=== 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: a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa


################# 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 2.6.6, ELPA 2022.11.001, LIBINT 2.6.0, LIBPEXSI 1.2.0,
#              LIBXC 6.2.0, LIBVORI 220621, LIBXSMM 1.17, PLUMED 2.8.2,
#              SIRIUS 7.4.3, SPGLIB 1.16.2
#
# Usage: Source this arch file and then run make as instructed.
#        A full toolchain installation is performed as default.
#        Replace or adapt the "module add" commands below if needed.
#
# Author: Matthias Krack (31.05.2023)
#
# \
   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 ${PWD}/tools/toolchain/install/setup; \
   printf "done\n"; \
   echo "Check the output above for error messages and consistency!"; \
   echo; \
   echo "If everything is OK, you can build a CP2K production binary with"; \
   echo "   make -j ARCH=${this_file%.*} VERSION=${this_file##*.}"; \
   echo; \
   echo "Alternatively, you can add further checks, e.g. for regression testing, with"; \
   echo "   make -j ARCH=${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"; \
   echo; \
   return

# Set options
DO_CHECKS      := no
USE_ACC        := yes
USE_COSMA      := 2.6.6
USE_ELPA       := 2022.11.001
USE_LIBINT     := 2.6.0
USE_LIBPEXSI   := 1.2.0
USE_LIBVORI    := 220621
USE_LIBXC      := 6.2.0
USE_LIBXSMM    := 1.17
USE_PLUMED     := 2.8.2
#USE_QUIP       := 0.9.10
USE_SIRIUS     := 7.4.3
USE_SPGLIB     := 1.16.2
# Only needed for SIRIUS
LIBVDWXC_VER   := 0.4.0
SPFFT_VER      := 1.0.6
SPLA_VER       := 1.5.5
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.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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/01
 job id: 47313028
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/02
 job id: 47313029
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/03
 job id: 47313033
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/04
 job id: 47313034
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/05
 job id: 47313036
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/06
 job id: 47313039
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/07
 job id: 47313040
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/08
 job id: 47313041
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/09
 job id: 47313045
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/10
 job id: 47313060
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/11
 job id: 47313070
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/12
 job id: 47313077
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/13
 job id: 47313087
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/14
 job id: 47313100
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/15
 job id: 47313120
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/16
 job id: 47313140
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/17
 job id: 47313147
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/18
 job id: 47313155
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/19
 job id: 47313157
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/20
 job id: 47313158
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/21
 job id: 47313160
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/22
 job id: 47313161
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/23
 job id: 47313165
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/24
 job id: 47313166
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/25
 job id: 47313170
 --- 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/26
 job id: 47313174
 --- 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 ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: 512 H2O (4 NVE MD steps on 64 nodes)
 input file: benchmarks/QS/00512_H2O/H2O-512_md.inp
 required files: []
 output file: result.log
 # nodes = 64
 # ranks/node = 12
 # threads/rank = 1
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/27
 job id: 47313175
 --- Point ---
 name: 601
 plot: h2o_512_md
 regex: CP2K  
 label: (64n/12r/1t)
 --- Point ---
 name: 602
 plot: h2o_512_md_mem
 regex: Estimated peak process memory 
 label: (64n/12r/1t)
 ~~~~~~~ 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]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_512_md", title="512 H2O (4 NVE MD steps on 64 nodes)", xlabel="Revision", ylabel="Time [s]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_512_md_mem", title="512 H2O (4 NVE MD steps on 64 nodes)", xlabel="Revision", ylabel="Est. peak process memory [MiB]"
=== END PLOTS (description) ===


============ RESULTS ============
 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_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          424                      8.
 MP_Sync                 3
 MP_comm_split           1
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.022    0.036  133.377  133.378
 farming_run                          1  2.0  132.873  132.875  133.348  133.352
 -------------------------------------------------------------------------------


 @@@@@@@@@@ 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               1.469792E+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              230                1103589.
 MP_Allreduce          571                1938539.
 MP_Sync                25
 MP_Alltoall            38                9316958.
 MP_SendRecv           120                 384007.
 MP_ISendRecv           45                 235435.
 MP_Wait               191
 MP_comm_split          10
 MP_ISend              127                3867574.
 MP_IRecv              127                3866554.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.006    0.024  114.668  114.668
 qs_energies                          1  2.0    0.000    0.000  114.463  114.464
 mp2_main                             1  3.0    0.000    0.000  112.305  112.306
 mp2_gpw_main                         1  4.0    0.019    0.025  111.226  111.228
 mp2_ri_gpw_compute_in                1  5.0    0.171    0.172   92.299   92.696
 mp2_ri_gpw_compute_in_loop           1  6.0    0.004    0.006   54.913   55.310
 mp2_eri_3c_integrate_gpw           272  7.0    0.153    0.166   41.361   46.544
 get_2c_integrals                     1  6.0    0.008    0.009   36.569   37.215
 integrate_v_rspace                 273  8.0    0.431    0.445   24.753   29.721
 pw_transfer                       6555 10.6    0.375    0.397   27.362   27.946
 fft_wrap_pw1pw2                   5465 11.4    0.045    0.047   26.033   26.542
 grid_integrate_task_list           273  9.0   20.571   26.015   20.571   26.015
 fft_wrap_pw1pw2_100               2178 12.4    1.175    1.327   23.556   24.068
 compute_2c_integrals                 1  7.0    0.002    0.002   19.455   19.456
 compute_2c_integrals_loop_lm         1  8.0    0.003    0.003   18.826   19.097
 mp2_eri_2c_integrate_gpw             1  9.0    2.391    2.440   18.823   19.093
 rpa_ri_compute_en                    1  5.0    0.019    0.021   18.818   19.038
 cp_fm_cholesky_decompose            12  8.2   17.094   17.743   17.094   17.743
 cholesky_decomp                      1  7.0    0.000    0.000   15.958   16.601
 fft3d_s                           5443 13.4   16.172   16.556   16.193   16.577
 ao_to_mo_and_store_B_mult_1        272  7.0   10.719   15.303   10.719   15.303
 calculate_wavefunction             272  8.0    5.407    5.565   12.532   13.146
 rpa_num_int                          1  6.0    0.000    0.000   10.688   10.697
 rpa_num_int_RPA_matrix_operati       8  7.0    0.000    0.000   10.667   10.692
 calc_mat_Q                           8  8.0    0.000    0.000    9.489    9.580
 contract_S_to_Q                      8  9.0    0.000    0.000    8.909    9.001
 parallel_gemm_fm                    14  9.1    0.000    0.000    8.491    8.610
 parallel_gemm_fm_cosma              14 10.1    8.491    8.610    8.491    8.610
 calc_potential_gpw                 544  9.5    0.005    0.006    8.222    8.580
 mp2_eri_2c_integrate_gpw_pot_l     272 10.0    0.001    0.002    8.175    8.418
 potential_pw2rs                    545 10.0    0.107    0.110    7.677    8.314
 collocate_single_gaussian          272 10.0    0.039    0.041    7.447    7.668
 create_integ_mat                     1  6.0    0.014    0.027    7.638    7.647
 array2fm                             1  7.0    0.000    0.000    6.660    7.095
 pw_scatter_s                      2720 13.7    4.422    4.542    4.422    4.542
 pw_gather_s                       2722 13.2    3.858    4.249    3.858    4.249
 array2fm_buffer_send                 1  8.0    2.965    3.151    2.965    3.151
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="10", plot="h2o_32_ri_rpa_mp2", label="RI-RPA (8n/2r/6t)", y=111.226281, yerr=0.000000
PlotPoint: name="11", plot="h2o_32_ri_rpa_mp2_mem", label="RI-RPA (8n/2r/6t)", y=2814.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_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          424                      9.
 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    0.038  396.018  396.019
 farming_run                          1  2.0  395.005  395.009  395.975  395.977
 -------------------------------------------------------------------------------


 @@@@@@@@@@ Run number: 2 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32             16777216       0.0%      0.0%    100.0%
 flops    14 x    32 x    32            565182464       0.0%      0.0%    100.0%
 flops    29 x    32 x    32            585367552       0.0%      0.0%    100.0%
 flops    14 x    14 x    32            626196480       0.0%      0.0%    100.0%
 flops    29 x    14 x    32            638582784       0.0%      0.0%    100.0%
 flops    14 x    29 x    32            638582784       0.0%      0.0%    100.0%
 flops    29 x    29 x    32            682057728       0.0%      0.0%    100.0%
 flops    14 x    32 x    14         897827141120       0.0%      0.0%    100.0%
 flops    29 x    32 x    14         929989394432       0.0%      0.0%    100.0%
 flops    14 x    32 x    29         929989394432       0.0%      0.0%    100.0%
 flops    29 x    32 x    29         963203301376       0.0%      0.0%    100.0%
 flops    32 x    32 x    14        1693481172992       0.0%      0.0%    100.0%
 flops    32 x    32 x    29        1753962643456       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         7.172206E+12       0.0%      0.0%    100.0%
 flops max/rank                    150.696064E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          249788822       0.0%      0.0%    100.0%
 number of processed stacks                 98736       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    2529.9
 marketing flops                     7.174951E+12
 -------------------------------------------------------------------------------
 # multiplications                           1140
 max memory usage/rank               1.230086E+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              743                 386399.
 MP_Allreduce         2021                  21391.
 MP_Sync                37
 MP_Alltoall            77                3696676.
