
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/09
 job id: 44334451
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/10
 job id: 44334452
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/11
 job id: 44334453
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/12
 job id: 44334454
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/13
 job id: 44334455
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/14
 job id: 44334456
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/15
 job id: 44334457
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/16
 job id: 44334458
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/17
 job id: 44334459
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/18
 job id: 44334460
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/19
 job id: 44334461
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/20
 job id: 44334462
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/21
 job id: 44334463
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/22
 job id: 44334467
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/23
 job id: 44334468
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/24
 job id: 44334469
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/25
 job id: 44334470
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/26
 job id: 44334471
 --- 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/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/01/result.log


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

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

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               15                 177869.
 MP_Allreduce          344                      9.
 MP_Sync                 3
 MP_comm_split           1
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.021    0.036  134.145  134.146
 farming_run                          1  2.0  133.685  133.686  134.113  134.116
 -------------------------------------------------------------------------------


 @@@@@@@@@@ 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               1.475863E+09
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                    2592
 MPI messages size (bytes):
  total size                         1.140326E+09
  min size                           0.000000E+00
  max size                           1.663488E+06
  average size                     439.940750E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                 132                        0
       128 < size <=     8192                 348                  2850816
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                1536                179306496
    131072 < size <=  4194304                 576                958169088
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         2308                     54.
 MP_Alltoall          4670                 822215.
 MP_ISend             2604                  90577.
 MP_IRecv             2604                  90574.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group               12
 MP_Bcast              228                1113141.
 MP_Allreduce          485                2282278.
 MP_Sync                27
 MP_Alltoall            38                9316958.
 MP_SendRecv           120                 384007.
 MP_ISendRecv           45                 235435.
 MP_Wait               191
 MP_comm_split           8
 MP_ISend              127                3867574.
 MP_IRecv              127                3866554.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.011    0.029  115.899  115.899
 qs_energies                          1  2.0    0.000    0.000  115.669  115.671
 mp2_main                             1  3.0    0.000    0.000  113.747  113.749
 mp2_gpw_main                         1  4.0    0.019    0.026  112.917  112.919
 mp2_ri_gpw_compute_in                1  5.0    0.172    0.177   93.854   94.337
 mp2_ri_gpw_compute_in_loop           1  6.0    0.004    0.005   55.441   55.923
 mp2_eri_3c_integrate_gpw           272  7.0    0.152    0.165   41.763   47.171
 get_2c_integrals                     1  6.0    0.001    0.008   37.545   38.240
 integrate_v_rspace                 273  8.0    0.434    0.449   25.068   30.188
 pw_transfer                       6555 10.6    0.381    0.402   27.418   28.316
 fft_wrap_pw1pw2                   5465 11.4    0.046    0.049   26.055   26.825
 grid_integrate_task_list           273  9.0   20.889   26.490   20.889   26.490
 fft_wrap_pw1pw2_100               2178 12.4    1.202    1.434   23.574   24.348
 compute_2c_integrals                 1  7.0    0.019    0.020   19.807   19.807
 compute_2c_integrals_loop_lm         1  8.0    0.003    0.004   18.912   19.506
 mp2_eri_2c_integrate_gpw             1  9.0    2.375    2.425   18.909   19.502
 rpa_ri_compute_en                    1  5.0    0.009    0.012   18.955   19.129
 cp_fm_cholesky_decompose            12  8.2   17.763   18.469   17.763   18.469
 cholesky_decomp                      1  7.0    0.000    0.000   16.584   17.284
 fft3d_s                           5443 13.4   16.128   16.665   16.151   16.687
 ao_to_mo_and_store_B_mult_1        272  7.0   10.844   15.549   10.844   15.549
 calculate_wavefunction             272  8.0    5.489    5.631   12.614   13.265
 rpa_num_int                          1  6.0    0.001    0.013   10.649   10.649
 rpa_num_int_RPA_matrix_operati       8  7.0    0.000    0.000   10.578   10.593
 calc_mat_Q                           8  8.0    0.000    0.000    9.355    9.447
 contract_S_to_Q                      8  9.0    0.000    0.000    8.775    8.866
 calc_potential_gpw                 544  9.5    0.005    0.005    8.276    8.696
 mp2_eri_2c_integrate_gpw_pot_l     272 10.0    0.001    0.002    8.244    8.626
 potential_pw2rs                    545 10.0    0.107    0.110    7.694    8.498
 parallel_gemm_fm                    14  9.1    0.000    0.000    8.349    8.457
 parallel_gemm_fm_cosma              14 10.1    8.349    8.457    8.349    8.457
 collocate_single_gaussian          272 10.0    0.039    0.041    7.473    7.790
 create_integ_mat                     1  6.0    0.022    0.027    7.718    7.718
 array2fm                             1  7.0    0.000    0.000    6.647    7.131
 pw_scatter_s                      2720 13.7    4.424    4.573    4.424    4.573
 pw_gather_s                       2722 13.2    3.886    4.220    3.886    4.220
 array2fm_buffer_send                 1  8.0    2.933    3.135    2.933    3.135
 pw_poisson_solve                   545 10.5    1.121    1.164    2.186    2.365
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="10", plot="h2o_32_ri_rpa_mp2", label="RI-RPA (8n/2r/6t)", y=112.919330, yerr=0.000000
PlotPoint: name="11", plot="h2o_32_ri_rpa_mp2_mem", label="RI-RPA (8n/2r/6t)", y=2747.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/02/result.log


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

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

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               22                 205321.
 MP_Allreduce          344                     10.
 MP_Sync                 4
 MP_comm_split           1
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.029    0.040  396.924  396.925
 farming_run                          1  2.0  396.020  396.024  396.881  396.888
 -------------------------------------------------------------------------------


 @@@@@@@@@@ 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         897827128576       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                          249788821       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               1.229562E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                   61440
 MPI messages size (bytes):
  total size                         6.073508E+09
  min size                           0.000000E+00
  max size                         642.960000E+03
  average size                      98.852664E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               32004                        0
       128 < size <=     8192                1820                 14909440
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072               18640               1081442304
    131072 < size <=  4194304                8976               4977156096
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         1003                     44.
 MP_Alltoall          1797                 713538.
 MP_ISend             3686                  54943.
 MP_IRecv             3622                  54292.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group               12
 MP_Bcast              703                 408373.
 MP_Allreduce         1821                  23730.
 MP_Sync                38
 MP_Alltoall            77                2371555.
 MP_SendRecv          2876                2171486.
 MP_ISendRecv         1034                 172620.
 MP_Wait              1346
 MP_comm_split           7
 MP_ISend              264                 362227.
 MP_IRecv              264                 362718.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.020    0.051  209.892  209.893
 qs_energies                          1  2.0    0.000    0.000  209.659  209.665
 scf_env_do_scf                       1  3.0    0.000    0.000  106.347  106.347
 qs_ks_update_qs_env                  5  5.0    0.000    0.000  105.437  105.445
 rebuild_ks_matrix                    4  6.0    0.000    0.000  105.436  105.444
 qs_ks_build_kohn_sham_matrix         4  7.0    0.055    0.064  105.436  105.444
 hfx_ks_matrix                        4  8.0    0.001    0.001  105.052  105.056
 integrate_four_center                4  9.0    0.144    0.453  105.052  105.055
 mp2_main                             1  3.0    0.000    0.000  102.995  103.001
 mp2_gpw_main                         1  4.0    0.034    0.061  102.098  102.107
 integrate_four_center_main           4 10.0    0.072    0.420   96.744   99.666
 integrate_four_center_bin          265 11.0   96.672   99.404   96.672   99.404
 init_scf_loop                        1  4.0    0.000    0.000   92.216   92.216
 mp2_ri_gpw_compute_in                1  5.0    0.065    0.079   74.826   75.866
 mp2_ri_gpw_compute_in_loop           1  6.0    0.002    0.002   54.454   55.493
 mp2_eri_3c_integrate_gpw            91  7.0    0.146    0.163   42.140   47.105
 integrate_v_rspace                  95  8.0    0.398    0.573   28.505   33.322
 pw_transfer                       2240 10.6    0.147    0.166   29.885   30.312
 fft_wrap_pw1pw2                   1868 11.4    0.018    0.021   28.911   29.362
 grid_integrate_task_list            95  9.0   23.800   28.825   23.800   28.825
 mp2_ri_gpw_compute_en                1  5.0    0.062    0.121   27.091   28.810
 ao_to_mo_and_store_B_mult_1         91  7.0   10.633   27.266   10.633   27.266
 fft_wrap_pw1pw2_100                730 12.4    1.264    1.477   26.620   27.025
 mp2_ri_gpw_compute_en_RI_loop        1  6.0    1.843    1.903   25.322   25.332
 get_2c_integrals                     1  6.0    0.002    0.013   20.247   20.308
 compute_2c_integrals                 1  7.0    0.003    0.004   19.215   19.225
 compute_2c_integrals_loop_lm         1  8.0    0.003    0.015   18.804   19.088
 mp2_eri_2c_integrate_gpw             1  9.0    1.743    1.940   18.801   19.088
 fft3d_s                           1823 13.4   18.391   18.821   18.404   18.834
 scf_env_do_scf_inner_loop            4  4.0    0.000    0.000   14.130   14.130
 calculate_wavefunction              91  8.0    2.031    2.070    9.749    9.995
 potential_pw2rs                    186 10.0    0.033    0.035    8.583    9.183
 mp2_ri_gpw_compute_en_expansio     172  7.0    0.554    0.600    8.760    9.115
 mp2_ri_gpw_compute_en_comm          22  7.0    0.491    0.506    8.333    8.585
 mp2_eri_2c_integrate_gpw_pot_l      91 10.0    0.001    0.001    8.209    8.576
 local_gemm                         172  8.0    8.206    8.568    8.206    8.568
 calc_potential_gpw                 182  9.5    0.002    0.002    7.928    8.211
 collocate_single_gaussian           91 10.0    0.017    0.026    7.846    8.077
 mp_sendrecv_dm3                   2068  8.0    6.389    6.641    6.389    6.641
 mp2_ri_gpw_compute_en_ener         172  7.0    6.340    6.420    6.340    6.420
 mp_sync                             38 10.4    3.005    5.817    3.005    5.817
 pw_gather_s                        912 13.2    4.900    5.365    4.900    5.365
 pw_scatter_s                       910 13.7    3.957    4.297    3.957    4.297
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="20", plot="h2o_32_ri_rpa_mp2", label="RI-MP2 (8n/6r/2t)", y=102.084944, yerr=0.000000
PlotPoint: name="21", plot="h2o_32_ri_rpa_mp2_mem", label="RI-MP2 (8n/6r/2t)", y=1517.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/03/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                     29.277748E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               5055360       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      29.1
 marketing flops                     2.107592E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             452.825088E+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                 586653.
 MP_SendRecv         22610                   5520.
 MP_ISendRecv        22610                   5520.
 MP_Wait             37876
 MP_comm_split          50
 MP_ISend            20771                  42672.
 MP_IRecv            20771                  42672.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.046    0.084   50.186   50.187
 qs_mol_dyn_low                       1  2.0    0.006    0.020   49.725   49.734
 qs_forces                           11  3.9    0.004    0.024   49.644   49.645
 qs_energies                         11  4.9    0.002    0.007   48.146   48.163
 scf_env_do_scf                      11  5.9    0.000    0.001   42.218   42.219
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.007   40.087   40.087
 dbcsr_multiply_generic            2286 12.5    0.091    0.098   31.373   31.744
 qs_scf_new_mos                     108  7.5    0.000    0.001   29.902   30.196
 qs_scf_loop_do_ot                  108  8.5    0.000    0.001   29.901   30.195
 ot_scf_mini                        108  9.5    0.002    0.003   28.256   28.434
 multiply_cannon                   2286 13.5    0.188    0.201   24.926   26.406
 multiply_cannon_loop              2286 14.5    1.509    1.599   24.229   25.706
 velocity_verlet                     10  3.0    0.001    0.002   24.570   24.574
 ot_mini                            108 10.5    0.001    0.001   17.545   17.801
 qs_ot_get_derivative               108 11.5    0.001    0.002   14.671   14.853
 mp_waitall_1                    245248 16.5    7.490   13.168    7.490   13.168
 multiply_cannon_metrocomm3       54864 15.5    0.068    0.075    5.377   11.822
 multiply_cannon_multrec          54864 15.5    4.282    6.696    7.508   10.929
 rebuild_ks_matrix                  119  8.3    0.000    0.000    8.015    8.152
 qs_ks_build_kohn_sham_matrix       119  9.3    0.010    0.012    8.014    8.152
 qs_ks_update_qs_env                119  7.6    0.001    0.001    7.078    7.204
 multiply_cannon_sync_h2d         54864 15.5    5.963    6.726    5.963    6.726
 qs_ot_get_p                        119 10.4    0.001    0.001    6.247    6.494
 mp_sum_l                          7207 12.9    4.551    6.010    4.551    6.010
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    4.860    5.284
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    4.897    5.004
 init_scf_run                        11  5.9    0.000    0.001    4.610    4.610
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    4.610    4.610
 sum_up_and_integrate               119 10.3    0.013    0.015    4.539    4.546
 integrate_v_rspace                 119 11.3    0.002    0.002    4.527    4.534
 dbcsr_mm_accdrv_process          76910 16.1    1.158    1.822    3.147    4.413
 qs_rho_update_rho_low              119  7.7    0.000    0.001    4.211    4.325
 calculate_rho_elec                 119  8.7    0.011    0.017    4.210    4.325
 qs_ot_p2m_diag                      50 11.0    0.004    0.006    3.616    3.651
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.859    3.053
 apply_single                       119 13.6    0.000    0.000    2.859    3.053
 calculate_dm_sparse                119  9.5    0.000    0.000    2.881    3.012
 cp_dbcsr_syevd                      50 12.0    0.002    0.003    2.841    2.842
 rs_pw_transfer                     974 11.9    0.011    0.012    2.759    2.840
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    2.644    2.645
 ot_diis_step                       108 11.5    0.006    0.006    2.644    2.644
 cp_fm_redistribute_end              50 14.0    2.408    2.624    2.413    2.625
 cp_fm_diag_elpa_base                50 14.0    0.210    2.532    0.211    2.542
 jit_kernel_multiply                 13 15.8    1.929    2.509    1.929    2.509
 calculate_first_density_matrix       1  7.0    0.004    0.011    2.474    2.478
 density_rs2pw                      119  9.7    0.004    0.004    2.235    2.334
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    2.279    2.333
 multiply_cannon_metrocomm1       54864 15.5    0.052    0.057    1.446    2.322
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.187    2.189
 acc_transpose_blocks             54864 15.5    0.231    0.251    1.721    2.152
 grid_integrate_task_list           119 12.3    2.034    2.128    2.034    2.128
 init_scf_loop                       11  6.9    0.000    0.003    2.109    2.109
 wfi_extrapolate                     11  7.9    0.001    0.001    2.078    2.078
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.927    1.987
 mp_sum_d                          4125 12.0    1.310    1.964    1.310    1.964
 pw_transfer                       1439 11.6    0.054    0.060    1.818    1.891
 potential_pw2rs                    119 12.3    0.004    0.004    1.876    1.887
 fft_wrap_pw1pw2                   1201 12.6    0.007    0.007    1.740    1.817
 make_m2s                          4572 13.5    0.053    0.055    1.610    1.660
 fft3d_ps                          1201 14.6    0.371    0.476    1.511    1.581
 make_images                       4572 14.5    0.132    0.138    1.528    1.576
 mp_waitany                       12084 13.8    1.284    1.457    1.284    1.457
 mp_alltoall_d11v                  2130 13.8    1.267    1.449    1.267    1.449
 fft_wrap_pw1pw2_140                487 13.2    0.082    0.096    1.348    1.427
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.001    1.400    1.420
 grid_collocate_task_list           119  9.7    1.295    1.362    1.295    1.362
 dbcsr_dot_sd                      1205 11.9    0.051    0.061    0.680    1.062
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.985    1.005
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="100", plot="h2o_64_md", label="(8n/12r/1t)", y=50.187000, yerr=0.000000
PlotPoint: name="101", plot="h2o_64_md_mem", label="(8n/12r/1t)", y=431.090909, yerr=1.239835
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/04/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                     57.173320E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               3066240       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      47.9
 marketing flops                     2.107592E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             487.915520E+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                1030452.
 MP_SendRecv         16779                  37093.
 MP_ISendRecv        16779                  37093.
 MP_Wait             23539
 MP_comm_split          50
 MP_ISend             5720                 128509.
 MP_IRecv             5720                 128509.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.042    0.111   39.351   39.352
 qs_mol_dyn_low                       1  2.0    0.003    0.004   38.948   38.955
 qs_forces                           11  3.9    0.004    0.006   38.677   38.679
 qs_energies                         11  4.9    0.003    0.007   36.984   36.988
 scf_env_do_scf                      11  5.9    0.001    0.001   31.597   31.598
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.008   29.134   29.134
 dbcsr_multiply_generic            2286 12.5    0.099    0.101   21.196   21.535
 qs_scf_new_mos                     108  7.5    0.001    0.001   19.887   20.139
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   19.887   20.139
 ot_scf_mini                        108  9.5    0.003    0.003   18.995   19.171
 velocity_verlet                     10  3.0    0.001    0.002   18.492   18.498
 multiply_cannon                   2286 13.5    0.211    0.219   16.251   17.908
 multiply_cannon_loop              2286 14.5    0.906    0.977   15.158   16.558
 ot_mini                            108 10.5    0.001    0.001   11.734   11.972
 mp_waitall_1                    200699 16.5    5.628   10.777    5.628   10.777
 multiply_cannon_metrocomm3       27432 15.5    0.068    0.070    4.141    9.548
 qs_ot_get_derivative               108 11.5    0.001    0.001    9.268    9.448
 multiply_cannon_multrec          27432 15.5    1.969    4.499    5.845    8.586
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.232    7.369
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.015    7.232    7.368
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.387    6.511
 dbcsr_mm_accdrv_process          47894 16.0    2.900    4.862    3.806    5.652
 qs_ot_get_p                        119 10.4    0.001    0.001    4.378    4.611
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    3.571    4.420
 sum_up_and_integrate               119 10.3    0.024    0.026    4.209    4.215
 integrate_v_rspace                 119 11.3    0.002    0.002    4.185    4.192
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    3.053    4.112
 apply_single                       119 13.6    0.000    0.000    3.053    4.111
 mp_sum_l                          7207 12.9    2.125    4.017    2.125    4.017
 init_scf_run                        11  5.9    0.000    0.001    4.015    4.016
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    4.015    4.016
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.835    3.871
 calculate_rho_elec                 119  8.7    0.021    0.024    3.834    3.871
 rs_pw_transfer                     974 11.9    0.010    0.011    2.709    3.187
 qs_ot_p2m_diag                      50 11.0    0.009    0.013    2.950    2.968
 multiply_cannon_sync_h2d         27432 15.5    2.201    2.840    2.201    2.840
 make_m2s                          4572 13.5    0.052    0.054    2.454    2.674
 density_rs2pw                      119  9.7    0.004    0.004    2.159    2.632
 make_images                       4572 14.5    0.199    0.235    2.366    2.584
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    2.517    2.518
 calculate_first_density_matrix       1  7.0    0.002    0.011    2.497    2.500
 init_scf_loop                       11  6.9    0.001    0.005    2.443    2.444
 ot_diis_step                       108 11.5    0.010    0.011    2.414    2.415
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    2.119    2.211
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    2.181    2.182
 cp_fm_redistribute_end              50 14.0    1.806    2.157    1.810    2.158
 calculate_dm_sparse                119  9.5    0.000    0.000    2.041    2.118
 cp_fm_diag_elpa_base                50 14.0    0.334    2.043    0.347    2.106
 pw_transfer                       1439 11.6    0.066    0.072    2.010    2.047
 grid_integrate_task_list           119 12.3    1.834    1.962    1.834    1.962
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.917    1.957
 potential_pw2rs                    119 12.3    0.006    0.006    1.937    1.948
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.920    1.922
 jit_kernel_multiply                 10 16.0    0.854    1.898    0.854    1.898
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.652    1.693
 fft3d_ps                          1201 14.6    0.513    0.564    1.617    1.657
 prepare_preconditioner              11  7.9    0.000    0.000    1.537    1.564
 make_preconditioner                 11  8.9    0.000    0.002    1.537    1.564
 make_images_data                  4572 15.5    0.045    0.051    1.133    1.561
 fft_wrap_pw1pw2_140                487 13.2    0.079    0.085    1.502    1.540
 acc_transpose_blocks             27432 15.5    0.108    0.113    1.186    1.495
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.437    1.493
 wfi_extrapolate                     11  7.9    0.001    0.001    1.463    1.463
 hybrid_alltoall_any               4725 16.4    0.051    0.111    0.987    1.440
 grid_collocate_task_list           119  9.7    1.229    1.353    1.229    1.353
 mp_alltoall_d11v                  2130 13.8    1.172    1.285    1.172    1.285
 mp_allgather_i34                  2286 14.5    0.533    1.272    0.533    1.272
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.254    1.261
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.161    1.205
 mp_waitany                        5720 13.7    0.641    1.156    0.641    1.156
 rs_pw_transfer_RS2PW_140           130 11.5    0.140    0.147    0.666    1.143
 qs_energies_init_hamiltonians       11  5.9    0.001    0.004    1.104    1.106
 mp_sum_d                          4125 12.0    0.597    1.033    0.597    1.033
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.905    0.919
 acc_transpose_blocks_kernels     27432 16.5    0.181    0.272    0.655    0.867
 mp_alltoall_z22v                  1201 16.6    0.709    0.813    0.709    0.813
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="102", plot="h2o_64_md", label="(8n/6r/2t)", y=39.352000, yerr=0.000000
PlotPoint: name="103", plot="h2o_64_md_mem", label="(8n/6r/2t)", y=465.272727, yerr=1.354515
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/05/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                     59.051995E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               3143552       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      46.8
 marketing flops                     2.107587E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             520.622080E+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                1607815.
 MP_SendRecv         11067                  57667.
 MP_ISendRecv        11067                  57667.
 MP_Wait             21987
 MP_comm_split          50
 MP_ISend             9880                  92618.
 MP_IRecv             9880                  92618.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.012    0.028   32.800   32.800
 qs_mol_dyn_low                       1  2.0    0.003    0.003   32.556   32.563
 qs_forces                           11  3.9    0.002    0.002   32.145   32.145
 qs_energies                         11  4.9    0.002    0.012   30.499   30.501
 scf_env_do_scf                      11  5.9    0.001    0.001   25.646   25.646
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   23.040   23.043
 dbcsr_multiply_generic            2286 12.5    0.091    0.095   16.348   16.437
 velocity_verlet                     10  3.0    0.001    0.002   15.706   15.719
 qs_scf_new_mos                     108  7.5    0.001    0.001   14.767   14.794
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   14.767   14.793
 ot_scf_mini                        108  9.5    0.002    0.003   14.051   14.069
 multiply_cannon                   2286 13.5    0.196    0.202   13.116   13.927
 multiply_cannon_loop              2286 14.5    0.639    0.666   12.330   13.147
 ot_mini                            108 10.5    0.001    0.001    8.673    8.688
 qs_ot_get_derivative               108 11.5    0.001    0.001    7.177    7.194
 multiply_cannon_multrec          18288 15.5    1.927    2.918    6.837    7.143
 rebuild_ks_matrix                  119  8.3    0.000    0.001    6.488    6.505
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    6.487    6.504
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.675    5.690
 dbcsr_mm_accdrv_process          38222 16.0    4.112    5.375    4.826    5.655
 sum_up_and_integrate               119 10.3    0.031    0.032    4.048    4.059
 integrate_v_rspace                 119 11.3    0.002    0.003    4.017    4.030
 init_scf_run                        11  5.9    0.000    0.001    3.630    3.630
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.630    3.630
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.508    3.515
 calculate_rho_elec                 119  8.7    0.030    0.031    3.508    3.515
 mp_waitall_1                    158411 16.6    2.588    3.390    2.588    3.390
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.699    3.334
 qs_ot_get_p                        119 10.4    0.001    0.001    3.218    3.253
 init_scf_loop                       11  6.9    0.000    0.001    2.588    2.594
 rs_pw_transfer                     974 11.9    0.009    0.010    2.315    2.565
 calculate_first_density_matrix       1  7.0    0.000    0.001    2.410    2.410
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.050    2.356
 apply_single                       119 13.6    0.000    0.000    2.050    2.356
 density_rs2pw                      119  9.7    0.004    0.004    2.032    2.278
 qs_ot_p2m_diag                      50 11.0    0.012    0.013    2.151    2.157
 multiply_cannon_metrocomm3       18288 15.5    0.044    0.045    1.399    2.062
 pw_transfer                       1439 11.6    0.066    0.073    2.018    2.033
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.923    1.942
 grid_integrate_task_list           119 12.3    1.808    1.909    1.808    1.909
 calculate_dm_sparse                119  9.5    0.000    0.000    1.885    1.895
 make_m2s                          4572 13.5    0.044    0.045    1.745    1.893
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.892    1.892
 potential_pw2rs                    119 12.3    0.007    0.008    1.817    1.830
 make_images                       4572 14.5    0.189    0.201    1.660    1.806
 prepare_preconditioner              11  7.9    0.000    0.000    1.776    1.778
 make_preconditioner                 11  8.9    0.000    0.001    1.776    1.778
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.627    1.712
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.670    1.671
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.665    1.666
 cp_fm_redistribute_end              50 14.0    1.242    1.646    1.243    1.646
 fft3d_ps                          1201 14.6    0.523    0.544    1.603    1.623
 multiply_cannon_sync_h2d         18288 15.5    1.408    1.617    1.408    1.617
 cp_fm_diag_elpa_base                50 14.0    0.387    1.566    0.401    1.610
 fft_wrap_pw1pw2_140                487 13.2    0.090    0.093    1.550    1.569
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.542    1.549
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.533    1.539
 ot_diis_step                       108 11.5    0.011    0.011    1.475    1.475
 mp_sum_l                          7207 12.9    1.107    1.436    1.107    1.436
 grid_collocate_task_list           119  9.7    1.214    1.359    1.214    1.359
 jit_kernel_multiply                  7 16.3    0.663    1.345    0.663    1.345
 acc_transpose_blocks             18288 15.5    0.075    0.077    1.248    1.282
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.262    1.267
 wfi_extrapolate                     11  7.9    0.001    0.001    1.173    1.173
 qs_energies_init_hamiltonians       11  5.9    0.000    0.001    0.950    0.950
 make_images_data                  4572 15.5    0.044    0.048    0.782    0.935
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.871    0.892
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.884    0.887
 hybrid_alltoall_any               4725 16.4    0.055    0.112    0.667    0.861
 acc_transpose_blocks_kernels     18288 16.5    0.209    0.221    0.808    0.831
 mp_waitany                        9880 13.7    0.527    0.794    0.527    0.794
 mp_alltoall_z22v                  1201 16.6    0.685    0.792    0.685    0.792
 rs_pw_transfer_RS2PW_140           130 11.5    0.119    0.123    0.509    0.765
 cp_fm_cholesky_invert               11 10.9    0.738    0.742    0.738    0.742
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.661    0.733
 mp_alltoall_d11v                  2130 13.8    0.642    0.730    0.642    0.730
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="104", plot="h2o_64_md", label="(8n/4r/3t)", y=32.800000, yerr=0.000000
PlotPoint: name="105", plot="h2o_64_md_mem", label="(8n/4r/3t)", y=496.090909, yerr=1.239835
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_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             559.366144E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1042416
 MPI messages size (bytes):
  total size                       150.443262E+09
  min size                           0.000000E+00
  max size                           1.188816E+06
  average size                     144.321719E+03
 MPI breakdown and total messages size (bytes):
             size <=      128              228256                        0
       128 < size <=     8192              126888               1039466496
      8192 < size <=    32768              191472               3137077248
     32768 < size <=   131072              295800              25899827200
    131072 < size <=  4194304              200000             120367247040
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3672                  62659.
 MP_Allreduce        10224                    344.
 MP_Sync               104
 MP_Alltoall          1582                2412273.
 MP_SendRecv          8211                  74133.
 MP_ISendRecv         8211                  74133.
 MP_Wait             16271
 MP_comm_split          50
 MP_ISend             7280                 135929.
 MP_IRecv             7280                 135929.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.046    0.097   35.286   35.286
 qs_mol_dyn_low                       1  2.0    0.003    0.004   34.931   34.938
 qs_forces                           11  3.9    0.003    0.013   34.868   34.870
 qs_energies                         11  4.9    0.006    0.017   33.121   33.127
 scf_env_do_scf                      11  5.9    0.003    0.023   27.803   27.804
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.010   24.369   24.370
 dbcsr_multiply_generic            2286 12.5    0.105    0.153   17.857   17.984
 velocity_verlet                     10  3.0    0.001    0.002   17.751   17.753
 qs_scf_new_mos                     108  7.5    0.001    0.001   15.831   15.883
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   15.830   15.883
 ot_scf_mini                        108  9.5    0.002    0.003   14.897   14.946
 multiply_cannon                   2286 13.5    0.227    0.262   14.255   14.676
 multiply_cannon_loop              2286 14.5    0.942    0.973   13.335   13.766
 ot_mini                            108 10.5    0.001    0.001    9.060    9.124
 multiply_cannon_multrec          27432 15.5    2.336    2.994    8.564    8.911
 dbcsr_mm_accdrv_process          47916 15.9    5.247    7.095    6.134    7.322
 qs_ot_get_derivative               108 11.5    0.001    0.001    7.259    7.311
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.623    6.675
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    6.623    6.675
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.883    5.928
 init_scf_run                        11  5.9    0.000    0.001    3.860    3.860
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.860    3.860
 sum_up_and_integrate               119 10.3    0.036    0.039    3.842    3.848
 integrate_v_rspace                 119 11.3    0.002    0.003    3.806    3.813
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.598    3.624
 calculate_rho_elec                 119  8.7    0.040    0.046    3.598    3.623
 init_scf_loop                       11  6.9    0.001    0.003    3.393    3.393
 qs_ot_get_p                        119 10.4    0.001    0.001    3.246    3.318
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.648    3.112
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.101    2.557
 apply_single                       119 13.6    0.000    0.000    2.101    2.557
 prepare_preconditioner              11  7.9    0.000    0.000    2.533    2.541
 make_preconditioner                 11  8.9    0.001    0.004    2.533    2.541
 calculate_first_density_matrix       1  7.0    0.001    0.005    2.482    2.483
 make_full_inverse_cholesky          11  9.9    0.000    0.000    2.144    2.472
 make_m2s                          4572 13.5    0.054    0.057    2.156    2.271
 mp_waitall_1                    137007 16.6    1.676    2.247    1.676    2.247
 rs_pw_transfer                     974 11.9    0.009    0.009    2.006    2.198
 density_rs2pw                      119  9.7    0.004    0.004    1.991    2.178
 pw_transfer                       1439 11.6    0.066    0.072    2.128    2.166
 make_images                       4572 14.5    0.270    0.331    2.049    2.164
 calculate_dm_sparse                119  9.5    0.000    0.000    2.021    2.079
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    2.034    2.077
 qs_ot_p2m_diag                      50 11.0    0.015    0.023    2.018    2.026
 grid_integrate_task_list           119 12.3    1.814    1.926    1.814    1.926
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.872    1.898
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.884    1.885
 jit_kernel_multiply                 10 15.9    0.827    1.813    0.827    1.813
 ot_diis_step                       108 11.5    0.012    0.012    1.761    1.762
 fft3d_ps                          1201 14.6    0.559    0.611    1.707    1.743
 fft_wrap_pw1pw2_140                487 13.2    0.088    0.095    1.677    1.724
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.001    0.004    1.694    1.713
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.708    1.709
 potential_pw2rs                    119 12.3    0.008    0.009    1.597    1.601
 mp_sum_l                          7207 12.9    1.041    1.562    1.041    1.562
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.479    1.480
 acc_transpose_blocks             27432 15.5    0.112    0.115    1.445    1.466
 cp_fm_redistribute_end              50 14.0    0.980    1.457    0.981    1.457
 cp_fm_diag_elpa_base                50 14.0    0.455    1.397    0.474    1.435
 grid_collocate_task_list           119  9.7    1.221    1.382    1.221    1.382
 wfi_extrapolate                     11  7.9    0.001    0.001    1.327    1.327
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.208    1.216
 multiply_cannon_metrocomm3       27432 15.5    0.038    0.039    0.703    1.209
 qs_energies_init_hamiltonians       11  5.9    0.008    0.013    1.145    1.156
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.091    1.111
 cp_fm_upper_to_full                 72 13.5    0.797    1.108    0.797    1.108
 multiply_cannon_sync_h2d         27432 15.5    0.996    1.096    0.996    1.096
 dbcsr_complete_redistribute        329 12.2    0.121    0.163    0.778    1.081
 mp_alltoall_d11v                  2130 13.8    0.752    0.943    0.752    0.943
 make_images_data                  4572 15.5    0.045    0.050    0.821    0.935
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.792    0.885
 copy_fm_to_dbcsr                   176 11.2    0.001    0.002    0.579    0.876
 hybrid_alltoall_any               4725 16.4    0.061    0.150    0.721    0.871
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.830    0.834
 acc_transpose_blocks_kernels     27432 16.5    0.268    0.276    0.819    0.828
 mp_alltoall_z22v                  1201 16.6    0.732    0.773    0.732    0.773
 mp_alltoall_i22                    627 13.8    0.455    0.750    0.455    0.750
 cp_fm_cholesky_invert               11 10.9    0.746    0.749    0.746    0.749
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="106", plot="h2o_64_md", label="(8n/3r/4t)", y=35.286000, yerr=0.000000
PlotPoint: name="107", plot="h2o_64_md_mem", label="(8n/3r/4t)", y=530.909091, yerr=2.906249
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_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             594.300928E+06
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  219456
 MPI messages size (bytes):
  total size                        97.042514E+09
  min size                           0.000000E+00
  max size                           3.276800E+06
  average size                     442.195750E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768              101892               3336634368
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304              116112              93705670464
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         8156                     20.
 MP_Alltoall          8655                  64935.
 MP_ISend            36532                 168375.
 MP_IRecv            36532                 168349.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3672                  62658.
 MP_Allreduce        10224                    344.
 MP_Sync               104
 MP_Alltoall          1582                3682667.
 MP_SendRecv          5355                  94533.
 MP_ISendRecv         5355                  94533.
 MP_Wait             11335
 MP_comm_split          50
 MP_ISend             5200                 225425.
 MP_IRecv             5200                 225425.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.013    0.028   28.786   28.787
 qs_mol_dyn_low                       1  2.0    0.003    0.003   28.553   28.560
 qs_forces                           11  3.9    0.002    0.002   28.002   28.003
 qs_energies                         11  4.9    0.001    0.001   26.300   26.302
 scf_env_do_scf                      11  5.9    0.000    0.001   21.276   21.277
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.007   18.786   18.787
 velocity_verlet                     10  3.0    0.002    0.002   14.773   14.806
 dbcsr_multiply_generic            2286 12.5    0.091    0.094   12.241   12.313
 qs_scf_new_mos                     108  7.5    0.001    0.001   10.763   10.791
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   10.762   10.790
 multiply_cannon                   2286 13.5    0.230    0.243    9.834   10.249
 ot_scf_mini                        108  9.5    0.002    0.002   10.093   10.121
 multiply_cannon_loop              2286 14.5    0.332    0.341    8.945    9.129
 multiply_cannon_multrec           9144 15.5    1.656    1.908    6.089    6.338
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.003    6.022
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    6.002    6.022
 ot_mini                            108 10.5    0.001    0.001    5.646    5.680
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.351    5.369
 dbcsr_mm_accdrv_process          12550 15.8    3.223    4.092    4.333    4.401
 qs_ot_get_derivative               108 11.5    0.001    0.001    4.362    4.391
 sum_up_and_integrate               119 10.3    0.038    0.042    3.668    3.675
 integrate_v_rspace                 119 11.3    0.003    0.003    3.630    3.638
 init_scf_run                        11  5.9    0.000    0.001    3.602    3.602
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.602    3.602
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.560    3.566
 calculate_rho_elec                 119  8.7    0.060    0.061    3.559    3.565
 qs_ot_get_p                        119 10.4    0.001    0.001    2.703    2.741
 init_scf_loop                       11  6.9    0.000    0.000    2.471    2.472
 calculate_first_density_matrix       1  7.0    0.001    0.001    2.469    2.469
 pw_transfer                       1439 11.6    0.067    0.070    2.154    2.164
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    2.060    2.072
 density_rs2pw                      119  9.7    0.004    0.004    1.880    2.015
 grid_integrate_task_list           119 12.3    1.840    1.951    1.840    1.951
 calculate_dm_sparse                119  9.5    0.000    0.000    1.823    1.841
 qs_ot_p2m_diag                      50 11.0    0.022    0.023    1.817    1.820
 mp_waitall_1                    115863 16.7    1.288    1.816    1.288    1.816
 make_m2s                          4572 13.5    0.034    0.036    1.664    1.814
 rs_pw_transfer                     974 11.9    0.008    0.008    1.642    1.759
 fft3d_ps                          1201 14.6    0.562    0.573    1.719    1.733
 fft_wrap_pw1pw2_140                487 13.2    0.087    0.090    1.716    1.727
 make_images                       4572 14.5    0.267    0.303    1.575    1.723
 prepare_preconditioner              11  7.9    0.000    0.000    1.715    1.719
 make_preconditioner                 11  8.9    0.000    0.000    1.715    1.719
 jit_kernel_multiply                  8 15.9    1.072    1.685    1.072    1.685
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.668    1.670
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.607    1.632
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.626    1.627
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    1.576    1.593
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.516    1.524
 potential_pw2rs                    119 12.3    0.010    0.011    1.406    1.409
 grid_collocate_task_list           119  9.7    1.272    1.389    1.272    1.389
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.346    1.347
 cp_fm_redistribute_end              50 14.0    0.672    1.328    0.673    1.328
 cp_fm_diag_elpa_base                50 14.0    0.611    1.261    0.654    1.316
 ot_diis_step                       108 11.5    0.012    0.013    1.272    1.272
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.244    1.249
 qs_energies_init_hamiltonians       11  5.9    0.000    0.001    1.215    1.216
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    1.150    1.168
 apply_single                       119 13.6    0.000    0.000    1.150    1.168
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.104    1.118
 wfi_extrapolate                     11  7.9    0.001    0.001    1.085    1.085
 acc_transpose_blocks              9144 15.5    0.038    0.039    0.999    1.004
 hybrid_alltoall_any               4725 16.4    0.062    0.175    0.772    0.966
 make_images_data                  4572 15.5    0.039    0.042    0.767    0.939
 mp_alltoall_d11v                  2130 13.8    0.767    0.931    0.767    0.931
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.864    0.911
 cp_fm_cholesky_invert               11 10.9    0.850    0.853    0.850    0.853
 multiply_cannon_sync_h2d          9144 15.5    0.712    0.793    0.712    0.793
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.775    0.777
 acc_transpose_blocks_kernels      9144 16.5    0.117    0.120    0.758    0.760
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    0.670    0.721
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.706    0.714
 multiply_cannon_metrocomm3        9144 15.5    0.019    0.019    0.308    0.666
 mp_alltoall_z22v                  1201 16.6    0.604    0.655    0.604    0.655
 jit_kernel_transpose                 5 15.6    0.640    0.642    0.640    0.642
 mp_allgather_i34                  2286 14.5    0.220    0.608    0.220    0.608
 yz_to_x                            606 15.1    0.266    0.276    0.580    0.595
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="108", plot="h2o_64_md", label="(8n/2r/6t)", y=28.787000, yerr=0.000000
PlotPoint: name="109", plot="h2o_64_md_mem", label="(8n/2r/6t)", y=563.363636, yerr=4.073701
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_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             766.615552E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                   91440
 MPI messages size (bytes):
  total size                        85.748679E+09
  min size                           0.000000E+00
  max size                           6.553600E+06
  average size                     937.758938E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                 572                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768               21148                692256768
     32768 < size <=   131072               19224               1259864064
    131072 < size <=  4194304               41040              21941452800
   4194304 < size <= 16777216                9456              61855174464
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3622                  63729.