 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    0.012    0.030  208.363  208.363
 qs_energies                          1  2.0    0.001    0.008  208.124  208.148
 scf_env_do_scf                       1  3.0    0.000    0.000  105.880  105.880
 qs_ks_update_qs_env                  5  5.0    0.000    0.000  104.982  104.991
 rebuild_ks_matrix                    4  6.0    0.000    0.000  104.981  104.990
 qs_ks_build_kohn_sham_matrix         4  7.0    0.056    0.065  104.981  104.990
 hfx_ks_matrix                        4  8.0    0.001    0.001  104.590  104.595
 integrate_four_center                4  9.0    0.144    0.450  104.590  104.594
 mp2_main                             1  3.0    0.004    0.039  101.952  101.977
 mp2_gpw_main                         1  4.0    0.034    0.061  101.029  101.057
 integrate_four_center_main           4 10.0    0.092    0.573   96.453   98.883
 integrate_four_center_bin          264 11.0   96.361   98.866   96.361   98.866
 init_scf_loop                        1  4.0    0.000    0.000   91.752   91.752
 mp2_ri_gpw_compute_in                1  5.0    0.065    0.074   74.311   75.474
 mp2_ri_gpw_compute_in_loop           1  6.0    0.002    0.002   53.959   55.123
 mp2_eri_3c_integrate_gpw            91  7.0    0.144    0.163   41.797   46.988
 integrate_v_rspace                  95  8.0    0.395    0.568   28.184   33.333
 pw_transfer                       2240 10.6    0.143    0.167   29.940   30.489
 fft_wrap_pw1pw2                   1868 11.4    0.018    0.020   28.945   29.540
 ao_to_mo_and_store_B_mult_1         91  7.0   10.484   29.476   10.484   29.476
 grid_integrate_task_list            95  9.0   23.469   28.730   23.469   28.730
 mp2_ri_gpw_compute_en                1  5.0    0.060    0.085   26.567   28.283
 fft_wrap_pw1pw2_100                730 12.4    1.283    1.455   26.657   27.268
 mp2_ri_gpw_compute_en_RI_loop        1  6.0    1.841    1.900   24.665   24.674
 get_2c_integrals                     1  6.0    0.000    0.001   20.261   20.287
 compute_2c_integrals                 1  7.0    0.002    0.003   19.247   19.252
 compute_2c_integrals_loop_lm         1  8.0    0.001    0.001   18.882   19.117
 mp2_eri_2c_integrate_gpw             1  9.0    1.739    1.845   18.880   19.116
 fft3d_s                           1823 13.4   18.455   19.091   18.468   19.104
 scf_env_do_scf_inner_loop            4  4.0    0.000    0.000   14.126   14.126
 calculate_wavefunction              91  8.0    2.011    2.051    9.741    9.963
 mp2_ri_gpw_compute_en_expansio     172  7.0    0.559    0.584    8.776    9.244
 potential_pw2rs                    186 10.0    0.033    0.035    8.665    9.157
 local_gemm                         172  8.0    8.216    8.680    8.216    8.680
 mp2_eri_2c_integrate_gpw_pot_l      91 10.0    0.001    0.001    8.248    8.631
 collocate_single_gaussian           91 10.0    0.017    0.020    7.908    8.130
 calc_potential_gpw                 182  9.5    0.002    0.002    7.894    8.067
 mp2_ri_gpw_compute_en_comm          22  7.0    0.504    0.523    7.652    8.014
 mp2_ri_gpw_compute_en_ener         172  7.0    6.351    6.427    6.351    6.427
 mp_sendrecv_dm3                   2068  8.0    5.673    5.997    5.673    5.997
 mp_sync                             37 10.5    2.806    5.735    2.806    5.735
 pw_gather_s                        912 13.2    4.917    5.528    4.917    5.528
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="20", plot="h2o_32_ri_rpa_mp2", label="RI-MP2 (8n/6r/2t)", y=101.030704, 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/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_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             451.407872E+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        10329                    270.
 MP_Sync               530
 MP_Alltoall          2083                 455331.
 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    0.025    0.045   53.618   53.619
 qs_mol_dyn_low                       1  2.0    0.003    0.003   53.364   53.371
 qs_forces                           11  3.9    0.002    0.003   53.303   53.304
 qs_energies                         11  4.9    0.001    0.001   51.806   51.822
 scf_env_do_scf                      11  5.9    0.000    0.001   45.614   45.614
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   43.469   43.470
 qs_scf_new_mos                     108  7.5    0.000    0.001   33.010   33.305
 qs_scf_loop_do_ot                  108  8.5    0.000    0.001   33.009   33.304
 dbcsr_multiply_generic            2286 12.5    0.093    0.099   32.686   33.097
 ot_scf_mini                        108  9.5    0.002    0.002   31.401   31.581
 multiply_cannon                   2286 13.5    0.188    0.195   25.456   27.078
 multiply_cannon_loop              2286 14.5    1.480    1.582   24.718   26.348
 velocity_verlet                     10  3.0    0.001    0.001   25.773   25.773
 ot_mini                            108 10.5    0.001    0.001   18.862   19.121
 qs_ot_get_derivative               108 11.5    0.001    0.001   15.992   16.182
 mp_waitall_1                    245248 16.5    8.082   14.066    8.082   14.066
 multiply_cannon_metrocomm3       54864 15.5    0.068    0.074    5.658   12.411
 multiply_cannon_multrec          54864 15.5    4.295    6.560    7.500   10.842
 qs_ot_get_p                        119 10.4    0.001    0.001    7.981    8.306
 rebuild_ks_matrix                  119  8.3    0.000    0.000    8.061    8.213
 qs_ks_build_kohn_sham_matrix       119  9.3    0.010    0.011    8.060    8.212
 qs_ks_update_qs_env                119  7.6    0.001    0.001    7.096    7.237
 multiply_cannon_sync_h2d         54864 15.5    5.955    6.975    5.955    6.975
 mp_sum_l                          7287 12.8    5.012    6.639    5.012    6.639
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    5.411    5.867
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    5.457    5.568
 qs_ot_p2m_diag                      50 11.0    0.004    0.006    5.332    5.379
 init_scf_run                        11  5.9    0.000    0.001    4.795    4.796
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    4.795    4.795
 sum_up_and_integrate               119 10.3    0.012    0.014    4.643    4.651
 integrate_v_rspace                 119 11.3    0.002    0.003    4.630    4.641
 qs_rho_update_rho_low              119  7.7    0.001    0.001    4.465    4.583
 calculate_rho_elec                 119  8.7    0.012    0.017    4.464    4.583
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    4.568    4.569
 dbcsr_mm_accdrv_process          76910 16.1    1.125    1.827    3.126    4.432
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    4.339    4.339
 cp_fm_redistribute_end              50 14.0    2.216    4.314    2.222    4.316
 cp_fm_diag_elpa_base                50 14.0    2.088    4.204    2.092    4.212
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.894    3.075
 apply_single                       119 13.6    0.000    0.000    2.893    3.075
 rs_pw_transfer                     974 11.9    0.012    0.013    2.877    3.038
 calculate_dm_sparse                119  9.5    0.000    0.001    2.823    2.972
 multiply_cannon_metrocomm1       54864 15.5    0.053    0.058    1.652    2.656
 ot_diis_step                       108 11.5    0.006    0.006    2.613    2.614
 jit_kernel_multiply                 13 15.8    1.941    2.537    1.941    2.537
 density_rs2pw                      119  9.7    0.004    0.005    2.409    2.533
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.502    2.507
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    2.377    2.432
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.242    2.244
 acc_transpose_blocks             54864 15.5    0.226    0.249    1.731    2.206
 wfi_extrapolate                     11  7.9    0.001    0.001    2.175    2.175
 init_scf_loop                       11  6.9    0.000    0.000    2.125    2.126
 grid_integrate_task_list           119 12.3    2.018    2.113    2.018    2.113
 pw_transfer                       1439 11.6    0.052    0.057    1.955    2.031
 make_m2s                          4572 13.5    0.054    0.056    1.910    1.979
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.928    1.973
 potential_pw2rs                    119 12.3    0.004    0.004    1.958    1.972
 fft_wrap_pw1pw2                   1201 12.6    0.007    0.007    1.879    1.957
 make_images                       4572 14.5    0.133    0.138    1.827    1.896
 mp_sum_d                          4135 12.0    1.227    1.841    1.227    1.841
 fft3d_ps                          1201 14.6    0.370    0.473    1.519    1.593
 mp_alltoall_d11v                  2130 13.8    1.347    1.530    1.347    1.530
 mp_waitany                       12084 13.8    1.328    1.495    1.328    1.495
 fft_wrap_pw1pw2_140                487 13.2    0.187    0.204    1.400    1.476
 grid_collocate_task_list           119  9.7    1.358    1.424    1.358    1.424
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.378    1.408
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="100", plot="h2o_64_md", label="(8n/12r/1t)", y=53.619000, yerr=0.000000
PlotPoint: name="101", plot="h2o_64_md_mem", label="(8n/12r/1t)", y=430.181818, yerr=1.113404
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/04/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                     57.173320E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               3066240       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      47.9
 marketing flops                     2.107592E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             486.572032E+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        10306                    303.
 MP_Sync                54
 MP_Alltoall          2060                 993022.
 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    0.012    0.028   40.313   40.314
 qs_mol_dyn_low                       1  2.0    0.003    0.003   40.059   40.067
 qs_forces                           11  3.9    0.002    0.003   39.085   39.087
 qs_energies                         11  4.9    0.001    0.001   37.357   37.360
 scf_env_do_scf                      11  5.9    0.000    0.001   32.034   32.035
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.007   29.493   29.494
 dbcsr_multiply_generic            2286 12.5    0.102    0.106   21.556   21.918
 qs_scf_new_mos                     108  7.5    0.001    0.001   20.096   20.345
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   20.095   20.344
 ot_scf_mini                        108  9.5    0.002    0.003   19.206   19.382
 velocity_verlet                     10  3.0    0.001    0.001   19.328   19.348
 multiply_cannon                   2286 13.5    0.207    0.216   16.524   18.158
 multiply_cannon_loop              2286 14.5    0.909    0.973   15.403   16.750
 ot_mini                            108 10.5    0.001    0.001   11.837   12.074
 mp_waitall_1                    200699 16.5    5.726   11.015    5.726   11.015
 qs_ot_get_derivative               108 11.5    0.001    0.001    9.371    9.549
 multiply_cannon_metrocomm3       27432 15.5    0.067    0.069    4.167    9.510
 multiply_cannon_multrec          27432 15.5    2.011    4.550    5.971    8.765
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.275    7.410
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    7.274    7.410
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.404    6.528
 dbcsr_mm_accdrv_process          47894 16.0    3.006    5.074    3.889    5.753
 qs_ot_get_p                        119 10.4    0.001    0.001    4.476    4.703
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    3.605    4.435
 sum_up_and_integrate               119 10.3    0.025    0.028    4.241    4.248
 integrate_v_rspace                 119 11.3    0.002    0.003    4.216    4.225
 init_scf_run                        11  5.9    0.000    0.001    4.116    4.117
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    4.116    4.116
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    3.062    4.102
 apply_single                       119 13.6    0.000    0.000    3.062    4.102
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.981    4.018
 calculate_rho_elec                 119  8.7    0.021    0.024    3.981    4.018
 mp_sum_l                          7287 12.8    2.027    3.968    2.027    3.968
 rs_pw_transfer                     974 11.9    0.010    0.011    2.737    3.208
 qs_ot_p2m_diag                      50 11.0    0.009    0.013    3.035    3.054
 multiply_cannon_sync_h2d         27432 15.5    2.189    2.856    2.189    2.856
 make_m2s                          4572 13.5    0.052    0.054    2.559    2.782
 density_rs2pw                      119  9.7    0.004    0.004    2.255    2.741
 make_images                       4572 14.5    0.200    0.238    2.470    2.689
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.606    2.607
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    2.597    2.597
 init_scf_loop                       11  6.9    0.000    0.000    2.520    2.521
 ot_diis_step                       108 11.5    0.010    0.011    2.416    2.416
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    2.193    2.285
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    2.262    2.263
 cp_fm_redistribute_end              50 14.0    1.148    2.236    1.151    2.239
 cp_fm_diag_elpa_base                50 14.0    1.056    2.146    1.084    2.182
 calculate_dm_sparse                119  9.5    0.000    0.001    2.043    2.121
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.061    2.064
 pw_transfer                       1439 11.6    0.066    0.070    1.969    2.001
 potential_pw2rs                    119 12.3    0.006    0.007    1.959    1.969
 grid_integrate_task_list           119 12.3    1.834    1.959    1.834    1.959
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.877    1.912
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.851    1.893
 jit_kernel_multiply                  9 16.2    0.830    1.881    0.830    1.881
 prepare_preconditioner              11  7.9    0.000    0.000    1.598    1.625
 make_preconditioner                 11  8.9    0.000    0.000    1.598    1.625
 acc_transpose_blocks             27432 15.5    0.110    0.116    1.264    1.601
 make_images_data                  4572 15.5    0.045    0.051    1.179    1.601
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.499    1.562
 hybrid_alltoall_any               4725 16.4    0.051    0.112    1.028    1.530
 fft_wrap_pw1pw2_140                487 13.2    0.203    0.212    1.478    1.511
 fft3d_ps                          1201 14.6    0.522    0.578    1.427    1.454
 wfi_extrapolate                     11  7.9    0.001    0.001    1.449    1.449
 grid_collocate_task_list           119  9.7    1.273    1.410    1.273    1.410
 mp_alltoall_d11v                  2130 13.8    1.190    1.361    1.190    1.361
 mp_allgather_i34                  2286 14.5    0.563    1.347    0.563    1.347
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.262    1.270
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.177    1.223
 rs_pw_transfer_RS2PW_140           130 11.5    0.140    0.149    0.566    1.038
 mp_sum_d                          4135 12.0    0.573    1.028    0.573    1.028
 mp_waitany                        5720 13.7    0.546    1.022    0.546    1.022
 mp_sum_dm                          438  4.9    0.972    1.020    0.972    1.020
 acc_transpose_blocks_kernels     27432 16.5    0.182    0.271    0.718    0.966
 md_write_output                     11  3.9    0.017    0.774    0.022    0.961
 md_output                           10  3.0    0.000    0.000    0.023    0.959
 update_particle_set                 20  4.0    0.000    0.000    0.937    0.957
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.932    0.946
 qs_energies_init_hamiltonians       11  5.9    0.001    0.005    0.940    0.941
 make_images_sizes                 4572 15.5    0.005    0.005    0.552    0.809
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="102", plot="h2o_64_md", label="(8n/6r/2t)", y=40.314000, yerr=0.000000
PlotPoint: name="103", plot="h2o_64_md_mem", label="(8n/6r/2t)", y=462.181818, yerr=1.465865
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_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             520.429568E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                  950976
 MPI messages size (bytes):
  total size                       203.844256E+09
  min size                           0.000000E+00
  max size                           1.638400E+06
  average size                     214.352688E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192              253512               2076770304
      8192 < size <=    32768              179424               2939682816
     32768 < size <=   131072              181440              14863564800
    131072 < size <=  4194304              330176             183964913216
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3622                  63497.
 MP_Allreduce        10155                    305.
 MP_Sync                54
 MP_Alltoall          1821                2493177.
 MP_SendRecv         11067                  57667.
 MP_ISendRecv        11067                  57667.
 MP_Wait             21987
 MP_ISend             9880                  92618.
 MP_IRecv             9880                  92618.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.053    0.103   34.660   34.661
 qs_mol_dyn_low                       1  2.0    0.003    0.003   34.212   34.233
 qs_forces                           11  3.9    0.003    0.010   32.787   32.787
 qs_energies                         11  4.9    0.002    0.014   31.183   31.186
 scf_env_do_scf                      11  5.9    0.001    0.001   26.372   26.372
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   23.750   23.750
 velocity_verlet                     10  3.0    0.001    0.001   17.113   17.157
 dbcsr_multiply_generic            2286 12.5    0.094    0.096   16.571   16.692
 qs_scf_new_mos                     108  7.5    0.001    0.001   15.283   15.301
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   15.282   15.301
 ot_scf_mini                        108  9.5    0.002    0.003   14.536   14.552
 multiply_cannon                   2286 13.5    0.196    0.203   13.138   13.880
 multiply_cannon_loop              2286 14.5    0.638    0.663   12.335   13.108
 ot_mini                            108 10.5    0.001    0.001    8.908    8.925
 qs_ot_get_derivative               108 11.5    0.001    0.001    7.380    7.397
 multiply_cannon_multrec          18288 15.5    1.967    2.983    6.777    7.152
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.530    6.556
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    6.530    6.556
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.766    5.791
 dbcsr_mm_accdrv_process          38222 16.0    3.981    5.436    4.724    5.533
 mp_waitall_1                    158411 16.6    2.804    4.117    2.804    4.117
 sum_up_and_integrate               119 10.3    0.031    0.032    4.100    4.103
 integrate_v_rspace                 119 11.3    0.003    0.003    4.069    4.076
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.630    3.638
 calculate_rho_elec                 119  8.7    0.031    0.032    3.629    3.637
 init_scf_run                        11  5.9    0.000    0.001    3.565    3.565
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.565    3.565
 qs_ot_get_p                        119 10.4    0.001    0.001    3.412    3.438
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.776    3.395
 rs_pw_transfer                     974 11.9    0.009    0.010    2.474    2.732
 multiply_cannon_metrocomm3       18288 15.5    0.044    0.046    1.531    2.664
 init_scf_loop                       11  6.9    0.001    0.005    2.603    2.604
 density_rs2pw                      119  9.7    0.004    0.004    2.107    2.390
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.054    2.378
 apply_single                       119 13.6    0.000    0.000    2.054    2.378
 qs_ot_p2m_diag                      50 11.0    0.012    0.013    2.318    2.323
 calculate_first_density_matrix       1  7.0    0.001    0.008    2.267    2.268
 cp_dbcsr_syevd                      50 12.0    0.003    0.004    2.051    2.051
 make_m2s                          4572 13.5    0.044    0.045    1.873    2.013
 pw_transfer                       1439 11.6    0.066    0.069    1.968    1.985
 make_images                       4572 14.5    0.191    0.202    1.787    1.927
 grid_integrate_task_list           119 12.3    1.803    1.893    1.803    1.893
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.875    1.893
 calculate_dm_sparse                119  9.5    0.000    0.000    1.850    1.861
 jit_kernel_multiply                 10 16.0    0.691    1.854    0.691    1.854
 potential_pw2rs                    119 12.3    0.007    0.008    1.843    1.850
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.793    1.802
 cp_fm_diag_elpa_base                50 14.0    1.769    1.779    1.791    1.800
 prepare_preconditioner              11  7.9    0.000    0.000    1.786    1.787
 make_preconditioner                 11  8.9    0.000    0.001    1.786    1.787
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.634    1.721
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.691    1.693
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.634    1.644
 multiply_cannon_sync_h2d         18288 15.5    1.380    1.587    1.380    1.587
 mp_sum_l                          7287 12.8    1.185    1.548    1.185    1.548
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.535    1.545
 ot_diis_step                       108 11.5    0.011    0.011    1.501    1.501
 fft_wrap_pw1pw2_140                487 13.2    0.253    0.260    1.478    1.496
 mp_sum_dm                          438  4.9    1.388    1.434    1.388    1.434
 md_write_output                     11  3.9    0.023    0.702    0.046    1.413
 update_particle_set                 20  4.0    0.000    0.000    1.365    1.409
 grid_collocate_task_list           119  9.7    1.247    1.398    1.247    1.398
 fft3d_ps                          1201 14.6    0.531    0.549    1.364    1.381
 acc_transpose_blocks             18288 15.5    0.076    0.078    1.255    1.271
 wfi_extrapolate                     11  7.9    0.001    0.001    1.238    1.238
 md_output                           10  3.0    0.000    0.000    0.040    1.202
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.196    1.202
 make_images_data                  4572 15.5    0.045    0.049    0.854    1.010
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    0.948    0.949
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.919    0.936
 hybrid_alltoall_any               4725 16.4    0.055    0.113    0.734    0.927
 mp_alltoall_d11v                  2130 13.8    0.726    0.856    0.726    0.856
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.837    0.839
 mp_waitany                        9880 13.7    0.537    0.832    0.537    0.832
 acc_transpose_blocks_kernels     18288 16.5    0.210    0.221    0.806    0.817
 rs_pw_transfer_RS2PW_140           130 11.5    0.119    0.122    0.522    0.792
 cp_fm_cholesky_invert               11 10.9    0.765    0.770    0.765    0.770
 mp_alltoall_z22v                  1201 16.6    0.681    0.754    0.681    0.754
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.654    0.738
 write_trajectory                    44  4.9    0.023    0.704    0.023    0.710
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="104", plot="h2o_64_md", label="(8n/4r/3t)", y=34.661000, yerr=0.000000
PlotPoint: name="105", plot="h2o_64_md_mem", label="(8n/4r/3t)", y=495.727273, yerr=1.600620
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_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             555.302912E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1042416
 MPI messages size (bytes):
  total size                       150.443262E+09
  min size                           0.000000E+00
  max size                           1.188816E+06
  average size                     144.321719E+03
 MPI breakdown and total messages size (bytes):
             size <=      128              228256                        0
       128 < size <=     8192              126888               1039466496
      8192 < size <=    32768              191472               3137077248
     32768 < size <=   131072              295800              25899827200
    131072 < size <=  4194304              200000             120367247040
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3622                  63496.