 MP_Allreduce        10074                    433.
 MP_Sync                54
 MP_Alltoall          1582                7383731.
 MP_SendRecv          2499                 189067.
 MP_ISendRecv         2499                 189067.
 MP_Wait              6399
 MP_ISend             3120                 546875.
 MP_IRecv             3120                 546875.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.026    0.045   42.233   42.233
 qs_mol_dyn_low                       1  2.0    0.003    0.003   41.679   41.699
 qs_forces                           11  3.9    0.001    0.002   41.618   41.619
 qs_energies                         11  4.9    0.015    0.016   39.629   39.632
 scf_env_do_scf                      11  5.9    0.001    0.001   33.849   33.850
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.007   25.946   25.949
 velocity_verlet                     10  3.0    0.002    0.002   23.648   23.653
 dbcsr_multiply_generic            2286 12.5    0.099    0.100   17.429   17.607
 qs_scf_new_mos                     108  7.5    0.001    0.001   15.922   16.020
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   15.921   16.020
 ot_scf_mini                        108  9.5    0.002    0.002   14.845   14.945
 multiply_cannon                   2286 13.5    0.303    0.316   13.529   14.481
 multiply_cannon_loop              2286 14.5    0.345    0.353   12.262   13.205
 ot_mini                            108 10.5    0.001    0.001    8.801    8.916
 multiply_cannon_multrec           9144 15.5    3.409    4.818    8.499    8.581
 init_scf_loop                       11  6.9    0.000    0.000    7.877    7.883
 rebuild_ks_matrix                  119  8.3    0.000    0.001    7.461    7.606
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.013    7.460    7.606
 prepare_preconditioner              11  7.9    0.000    0.000    6.886    6.899
 make_preconditioner                 11  8.9    0.000    0.000    6.886    6.899
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.751    6.882
 qs_ot_get_derivative               108 11.5    0.001    0.001    6.744    6.841
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.484    6.777
 dbcsr_mm_accdrv_process          12550 15.8    3.805    5.558    4.967    6.322
 cp_fm_upper_to_full                 72 14.2    3.163    4.507    3.163    4.507
 qs_rho_update_rho_low              119  7.7    0.001    0.001    4.367    4.372
 calculate_rho_elec                 119  8.7    0.118    0.121    4.366    4.371
 sum_up_and_integrate               119 10.3    0.066    0.067    4.112    4.118
 integrate_v_rspace                 119 11.3    0.003    0.003    4.046    4.052
 init_scf_run                        11  5.9    0.000    0.001    3.698    3.698
 scf_env_initial_rho_setup           11  6.9    0.002    0.003    3.698    3.698
 qs_ot_get_p                        119 10.4    0.001    0.001    3.295    3.433
 mp_waitall_1                     94719 16.7    2.393    3.427    2.393    3.427
 pw_transfer                       1439 11.6    0.069    0.070    2.902    2.910
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.424    2.887
 fft_wrap_pw1pw2                   1201 12.6    0.009    0.009    2.802    2.810
 dbcsr_complete_redistribute        329 12.2    0.286    0.290    1.958    2.767
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.249    2.482
 apply_single                       119 13.6    0.000    0.000    2.249    2.482
 make_m2s                          4572 13.5    0.038    0.038    2.269    2.449
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    1.635    2.438
 fft3d_ps                          1201 14.6    0.596    0.603    2.426    2.435
 fft_wrap_pw1pw2_140                487 13.2    0.095    0.097    2.346    2.357
 make_images                       4572 14.5    0.350    0.382    2.148    2.328
 density_rs2pw                      119  9.7    0.004    0.004    2.284    2.304
 mp_alltoall_i22                    627 13.8    1.439    2.269    1.439    2.269
 multiply_cannon_metrocomm3        9144 15.5    0.020    0.020    1.316    2.237
 calculate_first_density_matrix       1  7.0    0.000    0.001    2.204    2.207
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.397    2.193
 calculate_dm_sparse                119  9.5    0.000    0.000    2.145    2.165
 grid_integrate_task_list           119 12.3    2.057    2.072    2.057    2.072
 ot_diis_step                       108 11.5    0.014    0.014    2.028    2.029
 qs_ot_p2m_diag                      50 11.0    0.042    0.043    2.010    2.011
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.948    1.948
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    1.800    1.801
 mp_sum_l                          7207 12.9    1.099    1.776    1.099    1.776
 jit_kernel_multiply                 10 15.6    1.135    1.755    1.135    1.755
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.738    1.739
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.683    1.734
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.625    1.649
 rs_pw_transfer                     974 11.9    0.009    0.010    1.524    1.553
 cp_fm_cholesky_invert               11 10.9    1.543    1.547    1.543    1.547
 potential_pw2rs                    119 12.3    0.014    0.015    1.511    1.514
 grid_collocate_task_list           119  9.7    1.490    1.498    1.490    1.498
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.434    1.434
 cp_fm_diag_elpa_base                50 14.0    1.291    1.340    1.432    1.432
 wfi_extrapolate                     11  7.9    0.001    0.001    1.422    1.422
 hybrid_alltoall_any               4725 16.4    0.087    0.148    1.112    1.367
 make_images_data                  4572 15.5    0.043    0.046    1.077    1.299
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.217    1.225
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.139    1.159
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    1.138    1.156
 mp_alltoall_d11v                  2130 13.8    1.083    1.107    1.083    1.107
 multiply_cannon_sync_h2d          9144 15.5    1.043    1.045    1.043    1.045
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.984    1.023
 yz_to_x                            606 15.1    0.460    0.472    0.980    0.994
 qs_create_task_list                 11  7.9    0.029    0.033    0.971    0.984
 generate_qs_task_list               11  8.9    0.371    0.390    0.943    0.952
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.923    0.937
 mp_alltoall_z22v                  1201 16.6    0.878    0.923    0.878    0.923
 acc_transpose_blocks              9144 15.5    0.037    0.038    0.909    0.923
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="110", plot="h2o_64_md", label="(8n/1r/12t)", y=42.233000, yerr=0.000000
PlotPoint: name="111", plot="h2o_64_md_mem", label="(8n/1r/12t)", y=712.272727, yerr=16.917398
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/09/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                    198.287135E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               8410880       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     117.0
 marketing flops                    15.646302E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank             503.132160E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 8483040
 MPI messages size (bytes):
  total size                         1.160510E+12
  min size                           0.000000E+00
  max size                           1.161504E+06
  average size                     136.803609E+03
 MPI breakdown and total messages size (bytes):
             size <=      128             1836752                        0
       128 < size <=     8192             1040592               8524529664
      8192 < size <=    32768             1486976              24362614784
     32768 < size <=   131072             2491776             216971345920
    131072 < size <=  4194304             1626944             910632720448
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3521                  65372.
 MP_Allreduce         9840                    486.
 MP_Sync               100
 MP_Alltoall          1938                1379060.
 MP_SendRecv         20900                   9096.
 MP_ISendRecv        20900                   9096.
 MP_Wait             37268
 MP_comm_split          48
 MP_ISend            14300                  82312.
 MP_IRecv            14300                  82312.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.012    0.028   83.243   83.244
 qs_mol_dyn_low                       1  2.0    0.003    0.004   82.998   83.008
 qs_forces                           11  3.9    0.002    0.002   82.927   82.928
 qs_energies                         11  4.9    0.001    0.002   80.052   80.067
 scf_env_do_scf                      11  5.9    0.000    0.001   71.281   71.283
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.006   65.560   65.560
 dbcsr_multiply_generic            2055 12.4    0.104    0.110   51.800   52.059
 qs_scf_new_mos                      99  7.5    0.000    0.001   47.945   48.078
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   47.944   48.077
 ot_scf_mini                         99  9.5    0.002    0.002   45.593   45.689
 multiply_cannon                   2055 13.4    0.181    0.187   42.343   43.286
 velocity_verlet                     10  3.0    0.006    0.011   42.412   42.413
 multiply_cannon_loop              2055 14.4    1.563    1.596   41.353   42.321
 ot_mini                             99 10.5    0.001    0.001   27.265   27.378
 qs_ot_get_derivative                99 11.5    0.001    0.002   20.476   20.579
 multiply_cannon_multrec          49320 15.4   12.135   12.857   17.140   17.790
 rebuild_ks_matrix                  110  8.3    0.000    0.001   14.758   14.898
 qs_ks_build_kohn_sham_matrix       110  9.3    0.014    0.024   14.758   14.897
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.947   13.076
 mp_waitall_1                    220248 16.4   11.367   12.558   11.367   12.558
 multiply_cannon_sync_h2d         49320 15.4    9.948   10.478    9.948   10.478
 qs_ot_get_p                        110 10.4    0.001    0.001    9.768    9.911
 multiply_cannon_metrocomm3       49320 15.4    0.080    0.084    6.828    8.282
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    7.190    7.671
 apply_single                       110 13.6    0.000    0.001    7.190    7.671
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    6.914    7.462
 sum_up_and_integrate               110 10.3    0.037    0.043    7.208    7.224
 integrate_v_rspace                 110 11.3    0.003    0.003    7.171    7.195
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.745    6.870
 calculate_rho_elec                 110  8.6    0.021    0.026    6.744    6.869
 init_scf_run                        11  5.9    0.000    0.001    6.753    6.753
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    6.753    6.753
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    6.612    6.674
 ot_diis_step                        99 11.5    0.006    0.006    6.536    6.536
 qs_ot_p2m_diag                      48 11.0    0.012    0.019    6.420    6.447
 mp_sum_l                          6514 12.8    5.098    5.913    5.098    5.913
 init_scf_loop                       11  6.9    0.000    0.000    5.694    5.694
 cp_dbcsr_syevd                      48 12.0    0.002    0.003    5.367    5.368
 dbcsr_mm_accdrv_process          87628 16.1    2.065    2.171    4.884    5.159
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    4.898    4.899
 cp_fm_redistribute_end              48 14.0    4.275    4.873    4.279    4.874
 cp_fm_diag_elpa_base                48 14.0    0.589    4.731    0.593    4.760
 rs_pw_transfer                     902 11.9    0.012    0.013    3.791    4.321
 density_rs2pw                      110  9.6    0.004    0.005    3.553    4.100
 wfi_extrapolate                     11  7.9    0.001    0.001    4.058    4.058
 make_m2s                          4110 13.4    0.060    0.066    3.904    4.020
 make_images                       4110 14.4    0.177    0.191    3.809    3.929
 calculate_dm_sparse                110  9.5    0.000    0.001    3.709    3.857
 multiply_cannon_metrocomm1       49320 15.4    0.060    0.063    2.632    3.827
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    3.537    3.540
 prepare_preconditioner              11  7.9    0.000    0.000    3.458    3.482
 make_preconditioner                 11  8.9    0.000    0.000    3.458    3.482
 grid_integrate_task_list           110 12.3    3.254    3.426    3.254    3.426
 pw_transfer                       1331 11.6    0.056    0.065    3.354    3.421
 qs_ot_get_orbitals                  99 10.5    0.000    0.001    3.329    3.390
 fft_wrap_pw1pw2                   1111 12.6    0.007    0.008    3.265    3.334
 make_full_inverse_cholesky          11  9.9    0.000    0.000    3.219    3.261
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    3.210    3.258
 fft3d_ps                          1111 14.6    0.782    0.886    2.794    2.845
 fft_wrap_pw1pw2_140                451 13.1    0.170    0.191    2.753    2.832
 potential_pw2rs                    110 12.3    0.006    0.007    2.719    2.742
 calculate_first_density_matrix       1  7.0    0.000    0.001    2.605    2.612
 jit_kernel_multiply                 13 15.9    2.535    2.549    2.535    2.549
 mp_waitany                       14300 13.8    1.854    2.514    1.854    2.514
 mp_alltoall_d11v                  2046 13.8    2.104    2.485    2.104    2.485
 grid_collocate_task_list           110  9.6    2.083    2.305    2.083    2.305
 acc_transpose_blocks             49320 15.4    0.225    0.233    2.170    2.228
 mp_sum_d                          3879 11.9    1.465    1.983    1.465    1.983
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.953    1.970
 make_images_data                  4110 15.4    0.042    0.045    1.789    1.945
 cp_fm_cholesky_invert               11 10.9    1.867    1.871    1.867    1.871
 hybrid_alltoall_any               4261 16.3    0.081    0.477    1.561    1.855
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="200", plot="h2o_128_md", label="(8n/12r/1t)", y=83.244000, yerr=0.000000
PlotPoint: name="201", plot="h2o_128_md_mem", label="(8n/12r/1t)", y=477.545455, yerr=2.061052
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_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             589.471744E+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                2274706.
 MP_SendRecv         10340                  26400.
 MP_ISendRecv        10340                  26400.
 MP_Wait             22352
 MP_comm_split          48
 MP_ISend            10164                 155761.
 MP_IRecv            10164                 155761.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.018    0.027   69.618   69.618
 qs_mol_dyn_low                       1  2.0    0.003    0.004   69.353   69.365
 qs_forces                           11  3.9    0.002    0.002   69.244   69.244
 qs_energies                         11  4.9    0.001    0.002   65.885   65.888
 scf_env_do_scf                      11  5.9    0.000    0.001   57.185   57.189
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.007   49.397   49.397
 dbcsr_multiply_generic            2055 12.4    0.113    0.118   37.688   37.904
 velocity_verlet                     10  3.0    0.002    0.002   36.795   36.797
 qs_scf_new_mos                      99  7.5    0.001    0.001   32.702   32.832
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   32.702   32.831
 multiply_cannon                   2055 13.4    0.223    0.242   30.940   32.254
 ot_scf_mini                         99  9.5    0.003    0.003   31.034   31.167
 multiply_cannon_loop              2055 14.4    0.931    0.952   29.631   30.430
 ot_mini                             99 10.5    0.001    0.001   18.239   18.380
 multiply_cannon_multrec          24660 15.4    7.637    9.332   13.818   15.603
 rebuild_ks_matrix                  110  8.3    0.000    0.001   14.026   14.152
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.015   14.026   14.151
 qs_ot_get_derivative                99 11.5    0.001    0.002   12.478   12.613
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.347   12.465
 mp_waitall_1                    176588 16.5    7.723    9.957    7.723    9.957
 multiply_cannon_sync_h2d         24660 15.4    6.966    7.908    6.966    7.908
 multiply_cannon_metrocomm3       24660 15.4    0.069    0.070    5.128    7.846
 init_scf_loop                       11  6.9    0.000    0.000    7.752    7.753
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    6.462    7.107
 apply_single                       110 13.6    0.000    0.001    6.462    7.107
 sum_up_and_integrate               110 10.3    0.052    0.059    6.824    6.835
 integrate_v_rspace                 110 11.3    0.002    0.003    6.772    6.785
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.364    6.376
 calculate_rho_elec                 110  8.6    0.040    0.047    6.363    6.375
 dbcsr_mm_accdrv_process          52282 16.1    4.696    5.541    6.021    6.324
 qs_ot_get_p                        110 10.4    0.001    0.001    6.165    6.319
 init_scf_run                        11  5.9    0.000    0.001    6.282    6.282
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    6.282    6.282
 prepare_preconditioner              11  7.9    0.000    0.000    5.700    5.718
 make_preconditioner                 11  8.9    0.000    0.000    5.700    5.718
 ot_diis_step                        99 11.5    0.010    0.010    5.711    5.711
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.289    5.441
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    4.663    5.351
 make_m2s                          4110 13.4    0.057    0.060    4.259    4.666
 make_images                       4110 14.4    0.395    0.438    4.150    4.555
 qs_ot_p2m_diag                      48 11.0    0.028    0.044    4.241    4.263
 pw_transfer                       1331 11.6    0.067    0.075    3.868    4.027
 density_rs2pw                      110  9.6    0.004    0.004    3.468    3.931
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.761    3.922
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.799    3.800
 rs_pw_transfer                     902 11.9    0.012    0.013    3.159    3.668
 wfi_extrapolate                     11  7.9    0.001    0.001    3.577    3.577
 fft_wrap_pw1pw2_140                451 13.1    0.202    0.218    3.180    3.346
 grid_integrate_task_list           110 12.3    3.160    3.341    3.160    3.341
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.222    3.298
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    3.270    3.272
 fft3d_ps                          1111 14.6    1.103    1.314    3.111    3.257
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.254    3.256
 cp_fm_redistribute_end              48 14.0    2.434    3.227    2.436    3.228
 cp_fm_diag_elpa_base                48 14.0    0.758    3.074    0.789    3.169
 calculate_dm_sparse                110  9.5    0.001    0.001    3.036    3.065
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.913    2.965
 make_images_data                  4110 15.4    0.047    0.051    2.387    2.819
 hybrid_alltoall_any               4261 16.3    0.102    0.455    2.062    2.803
 cp_fm_cholesky_invert               11 10.9    2.711    2.718    2.711    2.718
 potential_pw2rs                    110 12.3    0.008    0.008    2.596    2.623
 calculate_first_density_matrix       1  7.0    0.000    0.001    2.611    2.615
 grid_collocate_task_list           110  9.6    2.057    2.475    2.057    2.475
 mp_sum_l                          6514 12.8    1.863    2.465    1.863    2.465
 mp_alltoall_d11v                  2046 13.8    1.781    2.202    1.781    2.202
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.964    1.986
 qs_energies_init_hamiltonians       11  5.9    0.013    0.023    1.898    1.898
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.843    1.857
 mp_waitany                       10164 13.8    1.244    1.832    1.244    1.832
 multiply_cannon_metrocomm4       22605 15.4    0.072    0.078    0.816    1.792
 jit_kernel_multiply                  9 16.4    0.975    1.708    0.975    1.708
 mp_irecv_dv                      57340 16.2    0.693    1.677    0.693    1.677
 mp_allgather_i34                  2055 14.4    0.635    1.656    0.635    1.656
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.608    1.619
 acc_transpose_blocks             24660 15.4    0.109    0.111    1.535    1.573
 rs_pw_transfer_RS2PW_140           121 11.5    0.222    0.233    0.976    1.474
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.001    1.364    1.470
 mp_alltoall_z22v                  1111 16.6    1.329    1.436    1.329    1.436
 dbcsr_complete_redistribute        325 12.2    0.239    0.299    1.150    1.419
 cp_fm_cholesky_decompose            22 10.9    1.388    1.394    1.388    1.394
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="202", plot="h2o_128_md", label="(8n/6r/2t)", y=69.618000, yerr=0.000000
PlotPoint: name="203", plot="h2o_128_md_mem", label="(8n/6r/2t)", y=556.909091, yerr=7.549287
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/11/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                    404.681598E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               3346752       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     294.1
 marketing flops                    15.646297E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank             660.226048E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                  854880
 MPI messages size (bytes):
  total size                       708.322787E+09
  min size                           0.000000E+00
  max size                           6.553600E+06
  average size                     828.564000E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768              222984               7302414336
     32768 < size <=   131072              153888              10085203968
    131072 < size <=  4194304              389376             200257044480
   4194304 < size <= 16777216               82208             490679162176
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3521                  65578.