 MP_Allreduce        10154                    346.
 MP_Sync                54
 MP_Alltoall          1582                2412273.
 MP_SendRecv          8211                  74133.
 MP_ISendRecv         8211                  74133.
 MP_Wait             16271
 MP_ISend             7280                 135929.
 MP_IRecv             7280                 135929.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.016    0.036   36.468   36.469
 qs_mol_dyn_low                       1  2.0    0.003    0.004   36.262   36.269
 qs_forces                           11  3.9    0.002    0.003   35.172   35.173
 qs_energies                         11  4.9    0.001    0.004   33.436   33.443
 scf_env_do_scf                      11  5.9    0.001    0.002   28.438   28.440
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   24.875   24.876
 velocity_verlet                     10  3.0    0.001    0.001   19.049   19.094
 dbcsr_multiply_generic            2286 12.5    0.098    0.102   18.169   18.287
 qs_scf_new_mos                     108  7.5    0.001    0.001   16.397   16.444
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   16.396   16.443
 ot_scf_mini                        108  9.5    0.002    0.003   15.462   15.509
 multiply_cannon                   2286 13.5    0.227    0.274   14.583   15.003
 multiply_cannon_loop              2286 14.5    0.949    0.979   13.633   14.023
 ot_mini                            108 10.5    0.001    0.001    9.363    9.422
 multiply_cannon_multrec          27432 15.5    2.376    3.070    8.627    8.967
 qs_ot_get_derivative               108 11.5    0.001    0.001    7.527    7.573
 dbcsr_mm_accdrv_process          47916 15.9    5.296    6.904    6.158    7.373
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.635    6.686
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    6.634    6.686
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.888    5.928
 sum_up_and_integrate               119 10.3    0.035    0.037    3.820    3.828
 integrate_v_rspace                 119 11.3    0.003    0.003    3.785    3.793
 init_scf_run                        11  5.9    0.000    0.001    3.642    3.643
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.642    3.643
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.585    3.613
 calculate_rho_elec                 119  8.7    0.040    0.046    3.585    3.612
 qs_ot_get_p                        119 10.4    0.001    0.001    3.478    3.553
 init_scf_loop                       11  6.9    0.001    0.007    3.543    3.544
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.784    3.184
 prepare_preconditioner              11  7.9    0.000    0.000    2.640    2.649
 make_preconditioner                 11  8.9    0.000    0.001    2.640    2.649
 make_full_inverse_cholesky          11  9.9    0.000    0.000    2.244    2.568
 mp_waitall_1                    137007 16.6    1.894    2.559    1.894    2.559
 make_m2s                          4572 13.5    0.054    0.055    2.209    2.330
 calculate_first_density_matrix       1  7.0    0.000    0.002    2.249    2.253
 make_images                       4572 14.5    0.271    0.332    2.102    2.222
 rs_pw_transfer                     974 11.9    0.009    0.009    2.020    2.212
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.057    2.188
 apply_single                       119 13.6    0.000    0.000    2.056    2.188
 qs_ot_p2m_diag                      50 11.0    0.015    0.023    2.173    2.181
 density_rs2pw                      119  9.7    0.004    0.004    1.970    2.161
 calculate_dm_sparse                119  9.5    0.000    0.000    2.037    2.090
 pw_transfer                       1439 11.6    0.066    0.070    2.013    2.048
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.919    1.959
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.934    1.959
 grid_integrate_task_list           119 12.3    1.833    1.931    1.833    1.931
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.857    1.858
 jit_kernel_multiply                 10 16.1    0.802    1.826    0.802    1.826
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.804    1.805
 ot_diis_step                       108 11.5    0.012    0.012    1.794    1.794
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.633    1.647
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.615    1.625
 cp_fm_diag_elpa_base                50 14.0    1.580    1.600    1.613    1.623
 fft_wrap_pw1pw2_140                487 13.2    0.289    0.302    1.578    1.621
 potential_pw2rs                    119 12.3    0.009    0.010    1.559    1.566
 multiply_cannon_metrocomm3       27432 15.5    0.038    0.040    0.831    1.519
 acc_transpose_blocks             27432 15.5    0.111    0.113    1.474    1.501
 fft3d_ps                          1201 14.6    0.557    0.610    1.358    1.383
 grid_collocate_task_list           119  9.7    1.250    1.363    1.250    1.363
 wfi_extrapolate                     11  7.9    0.001    0.001    1.337    1.337
 mp_sum_l                          7287 12.8    0.960    1.275    0.960    1.275
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.231    1.241
 cp_fm_upper_to_full                 72 14.2    0.805    1.150    0.805    1.150
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.112    1.130
 mp_sum_dm                          438  4.9    1.053    1.105    1.053    1.105
 qs_energies_init_hamiltonians       11  5.9    0.000    0.001    1.086    1.087
 md_write_output                     11  3.9    0.016    0.368    0.046    1.077
 md_output                           10  3.0    0.000    0.000    0.047    1.075
 update_particle_set                 20  4.0    0.000    0.000    1.029    1.074
 dbcsr_complete_redistribute        329 12.2    0.120    0.146    0.776    1.042
 multiply_cannon_sync_h2d         27432 15.5    0.997    1.037    0.997    1.037
 make_images_data                  4572 15.5    0.045    0.048    0.871    1.003
 mp_alltoall_d11v                  2130 13.8    0.746    0.927    0.746    0.927
 hybrid_alltoall_any               4725 16.4    0.062    0.151    0.752    0.924
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.792    0.870
 acc_transpose_blocks_kernels     27432 16.5    0.269    0.277    0.836    0.855
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.840    0.846
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    0.569    0.833
 cp_fm_cholesky_invert               11 10.9    0.805    0.808    0.805    0.808
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="106", plot="h2o_64_md", label="(8n/3r/4t)", y=36.469000, yerr=0.000000
PlotPoint: name="107", plot="h2o_64_md_mem", label="(8n/3r/4t)", y=528.363636, yerr=2.346089
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/07/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                    117.977176E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               1384136       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     106.2
 marketing flops                     2.107587E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             596.946944E+06
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  219456
 MPI messages size (bytes):
  total size                        97.042514E+09
  min size                           0.000000E+00
  max size                           3.276800E+06
  average size                     442.195750E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768              101892               3336634368
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304              116112              93705670464
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         8156                     20.
 MP_Alltoall          8655                  64935.
 MP_ISend            36532                 168375.
 MP_IRecv            36532                 168349.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3622                  63495.
 MP_Allreduce        10154                    346.
 MP_Sync                54
 MP_Alltoall          1582                3682667.
 MP_SendRecv          5355                  94533.
 MP_ISendRecv         5355                  94533.
 MP_Wait             11335
 MP_ISend             5200                 225425.
 MP_IRecv             5200                 225425.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.024    0.051   29.238   29.239
 qs_mol_dyn_low                       1  2.0    0.003    0.003   28.934   28.942
 qs_forces                           11  3.9    0.002    0.002   28.710   28.710
 qs_energies                         11  4.9    0.001    0.001   26.988   26.991
 scf_env_do_scf                      11  5.9    0.000    0.001   21.887   21.887
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   19.341   19.342
 velocity_verlet                     10  3.0    0.001    0.001   14.798   14.811
 dbcsr_multiply_generic            2286 12.5    0.091    0.096   12.521   12.592
 qs_scf_new_mos                     108  7.5    0.001    0.001   11.196   11.224
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   11.195   11.224
 ot_scf_mini                        108  9.5    0.002    0.002   10.503   10.531
 multiply_cannon                   2286 13.5    0.227    0.238    9.881   10.362
 multiply_cannon_loop              2286 14.5    0.332    0.344    8.961    9.147
 multiply_cannon_multrec           9144 15.5    1.669    1.904    6.048    6.317
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.080    6.102
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    6.079    6.102
 ot_mini                            108 10.5    0.001    0.001    5.858    5.894
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.420    5.440
 qs_ot_get_derivative               108 11.5    0.001    0.001    4.536    4.564
 dbcsr_mm_accdrv_process          12550 15.8    3.159    4.007    4.278    4.362
 sum_up_and_integrate               119 10.3    0.038    0.042    3.741    3.745
 integrate_v_rspace                 119 11.3    0.003    0.003    3.703    3.708
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.614    3.623
 calculate_rho_elec                 119  8.7    0.060    0.061    3.613    3.623
 init_scf_run                        11  5.9    0.000    0.001    3.618    3.618
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    3.617    3.618
 qs_ot_get_p                        119 10.4    0.001    0.001    2.851    2.901
 init_scf_loop                       11  6.9    0.000    0.000    2.526    2.527
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.450    2.451
 pw_transfer                       1439 11.6    0.066    0.071    2.102    2.113
 density_rs2pw                      119  9.7    0.004    0.004    1.901    2.048
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    2.008    2.019
 make_m2s                          4572 13.5    0.034    0.035    1.812    1.986
 jit_kernel_multiply                 10 15.8    1.081    1.977    1.081    1.977
 mp_waitall_1                    115863 16.7    1.496    1.961    1.496    1.961
 grid_integrate_task_list           119 12.3    1.860    1.957    1.860    1.957
 rs_pw_transfer                     974 11.9    0.008    0.008    1.767    1.905
 qs_ot_p2m_diag                      50 11.0    0.022    0.023    1.899    1.903
 make_images                       4572 14.5    0.268    0.304    1.722    1.895
 calculate_dm_sparse                119  9.5    0.000    0.000    1.786    1.803
 prepare_preconditioner              11  7.9    0.000    0.000    1.770    1.777
 make_preconditioner                 11  8.9    0.000    0.000    1.770    1.777
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.705    1.707
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.700    1.701
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.662    1.689
 fft_wrap_pw1pw2_140                487 13.2    0.365    0.374    1.636    1.651
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    1.604    1.619
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.535    1.543
 potential_pw2rs                    119 12.3    0.010    0.011    1.447    1.451
 grid_collocate_task_list           119  9.7    1.298    1.415    1.298    1.415
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.400    1.409
 cp_fm_diag_elpa_base                50 14.0    1.372    1.389    1.398    1.407
 fft3d_ps                          1201 14.6    0.563    0.574    1.341    1.354
 ot_diis_step                       108 11.5    0.012    0.013    1.306    1.307
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    1.270    1.271
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.193    1.208
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    1.175    1.194
 apply_single                       119 13.6    0.000    0.000    1.175    1.194
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.188    1.192
 wfi_extrapolate                     11  7.9    0.001    0.001    1.115    1.115
 hybrid_alltoall_any               4725 16.4    0.063    0.175    0.826    1.070
 make_images_data                  4572 15.5    0.039    0.042    0.847    1.062
 acc_transpose_blocks              9144 15.5    0.038    0.039    0.953    0.962
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.001    0.867    0.917
 mp_alltoall_d11v                  2130 13.8    0.804    0.902    0.804    0.902
 cp_fm_cholesky_invert               11 10.9    0.875    0.878    0.875    0.878
 multiply_cannon_sync_h2d          9144 15.5    0.714    0.800    0.714    0.800
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.785    0.787
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    0.726    0.779
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.742    0.752
 acc_transpose_blocks_kernels      9144 16.5    0.117    0.120    0.709    0.711
 multiply_cannon_metrocomm3        9144 15.5    0.019    0.019    0.327    0.695
 mp_allgather_i34                  2286 14.5    0.255    0.687    0.255    0.687
 mp_alltoall_z22v                  1201 16.6    0.653    0.680    0.653    0.680
 mp_waitany                        5200 13.7    0.484    0.602    0.484    0.602
 jit_kernel_transpose                 5 15.6    0.592    0.594    0.592    0.594
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="108", plot="h2o_64_md", label="(8n/2r/6t)", y=29.239000, yerr=0.000000
PlotPoint: name="109", plot="h2o_64_md_mem", label="(8n/2r/6t)", y=566.363636, yerr=4.518100
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_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             753.213440E+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        10154                    429.
 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    0.015    0.031   41.986   41.987
 qs_mol_dyn_low                       1  2.0    0.003    0.003   41.787   41.794
 qs_forces                           11  3.9    0.002    0.003   41.414   41.415
 qs_energies                         11  4.9    0.001    0.001   39.405   39.408
 scf_env_do_scf                      11  5.9    0.001    0.001   33.782   33.782
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.006   25.733   25.733
 velocity_verlet                     10  3.0    0.001    0.001   24.003   24.047
 dbcsr_multiply_generic            2286 12.5    0.100    0.103   17.382   17.614
 qs_scf_new_mos                     108  7.5    0.001    0.001   15.927   16.027
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   15.927   16.027
 ot_scf_mini                        108  9.5    0.002    0.002   14.843   14.945
 multiply_cannon                   2286 13.5    0.304    0.316   13.501   14.475
 multiply_cannon_loop              2286 14.5    0.346    0.358   12.256   13.212
 ot_mini                            108 10.5    0.001    0.001    8.831    8.949
 multiply_cannon_multrec           9144 15.5    3.406    4.766    8.543    8.643
 init_scf_loop                       11  6.9    0.000    0.000    8.022    8.024
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.295    7.439
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.013    7.295    7.439
 prepare_preconditioner              11  7.9    0.000    0.000    7.056    7.070
 make_preconditioner                 11  8.9    0.000    0.000    7.056    7.070
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.570    6.947
 qs_ot_get_derivative               108 11.5    0.001    0.001    6.785    6.886
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.574    6.705
 dbcsr_mm_accdrv_process          12550 15.8    4.247    5.636    5.012    6.357
 cp_fm_upper_to_full                 72 14.2    3.256    4.685    3.256    4.685
 qs_rho_update_rho_low              119  7.7    0.001    0.001    4.335    4.340
 calculate_rho_elec                 119  8.7    0.119    0.122    4.334    4.340
 sum_up_and_integrate               119 10.3    0.064    0.066    4.006    4.012
 integrate_v_rspace                 119 11.3    0.004    0.004    3.942    3.948
 init_scf_run                        11  5.9    0.000    0.001    3.591    3.591
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    3.591    3.591
 qs_ot_get_p                        119 10.4    0.001    0.001    3.275    3.413
 mp_waitall_1                     94719 16.7    2.368    3.261    2.368    3.261
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.509    2.920
 dbcsr_complete_redistribute        329 12.2    0.288    0.293    2.023    2.901
 pw_transfer                       1439 11.6    0.068    0.069    2.673    2.679
 fft_wrap_pw1pw2                   1201 12.6    0.009    0.009    2.575    2.581
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    1.710    2.565
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.195    2.509
 apply_single                       119 13.6    0.000    0.000    2.195    2.509
 make_m2s                          4572 13.5    0.037    0.038    2.325    2.495
 make_images                       4572 14.5    0.349    0.379    2.203    2.373
 mp_alltoall_i22                    627 13.8    1.464    2.340    1.464    2.340
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.481    2.331
 density_rs2pw                      119  9.7    0.004    0.004    2.226    2.238
 fft_wrap_pw1pw2_140                487 13.2    0.617    0.623    2.167    2.174
 calculate_dm_sparse                119  9.5    0.000    0.000    2.144    2.161
 multiply_cannon_metrocomm3        9144 15.5    0.020    0.020    1.262    2.128
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.084    2.085
 grid_integrate_task_list           119 12.3    2.061    2.077    2.061    2.077
 ot_diis_step                       108 11.5    0.014    0.014    2.019    2.020
 qs_ot_p2m_diag                      50 11.0    0.043    0.044    1.998    1.999
 mp_sum_l                          7287 12.8    1.013    1.808    1.013    1.808
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.793    1.793
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    1.764    1.765
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.683    1.736
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.723    1.723
 fft3d_ps                          1201 14.6    0.597    0.607    1.592    1.596
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.535    1.574
 rs_pw_transfer                     974 11.9    0.009    0.009    1.515    1.546
 cp_fm_cholesky_invert               11 10.9    1.535    1.538    1.535    1.538
 grid_collocate_task_list           119  9.7    1.508    1.513    1.508    1.513
 hybrid_alltoall_any               4725 16.4    0.087    0.146    1.187    1.452
 wfi_extrapolate                     11  7.9    0.001    0.001    1.432    1.432
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.432    1.432
 cp_fm_diag_elpa_base                50 14.0    1.281    1.335    1.430    1.430
 potential_pw2rs                    119 12.3    0.014    0.014    1.395    1.396
 make_images_data                  4572 15.5    0.042    0.045    1.138    1.358
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.209    1.217
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.145    1.165
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    1.101    1.117
 mp_alltoall_d11v                  2130 13.8    1.085    1.116    1.085    1.116
 multiply_cannon_sync_h2d          9144 15.5    1.042    1.047    1.042    1.047
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    0.986    1.038
 qs_create_task_list                 11  7.9    0.012    0.013    0.943    0.953
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.933    0.946
 generate_qs_task_list               11  8.9    0.368    0.386    0.931    0.941
 acc_transpose_blocks              9144 15.5    0.039    0.039    0.904    0.911
 mp_alltoall_z22v                  1201 16.6    0.860    0.880    0.860    0.880
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="110", plot="h2o_64_md", label="(8n/1r/12t)", y=41.987000, yerr=0.000000
PlotPoint: name="111", plot="h2o_64_md_mem", label="(8n/1r/12t)", y=709.909091, yerr=12.078941
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/09/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                    198.287135E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               8410880       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     117.0
 marketing flops                    15.646302E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank             501.571584E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 8483040
 MPI messages size (bytes):
  total size                         1.160510E+12
  min size                           0.000000E+00
  max size                           1.161504E+06
  average size                     136.803609E+03
 MPI breakdown and total messages size (bytes):
             size <=      128             1836752                        0
       128 < size <=     8192             1040592               8524529664
      8192 < size <=    32768             1486976              24362614784
     32768 < size <=   131072             2491776             216971345920
    131072 < size <=  4194304             1626944             910632720448
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3473                  66218.