 MP_Allreduce         9838                    559.
 MP_Sync               100
 MP_Alltoall          1496                4511006.
 MP_SendRecv          6820                  27424.
 MP_ISendRecv         6820                  27424.
 MP_Wait             25498
 MP_comm_split          48
 MP_ISend            17072                 115022.
 MP_IRecv            17072                 115022.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.069    0.131   61.799   61.800
 qs_mol_dyn_low                       1  2.0    0.003    0.004   61.239   61.249
 qs_forces                           11  3.9    0.005    0.026   61.151   61.152
 qs_energies                         11  4.9    0.004    0.023   57.879   57.884
 scf_env_do_scf                      11  5.9    0.001    0.001   49.779   49.779
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.007   41.005   41.005
 velocity_verlet                     10  3.0    0.002    0.002   33.321   33.324
 dbcsr_multiply_generic            2055 12.4    0.108    0.116   28.850   29.187
 qs_scf_new_mos                      99  7.5    0.001    0.001   25.687   25.802
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   25.686   25.801
 ot_scf_mini                         99  9.5    0.002    0.003   24.439   24.572
 multiply_cannon                   2055 13.4    0.213    0.228   22.290   23.539
 multiply_cannon_loop              2055 14.4    0.620    0.636   21.005   21.923
 ot_mini                             99 10.5    0.001    0.001   13.868   14.005
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.620   12.781
 qs_ks_build_kohn_sham_matrix       110  9.3    0.014    0.022   12.620   12.781
 qs_ks_update_qs_env                110  7.6    0.001    0.001   11.123   11.266
 multiply_cannon_multrec          16440 15.4    3.874    4.924    9.629   10.608
 mp_waitall_1                    139946 16.5    7.247   10.463    7.247   10.463
 qs_ot_get_derivative                99 11.5    0.001    0.002    9.341    9.473
 init_scf_loop                       11  6.9    0.001    0.007    8.736    8.737
 multiply_cannon_metrocomm3       16440 15.4    0.043    0.045    4.487    7.449
 prepare_preconditioner              11  7.9    0.000    0.000    6.929    6.945
 make_preconditioner                 11  8.9    0.000    0.002    6.929    6.945
 sum_up_and_integrate               110 10.3    0.060    0.060    6.679    6.696
 integrate_v_rspace                 110 11.3    0.002    0.003    6.619    6.637
 make_full_inverse_cholesky          11  9.9    0.000    0.000    6.267    6.621
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.064    6.070
 calculate_rho_elec                 110  8.6    0.058    0.059    6.064    6.069
 dbcsr_mm_accdrv_process          34862 16.1    4.731    5.441    5.611    5.837
 qs_ot_get_p                        110 10.4    0.001    0.001    5.655    5.823
 init_scf_run                        11  5.9    0.000    0.001    5.575    5.576
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.575    5.575
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    5.034    5.442
 apply_single                       110 13.6    0.000    0.000    5.034    5.442
 make_m2s                          4110 13.4    0.050    0.053    4.286    4.714
 make_images                       4110 14.4    0.388    0.502    4.170    4.599
 ot_diis_step                        99 11.5    0.011    0.011    4.492    4.492
 density_rs2pw                      110  9.6    0.004    0.005    3.182    4.422
 multiply_cannon_sync_h2d         16440 15.4    3.687    4.379    3.687    4.379
 qs_ot_p2m_diag                      48 11.0    0.042    0.044    4.006    4.010
 rs_pw_transfer                     902 11.9    0.010    0.012    2.771    3.991
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.188    3.818
 pw_transfer                       1331 11.6    0.066    0.076    3.792    3.805
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.685    3.701
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.664    3.665
 grid_integrate_task_list           110 12.3    3.161    3.433    3.161    3.433
 fft_wrap_pw1pw2_140                451 13.1    0.213    0.217    3.158    3.176
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.118    3.119
 cp_fm_redistribute_end              48 14.0    1.947    3.091    1.951    3.093
 wfi_extrapolate                     11  7.9    0.001    0.001    3.048    3.048
 cp_fm_diag_elpa_base                48 14.0    1.078    2.933    1.137    3.041
 make_images_data                  4110 15.4    0.043    0.048    2.514    3.033
 fft3d_ps                          1111 14.6    1.116    1.134    2.983    2.998
 hybrid_alltoall_any               4261 16.3    0.105    0.377    2.176    2.938
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.002    2.806    2.807
 cp_fm_cholesky_invert               11 10.9    2.740    2.746    2.740    2.746
 calculate_dm_sparse                110  9.5    0.001    0.001    2.544    2.577
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.446    2.513
 mp_waitany                       17072 13.8    1.234    2.511    1.234    2.511
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.436    2.507
 multiply_cannon_metrocomm4       14385 15.4    0.044    0.049    0.886    2.500
 grid_collocate_task_list           110  9.6    2.073    2.480    2.073    2.480
 calculate_first_density_matrix       1  7.0    0.001    0.003    2.438    2.440
 mp_sum_l                          6514 12.8    1.668    2.402    1.668    2.402
 potential_pw2rs                    110 12.3    0.011    0.011    2.389    2.396
 mp_irecv_dv                      48980 15.7    0.816    2.375    0.816    2.375
 mp_alltoall_d11v                  2046 13.8    1.808    2.299    1.808    2.299
 rs_pw_transfer_RS2PW_140           121 11.5    0.179    0.188    0.915    2.141
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    2.022    2.023
 dbcsr_complete_redistribute        325 12.2    0.340    0.368    1.489    1.960
 jit_kernel_multiply                 10 16.4    0.493    1.913    0.493    1.913
 cp_fm_upper_to_full                 70 13.6    1.408    1.861    1.408    1.861
 mp_allgather_i34                  2055 14.4    0.606    1.761    0.606    1.761
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.703    1.724
 cp_fm_cholesky_decompose            22 10.9    1.680    1.703    1.680    1.703
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.001    1.362    1.497
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.478    1.490
 copy_fm_to_dbcsr                   174 11.2    0.001    0.002    1.018    1.481
 rs_gather_matrices                 110 12.3    0.232    0.258    0.995    1.417
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.309    1.316
 acc_transpose_blocks             16440 15.4    0.070    0.073    1.206    1.244
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="204", plot="h2o_128_md", label="(8n/4r/3t)", y=61.800000, yerr=0.000000
PlotPoint: name="205", plot="h2o_128_md_mem", label="(8n/4r/3t)", y=625.727273, yerr=8.539650
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_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             734.625792E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                  937080
 MPI messages size (bytes):
  total size                       523.723932E+09
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     558.889250E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6996                        0
       128 < size <=     8192                 264                  2162688
      8192 < size <=    32768              304932               8165326848
     32768 < size <=   131072              110640               6338641920
    131072 < size <=  4194304              489498             400769458320
   4194304 < size <= 16777216               24750             108449092400
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3521                  65576.
 MP_Allreduce         9838                    600.
 MP_Sync               100
 MP_Alltoall          1496                5863162.
 MP_SendRecv          5060                  43184.
 MP_ISendRecv         5060                  43184.
 MP_Wait             20042
 MP_comm_split          48
 MP_ISend            13376                 163145.
 MP_IRecv            13376                 163145.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.017    0.028   70.487   70.487
 qs_mol_dyn_low                       1  2.0    0.003    0.003   70.224   70.242
 qs_forces                           11  3.9    0.006    0.023   70.151   70.152
 qs_energies                         11  4.9    0.001    0.001   66.595   66.603
 scf_env_do_scf                      11  5.9    0.000    0.001   57.968   57.971
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.006   45.015   45.015
 velocity_verlet                     10  3.0    0.001    0.002   39.932   39.934
 dbcsr_multiply_generic            2055 12.4    0.115    0.117   30.783   31.066
 qs_scf_new_mos                      99  7.5    0.001    0.001   28.695   28.814
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   28.695   28.813
 ot_scf_mini                         99  9.5    0.003    0.003   27.029   27.156
 multiply_cannon                   2055 13.4    0.241    0.272   22.875   24.240
 multiply_cannon_loop              2055 14.4    0.889    0.908   21.349   22.075
 ot_mini                             99 10.5    0.001    0.001   15.116   15.274
 multiply_cannon_multrec          24660 15.4    4.182    6.662   12.619   13.876
 rebuild_ks_matrix                  110  8.3    0.000    0.000   13.044   13.171
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.013   13.044   13.171
 init_scf_loop                       11  6.9    0.000    0.000   12.894   12.894
 qs_ks_update_qs_env                110  7.6    0.001    0.001   11.510   11.618
 prepare_preconditioner              11  7.9    0.000    0.000   11.018   11.039
 make_preconditioner                 11  8.9    0.000    0.000   11.018   11.039
 qs_ot_get_derivative                99 11.5    0.001    0.001   10.864   10.989
 make_full_inverse_cholesky          11  9.9    0.000    0.000    9.168   10.659
 dbcsr_mm_accdrv_process          52304 16.0    6.869    8.040    8.291    9.293
 mp_waitall_1                    121746 16.5    5.259    7.414    5.259    7.414
 sum_up_and_integrate               110 10.3    0.068    0.070    7.106    7.122
 integrate_v_rspace                 110 11.3    0.003    0.003    7.038    7.056
 qs_ot_get_p                        110 10.4    0.001    0.001    6.718    6.887
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.783    6.796
 calculate_rho_elec                 110  8.6    0.077    0.081    6.783    6.796
 make_m2s                          4110 13.4    0.060    0.061    6.012    6.240
 make_images                       4110 14.4    0.571    0.693    5.872    6.094
 init_scf_run                        11  5.9    0.000    0.001    5.777    5.778
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.777    5.777
 cp_fm_upper_to_full                 70 13.8    3.329    4.736    3.329    4.736
 qs_ot_p2m_diag                      48 11.0    0.055    0.064    4.646    4.661
 pw_transfer                       1331 11.6    0.066    0.075    4.345    4.376
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    4.238    4.273
 ot_diis_step                        99 11.5    0.011    0.011    4.188    4.189
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.067    4.147
 apply_single                       110 13.6    0.000    0.000    4.067    4.147
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    4.114    4.116
 density_rs2pw                      110  9.6    0.004    0.004    3.597    4.113
 dbcsr_complete_redistribute        325 12.2    0.414    0.467    2.921    4.063
 multiply_cannon_metrocomm3       24660 15.4    0.036    0.036    1.654    3.734
 fft_wrap_pw1pw2_140                451 13.1    0.202    0.212    3.563    3.602
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.490    3.559
 fft3d_ps                          1111 14.6    1.092    1.128    3.531    3.557
 multiply_cannon_sync_h2d         24660 15.4    3.185    3.476    3.185    3.476
 rs_pw_transfer                     902 11.9    0.010    0.011    2.943    3.453
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.445    3.448
 cp_fm_cholesky_invert               11 10.9    3.424    3.435    3.424    3.435
 grid_integrate_task_list           110 12.3    3.257    3.422    3.257    3.422
 make_images_data                  4110 15.4    0.046    0.050    3.122    3.415
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    2.280    3.411
 cp_fm_redistribute_end              48 14.0    1.716    3.397    1.718    3.398
 cp_fm_diag_elpa_base                48 14.0    1.593    3.246    1.674    3.356
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.260    3.323
 hybrid_alltoall_any               4261 16.3    0.119    0.457    2.574    3.320
 wfi_extrapolate                     11  7.9    0.001    0.001    3.195    3.195
 calculate_dm_sparse                110  9.5    0.001    0.001    3.000    3.034
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.841    2.957
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.927    2.929
 mp_alltoall_i22                    605 13.7    1.704    2.888    1.704    2.888
 mp_alltoall_d11v                  2046 13.8    2.193    2.646    2.193    2.646
 potential_pw2rs                    110 12.3    0.012    0.013    2.624    2.638
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.497    2.537
 calculate_first_density_matrix       1  7.0    0.000    0.001    2.478    2.479
 grid_collocate_task_list           110  9.6    2.184    2.432    2.184    2.432
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    2.278    2.283
 jit_kernel_multiply                 12 15.7    1.094    2.229    1.094    2.229
 cp_fm_cholesky_decompose            22 10.9    1.945    1.997    1.945    1.997
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.809    1.836
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.781    1.799
 mp_allgather_i34                  2055 14.4    0.627    1.778    0.627    1.778
 mp_sum_l                          6514 12.8    1.209    1.726    1.209    1.726
 mp_waitany                       13376 13.8    1.195    1.701    1.195    1.701
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.594    1.696
 mp_alltoall_z22v                  1111 16.6    1.579    1.683    1.579    1.683
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.589    1.607
 acc_transpose_blocks             24660 15.4    0.105    0.107    1.533    1.560
 multiply_cannon_metrocomm4       20550 15.4    0.057    0.061    0.842    1.559
 rs_gather_matrices                 110 12.3    0.265    0.293    1.069    1.503
 mp_irecv_dv                      62702 16.1    0.744    1.480    0.744    1.480
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="206", plot="h2o_128_md", label="(8n/3r/4t)", y=70.487000, yerr=0.000000
PlotPoint: name="207", plot="h2o_128_md_mem", label="(8n/3r/4t)", y=695.818182, yerr=10.538399
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_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             832.282624E+06
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  197280
 MPI messages size (bytes):
  total size                       339.125567E+09
  min size                           0.000000E+00
  max size                          13.107200E+06
  average size                       1.719006E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 132                  4325376
     32768 < size <=   131072               88656              11620319232
    131072 < size <=  4194304               89424             117209825280
   4194304 < size <= 16777216               17616             210291069504
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         7346                     33.
 MP_Alltoall          8043                 263767.
 MP_ISend            32836                 654203.
 MP_IRecv            32836                 654587.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3521                  65574.
 MP_Allreduce         9838                    640.
 MP_Sync               100
 MP_Alltoall          1496                8504061.
 MP_SendRecv          3300                  54848.
 MP_ISendRecv         3300                  54848.
 MP_Wait             13926
 MP_comm_split          48
 MP_ISend             9240                 278857.
 MP_IRecv             9240                 278857.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.027    0.053   59.076   59.077
 qs_mol_dyn_low                       1  2.0    0.003    0.003   58.767   58.776
 qs_forces                           11  3.9    0.002    0.002   58.696   58.697
 qs_energies                         11  4.9    0.001    0.001   54.947   54.953
 scf_env_do_scf                      11  5.9    0.000    0.001   46.380   46.380
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.006   37.860   37.861
 velocity_verlet                     10  3.0    0.011    0.013   33.031   33.034
 dbcsr_multiply_generic            2055 12.4    0.105    0.106   23.529   23.655
 qs_scf_new_mos                      99  7.5    0.001    0.001   21.768   21.808
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   21.767   21.808
 ot_scf_mini                         99  9.5    0.002    0.002   20.490   20.516
 multiply_cannon                   2055 13.4    0.247    0.259   17.646   19.141
 multiply_cannon_loop              2055 14.4    0.323    0.337   16.272   16.616
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.625   12.649
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.013   12.625   12.648
 qs_ks_update_qs_env                110  7.6    0.001    0.001   11.229   11.254
 ot_mini                             99 10.5    0.001    0.001   10.855   10.873
 multiply_cannon_multrec           8220 15.4    3.268    4.602    7.581    8.534
 init_scf_loop                       11  6.9    0.000    0.000    8.469    8.470
 mp_waitall_1                    103326 16.6    6.513    8.180    6.513    8.180
 qs_ot_get_derivative                99 11.5    0.001    0.001    7.103    7.127
 sum_up_and_integrate               110 10.3    0.079    0.082    6.986    7.002
 integrate_v_rspace                 110 11.3    0.003    0.003    6.907    6.921
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.869    6.887
 calculate_rho_elec                 110  8.6    0.115    0.116    6.868    6.886
 prepare_preconditioner              11  7.9    0.000    0.000    6.651    6.655
 make_preconditioner                 11  8.9    0.000    0.000    6.651    6.655
 make_full_inverse_cholesky          11  9.9    0.000    0.000    6.213    6.301
 qs_ot_get_p                        110 10.4    0.001    0.001    5.628    5.652
 init_scf_run                        11  5.9    0.000    0.001    5.362    5.362
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.361    5.362
 dbcsr_mm_accdrv_process          17442 15.9    2.888    3.921    4.182    5.175
 make_m2s                          4110 13.4    0.039    0.040    4.530    4.801
 make_images                       4110 14.4    0.632    0.686    4.401    4.671
 pw_transfer                       1331 11.6    0.067    0.074    4.637    4.655
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.009    4.529    4.551
 multiply_cannon_metrocomm3        8220 15.4    0.017    0.018    2.875    4.255
 qs_ot_p2m_diag                      48 11.0    0.081    0.084    4.123    4.128
 fft_wrap_pw1pw2_140                451 13.1    0.213    0.217    3.842    3.875
 density_rs2pw                      110  9.6    0.004    0.004    3.494    3.864
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.803    3.804
 fft3d_ps                          1111 14.6    1.163    1.210    3.774    3.786
 ot_diis_step                        99 11.5    0.012    0.012    3.725    3.726
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    3.639    3.667
 apply_single                       110 13.6    0.000    0.000    3.639    3.667
 grid_integrate_task_list           110 12.3    3.357    3.521    3.357    3.521
 cp_fm_cholesky_invert               11 10.9    3.234    3.238    3.234    3.238
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.235    3.236
 cp_fm_redistribute_end              48 14.0    0.825    3.194    0.833    3.196
 cp_fm_diag_elpa_base                48 14.0    2.164    2.982    2.348    3.141
 make_images_data                  4110 15.4    0.038    0.043    2.597    3.070
 multiply_cannon_sync_h2d          8220 15.4    2.914    3.034    2.914    3.034
 hybrid_alltoall_any               4261 16.3    0.199    0.858    2.493    2.987
 wfi_extrapolate                     11  7.9    0.001    0.001    2.922    2.924
 rs_pw_transfer                     902 11.9    0.010    0.010    2.459    2.851
 qs_energies_init_hamiltonians       11  5.9    0.000    0.001    2.722    2.722
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.594    2.596
 calculate_dm_sparse                110  9.5    0.001    0.001    2.554    2.591
 grid_collocate_task_list           110  9.6    2.279    2.537    2.279    2.537
 potential_pw2rs                    110 12.3    0.015    0.015    2.402    2.410
 calculate_first_density_matrix       1  7.0    0.001    0.001    2.326    2.327
 mp_alltoall_d11v                  2046 13.8    2.000    2.232    2.000    2.232
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.166    2.177
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    2.123    2.136
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    1.973    1.985
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.765    1.970
 cp_fm_cholesky_decompose            22 10.9    1.925    1.940    1.925    1.940
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.735    1.738
 mp_allgather_i34                  2055 14.4    0.556    1.715    0.556    1.715
 dbcsr_complete_redistribute        325 12.2    0.571    0.601    1.602    1.695
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    1.558    1.685
 multiply_cannon_metrocomm1        8220 15.4    0.021    0.022    1.097    1.555
 mp_waitany                        9240 13.8    1.115    1.540    1.115    1.540
 mp_alltoall_z22v                  1111 16.6    1.498    1.526    1.498    1.526
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.479    1.491
 jit_kernel_multiply                  8 15.8    0.988    1.465    0.988    1.465
 qs_create_task_list                 11  7.9    0.002    0.003    1.240    1.349
 generate_qs_task_list               11  8.9    0.379    0.448    1.238    1.348
 yz_to_x                            561 15.1    0.526    0.539    1.298    1.309
 x_to_yz                            550 16.1    0.573    0.583    1.299    1.309
 rs_gather_matrices                 110 12.3    0.324    0.365    1.051    1.280
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.231    1.261
 rs_pw_transfer_RS2PW_140           121 11.5    0.161    0.165    0.820    1.217
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="208", plot="h2o_128_md", label="(8n/2r/6t)", y=59.077000, yerr=0.000000
PlotPoint: name="209", plot="h2o_128_md_mem", label="(8n/2r/6t)", y=786.272727, yerr=12.322123
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_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               1.374552E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                   82200
 MPI messages size (bytes):
  total size                       297.640985E+09
  min size                           0.000000E+00
  max size                          26.214400E+06
  average size                       3.620936E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                 572                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                  44                  1441792
     32768 < size <=   131072               18560               2432696320
    131072 < size <=  4194304               54216              84915781632
   4194304 < size <= 16777216                   0                        0
  16777216 < size                            8808             210291069504
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3462                  67104.