 MP_Allreduce         9776                    488.
 MP_Sync                52
 MP_Alltoall          1938                 999467.
 MP_SendRecv         20900                   9096.
 MP_ISendRecv        20900                   9096.
 MP_Wait             37268
 MP_ISend            14300                  82312.
 MP_IRecv            14300                  82312.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.058    0.108   89.110   89.113
 qs_mol_dyn_low                       1  2.0    0.004    0.009   88.527   88.535
 qs_forces                           11  3.9    0.004    0.012   88.449   88.454
 qs_energies                         11  4.9    0.001    0.005   85.438   85.452
 scf_env_do_scf                      11  5.9    0.000    0.001   76.027   76.029
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.006   69.582   69.583
 dbcsr_multiply_generic            2055 12.4    0.107    0.109   52.154   52.420
 qs_scf_new_mos                      99  7.5    0.001    0.001   50.202   50.311
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   50.202   50.310
 ot_scf_mini                         99  9.5    0.002    0.002   47.770   47.854
 velocity_verlet                     10  3.0    0.001    0.002   45.735   45.736
 multiply_cannon                   2055 13.4    0.179    0.185   42.553   43.275
 multiply_cannon_loop              2055 14.4    1.525    1.566   41.320   42.081
 ot_mini                             99 10.5    0.001    0.002   27.492   27.558
 qs_ot_get_derivative                99 11.5    0.001    0.001   20.706   20.799
 multiply_cannon_multrec          49320 15.4   12.376   13.147   17.232   17.992
 rebuild_ks_matrix                  110  8.3    0.000    0.000   15.685   15.768
 qs_ks_build_kohn_sham_matrix       110  9.3    0.011    0.014   15.684   15.768
 qs_ks_update_qs_env                110  7.6    0.001    0.001   13.754   13.827
 mp_waitall_1                    220248 16.4   11.795   12.840   11.795   12.840
 qs_ot_get_p                        110 10.4    0.001    0.002   11.644   11.740
 multiply_cannon_sync_h2d         49320 15.4   10.211   10.783   10.211   10.783
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    7.870    8.424
 qs_ot_p2m_diag                      48 11.0    0.013    0.019    8.132    8.183
 sum_up_and_integrate               110 10.3    0.037    0.046    8.015    8.030
 qs_rho_update_rho_low              110  7.6    0.001    0.003    7.863    8.017
 calculate_rho_elec                 110  8.6    0.022    0.027    7.862    8.016
 integrate_v_rspace                 110 11.3    0.003    0.004    7.978    8.001
 apply_preconditioner_dbcsr         110 12.6    0.000    0.001    7.231    7.714
 apply_single                       110 13.6    0.000    0.000    7.230    7.714
 multiply_cannon_metrocomm3       49320 15.4    0.079    0.082    6.490    7.520
 init_scf_run                        11  5.9    0.000    0.001    7.215    7.215
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    7.215    7.215
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    7.150    7.151
 ot_diis_step                        99 11.5    0.006    0.008    6.585    6.586
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    6.381    6.406
 cp_fm_diag_elpa_base                48 14.0    6.357    6.382    6.379    6.404
 init_scf_loop                       11  6.9    0.000    0.001    6.395    6.397
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    5.971    6.026
 rs_pw_transfer                     902 11.9    0.011    0.013    5.111    5.712
 mp_sum_l                          6594 12.7    4.493    5.350    4.493    5.350
 density_rs2pw                      110  9.6    0.004    0.005    4.573    5.191
 dbcsr_mm_accdrv_process          87628 16.1    1.923    2.014    4.731    4.974
 make_m2s                          4110 13.4    0.061    0.066    4.690    4.880
 make_images                       4110 14.4    0.178    0.194    4.592    4.786
 wfi_extrapolate                     11  7.9    0.001    0.003    4.425    4.425
 prepare_preconditioner              11  7.9    0.000    0.000    4.114    4.129
 make_preconditioner                 11  8.9    0.000    0.000    4.114    4.129
 multiply_cannon_metrocomm1       49320 15.4    0.062    0.065    2.606    4.101
 pw_transfer                       1331 11.6    0.056    0.064    3.892    4.047
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.009    3.803    3.961
 make_full_inverse_cholesky          11  9.9    0.000    0.000    3.890    3.941
 calculate_dm_sparse                110  9.5    0.001    0.001    3.803    3.913
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    3.710    3.720
 potential_pw2rs                    110 12.3    0.006    0.007    3.438    3.512
 grid_integrate_task_list           110 12.3    3.256    3.414    3.256    3.414
 qs_ot_get_orbitals                  99 10.5    0.000    0.001    3.317    3.411
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    3.262    3.310
 fft_wrap_pw1pw2_140                451 13.1    0.452    0.499    3.071    3.228
 fft3d_ps                          1111 14.6    0.783    0.879    2.995    3.133
 mp_alltoall_d11v                  2046 13.8    2.354    2.946    2.354    2.946
 calculate_first_density_matrix       1  7.0    0.000    0.002    2.664    2.671
 mp_waitany                       14300 13.8    1.935    2.636    1.935    2.636
 jit_kernel_multiply                 13 15.9    2.532    2.561    2.532    2.561
 grid_collocate_task_list           110  9.6    2.158    2.353    2.158    2.353
 make_images_data                  4110 15.4    0.043    0.046    2.031    2.344
 cp_fm_cholesky_invert               11 10.9    2.257    2.261    2.257    2.261
 acc_transpose_blocks             49320 15.4    0.209    0.219    2.121    2.217
 hybrid_alltoall_any               4261 16.3    0.083    0.485    1.717    2.129
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    2.063    2.079
 mp_alltoall_z22v                  1111 16.6    1.831    2.048    1.831    2.048
 mp_sum_d                          3889 11.9    1.372    1.852    1.372    1.852
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="200", plot="h2o_128_md", label="(8n/12r/1t)", y=89.113000, yerr=0.000000
PlotPoint: name="201", plot="h2o_128_md_mem", label="(8n/12r/1t)", y=476.454545, yerr=2.903404
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/10/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                    390.715586E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               5019072       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     196.1
 marketing flops                    15.646302E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank             586.465280E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1972800
 MPI messages size (bytes):
  total size                         1.077520E+12
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     546.188250E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               14916                        0
       128 < size <=     8192              222984               1826684928
      8192 < size <=    32768              520356              13399818240
     32768 < size <=   131072              372336              35386294272
    131072 < size <=  4194304              787758             788321309808
   4194304 < size <= 16777216               54450             238588003280
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3473                  66437.
 MP_Allreduce         9775                    566.
 MP_Sync                52
 MP_Alltoall          1717                3002313.
 MP_SendRecv         10340                  26400.
 MP_ISendRecv        10340                  26400.
 MP_Wait             22352
 MP_ISend            10164                 155761.
 MP_IRecv            10164                 155761.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.014    0.031   79.938   79.939
 qs_mol_dyn_low                       1  2.0    0.003    0.003   79.628   79.637
 qs_forces                           11  3.9    0.003    0.003   78.315   78.319
 qs_energies                         11  4.9    0.001    0.001   74.882   74.890
 scf_env_do_scf                      11  5.9    0.000    0.001   63.506   63.509
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.007   54.735   54.736
 dbcsr_multiply_generic            2055 12.4    0.133    0.137   41.586   41.881
 velocity_verlet                     10  3.0    0.001    0.001   39.899   39.926
 qs_scf_new_mos                      99  7.5    0.001    0.001   36.743   36.877
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   36.742   36.876
 multiply_cannon                   2055 13.4    0.220    0.242   33.807   35.317
 ot_scf_mini                         99  9.5    0.003    0.003   35.030   35.159
 multiply_cannon_loop              2055 14.4    0.927    0.947   32.279   33.257
 ot_mini                             99 10.5    0.001    0.001   19.398   19.539
 multiply_cannon_multrec          24660 15.4    7.603    9.152   14.147   15.921
 rebuild_ks_matrix                  110  8.3    0.000    0.000   14.683   14.815
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.014   14.683   14.815
 qs_ot_get_derivative                99 11.5    0.001    0.001   13.469   13.600
 mp_waitall_1                    176588 16.5   10.383   13.155   10.383   13.155
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.955   13.069
 multiply_cannon_metrocomm3       24660 15.4    0.067    0.071    6.625    9.586
 qs_ot_get_p                        110 10.4    0.001    0.001    8.789    8.951
 init_scf_run                        11  5.9    0.000    0.001    8.940    8.941
 scf_env_initial_rho_setup           11  6.9    0.000    0.001    8.940    8.941
 init_scf_loop                       11  6.9    0.000    0.000    8.724    8.725
 qs_rho_update_rho_low              110  7.6    0.001    0.001    7.212    8.416
 calculate_rho_elec                 110  8.6    0.040    0.048    7.212    8.416
 multiply_cannon_sync_h2d         24660 15.4    6.941    8.143    6.941    8.143
 dbcsr_mm_accdrv_process          52282 16.1    4.727    6.656    6.383    8.116
 sum_up_and_integrate               110 10.3    0.052    0.059    7.440    7.451
 integrate_v_rspace                 110 11.3    0.002    0.003    7.387    7.398
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    6.607    7.330
 apply_single                       110 13.6    0.000    0.001    6.607    7.330
 prepare_preconditioner              11  7.9    0.000    0.000    6.611    6.636
 make_preconditioner                 11  8.9    0.000    0.000    6.611    6.636
 qs_ot_p2m_diag                      48 11.0    0.029    0.044    6.410    6.430
 make_full_inverse_cholesky          11  9.9    0.000    0.000    6.154    6.319
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    5.909    5.910
 ot_diis_step                        99 11.5    0.010    0.010    5.877    5.878
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    4.931    5.604
 make_m2s                          4110 13.4    0.057    0.060    5.110    5.590
 make_images                       4110 14.4    0.402    0.447    5.000    5.475
 calculate_dm_sparse                110  9.5    0.001    0.001    5.302    5.358
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    5.072    5.085
 calculate_first_density_matrix       1  7.0    0.000    0.000    5.056    5.084
 cp_fm_diag_elpa_base                48 14.0    5.004    5.040    5.068    5.083
 density_rs2pw                      110  9.6    0.004    0.005    4.244    4.800
 rs_pw_transfer                     902 11.9    0.012    0.013    4.068    4.613
 pw_transfer                       1331 11.6    0.067    0.073    4.277    4.441
 fft_wrap_pw1pw2                   1111 12.6    0.009    0.009    4.169    4.331
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    3.837    3.872
 wfi_extrapolate                     11  7.9    0.001    0.001    3.746    3.746
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.626    3.696
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.002    3.571    3.574
 mp_alltoall_d11v                  2046 13.8    2.051    3.417    2.051    3.417
 grid_integrate_task_list           110 12.3    3.137    3.403    3.137    3.403
 fft_wrap_pw1pw2_140                451 13.1    0.515    0.532    3.171    3.337
 fft3d_ps                          1111 14.6    1.112    1.340    3.148    3.324
 make_images_data                  4110 15.4    0.047    0.051    2.737    3.238
 potential_pw2rs                    110 12.3    0.008    0.009    3.172    3.218
 cp_fm_cholesky_invert               11 10.9    3.141    3.149    3.141    3.149
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    3.075    3.133
 hybrid_alltoall_any               4261 16.3    0.103    0.445    2.375    3.076
 mp_sum_l                          6594 12.7    2.025    2.785    2.025    2.785
 jit_kernel_multiply                 13 16.2    1.306    2.665    1.306    2.665
 grid_collocate_task_list           110  9.6    2.101    2.537    2.101    2.537
 acc_transpose_blocks             24660 15.4    0.112    0.114    1.901    2.193
 multiply_cannon_metrocomm1       24660 15.4    0.036    0.038    0.647    2.174
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    2.121    2.139
 rs_scatter_matrices                121  9.7    0.356    0.428    0.821    2.014
 mp_allgather_i34                  2055 14.4    0.855    1.963    0.855    1.963
 multiply_cannon_metrocomm4       22605 15.4    0.079    0.082    0.813    1.922
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.887    1.907
 qs_energies_init_hamiltonians       11  5.9    0.001    0.007    1.877    1.881
 mp_waitany                       10164 13.8    1.327    1.843    1.327    1.843
 mp_alltoall_z22v                  1111 16.6    1.724    1.825    1.724    1.825
 cp_fm_cholesky_decompose            22 10.9    1.793    1.799    1.793    1.799
 dbcsr_complete_redistribute        325 12.2    0.249    0.394    1.417    1.710
 mp_irecv_dv                      57340 16.2    0.686    1.708    0.686    1.708
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="202", plot="h2o_128_md", label="(8n/6r/2t)", y=79.939000, yerr=0.000000
PlotPoint: name="203", plot="h2o_128_md_mem", label="(8n/6r/2t)", y=554.636364, yerr=7.227130
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_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             660.189184E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                  854880
 MPI messages size (bytes):
  total size                       708.322787E+09
  min size                           0.000000E+00
  max size                           6.553600E+06
  average size                     828.564000E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768              222984               7302414336
     32768 < size <=   131072              153888              10085203968
    131072 < size <=  4194304              389376             200257044480
   4194304 < size <= 16777216               82208             490679162176
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3473                  66428.
 MP_Allreduce         9774                    562.
 MP_Sync                52
 MP_Alltoall          1496                4511006.
 MP_SendRecv          6820                  27424.
 MP_ISendRecv         6820                  27424.
 MP_Wait             25498
 MP_ISend            17072                 115022.
 MP_IRecv            17072                 115022.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.024    0.079   65.945   65.946
 qs_mol_dyn_low                       1  2.0    0.003    0.003   65.504   65.513
 qs_forces                           11  3.9    0.006    0.031   64.880   64.881
 qs_energies                         11  4.9    0.003    0.020   61.572   61.575
 scf_env_do_scf                      11  5.9    0.001    0.001   53.180   53.180
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.006   43.786   43.787
 velocity_verlet                     10  3.0    0.002    0.006   34.724   34.743
 dbcsr_multiply_generic            2055 12.4    0.111    0.127   30.237   30.770
 qs_scf_new_mos                      99  7.5    0.001    0.001   27.860   27.963
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   27.860   27.963
 ot_scf_mini                         99  9.5    0.002    0.003   26.576   26.693
 multiply_cannon                   2055 13.4    0.212    0.222   23.079   25.232
 multiply_cannon_loop              2055 14.4    0.620    0.635   21.639   23.231
 ot_mini                             99 10.5    0.001    0.001   14.858   14.982
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.870   13.076
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.014   12.869   13.075
 qs_ks_update_qs_env                110  7.6    0.001    0.001   11.322   11.516
 mp_waitall_1                    139946 16.5    7.809   11.275    7.809   11.275
 multiply_cannon_multrec          16440 15.4    3.855    4.994    9.863   10.870
 qs_ot_get_derivative                99 11.5    0.001    0.001   10.173   10.284
 init_scf_loop                       11  6.9    0.001    0.006    9.356    9.358
 multiply_cannon_metrocomm3       16440 15.4    0.042    0.046    4.740    8.688
 prepare_preconditioner              11  7.9    0.000    0.001    7.525    7.548
 make_preconditioner                 11  8.9    0.000    0.002    7.525    7.548
 make_full_inverse_cholesky          11  9.9    0.000    0.001    6.851    7.221
 sum_up_and_integrate               110 10.3    0.061    0.062    6.950    6.964
 integrate_v_rspace                 110 11.3    0.003    0.004    6.889    6.904
 qs_ot_get_p                        110 10.4    0.001    0.001    6.691    6.861
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.475    6.487
 calculate_rho_elec                 110  8.6    0.059    0.059    6.474    6.487
 dbcsr_mm_accdrv_process          34862 16.1    5.036    5.674    5.864    6.063
 init_scf_run                        11  5.9    0.000    0.001    5.935    5.936
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.935    5.936
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    5.053    5.600
 apply_single                       110 13.6    0.000    0.000    5.053    5.600
 make_m2s                          4110 13.4    0.050    0.051    4.485    4.913
 qs_ot_p2m_diag                      48 11.0    0.042    0.044    4.809    4.827
 make_images                       4110 14.4    0.394    0.513    4.370    4.798
 density_rs2pw                      110  9.6    0.004    0.005    3.557    4.780
 ot_diis_step                        99 11.5    0.010    0.010    4.595    4.595
 rs_pw_transfer                     902 11.9    0.010    0.011    3.420    4.595
 cp_dbcsr_syevd                      48 12.0    0.003    0.004    4.413    4.414
 multiply_cannon_sync_h2d         16440 15.4    3.661    4.285    3.661    4.285
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.371    3.981
 pw_transfer                       1331 11.6    0.066    0.074    3.750    3.778
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.749    3.758
 cp_fm_diag_elpa_base                48 14.0    3.673    3.700    3.747    3.756
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.642    3.673
 grid_integrate_task_list           110 12.3    3.162    3.497    3.162    3.497
 cp_fm_cholesky_invert               11 10.9    3.227    3.235    3.227    3.235
 make_images_data                  4110 15.4    0.043    0.047    2.512    3.124
 wfi_extrapolate                     11  7.9    0.001    0.001    3.085    3.085
 fft_wrap_pw1pw2_140                451 13.1    0.635    0.643    3.026    3.060
 hybrid_alltoall_any               4261 16.3    0.106    0.378    2.240    2.954
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.880    2.946
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.912    2.913
 mp_sum_l                          6594 12.7    2.079    2.834    2.079    2.834
 calculate_first_density_matrix       1  7.0    0.000    0.003    2.750    2.751
 calculate_dm_sparse                110  9.5    0.001    0.001    2.700    2.729
 potential_pw2rs                    110 12.3    0.011    0.012    2.681    2.711
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.577    2.635
 mp_waitany                       17072 13.8    1.328    2.571    1.328    2.571
 grid_collocate_task_list           110  9.6    2.119    2.528    2.119    2.528
 multiply_cannon_metrocomm4       14385 15.4    0.046    0.050    0.893    2.493
 fft3d_ps                          1111 14.6    1.090    1.097    2.466    2.490
 mp_irecv_dv                      48980 15.7    0.823    2.364    0.823    2.364
 mp_alltoall_d11v                  2046 13.8    1.831    2.318    1.831    2.318
 rs_pw_transfer_RS2PW_140           121 11.5    0.176    0.181    0.946    2.135
 qs_energies_init_hamiltonians       11  5.9    0.001    0.006    1.975    1.976
 dbcsr_complete_redistribute        325 12.2    0.320    0.355    1.495    1.969
 mp_allgather_i34                  2055 14.4    0.762    1.851    0.762    1.851
 cp_fm_upper_to_full                 70 14.2    1.406    1.806    1.406    1.806
 cp_fm_cholesky_decompose            22 10.9    1.748    1.768    1.748    1.768
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.746    1.761
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.601    1.618
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.361    1.472
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    1.005    1.465
 rs_gather_matrices                 110 12.3    0.231    0.258    0.969    1.460
 qs_ot_get_orbitals                  99 10.5    0.000    0.001    1.421    1.453
 acc_transpose_blocks             16440 15.4    0.074    0.077    1.304    1.332
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="204", plot="h2o_128_md", label="(8n/4r/3t)", y=65.946000, yerr=0.000000
PlotPoint: name="205", plot="h2o_128_md_mem", label="(8n/4r/3t)", y=625.909091, yerr=7.609259
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_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             743.710720E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                  937080
 MPI messages size (bytes):
  total size                       523.723932E+09
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     558.889250E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6996                        0
       128 < size <=     8192                 264                  2162688
      8192 < size <=    32768              304932               8165326848
     32768 < size <=   131072              110640               6338641920
    131072 < size <=  4194304              489498             400769458320
   4194304 < size <= 16777216               24750             108449092400
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3473                  66426.