 MP_Allreduce         9672                    819.
 MP_Sync                52
 MP_Alltoall          1474               16505187.
 MP_SendRecv          2310                 360267.
 MP_ISendRecv         2310                 360267.
 MP_Wait              5214
 MP_ISend             2420                1187840.
 MP_IRecv             2420                1187840.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.308    0.316   89.932   89.932
 qs_mol_dyn_low                       1  2.0    0.003    0.004   89.134   89.142
 qs_forces                           11  3.9    0.043    0.050   89.035   89.036
 qs_energies                         11  4.9    0.002    0.002   84.811   84.825
 scf_env_do_scf                      11  5.9    0.001    0.001   74.389   74.390
 velocity_verlet                     10  3.0    0.002    0.002   56.917   56.927
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.006   45.479   45.481
 dbcsr_multiply_generic            2055 12.4    0.118    0.120   29.005   29.040
 init_scf_loop                       11  6.9    0.000    0.000   28.839   28.842
 prepare_preconditioner              11  7.9    0.000    0.000   26.744   26.749
 make_preconditioner                 11  8.9    0.000    0.000   26.744   26.749
 qs_scf_new_mos                      99  7.5    0.001    0.001   26.642   26.701
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   26.641   26.701
 make_full_inverse_cholesky          11  9.9    0.000    0.000   20.914   26.225
 ot_scf_mini                         99  9.5    0.002    0.002   24.879   24.918
 multiply_cannon                   2055 13.4    0.345    0.384   21.909   22.788
 multiply_cannon_loop              2055 14.4    0.342    0.346   20.079   20.577
 cp_fm_upper_to_full                 70 14.2   12.792   18.353   12.792   18.353
 rebuild_ks_matrix                  110  8.3    0.001    0.001   14.538   14.552
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.014   14.537   14.552
 ot_mini                             99 10.5    0.001    0.001   13.641   13.671
 qs_ks_update_qs_env                110  7.6    0.001    0.001   13.190   13.204
 dbcsr_complete_redistribute        325 12.2    1.016    1.045    7.418   10.735
 multiply_cannon_multrec           8220 15.4    4.368    4.558    9.846    9.962
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    6.381    9.703
 qs_ot_get_derivative                99 11.5    0.001    0.001    9.092    9.129
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    5.814    9.112
 mp_alltoall_i22                    605 13.7    5.448    8.764    5.448    8.764
 mp_waitall_1                     84994 16.7    7.717    8.580    7.717    8.580
 qs_rho_update_rho_low              110  7.6    0.001    0.001    7.953    7.989
 calculate_rho_elec                 110  8.6    0.227    0.227    7.952    7.989
 sum_up_and_integrate               110 10.3    0.151    0.153    7.629    7.645
 integrate_v_rspace                 110 11.3    0.003    0.004    7.478    7.494
 init_scf_run                        11  5.9    0.000    0.001    6.106    6.106
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    6.105    6.106
 qs_ot_get_p                        110 10.4    0.001    0.001    6.015    6.035
 make_m2s                          4110 13.4    0.043    0.043    5.310    5.770
 dbcsr_mm_accdrv_process          11614 15.7    3.199    3.619    5.335    5.607
 make_images                       4110 14.4    0.875    0.927    5.123    5.583
 pw_transfer                       1331 11.6    0.076    0.076    5.518    5.524
 cp_fm_cholesky_invert               11 10.9    5.447    5.451    5.447    5.451
 fft_wrap_pw1pw2                   1111 12.6    0.009    0.009    5.401    5.407
 multiply_cannon_metrocomm3        8220 15.4    0.018    0.019    4.787    5.301
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.654    5.100
 apply_single                       110 13.6    0.000    0.000    4.654    5.100
 fft_wrap_pw1pw2_140                451 13.1    0.221    0.226    4.676    4.681
 fft3d_ps                          1111 14.6    1.296    1.305    4.595    4.604
 ot_diis_step                        99 11.5    0.015    0.015    4.531    4.531
 qs_ot_p2m_diag                      48 11.0    0.151    0.155    4.322    4.329
 density_rs2pw                      110  9.6    0.004    0.004    3.955    4.001
 multiply_cannon_sync_h2d          8220 15.4    3.951    3.958    3.951    3.958
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.880    3.881
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    3.716    3.729
 grid_integrate_task_list           110 12.3    3.664    3.721    3.664    3.721
 hybrid_alltoall_any               4261 16.3    0.257    0.559    2.910    3.630
 make_images_data                  4110 15.4    0.042    0.045    2.904    3.493
 wfi_extrapolate                     11  7.9    0.001    0.001    3.343    3.343
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    2.903    3.343
 calculate_dm_sparse                110  9.5    0.001    0.001    3.268    3.285
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.262    3.262
 cp_fm_diag_elpa_base                48 14.0    2.718    2.914    3.259    3.259
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    3.085    3.093
 potential_pw2rs                    110 12.3    0.021    0.021    2.713    2.718
 grid_collocate_task_list           110  9.6    2.634    2.684    2.634    2.684
 calculate_first_density_matrix       1  7.0    0.002    0.003    2.640    2.641
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.600    2.605
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.475    2.496
 rs_pw_transfer                     902 11.9    0.011    0.011    2.463    2.494
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    2.240    2.281
 cp_fm_cholesky_decompose            22 10.9    2.150    2.172    2.150    2.172
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    2.085    2.149
 mp_alltoall_d11v                  2046 13.8    2.039    2.097    2.039    2.097
 jit_kernel_multiply                 10 15.4    1.937    2.067    1.937    2.067
 qs_create_task_list                 11  7.9    0.011    0.022    1.918    1.965
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.956    1.958
 generate_qs_task_list               11  8.9    0.735    0.790    1.906    1.944
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.799    1.823
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.802    1.816
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="210", plot="h2o_128_md", label="(8n/1r/12t)", y=89.932000, yerr=0.000000
PlotPoint: name="211", plot="h2o_128_md_mem", label="(8n/1r/12t)", y=1218.818182, yerr=62.198828
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/15/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1410022950912       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1924145348608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1957871443968       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1963542011904       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2714615709696       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4377645416448       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5350455508992       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5395653328896       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6594687401984       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11444706349056       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15019182452736       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15019182452736       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19624853225472       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        92.796564E+12       0.0%      0.0%    100.0%
 flops max/rank                      1.086554E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6705499488       0.0%      0.0%    100.0%
 number of processed stacks              11851392       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     565.8
 marketing flops                   143.508480E+12
 -------------------------------------------------------------------------------
 # multiplications                           2485
 max memory usage/rank             628.781056E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                10258080
 MPI messages size (bytes):
  total size                         4.456716E+12
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     434.459125E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               65736                        0
       128 < size <=     8192                1232                 10092544
      8192 < size <=    32768             3542056              94711185408
     32768 < size <=   131072             1282176              73356279808
    131072 < size <=  4194304             5107038            3151762090568
   4194304 < size <= 16777216              259842            1136842803272
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4085                  56756.
 MP_Allreduce        11253                    786.
 MP_Sync               168
 MP_Alltoall          2210                2520174.
 MP_SendRecv         24130                  18752.
 MP_ISendRecv        24130                  18752.
 MP_Wait             42150
 MP_comm_split          82
 MP_ISend            15900                 108037.
 MP_IRecv            15900                 108037.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.028    0.079  205.257  205.259
 qs_mol_dyn_low                       1  2.0    0.003    0.003  204.698  204.714
 qs_forces                           11  3.9    0.003    0.003  204.460  204.461
 qs_energies                         11  4.9    0.005    0.010  198.813  198.825
 scf_env_do_scf                      11  5.9    0.001    0.001  182.042  182.046
 scf_env_do_scf_inner_loop          116  6.6    0.002    0.008  160.981  160.983
 dbcsr_multiply_generic            2485 12.5    0.174    0.179  123.489  124.165
 velocity_verlet                     10  3.0    0.001    0.002  122.975  122.978
 qs_scf_new_mos                     116  7.6    0.001    0.001  120.241  120.460
 qs_scf_loop_do_ot                  116  8.6    0.001    0.001  120.240  120.459
 ot_scf_mini                        116  9.6    0.003    0.003  113.668  113.817
 multiply_cannon                   2485 13.5    0.233    0.240  100.045  102.563
 multiply_cannon_loop              2485 14.5    2.120    2.189   97.817  100.240
 ot_mini                            116 10.6    0.001    0.001   65.137   65.324
 multiply_cannon_multrec          59640 15.5   32.855   34.616   41.135   43.118
 qs_ot_get_derivative               116 11.6    0.001    0.001   40.516   40.665
 rebuild_ks_matrix                  127  8.3    0.001    0.001   34.089   34.323
 qs_ks_build_kohn_sham_matrix       127  9.3    0.016    0.021   34.089   34.322
 mp_waitall_1                    264810 16.5   28.403   31.975   28.403   31.975
 qs_ks_update_qs_env                127  7.6    0.001    0.001   30.605   30.815
 multiply_cannon_sync_h2d         59640 15.5   27.022   28.747   27.022   28.747
 qs_ot_get_p                        127 10.4    0.001    0.001   26.684   26.970
 apply_preconditioner_dbcsr         127 12.6    0.000    0.001   24.079   24.824
 apply_single                       127 13.6    0.001    0.001   24.079   24.824
 ot_diis_step                       116 11.6    0.007    0.008   24.206   24.208
 init_scf_loop                       11  6.9    0.000    0.001   20.980   20.981
 qs_ot_p2m_diag                      82 11.4    0.076    0.090   19.841   19.953
 qs_ot_get_derivative_diag           76 12.4    0.002    0.002   18.699   18.794
 multiply_cannon_metrocomm3       59640 15.5    0.116    0.120   15.538   18.561
 cp_dbcsr_syevd                      82 12.4    0.004    0.005   17.155   17.157
 prepare_preconditioner              11  7.9    0.000    0.000   16.307   16.343
 make_preconditioner                 11  8.9    0.000    0.000   16.307   16.343
 make_full_inverse_cholesky          11  9.9    0.000    0.000   15.520   15.734
 sum_up_and_integrate               127 10.3    0.090    0.107   14.576   14.593
 integrate_v_rspace                 127 11.3    0.003    0.004   14.486   14.505
 make_m2s                          4970 13.5    0.103    0.110   14.015   14.362
 cp_fm_diag_elpa                     82 13.4    0.000    0.001   14.309   14.315
 qs_rho_update_rho_low              127  7.7    0.001    0.001   14.143   14.264
 calculate_rho_elec                 127  8.7    0.045    0.064   14.142   14.263
 cp_fm_redistribute_end              82 14.4   11.316   14.238   11.327   14.240
 make_images                       4970 14.5    0.398    0.416   13.835   14.197
 cp_fm_diag_elpa_base                82 14.4    2.871   13.848    2.902   13.992
 init_scf_run                        11  5.9    0.000    0.001   12.556   12.557
 scf_env_initial_rho_setup           11  6.9    0.001    0.003   12.556   12.557
 density_rs2pw                      127  9.7    0.006    0.007    7.554   10.825
 mp_sum_l                          7804 13.0    8.176    9.529    8.176    9.529
 rs_pw_transfer                    1038 11.9    0.016    0.019    6.086    9.363
 wfi_extrapolate                     11  7.9    0.001    0.001    9.269    9.269
 cp_fm_cholesky_invert               11 10.9    9.211    9.219    9.211    9.219
 pw_transfer                       1535 11.6    0.076    0.093    8.339    8.579
 calculate_dm_sparse                127  9.5    0.001    0.001    8.375    8.488
 dbcsr_mm_accdrv_process         123452 16.2    3.259    3.418    7.842    8.380
 fft_wrap_pw1pw2                   1281 12.7    0.010    0.011    8.133    8.377
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    7.951    8.090
 qs_ot_get_orbitals                 116 10.6    0.001    0.001    7.904    8.018
 make_images_data                  4970 15.5    0.065    0.072    6.889    7.727
 multiply_cannon_metrocomm1       59640 15.5    0.088    0.092    6.090    7.633
 grid_integrate_task_list           127 12.3    7.023    7.505    7.023    7.505
 fft_wrap_pw1pw2_140                519 13.2    0.439    0.506    6.984    7.263
 hybrid_alltoall_any               5155 16.4    0.287    2.253    6.041    7.249
 fft3d_ps                          1281 14.7    2.094    2.873    6.931    7.117
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.003    6.710    6.720
 mp_waitany                       15900 13.9    2.727    5.984    2.727    5.984
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.762    5.873
 mp_alltoall_d11v                  2401 14.1    4.393    5.838    4.393    5.838
 grid_collocate_task_list           127  9.7    4.513    5.769    4.513    5.769
 rs_pw_transfer_RS2PW_140           138 11.5    0.276    0.294    2.147    5.439
 potential_pw2rs                    127 12.3    0.009    0.011    4.943    4.973
 cp_fm_cholesky_decompose            22 10.9    4.856    4.871    4.856    4.871
 mp_sum_d                          4442 12.2    3.639    4.352    3.639    4.352
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="400", plot="h2o_256_md", label="(8n/12r/1t)", y=205.259000, yerr=0.000000
PlotPoint: name="401", plot="h2o_256_md_mem", label="(8n/12r/1t)", y=594.818182, yerr=6.644453
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/16/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420239992832       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528891191296       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514751E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.183246E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755938624       0.0%      0.0%    100.0%
 number of processed stacks               5975232       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1130.7
 marketing flops                   144.580175E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank             831.668224E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 2406720
 MPI messages size (bytes):
  total size                         4.100942E+12
  min size                           0.000000E+00
  max size                          17.653760E+06
  average size                       1.703955E+06
 MPI breakdown and total messages size (bytes):
             size <=      128               14916                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768               70860               2317615104
     32768 < size <=   131072              722992              55511613440
    131072 < size <=  4194304             1375664            1398181724160
   4194304 < size <= 16777216              154704            1463834332048
  16777216 < size                           67584            1181116006400
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4075                  57341.
 MP_Allreduce        11227                    947.
 MP_Sync               170
 MP_Alltoall          1969                5619064.
 MP_SendRecv         12032                  47072.
 MP_ISendRecv        12032                  47072.
 MP_Wait             25916
 MP_comm_split          83
 MP_ISend            11748                 212467.
 MP_IRecv            11748                 212467.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.018    0.035  194.318  194.319
 qs_mol_dyn_low                       1  2.0    0.003    0.008  193.929  193.951
 qs_forces                           11  3.9    0.003    0.003  193.797  193.801
 qs_energies                         11  4.9    0.001    0.002  186.915  186.927
 scf_env_do_scf                      11  5.9    0.001    0.001  170.368  170.378
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.009  136.377  136.380
 velocity_verlet                     10  3.0    0.001    0.002  122.737  122.739
 dbcsr_multiply_generic            2507 12.6    0.185    0.192   98.346   99.650
 qs_scf_new_mos                     117  7.6    0.001    0.001   95.290   95.851
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   95.290   95.851
 ot_scf_mini                        117  9.6    0.004    0.004   90.429   91.010
 multiply_cannon                   2507 13.6    0.483    0.536   77.640   82.215
 multiply_cannon_loop              2507 14.6    1.260    1.305   74.310   77.004
 ot_mini                            117 10.6    0.001    0.001   50.449   51.016
 mp_waitall_1                    214728 16.6   26.162   40.870   26.162   40.870
 multiply_cannon_multrec          30084 15.6   21.429   26.500   31.007   36.537
 rebuild_ks_matrix                  128  8.3    0.001    0.001   34.186   34.839
 qs_ks_build_kohn_sham_matrix       128  9.3    0.016    0.019   34.186   34.839
 init_scf_loop                       11  6.9    0.000    0.000   33.896   33.897
 qs_ks_update_qs_env                128  7.6    0.001    0.001   30.779   31.380
 multiply_cannon_metrocomm3       30084 15.6    0.094    0.100   16.855   29.957
 prepare_preconditioner              11  7.9    0.000    0.000   29.359   29.435
 make_preconditioner                 11  8.9    0.000    0.000   29.359   29.435
 qs_ot_get_derivative               117 11.6    0.001    0.002   28.228   28.809
 make_full_inverse_cholesky          11  9.9    0.000    0.000   27.982   28.545
 apply_preconditioner_dbcsr         128 12.6    0.000    0.000   22.212   23.480
 apply_single                       128 13.6    0.001    0.001   22.212   23.479
 qs_ot_get_p                        128 10.4    0.001    0.001   21.696   22.370
 ot_diis_step                       117 11.6    0.014    0.015   22.047   22.049
 multiply_cannon_sync_h2d         30084 15.6   18.766   21.329   18.766   21.329
 cp_fm_cholesky_invert               11 10.9   17.265   17.278   17.265   17.278
 qs_ot_p2m_diag                      83 11.4    0.188    0.216   16.756   16.796
 make_m2s                          5014 13.6    0.091    0.095   14.707   16.224
 make_images                       5014 14.6    1.138    1.324   14.497   16.014
 cp_dbcsr_syevd                      83 12.4    0.005    0.006   15.574   15.575
 sum_up_and_integrate               128 10.3    0.116    0.131   15.226   15.255
 integrate_v_rspace                 128 11.3    0.003    0.003   15.110   15.144
 qs_rho_update_rho_low              128  7.7    0.001    0.001   14.424   14.461
 calculate_rho_elec                 128  8.7    0.088    0.105   14.423   14.461
 cp_fm_diag_elpa                     83 13.4    0.000    0.001   12.447   12.468
 cp_fm_redistribute_end              83 14.4    7.277   12.396    7.290   12.399
 cp_fm_diag_elpa_base                83 14.4    4.862   11.849    5.078   12.220
 init_scf_run                        11  5.9    0.000    0.001   11.725   11.726
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   11.724   11.726
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002   11.097   11.519
 multiply_cannon_metrocomm4       27577 15.6    0.094    0.109    3.894   11.160
 make_images_data                  5014 15.6    0.064    0.071    9.046   10.860
 mp_irecv_dv                      69486 16.3    3.700   10.765    3.700   10.765
 density_rs2pw                      128  9.7    0.006    0.007    7.744   10.251
 hybrid_alltoall_any               5200 16.5    0.339    1.491    7.725   10.081
 dbcsr_mm_accdrv_process          62242 16.2    4.493    5.175    9.049    9.651
 pw_transfer                       1547 11.6    0.088    0.108    9.412    9.511
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.011    9.185    9.288
 wfi_extrapolate                     11  7.9    0.001    0.001    8.532    8.534
 rs_pw_transfer                    1046 11.9    0.014    0.016    5.947    8.458
 fft_wrap_pw1pw2_140                523 13.2    0.472    0.523    8.104    8.221
 fft3d_ps                          1291 14.7    2.751    2.936    7.548    7.606
 grid_integrate_task_list           128 12.3    7.176    7.524    7.176    7.524
 cp_fm_cholesky_decompose            22 10.9    7.116    7.190    7.116    7.190
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    6.317    7.037
 calculate_dm_sparse                128  9.5    0.001    0.001    6.561    6.689
 mp_sum_l                          7870 13.0    4.233    6.388    4.233    6.388
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.158    6.168
 grid_collocate_task_list           128  9.7    4.697    5.867    4.697    5.867
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.273    5.475
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    5.392    5.466
 mp_alltoall_d11v                  2415 14.1    4.429    5.385    4.429    5.385
 potential_pw2rs                    128 12.3    0.015    0.017    5.337    5.363
 mp_allgather_i34                  2507 14.6    1.896    5.282    1.896    5.282
 mp_waitany                       11748 13.9    2.522    5.040    2.522    5.040
 rs_pw_transfer_RS2PW_140           139 11.5    0.352    0.376    2.097    4.601
 dbcsr_complete_redistribute        395 12.7    0.771    0.856    3.261    4.135
 mp_sum_d                          4455 12.2    2.767    4.043    2.767    4.043
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="402", plot="h2o_256_md", label="(8n/6r/2t)", y=194.319000, yerr=0.000000
PlotPoint: name="403", plot="h2o_256_md_mem", label="(8n/6r/2t)", y=793.090909, yerr=1.928473
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/17/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1430460020736       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1958505086976       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1986244964352       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1992000282624       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2753956716544       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4454954827776       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5444944789504       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5492290093056       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6712799002624       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11613089636352       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15239146475520       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15239146475520       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19911124992000       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        94.228663E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.950886E+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               4015680       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1694.9
 marketing flops                   145.646636E+12
 -------------------------------------------------------------------------------
 # multiplications                           2527
 max memory usage/rank             935.190528E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                 1051232
 MPI messages size (bytes):
  total size                         2.737039E+12
  min size                           0.000000E+00
  max size                          26.214400E+06
  average size                       2.603648E+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              284160              37245419520
    131072 < size <=  4194304              665408            1004401590272
   4194304 < size <= 16777216               66080             937889764224
  16777216 < size                           28896             757491302400
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4113                  56816.
 MP_Allreduce        11321                    983.
 MP_Sync               170
 MP_Alltoall          1724                9394172.
 MP_SendRecv          7998                  75008.
 MP_ISendRecv         7998                  75008.
 MP_Wait             21986
 MP_comm_split          83
 MP_ISend            11836                 275177.
 MP_IRecv            11836                 275177.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.186    0.201  180.123  180.124
 qs_mol_dyn_low                       1  2.0    0.003    0.003  179.346  179.359
 qs_forces                           11  3.9    0.010    0.011  179.240  179.248
 qs_energies                         11  4.9    0.001    0.002  172.557  172.565
 scf_env_do_scf                      11  5.9    0.001    0.001  156.890  156.890
 scf_env_do_scf_inner_loop          118  6.6    0.003    0.033  121.062  121.063
 velocity_verlet                     10  3.0    0.002    0.002  115.908  115.910
 dbcsr_multiply_generic            2527 12.6    0.183    0.186   82.700   83.777
 qs_scf_new_mos                     118  7.6    0.001    0.001   81.493   81.843
 qs_scf_loop_do_ot                  118  8.6    0.001    0.001   81.493   81.842
 ot_scf_mini                        118  9.6    0.004    0.004   77.298   77.758
 multiply_cannon                   2527 13.6    0.503    0.524   62.498   66.728
 multiply_cannon_loop              2527 14.6    0.865    0.897   59.422   61.836
 ot_mini                            118 10.6    0.001    0.001   43.172   43.608
 init_scf_loop                       11  6.9    0.000    0.000   35.729   35.730
 mp_waitall_1                    171878 16.6   25.987   35.206   25.987   35.206
 rebuild_ks_matrix                  129  8.3    0.001    0.001   31.722   32.259
 qs_ks_build_kohn_sham_matrix       129  9.3    0.016    0.019   31.722   32.258
 prepare_preconditioner              11  7.9    0.000    0.000   31.586   31.641
 make_preconditioner                 11  8.9    0.000    0.000   31.586   31.641
 make_full_inverse_cholesky          11  9.9    0.000    0.000   29.094   30.649
 qs_ks_update_qs_env                129  7.6    0.001    0.001   28.621   29.116
 multiply_cannon_multrec          20216 15.6   13.393   16.937   22.147   25.656
 multiply_cannon_metrocomm3       20216 15.6    0.061    0.064   15.893   25.330
 qs_ot_get_derivative               118 11.6    0.002    0.002   23.008   23.468
 apply_preconditioner_dbcsr         129 12.6    0.000    0.000   20.187   21.183
 apply_single                       129 13.6    0.001    0.001   20.187   21.182
 ot_diis_step                       118 11.6    0.018    0.018   20.042   20.043
 qs_ot_get_p                        129 10.4    0.001    0.001   19.289   19.758
 multiply_cannon_sync_h2d         20216 15.6   14.386   16.221   14.386   16.221
 make_m2s                          5054 13.6    0.082    0.088   15.079   15.873
 make_images                       5054 14.6    1.163    1.255   14.844   15.638
 sum_up_and_integrate               129 10.3    0.135    0.145   15.259   15.289
 integrate_v_rspace                 129 11.3    0.004    0.004   15.123   15.151
 qs_ot_p2m_diag                      83 11.4    0.265    0.272   15.051   15.063
 qs_rho_update_rho_low              129  7.7    0.001    0.001   14.888   14.926
 calculate_rho_elec                 129  8.7    0.133    0.148   14.887   14.925
 cp_fm_cholesky_invert               11 10.9   14.799   14.808   14.799   14.808
 cp_dbcsr_syevd                      83 12.4    0.005    0.005   13.937   13.939
 cp_fm_diag_elpa                     83 13.4    0.000    0.001   10.817   10.818
 cp_fm_redistribute_end              83 14.4    4.088   10.753    4.102   10.756
 init_scf_run                        11  5.9    0.000    0.001   10.631   10.632
 cp_fm_diag_elpa_base                83 14.4    6.221   10.150    6.631   10.632
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   10.631   10.631
 make_images_data                  5054 15.6    0.061    0.069    9.389   10.627
 pw_transfer                       1559 11.6    0.088    0.110    9.564    9.687
 hybrid_alltoall_any               5240 16.5    0.437    2.003    8.184    9.631
 multiply_cannon_metrocomm4       17689 15.6    0.062    0.073    3.546    9.505
 fft_wrap_pw1pw2                   1301 12.7    0.010    0.011    9.336    9.464
 density_rs2pw                      129  9.7    0.006    0.006    7.592    9.451
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002    9.017    9.345
 mp_irecv_dv                      50625 16.2    3.421    9.253    3.421    9.253
 dbcsr_mm_accdrv_process          41830 16.2    4.419    5.287    8.204    8.345
 fft_wrap_pw1pw2_140                527 13.2    0.482    0.532    8.169    8.306
 grid_integrate_task_list           129 12.3    7.377    7.868    7.377    7.868
 fft3d_ps                          1301 14.7    2.693    2.929    7.582    7.669
 cp_fm_upper_to_full                105 14.5    5.846    7.545    5.846    7.545
 wfi_extrapolate                     11  7.9    0.001    0.001    7.542    7.542
 cp_fm_cholesky_decompose            22 10.9    7.363    7.380    7.363    7.380
 rs_pw_transfer                    1054 12.0    0.014    0.015    5.421    7.308
 dbcsr_complete_redistribute        395 12.7    1.178    1.212    4.742    6.539
 calculate_dm_sparse                129  9.5    0.001    0.001    5.797    5.872
 grid_collocate_task_list           129  9.7    4.944    5.852    4.944    5.852
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.516    5.520
 copy_fm_to_dbcsr                   209 11.7    0.002    0.002    3.536    5.330
 qs_ot_get_derivative_taylor         41 13.0    0.001    0.001    4.666    5.325
 mp_alltoall_d11v                  2423 14.1    4.491    5.255    4.491    5.255
 potential_pw2rs                    129 12.3    0.020    0.022    5.171    5.186
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.594    4.736
 mp_sum_l                          7930 13.1    3.298    4.597    3.298    4.597
 mp_allgather_i34                  2527 14.6    1.587    4.538    1.587    4.538
 mp_waitany                       11836 13.9    2.426    4.412    2.426    4.412
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    2.472    4.231
 qs_ot_get_orbitals                 118 10.6    0.001    0.001    4.138    4.170
 mp_alltoall_i22                    718 14.1    2.079    3.986    2.079    3.986
 rs_pw_transfer_RS2PW_140           140 11.5    0.334    0.353    1.961    3.840
 qs_energies_init_hamiltonians       11  5.9    0.000    0.001    3.753    3.753
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    3.619    3.661
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="404", plot="h2o_256_md", label="(8n/4r/3t)", y=180.124000, yerr=0.000000
PlotPoint: name="405", plot="h2o_256_md_mem", label="(8n/4r/3t)", y=887.272727, yerr=9.185868
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_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               1.134948E+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             4103                  56948.
 MP_Allreduce        11296                   1066.
 MP_Sync               170
 MP_Alltoall          1712               12503107.
 MP_SendRecv          5888                  75008.
 MP_ISendRecv         5888                  75008.
 MP_Wait             22442
 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    0.061    0.098  199.959  199.962
 qs_mol_dyn_low                       1  2.0    0.003    0.005  199.358  199.372
 qs_forces                           11  3.9    0.003    0.003  199.228  199.236
 qs_energies                         11  4.9    0.004    0.008  191.927  191.934
 scf_env_do_scf                      11  5.9    0.001    0.003  174.432  174.439
 velocity_verlet                     10  3.0    0.002    0.002  131.769  131.772
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.009  125.364  125.365
 qs_scf_new_mos                     117  7.6    0.001    0.001   86.134   86.468
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   86.134   86.467
 dbcsr_multiply_generic            2507 12.6    0.190    0.195   81.902   82.592
 ot_scf_mini                        117  9.6    0.003    0.005   81.572   81.867
 multiply_cannon                   2507 13.6    0.554    0.597   55.694   58.049
 multiply_cannon_loop              2507 14.6    1.188    1.217   51.683   53.289
 init_scf_loop                       11  6.9    0.001    0.003   48.929   48.931
 prepare_preconditioner              11  7.9    0.000    0.000   44.659   44.702
 make_preconditioner                 11  8.9    0.000    0.002   44.659   44.702
 ot_mini                            117 10.6    0.001    0.001   44.333   44.616
 make_full_inverse_cholesky          11  9.9    0.000    0.000   38.264   43.277
 rebuild_ks_matrix                  128  8.3    0.001    0.001   31.043   31.270
 qs_ks_build_kohn_sham_matrix       128  9.3    0.017    0.019   31.042   31.270
 multiply_cannon_multrec          30084 15.6   14.044   18.718   25.930   30.371
 mp_waitall_1                    147882 16.7   18.978   29.358   18.978   29.358
 qs_ks_update_qs_env                128  7.6    0.001    0.001   27.992   28.188
 qs_ot_get_derivative               117 11.6    0.001    0.002   24.346   24.619
 qs_ot_get_p                        128 10.4    0.001    0.001   23.113   23.425
 make_m2s                          5014 13.6    0.095    0.100   21.192   22.058
 make_images                       5014 14.6    1.942    2.207   20.888   21.755
 ot_diis_step                       117 11.6    0.018    0.018   19.826   19.828
 apply_preconditioner_dbcsr         128 12.6    0.000    0.001   19.325   19.826
 apply_single                       128 13.6    0.001    0.001   19.324   19.826
 qs_ot_p2m_diag                      83 11.4    0.343    0.390   18.446   18.501
 cp_fm_cholesky_invert               11 10.9   17.943   17.954   17.943   17.954
 cp_dbcsr_syevd                      83 12.4    0.005    0.005   17.093   17.097
 cp_fm_upper_to_full                105 14.7   11.125   16.475   11.125   16.475
 multiply_cannon_metrocomm3       30084 15.6    0.047    0.049    6.998   15.957
 sum_up_and_integrate               128 10.3    0.141    0.153   15.528   15.552
 qs_rho_update_rho_low              128  7.7    0.001    0.001   15.457   15.512
 calculate_rho_elec                 128  8.7    0.175    0.190   15.456   15.511
 integrate_v_rspace                 128 11.3    0.003    0.004   15.387   15.417
 cp_fm_diag_elpa                     83 13.4    0.000    0.001   13.710   13.716
 cp_fm_redistribute_end              83 14.4    2.370   13.578    2.391   13.583
 cp_fm_diag_elpa_base                83 14.4   10.534   12.897   11.143   13.384
 dbcsr_complete_redistribute        395 12.7    1.610    1.727    9.312   13.095
 make_images_data                  5014 15.6    0.064    0.068   11.483   12.879
 multiply_cannon_sync_h2d         30084 15.6   11.695   12.462   11.695   12.462
 dbcsr_mm_accdrv_process          62264 16.2    7.347    8.244   11.462   11.927
 hybrid_alltoall_any               5200 16.5    0.525    2.208   10.325   11.923
 copy_fm_to_dbcsr                   209 11.7    0.002    0.003    7.825   11.601
 init_scf_run                        11  5.9    0.000    0.001   11.402   11.403
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   11.401   11.403
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002   10.116   10.318
 pw_transfer                       1547 11.6    0.090    0.108   10.111   10.219
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    6.372   10.006
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.012    9.881    9.993
 mp_alltoall_i22                    716 14.1    5.627    9.306    5.627    9.306
 density_rs2pw                      128  9.7    0.006    0.006    7.751    9.094
 fft_wrap_pw1pw2_140                523 13.2    0.480    0.494    8.638    8.761
 cp_fm_cholesky_decompose            22 10.9    8.129    8.228    8.129    8.228
 fft3d_ps                          1291 14.7    2.776    2.885    8.107    8.201
 wfi_extrapolate                     11  7.9    0.001    0.001    8.110    8.110
 grid_integrate_task_list           128 12.3    7.493    7.961    7.493    7.961
 multiply_cannon_metrocomm4       25070 15.6    0.075    0.086    2.765    7.095
 mp_irecv_dv                      76098 16.2    2.623    6.835    2.623    6.835
 rs_pw_transfer                    1046 11.9    0.013    0.015    5.385    6.825
 calculate_dm_sparse                128  9.5    0.001    0.001    6.248    6.331
 mp_alltoall_d11v                  2415 14.1    5.415    6.055    5.415    6.055
 grid_collocate_task_list           128  9.7    5.077    5.806    5.077    5.806
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.667    5.730
 potential_pw2rs                    128 12.3    0.023    0.023    5.215    5.240
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    4.743    4.837
 qs_energies_init_hamiltonians       11  5.9    0.002    0.007    4.569    4.570
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.001    4.450    4.548
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    4.409    4.465
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="406", plot="h2o_256_md", label="(8n/3r/4t)", y=199.962000, yerr=0.000000
PlotPoint: name="407", plot="h2o_256_md_mem", label="(8n/3r/4t)", y=1066.090909, yerr=23.596820
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/19/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1430456039424       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1962800054272       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1986255912960       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1992003932160       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2753958699008       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4454954827776       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5444944789504       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5492290093056       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6712799002624       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11613072052224       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15239176077312       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15239176077312       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19911132921856       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        94.233020E+12       0.0%      0.0%    100.0%
 flops max/rank                      5.910120E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6806383904       0.0%      0.0%    100.0%
 number of processed stacks               1976928       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    3442.9
 marketing flops                   145.650931E+12
 -------------------------------------------------------------------------------
 # multiplications                           2529
 max memory usage/rank               1.473638E+09
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  242784
 MPI messages size (bytes):
  total size                         1.341806E+12
  min size                           0.000000E+00
  max size                          52.428800E+06
  average size                       5.526748E+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              115008              60297314304
   4194304 < size <= 16777216              105840             554906419200
  16777216 < size                           20352             726592466352
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         9010                     51.
 MP_Alltoall          9724                 794507.
 MP_ISend            40420                2100460.
 MP_IRecv            40420                2099564.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4043                  57630.
 MP_Allreduce        11104                   1171.
 MP_Sync                88
 MP_Alltoall          1724               18848034.
 MP_SendRecv          3870                 122880.
 MP_ISendRecv         3870                 122880.
 MP_Wait             16244
 MP_ISend            10760                 423501.
 MP_IRecv            10760                 423501.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.035    0.055  182.832  182.832
 qs_mol_dyn_low                       1  2.0    0.003    0.004  182.359  182.371
 qs_forces                           11  3.9    0.003    0.003  182.227  182.235
 qs_energies                         11  4.9    0.002    0.003  174.510  174.516
 scf_env_do_scf                      11  5.9    0.001    0.001  156.841  156.848
 velocity_verlet                     10  3.0    0.002    0.002  119.629  119.635
 scf_env_do_scf_inner_loop          118  6.6    0.003    0.009  119.386  119.386
 qs_scf_new_mos                     118  7.6    0.001    0.001   78.971   79.092
 qs_scf_loop_do_ot                  118  8.6    0.001    0.001   78.970   79.091
 dbcsr_multiply_generic            2529 12.6    0.184    0.189   76.003   76.477
 ot_scf_mini                        118  9.6    0.004    0.004   74.418   74.531
 multiply_cannon                   2529 13.6    0.590    0.619   54.984   59.634
 multiply_cannon_loop              2529 14.6    0.452    0.460   50.101   51.071
 ot_mini                            118 10.6    0.001    0.001   40.562   40.677
 init_scf_loop                       11  6.9    0.000    0.000   37.303   37.305
 mp_waitall_1                    126876 16.7   26.973   34.271   26.973   34.271
 prepare_preconditioner              11  7.9    0.000    0.000   33.199   33.222
 make_preconditioner                 11  8.9    0.000    0.000   33.199   33.222
 make_full_inverse_cholesky          11  9.9    0.000    0.000   31.012   31.278
 rebuild_ks_matrix                  129  8.3    0.001    0.001   31.146   31.270
 qs_ks_build_kohn_sham_matrix       129  9.3    0.017    0.018   31.145   31.270
 qs_ks_update_qs_env                129  7.6    0.001    0.001   28.251   28.357
 multiply_cannon_multrec          10116 15.6   10.431   14.307   17.777   21.050
 qs_ot_get_p                        129 10.4    0.001    0.001   20.584   20.720
 qs_ot_get_derivative               118 11.6    0.002    0.002   20.475   20.581
 ot_diis_step                       118 11.6    0.020    0.021   20.016   20.017
 apply_preconditioner_dbcsr         129 12.6    0.000    0.000   19.556   19.822
 apply_single                       129 13.6    0.001    0.001   19.556   19.822
 make_m2s                          5058 13.6    0.067    0.071   17.211   19.711
 multiply_cannon_metrocomm3       10116 15.6    0.023    0.025   12.172   19.444
 make_images                       5058 14.6    2.279    2.653   16.903   19.405
 cp_fm_cholesky_invert               11 10.9   18.990   18.996   18.990   18.996
 qs_ot_p2m_diag                      84 11.4    0.502    0.507   16.502   16.521
 qs_rho_update_rho_low              129  7.7    0.001    0.001   16.226   16.290
 calculate_rho_elec                 129  8.7    0.260    0.271   16.226   16.289
 sum_up_and_integrate               129 10.3    0.182    0.191   15.763   15.812
 integrate_v_rspace                 129 11.3    0.004    0.004   15.580   15.631
 cp_dbcsr_syevd                      84 12.4    0.005    0.006   15.319   15.321
 make_images_data                  5058 15.6    0.053    0.062   10.644   13.450
 hybrid_alltoall_any               5245 16.5    0.841    3.831   10.406   12.942
 multiply_cannon_sync_h2d         10116 15.6   11.715   12.219   11.715   12.219
 cp_fm_diag_elpa                     84 13.4    0.000    0.000   12.078   12.088
 cp_fm_diag_elpa_base                84 14.4   11.814   11.908   12.070   12.079
 init_scf_run                        11  5.9    0.000    0.001   10.764   10.764
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   10.764   10.764
 pw_transfer                       1559 11.6    0.088    0.098   10.636   10.673
 fft_wrap_pw1pw2                   1301 12.7    0.010    0.011   10.410   10.450
 fft_wrap_pw1pw2_140                527 13.2    0.501    0.531    9.121    9.166
 cp_fm_cholesky_decompose            22 10.9    8.475    8.580    8.475    8.580
 fft3d_ps                          1301 14.7    2.727    2.803    8.552    8.580
 density_rs2pw                      129  9.7    0.005    0.006    7.561    8.469
 qs_ot_get_derivative_diag           78 12.4    0.002    0.003    8.378    8.461
 mp_allgather_i34                  2529 14.6    3.068    8.201    3.068    8.201
 grid_integrate_task_list           129 12.3    7.810    8.181    7.810    8.181
 multiply_cannon_metrocomm1       10116 15.6    0.029    0.029    4.788    7.871
 wfi_extrapolate                     11  7.9    0.001    0.001    7.708    7.709
 dbcsr_mm_accdrv_process          20934 16.1    2.668    3.427    6.969    7.596
 mp_alltoall_d11v                  2429 14.1    5.670    6.501    5.670    6.501
 calculate_dm_sparse                129  9.5    0.001    0.001    6.206    6.290
 grid_collocate_task_list           129  9.7    5.437    6.102    5.437    6.102
 dbcsr_complete_redistribute        397 12.7    2.159    2.232    5.469    5.923
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.407    5.418
 rs_pw_transfer                    1054 12.0    0.012    0.013    4.430    5.349
 qs_energies_init_hamiltonians       11  5.9    0.000    0.001    5.315    5.316
 potential_pw2rs                    129 12.3    0.026    0.027    4.947    4.967
 multiply_cannon_metrocomm4        7587 15.6    0.024    0.027    1.868    4.315
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.221    4.246
 mp_irecv_dv                      29102 15.9    1.831    4.238    1.831    4.238
 copy_fm_to_dbcsr                   210 11.7    0.002    0.002    3.585    3.943
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    3.549    3.845
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    3.815    3.834
 copy_dbcsr_to_fm                   187 11.8    0.004    0.004    3.699    3.832
 qs_ot_get_orbitals                 118 10.6    0.001    0.001    3.786    3.811
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="408", plot="h2o_256_md", label="(8n/2r/6t)", y=182.832000, yerr=0.000000
PlotPoint: name="409", plot="h2o_256_md_mem", label="(8n/2r/6t)", y=1380.181818, yerr=44.392502
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_performance_tests/20/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1410022950912       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1924145348608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1957871443968       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1963544850432       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2714615709696       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4377645416448       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5350455508992       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5395653328896       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6594687401984       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11444706349056       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15019187724288       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15019187724288       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                        92.796577E+12       0.0%      0.0%    100.0%
 flops max/rank                     11.606413E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6705500544       0.0%      0.0%    100.0%
 number of processed stacks               1947808       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    3442.6
 marketing flops                   143.507742E+12
 -------------------------------------------------------------------------------
 # multiplications                           2485
 max memory usage/rank               3.002122E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                   99400
 MPI messages size (bytes):
  total size                         1.127422E+12
  min size                           0.000000E+00
  max size                         104.857600E+06
  average size                      11.342272E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                 572                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                  44                  2883584
    131072 < size <=  4194304               44768              34745614336
   4194304 < size <= 16777216               43984             376564613120
  16777216 < size                           10032             716108613552
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3955                  59820.
 MP_Allreduce        10885                   1518.
 MP_Sync                86
 MP_Alltoall          1700               36954374.
 MP_SendRecv          1778                 218624.
 MP_ISendRecv         1778                 218624.
 MP_Wait              9728
 MP_ISend             6360                1080477.
 MP_IRecv             6360                1080477.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.054    0.059  306.755  306.755
 qs_mol_dyn_low                       1  2.0    0.003    0.004  306.086  306.097
 qs_forces                           11  3.9    0.003    0.003  305.985  305.986
 qs_energies                         11  4.9    0.002    0.002  296.542  296.556
 scf_env_do_scf                      11  5.9    0.001    0.001  273.799  273.811
 velocity_verlet                     10  3.0    0.002    0.002  220.406  220.414
 scf_env_do_scf_inner_loop          116  6.6    0.003    0.010  145.511  145.514
 init_scf_loop                       11  6.9    0.000    0.000  128.025  128.030
 prepare_preconditioner              11  7.9    0.000    0.000  122.720  122.751
 make_preconditioner                 11  8.9    0.000    0.000  122.720  122.751
 make_full_inverse_cholesky          11  9.9    0.000    0.000   98.272  119.797
 qs_scf_new_mos                     116  7.6    0.001    0.001   93.890   94.004
 qs_scf_loop_do_ot                  116  8.6    0.001    0.001   93.889   94.003
 ot_scf_mini                        116  9.6    0.004    0.004   89.062   89.094
 dbcsr_multiply_generic            2485 12.5    0.210    0.218   84.857   85.488
 cp_fm_upper_to_full                104 14.8   53.380   76.775   53.380   76.775
 multiply_cannon                   2485 13.5    0.699    0.765   59.872   60.357
 multiply_cannon_loop              2485 14.5    0.469    0.481   56.122   57.624
 ot_mini                            116 10.6    0.001    0.001   45.595   45.625
 dbcsr_complete_redistribute        393 12.7    3.977    4.019   30.299   43.642
 copy_fm_to_dbcsr                   208 11.6    0.001    0.002   26.808   40.188
 rebuild_ks_matrix                  127  8.3    0.001    0.001   38.938   38.984
 qs_ks_build_kohn_sham_matrix       127  9.3    0.017    0.017   38.938   38.983
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000   24.403   37.649
 qs_ks_update_qs_env                127  7.6    0.001    0.001   35.820   35.867
 mp_alltoall_i22                    712 14.1   22.179   35.745   22.179   35.745
 cp_fm_cholesky_invert               11 10.9   35.105   35.111   35.105   35.111
 mp_waitall_1                    102768 16.8   30.000   33.980   30.000   33.980
 qs_ot_get_p                        127 10.4    0.001    0.001   27.740   27.796
 qs_ot_get_derivative               116 11.6    0.002    0.002   25.203   25.235
 qs_ot_p2m_diag                      82 11.4    0.867    0.873   23.453   23.488
 cp_dbcsr_syevd                      82 12.4    0.006    0.006   21.660   21.662
 multiply_cannon_metrocomm3        9940 15.5    0.024    0.024   20.211   21.510
 make_m2s                          4970 13.5    0.075    0.077   20.171   21.183
 qs_rho_update_rho_low              127  7.7    0.001    0.001   21.123   21.146
 calculate_rho_elec                 127  8.7    0.479    0.480   21.123   21.146
 make_images                       4970 14.5    3.684    3.822   19.696   20.711
 ot_diis_step                       116 11.6    0.022    0.023   20.352   20.352
 sum_up_and_integrate               127 10.3    0.318    0.321   19.978   20.048
 apply_preconditioner_dbcsr         127 12.6    0.000    0.000   19.603   19.850
 apply_single                       127 13.6    0.001    0.001   19.603   19.849
 integrate_v_rspace                 127 11.3    0.004    0.004   19.659   19.731
 cp_fm_diag_elpa                     82 13.4    0.000    0.000   18.361   18.362
 cp_fm_diag_elpa_base                82 14.4   13.955   15.595   18.357   18.357
 multiply_cannon_multrec           9940 15.5   10.392   12.140   17.786   17.899
 multiply_cannon_sync_h2d          9940 15.5   15.543   15.553   15.543   15.553
 pw_transfer                       1535 11.6    0.093    0.093   12.875   12.882
 make_images_data                  4970 15.5    0.059    0.064   10.854   12.774
 init_scf_run                        11  5.9    0.000    0.001   12.655   12.655
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   12.654   12.655
 fft_wrap_pw1pw2                   1281 12.7    0.011    0.011   12.641   12.650
 hybrid_alltoall_any               5155 16.4    1.295    3.026   10.855   12.619
 fft_wrap_pw1pw2_140                519 13.2    0.538    0.543   11.173   11.179
 fft3d_ps                          1281 14.7    2.720    2.727   10.692   10.703
 qs_ot_get_derivative_diag           76 12.4    0.002    0.002    9.856    9.888
 cp_fm_cholesky_decompose            22 10.9    9.583    9.608    9.583    9.608
 mp_alltoall_d11v                  2401 14.1    8.556    9.490    8.556    9.490
 wfi_extrapolate                     11  7.9    0.001    0.001    9.386    9.386
 dbcsr_mm_accdrv_process          20590 16.0    3.803    5.760    7.157    9.022
 density_rs2pw                      127  9.7    0.005    0.005    8.717    8.857
 grid_integrate_task_list           127 12.3    8.523    8.686    8.523    8.686
 qs_energies_init_hamiltonians       11  5.9    0.003    0.018    8.031    8.033
 calculate_dm_sparse                127  9.5    0.001    0.001    6.755    6.860
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.431    6.529
 grid_collocate_task_list           127  9.7    6.322    6.350    6.322    6.350
 rs_scatter_matrices                138  9.7    3.522    4.437    6.058    6.288
 copy_dbcsr_to_fm                   185 11.7    0.004    0.004    6.164    6.254
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="410", plot="h2o_256_md", label="(8n/1r/12t)", y=306.755000, yerr=0.000000
PlotPoint: name="411", plot="h2o_256_md_mem", label="(8n/1r/12t)", y=2680.545455, yerr=168.871852
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_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               1.262309E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                  458208
 MPI messages size (bytes):
  total size                         3.456111E+12
  min size                           0.000000E+00
  max size                          18.735064E+06
  average size                       7.542668E+06
 MPI breakdown and total messages size (bytes):
             size <=      128              112896                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 224                  5687808
     32768 < size <=   131072               10528                813356544
    131072 < size <=  4194304               36422              76284728544
   4194304 < size <= 16777216              294266            3312457683808
  16777216 < size                            3872              66548597808
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 255669.
 MP_Allreduce         3059                   6274.
 MP_Sync                 4
 MP_Alltoall            54                6805335.
 MP_SendRecv           285                  19200.
 MP_ISendRecv          285                  19200.
 MP_Wait              1017
 MP_ISend              642                 197829.
 MP_IRecv              642                 197607.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.041    0.076   85.599   85.601
 qs_energies                          1  2.0    0.000    0.000   85.102   85.117
 ls_scf                               1  3.0    0.000    0.000   84.194   84.209
 dbcsr_multiply_generic             111  6.7    0.015    0.016   73.121   73.256
 multiply_cannon                    111  7.7    0.017    0.020   56.141   57.282
 multiply_cannon_loop               111  8.7    0.209    0.225   52.644   54.012
 ls_scf_main                          1  4.0    0.000    0.000   52.749   52.749
 density_matrix_trs4                  2  5.0    0.002    0.003   47.124   47.210
 ls_scf_init_scf                      1  4.0    0.000    0.000   28.393   28.394
 mp_waitall_1                     11031 10.9   23.038   27.410   23.038   27.410
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   27.267   27.323
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   25.127   25.148
 multiply_cannon_multrec           2664  9.7    8.158    8.968   15.437   17.214
 multiply_cannon_sync_h2d          2664  9.7   13.436   15.428   13.436   15.428
 multiply_cannon_metrocomm1        2664  9.7    0.009    0.010   10.004   14.004
 make_m2s                           222  7.7    0.008    0.011   13.178   13.809
 make_images                        222  8.7    0.099    0.112   13.157   13.788
 multiply_cannon_metrocomm3        2664  9.7    0.009    0.011    5.609    9.203
 make_images_data                   222  9.7    0.004    0.005    7.755    8.352
 hybrid_alltoall_any                227 10.6    0.215    1.830    6.643    8.099
 dbcsr_mm_accdrv_process           4760 10.4    0.502    0.601    6.896    7.845
 dbcsr_mm_accdrv_process_sort      4760 11.4    6.193    7.088    6.193    7.088
 calculate_norms                   4752  9.8    5.504    6.260    5.504    6.260
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.164    5.278
 mp_sum_l                           807  5.4    3.304    4.936    3.304    4.936
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    2.443    3.755
 multiply_cannon_metrocomm4        2442  9.7    0.012    0.015    2.075    3.625
 mp_irecv_dv                       6231 10.9    2.057    3.595    2.057    3.595
 make_images_sizes                  222  9.7    0.000    0.000    0.752    3.405
 mp_alltoall_i44                    222 10.7    0.752    3.405    0.752    3.405
 arnoldi_extremal                     4  6.8    0.000    0.000    3.308    3.344
 arnoldi_normal_ev                    4  7.8    0.001    0.002    3.308    3.344
 build_subspace                      16  8.4    0.009    0.012    3.208    3.210
 ls_scf_post                          1  4.0    0.000    0.000    3.052    3.067
 ls_scf_store_result                  1  5.0    0.000    0.000    2.867    2.908
 dbcsr_special_finalize             555  9.7    0.005    0.006    2.320    2.809
 dbcsr_merge_single_wm              555 10.7    0.462    0.614    2.312    2.801
 make_images_pack                   222  9.7    2.203    2.621    2.205    2.623
 dbcsr_matrix_vector_mult           304  9.0    0.005    0.012    2.343    2.591
 dbcsr_sort_data                    658 11.4    2.109    2.494    2.109    2.494
 dbcsr_matrix_vector_mult_local     304 10.0    2.066    2.465    2.068    2.467
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.293    2.359
 buffer_matrices_ensure_size        222  8.7    1.767    2.134    1.767    2.134
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.797    1.799
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.788    1.789
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.001    1.788    1.789
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="500", plot="h2o_32_nrep3_ls", label="(8n/12r/1t)", y=85.601000, yerr=0.000000
PlotPoint: name="501", plot="h2o_32_nrep3_ls_mem", label="(8n/12r/1t)", y=1142.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_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               2.105053E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                  106560
 MPI messages size (bytes):
  total size                         2.699093E+12
  min size                           0.000000E+00
  max size                          72.286792E+06
  average size                      25.329324E+06
 MPI breakdown and total messages size (bytes):
             size <=      128               23040                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                3264                325830144
    131072 < size <=  4194304                5280               3328561104
   4194304 < size <= 16777216               12709             156766962056
  16777216 < size                           62267            2538670978840
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 266696.
 MP_Allreduce         3058                  10339.
 MP_Sync                 4
 MP_Alltoall            47               15335933.
 MP_SendRecv           141                  57600.
 MP_ISendRecv          141                  57600.
 MP_Wait               687
 MP_ISend              462                 414589.
 MP_IRecv              462                 413870.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.026    0.040   90.467   90.467
 qs_energies                          1  2.0    0.000    0.000   89.978   89.981
 ls_scf                               1  3.0    0.000    0.000   88.667   88.670
 dbcsr_multiply_generic             111  6.7    0.015    0.017   74.600   74.906
 multiply_cannon                    111  7.7    0.028    0.037   53.142   56.387
 ls_scf_main                          1  4.0    0.000    0.000   54.656   54.662
 multiply_cannon_loop               111  8.7    0.117    0.123   49.937   52.805
 density_matrix_trs4                  2  5.0    0.002    0.003   48.843   49.052
 ls_scf_init_scf                      1  4.0    0.000    0.000   30.489   30.490
 mp_waitall_1                      9105 10.9   20.908   30.040   20.908   30.040
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   29.312   29.395
 multiply_cannon_multrec           1332  9.7   13.159   17.082   22.358   27.477
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   26.909   26.919
 multiply_cannon_metrocomm3        1332  9.7    0.006    0.008   11.640   20.864
 make_m2s                           222  7.7    0.006    0.007   15.056   15.670
 make_images                        222  8.7    1.572    1.965   15.026   15.641
 dbcsr_mm_accdrv_process           4041 10.4    0.282    0.461    8.796   10.347
 dbcsr_mm_accdrv_process_sort      4041 11.4    8.378    9.899    8.378    9.899
 make_images_data                   222  9.7    0.004    0.004    8.587    9.397
 hybrid_alltoall_any                227 10.6    0.525    2.495    8.055    8.982
 mp_sum_l                           807  5.4    5.092    7.969    5.092    7.969
 multiply_cannon_metrocomm4        1221  9.7    0.006    0.008    3.244    7.543
 mp_irecv_dv                       3311 11.0    3.225    7.477    3.225    7.477
 calculate_norms                   2376  9.8    6.015    6.846    6.015    6.846
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.910    6.228
 multiply_cannon_sync_h2d          1332  9.7    4.780    5.891    4.780    5.891
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.104    5.371
 arnoldi_extremal                     4  6.8    0.000    0.000    4.749    4.769
 arnoldi_normal_ev                    4  7.8    0.001    0.005    4.749    4.769
 build_subspace                      16  8.4    0.014    0.021    4.493    4.498
 ls_scf_post                          1  4.0    0.000    0.000    3.523    3.525
 dbcsr_matrix_vector_mult           304  9.0    0.009    0.021    3.217    3.451
 ls_scf_store_result                  1  5.0    0.000    0.000    3.225    3.342
 dbcsr_matrix_vector_mult_local     304 10.0    2.772    3.254    2.774    3.256
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.004    1.320    2.976
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.642    2.773
 make_images_pack                   222  9.7    2.033    2.411    2.035    2.413
 mp_allgather_i34                   111  8.7    0.901    2.228    0.901    2.228
 dbcsr_sort_data                    436 11.2    1.815    2.018    1.815    2.018
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.886    1.888
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.873    1.876
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.001    1.873    1.875
 dbcsr_data_new                    4174 10.1    1.615    1.834    1.615    1.834
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="502", plot="h2o_32_nrep3_ls", label="(8n/6r/2t)", y=90.467000, yerr=0.000000
PlotPoint: name="503", plot="h2o_32_nrep3_ls_mem", label="(8n/6r/2t)", y=1726.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_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               2.683335E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                   46176
 MPI messages size (bytes):
  total size                         1.924064E+12
  min size                           0.000000E+00
  max size                         108.059888E+06
  average size                      41.668048E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                9984                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304                3328               1170063360
   4194304 < size <= 16777216                1870              19378539600
  16777216 < size                           30994            1903514987232
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 265470.
 MP_Allreduce         3058                  11181.
 MP_Sync                 4
 MP_Alltoall            47               23526250.
 MP_SendRecv            93                  57600.
 MP_ISendRecv           93                  57600.
 MP_Wait               639
 MP_ISend              462                 560046.
 MP_IRecv              462                 560662.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.040    0.056   94.986   94.987
 qs_energies                          1  2.0    0.000    0.000   94.307   94.354
 ls_scf                               1  3.0    0.000    0.001   92.903   92.952
 dbcsr_multiply_generic             111  6.7    0.015    0.016   77.295   77.584
 ls_scf_main                          1  4.0    0.000    0.000   58.272   58.277
 multiply_cannon                    111  7.7    0.043    0.102   53.204   57.880
 multiply_cannon_loop               111  8.7    0.100    0.108   49.675   53.278
 density_matrix_trs4                  2  5.0    0.002    0.003   52.257   52.436
 mp_waitall_1                      7281 11.0   24.464   34.208   24.464   34.208
 ls_scf_init_scf                      1  4.0    0.000    0.002   30.987   30.990
 ls_scf_init_matrix_S                 1  5.0    0.000    0.001   29.755   29.836
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.352   27.365
 multiply_cannon_multrec            888  9.7   12.517   15.128   20.996   24.204
 multiply_cannon_metrocomm3         888  9.7    0.004    0.004   11.531   23.020
 make_m2s                           222  7.7    0.006    0.007   17.167   18.370
 make_images                        222  8.7    1.964    2.282   17.129   18.329
 hybrid_alltoall_any                227 10.6    0.620    2.853    9.531   10.858
 make_images_data                   222  9.7    0.003    0.004    9.870   10.847
 mp_sum_l                           807  5.4    5.372    9.407    5.372    9.407
 dbcsr_mm_accdrv_process           3754 10.4    0.245    0.410    8.008    9.189
 dbcsr_mm_accdrv_process_sort      3754 11.4    7.639    8.779    7.639    8.779
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    4.244    7.582
 multiply_cannon_sync_h2d           888  9.7    6.091    7.449    6.091    7.449
 multiply_cannon_metrocomm4         777  9.7    0.004    0.005    2.481    7.223
 mp_irecv_dv                       2335 11.1    2.466    7.180    2.466    7.180
 multiply_cannon_metrocomm1         888  9.7    0.002    0.003    3.685    6.498
 arnoldi_extremal                     4  6.8    0.000    0.000    5.288    5.306
 arnoldi_normal_ev                    4  7.8    0.001    0.005    5.288    5.306
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.943    5.130
 build_subspace                      16  8.4    0.014    0.020    4.980    4.986
 calculate_norms                   1584  9.8    4.281    4.648    4.281    4.648
 dbcsr_matrix_vector_mult           304  9.0    0.009    0.020    3.554    3.894
 mp_allgather_i34                   111  8.7    1.365    3.854    1.365    3.854
 ls_scf_post                          1  4.0    0.006    0.050    3.644    3.694
 dbcsr_matrix_vector_mult_local     304 10.0    3.041    3.606    3.043    3.608
 ls_scf_store_result                  1  5.0    0.000    0.000    3.367    3.466
 ls_scf_dm_to_ks                      2  5.0    0.000    0.001    2.907    3.016
 dbcsr_sort_data                    325 11.1    1.899    2.123    1.899    2.123
 make_images_pack                   222  9.7    1.812    2.116    1.815    2.119
 make_images_sizes                  222  9.7    0.000    0.000    0.970    2.081
 mp_alltoall_i44                    222 10.7    0.969    2.080    0.969    2.080
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.982    1.984
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.963    1.966
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.003    1.963    1.966
 dbcsr_data_release                9322 10.9    1.309    1.957    1.309    1.957
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="504", plot="h2o_32_nrep3_ls", label="(8n/4r/3t)", y=94.987000, yerr=0.000000
PlotPoint: name="505", plot="h2o_32_nrep3_ls_mem", label="(8n/4r/3t)", y=2180.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_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               3.350209E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                   50616
 MPI messages size (bytes):
  total size                         1.536549E+12
  min size                           0.000000E+00
  max size                          72.286792E+06
  average size                      30.356986E+06
 MPI breakdown and total messages size (bytes):
             size <=      128               10368                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                1056                104411904
    131072 < size <=  4194304                3168                831638784
   4194304 < size <= 16777216                3103              33613273640
  16777216 < size                           32921            1501999894888
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 266696.
 MP_Allreduce         3058                  13371.
 MP_Sync                 4
 MP_Alltoall            47               30278988.
 MP_SendRecv            69                  86400.
 MP_ISendRecv           69                  86400.
 MP_Wait               531
 MP_ISend              378                 823502.
 MP_IRecv              378                 823753.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.087    0.111   98.407   98.409
 qs_energies                          1  2.0    0.003    0.028   97.542   97.565
 ls_scf                               1  3.0    0.005    0.011   95.802   95.807
 dbcsr_multiply_generic             111  6.7    0.017    0.021   78.827   79.089
 ls_scf_main                          1  4.0    0.000    0.002   59.444   59.451
 multiply_cannon                    111  7.7    0.058    0.164   51.546   56.078
 density_matrix_trs4                  2  5.0    0.002    0.005   53.201   53.305
 multiply_cannon_loop               111  8.7    0.115    0.126   46.581   49.636
 ls_scf_init_scf                      1  4.0    0.001    0.003   33.020   33.031
 ls_scf_init_matrix_S                 1  5.0    0.000    0.001   31.663   31.722
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   29.139   29.150
 mp_waitall_1                      6369 11.0   23.114   29.066   23.114   29.066
 multiply_cannon_multrec           1332  9.7   14.168   16.739   21.999   24.764
 make_m2s                           222  7.7    0.007    0.008   21.473   22.869
 make_images                        222  8.7    3.132    3.584   21.423   22.822
 multiply_cannon_metrocomm3        1332  9.7    0.003    0.003    9.185   17.139
 make_images_data                   222  9.7    0.004    0.004   12.084   13.766
 hybrid_alltoall_any                227 10.6    0.796    3.780   11.445   13.253
 dbcsr_mm_accdrv_process           3641 10.4    0.227    0.409    7.466    8.972
 dbcsr_mm_accdrv_process_sort      3641 11.4    7.089    8.564    7.089    8.564
 mp_sum_l                           807  5.4    4.246    8.230    4.246    8.230
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.225    6.557
 multiply_cannon_metrocomm4        1110  9.7    0.004    0.006    2.094    6.106
 multiply_cannon_sync_h2d          1332  9.7    5.488    6.087    5.488    6.087
 mp_irecv_dv                       3229 10.9    2.072    6.030    2.072    6.030
 arnoldi_extremal                     4  6.8    0.000    0.003    5.523    5.534
 arnoldi_normal_ev                    4  7.8    0.003    0.014    5.523    5.534
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.003    2.673    5.335
 build_subspace                      16  8.4    0.018    0.026    5.151    5.162
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.593    4.803
 calculate_norms                   2376  9.8    4.190    4.508    4.190    4.508
 mp_allgather_i34                   111  8.7    2.092    4.236    2.092    4.236
 dbcsr_matrix_vector_mult           304  9.0    0.010    0.020    3.725    4.070
 dbcsr_matrix_vector_mult_local     304 10.0    3.192    3.696    3.194    3.698
 dbcsr_sort_data                    658 11.4    3.092    3.416    3.092    3.416
 ls_scf_post                          1  4.0    0.000    0.001    3.333    3.338
 dbcsr_special_finalize             555  9.7    0.006    0.007    2.841    3.193
 dbcsr_merge_single_wm              555 10.7    0.537    0.658    2.833    3.185
 ls_scf_dm_to_ks                      2  5.0    0.000    0.004    3.121    3.181
 ls_scf_store_result                  1  5.0    0.000    0.000    2.985    3.050
 dbcsr_data_release               10477 10.7    1.590    2.413    1.590    2.413
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.108    2.118
 rebuild_ks_matrix                    3  7.3    0.000    0.000    2.085    2.095
 qs_ks_build_kohn_sham_matrix         3  8.3    0.010    0.020    2.085    2.094
 dbcsr_finalize                     304  7.8    0.049    0.061    1.802    1.991
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="506", plot="h2o_32_nrep3_ls", label="(8n/3r/4t)", y=98.409000, yerr=0.000000
PlotPoint: name="507", plot="h2o_32_nrep3_ls_mem", label="(8n/3r/4t)", y=2704.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_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               4.632961E+09
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                   10656
 MPI messages size (bytes):
  total size                         1.149035E+12
  min size                           0.000000E+00
  max size                         203.538048E+06
  average size                     107.829832E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                2304                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304                 768                702038016
   4194304 < size <= 16777216                   0                        0
  16777216 < size                            7584            1148332810224
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast                2                     12.
 MP_Allreduce          705                    128.
 MP_Alltoall           310               12920694.
 MP_ISend             1776               40180424.
 MP_IRecv             1776               40465030.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 265558.
 MP_Allreduce         3049                  15663.
 MP_Sync                 4
 MP_Alltoall            47               46208988.
 MP_SendRecv            45                 115200.
 MP_ISendRecv           45                 115200.
 MP_Wait               528
 MP_ISend              420                 924980.
 MP_IRecv              420                 924528.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.042    0.056   99.895   99.896
 qs_energies                          1  2.0    0.000    0.000   99.072   99.077
 ls_scf                               1  3.0    0.000    0.000   97.130   97.140
 dbcsr_multiply_generic             111  6.7    0.017    0.018   78.208   78.418
 ls_scf_main                          1  4.0    0.000    0.000   62.585   62.585
 multiply_cannon                    111  7.7    0.087    0.157   55.279   60.864
 density_matrix_trs4                  2  5.0    0.002    0.003   55.257   55.347
 multiply_cannon_loop               111  8.7    0.069    0.077   50.892   52.487
 mp_waitall_1                      5436 11.0   27.142   32.690   27.142   32.690
 ls_scf_init_scf                      1  4.0    0.000    0.000   30.958   30.964
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   29.529   29.602
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.349   27.360
 multiply_cannon_multrec            444  9.7   13.865   16.410   20.863   23.164
 make_m2s                           222  7.7    0.004    0.005   18.137   20.507
 make_images                        222  8.7    3.712    4.414   18.076   20.446
 multiply_cannon_metrocomm1         444  9.7    0.002    0.002   11.409   16.903
 multiply_cannon_metrocomm3         444  9.7    0.001    0.001    6.238   14.147
 make_images_data                   222  9.7    0.003    0.004   10.289   12.679
 hybrid_alltoall_any                227 10.6    0.783    3.739   10.129   12.566
 dbcsr_mm_accdrv_process           3003 10.4    0.175    0.346    6.702    7.852
 multiply_cannon_sync_h2d           444  9.7    6.518    7.749    6.518    7.749
 dbcsr_mm_accdrv_process_sort      3003 11.4    6.387    7.502    6.387    7.502
 mp_allgather_i34                   111  8.7    2.621    7.021    2.621    7.021
 arnoldi_extremal                     4  6.8    0.000    0.000    5.884    5.896
 arnoldi_normal_ev                    4  7.8    0.001    0.004    5.884    5.896
 build_subspace                      16  8.4    0.015    0.020    5.497    5.505
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.575    4.694
 mp_sum_l                           807  5.4    2.834    4.607    2.834    4.607
 dbcsr_matrix_vector_mult           304  9.0    0.011    0.020    4.217    4.428
 multiply_cannon_metrocomm4         333  9.7    0.001    0.002    1.680    4.393
 mp_irecv_dv                       1241 11.2    1.663    4.360    1.663    4.360
 dbcsr_matrix_vector_mult_local     304 10.0    3.682    4.165    3.685    4.167
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    3.719    3.802
 make_images_sizes                  222  9.7    0.000    0.000    1.209    3.776
 mp_alltoall_i44                    222 10.7    1.209    3.776    1.209    3.776
 calculate_norms                    792  9.8    3.541    3.676    3.541    3.676
 ls_scf_post                          1  4.0    0.000    0.000    3.587    3.591
 ls_scf_store_result                  1  5.0    0.000    0.000    3.360    3.412
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    1.914    3.328
 dbcsr_finalize                     304  7.8    0.062    0.078    2.202    2.273
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.267    2.268
 rebuild_ks_matrix                    3  7.3    0.000    0.000    2.234    2.235
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.002    2.234    2.235
 dbcsr_merge_all                    275  8.9    0.472    0.523    2.051    2.107
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="508", plot="h2o_32_nrep3_ls", label="(8n/2r/6t)", y=99.896000, yerr=0.000000
PlotPoint: name="509", plot="h2o_32_nrep3_ls_mem", label="(8n/2r/6t)", y=3681.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0ea91c6b73893ebcd66acc6836a089d1c601130e_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               8.706761E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                    4440
 MPI messages size (bytes):
  total size                       770.525954E+09
  min size                           0.000000E+00
  max size                         399.069120E+06
  average size                     173.541888E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                 640                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304                 640                468025344
   4194304 < size <= 16777216                   0                        0
  16777216 < size                            3160             770057961712
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 284111.
 MP_Allreduce         3043                  21950.
 MP_Sync                 4
 MP_Alltoall            47               88727262.
 MP_SendRecv            42                 732600.
 MP_ISendRecv           42                 732600.
 MP_Wait               267
 MP_ISend              180                3337386.
 MP_IRecv              180                3339494.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.087    0.101  108.725  108.725
 qs_energies                          1  2.0    0.000    0.000  107.292  107.307
 ls_scf                               1  3.0    0.000    0.000  104.370  104.384
 dbcsr_multiply_generic             111  6.7    0.023    0.026   77.613   77.706
 ls_scf_main                          1  4.0    0.000    0.000   66.285   66.286
 density_matrix_trs4                  2  5.0    0.002    0.003   56.982   57.044
 multiply_cannon                    111  7.7    0.143    0.216   49.878   51.478
 multiply_cannon_loop               111  8.7    0.067    0.070   46.517   47.654
 ls_scf_init_scf                      1  4.0    0.000    0.000   34.398   34.399
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   32.708   32.726
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   29.875   29.883
 mp_waitall_1                      4527 11.1   22.605   26.142   22.605   26.142
 make_m2s                           222  7.7    0.005    0.005   24.100   24.989
 make_images                        222  8.7    4.567    4.953   23.994   24.882
 multiply_cannon_multrec            444  9.7   17.846   18.660   22.423   23.233
 hybrid_alltoall_any                227 10.6    1.658    3.622   13.151   16.048
 make_images_data                   222  9.7    0.003    0.003   13.367   15.692
 multiply_cannon_metrocomm3         444  9.7    0.001    0.001   10.647   11.310
 multiply_cannon_sync_h2d           444  9.7    8.846    8.898    8.846    8.898
 arnoldi_extremal                     4  6.8    0.000    0.000    7.474    7.484
 arnoldi_normal_ev                    4  7.8    0.002    0.008    7.474    7.484
 build_subspace                      16  8.4    0.026    0.036    6.933    6.945
 dbcsr_matrix_vector_mult           304  9.0    0.016    0.033    5.478    5.621
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    5.248    5.339
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.024    5.265
 dbcsr_matrix_vector_mult_local     304 10.0    4.971    5.259    4.974    5.261
 dbcsr_mm_accdrv_process           1814 10.4    0.230    0.317    4.411    4.535
 dbcsr_mm_accdrv_process_sort      1814 11.4    4.112    4.240    4.112    4.240
 ls_scf_post                          1  4.0    0.000    0.000    3.686    3.700
 make_images_sizes                  222  9.7    0.000    0.000    1.432    3.506
 mp_alltoall_i44                    222 10.7    1.432    3.506    1.432    3.506
 ls_scf_store_result                  1  5.0    0.000    0.000    3.431    3.445
 calculate_norms                    792  9.8    3.242    3.284    3.242    3.284
 dbcsr_finalize                     304  7.8    0.082    0.090    3.085    3.169
 mp_allgather_i34                   111  8.7    1.002    3.047    1.002    3.047
 dbcsr_merge_all                    275  8.9    0.891    0.914    2.872    2.950
 qs_energies_init_hamiltonians        1  3.0    0.001    0.003    2.892    2.892
 dbcsr_complete_redistribute          5  7.6    1.428    1.461    2.759    2.863
 dbcsr_data_release               12724 10.6    2.320    2.826    2.320    2.826
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.621    2.622
 rebuild_ks_matrix                    3  7.3    0.000    0.000    2.555    2.556
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.001    2.555    2.556
 matrix_ls_to_qs                      2  6.0    0.000    0.000    2.400    2.520
 dbcsr_sort_data                    325 11.1    2.439    2.507    2.439    2.507
 dbcsr_new_transposed                 4  7.5    0.245    0.254    2.290    2.304
 dbcsr_frobenius_norm                74  6.6    2.057    2.134    2.208    2.264
 dbcsr_add_d                        103  6.2    0.000    0.000    2.132    2.206
 dbcsr_add_anytype                  103  7.2    0.859    0.892    2.132    2.206
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="510", plot="h2o_32_nrep3_ls", label="(8n/1r/12t)", y=108.725000, yerr=0.000000
PlotPoint: name="511", plot="h2o_32_nrep3_ls_mem", label="(8n/1r/12t)", y=6832.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


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

CommitSHA: 0ea91c6b73893ebcd66acc6836a089d1c601130e
Summary: empty
Status: OK