 MP_Allreduce         9774                    603.
 MP_Sync                52
 MP_Alltoall          1496                5863162.
 MP_SendRecv          5060                  43184.
 MP_ISendRecv         5060                  43184.
 MP_Wait             20042
 MP_ISend            13376                 163145.
 MP_IRecv            13376                 163145.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.040    0.061   71.574   71.575
 qs_mol_dyn_low                       1  2.0    0.003    0.004   71.026   71.035
 qs_forces                           11  3.9    0.004    0.017   70.959   70.960
 qs_energies                         11  4.9    0.003    0.011   67.422   67.425
 scf_env_do_scf                      11  5.9    0.002    0.010   58.665   58.667
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.007   45.759   45.761
 velocity_verlet                     10  3.0    0.001    0.002   39.099   39.101
 dbcsr_multiply_generic            2055 12.4    0.114    0.119   30.467   30.708
 qs_scf_new_mos                      99  7.5    0.001    0.001   29.558   29.664
 qs_scf_loop_do_ot                   99  8.5    0.001    0.004   29.557   29.664
 ot_scf_mini                         99  9.5    0.003    0.004   27.907   28.022
 multiply_cannon                   2055 13.4    0.244    0.269   22.657   23.496
 multiply_cannon_loop              2055 14.4    0.892    0.916   21.146   21.749
 ot_mini                             99 10.5    0.001    0.001   14.785   14.925
 multiply_cannon_multrec          24660 15.4    4.226    6.933   12.678   13.814
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.860   12.969
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.016   12.859   12.968
 init_scf_loop                       11  6.9    0.001    0.006   12.860   12.862
 qs_ks_update_qs_env                110  7.6    0.001    0.001   11.341   11.442
 prepare_preconditioner              11  7.9    0.000    0.001   11.020   11.034
 make_preconditioner                 11  8.9    0.000    0.002   11.020   11.034
 qs_ot_get_derivative                99 11.5    0.001    0.001   10.611   10.731
 make_full_inverse_cholesky          11  9.9    0.000    0.001    9.180   10.703
 dbcsr_mm_accdrv_process          52304 16.0    7.059    8.718    8.304    9.252
 qs_ot_get_p                        110 10.4    0.001    0.001    8.035    8.195
 sum_up_and_integrate               110 10.3    0.067    0.070    7.075    7.090
 integrate_v_rspace                 110 11.3    0.003    0.003    7.008    7.027
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.832    6.839
 calculate_rho_elec                 110  8.6    0.078    0.082    6.832    6.839
 mp_waitall_1                    121746 16.5    5.004    6.818    5.004    6.818
 make_m2s                          4110 13.4    0.059    0.062    6.061    6.416
 make_images                       4110 14.4    0.578    0.696    5.919    6.271
 init_scf_run                        11  5.9    0.000    0.001    5.899    5.899
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.898    5.899
 qs_ot_p2m_diag                      48 11.0    0.055    0.064    5.808    5.822
 cp_dbcsr_syevd                      48 12.0    0.003    0.004    5.260    5.263
 cp_fm_upper_to_full                 70 14.2    3.486    5.064    3.486    5.064
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    4.476    4.486
 cp_fm_diag_elpa_base                48 14.0    4.297    4.366    4.473    4.484
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.048    4.171
 apply_single                       110 13.6    0.000    0.000    4.048    4.171
 density_rs2pw                      110  9.6    0.004    0.005    3.634    4.155
 pw_transfer                       1331 11.6    0.066    0.076    4.105    4.146
 ot_diis_step                        99 11.5    0.011    0.011    4.136    4.137
 dbcsr_complete_redistribute        325 12.2    0.413    0.475    2.871    4.085
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.009    3.999    4.043
 rs_pw_transfer                     902 11.9    0.010    0.011    3.189    3.739
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.456    3.512
 copy_fm_to_dbcsr                   174 11.2    0.001    0.002    2.308    3.505
 make_images_data                  4110 15.4    0.046    0.050    3.059    3.498
 grid_integrate_task_list           110 12.3    3.263    3.490    3.263    3.490
 hybrid_alltoall_any               4261 16.3    0.121    0.460    2.558    3.446
 qs_ot_get_derivative_diag           47 12.0    0.001    0.002    3.350    3.417
 multiply_cannon_sync_h2d         24660 15.4    3.183    3.347    3.183    3.347
 cp_fm_cholesky_invert               11 10.9    3.293    3.303    3.293    3.303
 fft_wrap_pw1pw2_140                451 13.1    0.666    0.688    3.244    3.295
 wfi_extrapolate                     11  7.9    0.001    0.001    3.167    3.167
 multiply_cannon_metrocomm3       24660 15.4    0.036    0.037    1.370    3.148
 calculate_dm_sparse                110  9.5    0.001    0.001    3.008    3.038
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.830    2.996
 mp_alltoall_i22                    605 13.7    1.761    2.957    1.761    2.957
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.902    2.903
 fft3d_ps                          1111 14.6    1.086    1.117    2.763    2.782
 potential_pw2rs                    110 12.3    0.013    0.013    2.671    2.688
 calculate_first_density_matrix       1  7.0    0.001    0.004    2.612    2.614
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.001    2.464    2.503
 grid_collocate_task_list           110  9.6    2.223    2.446    2.223    2.446
 qs_energies_init_hamiltonians       11  5.9    0.001    0.004    2.306    2.307
 mp_alltoall_d11v                  2046 13.8    2.007    2.272    2.007    2.272
 cp_fm_cholesky_decompose            22 10.9    2.059    2.107    2.059    2.107
 jit_kernel_multiply                 10 15.9    0.912    1.816    0.912    1.816
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.762    1.792
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.765    1.775
 mp_sum_l                          6594 12.7    1.088    1.707    1.088    1.707
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.598    1.699
 mp_waitany                       13376 13.8    1.203    1.676    1.203    1.676
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.606    1.622
 multiply_cannon_metrocomm4       20550 15.4    0.060    0.063    0.848    1.577
 acc_transpose_blocks             24660 15.4    0.104    0.106    1.527    1.554
 mp_alltoall_z22v                  1111 16.6    1.463    1.523    1.463    1.523
 mp_irecv_dv                      62702 16.1    0.747    1.499    0.747    1.499
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="206", plot="h2o_128_md", label="(8n/3r/4t)", y=71.575000, yerr=0.000000
PlotPoint: name="207", plot="h2o_128_md_mem", label="(8n/3r/4t)", y=700.272727, yerr=11.909438
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_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             844.091392E+06
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  197280
 MPI messages size (bytes):
  total size                       339.125567E+09
  min size                           0.000000E+00
  max size                          13.107200E+06
  average size                       1.719006E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 132                  4325376
     32768 < size <=   131072               88656              11620319232
    131072 < size <=  4194304               89424             117209825280
   4194304 < size <= 16777216               17616             210291069504
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         7346                     33.
 MP_Alltoall          8043                 263767.
 MP_ISend            32836                 654203.
 MP_IRecv            32836                 654587.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3473                  66424.
 MP_Allreduce         9774                    644.
 MP_Sync                52
 MP_Alltoall          1496                8504061.
 MP_SendRecv          3300                  54848.
 MP_ISendRecv         3300                  54848.
 MP_Wait             13926
 MP_ISend             9240                 278857.
 MP_IRecv             9240                 278857.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.015    0.032   56.944   56.944
 qs_mol_dyn_low                       1  2.0    0.003    0.003   56.570   56.579
 qs_forces                           11  3.9    0.003    0.003   56.504   56.505
 qs_energies                         11  4.9    0.001    0.001   52.753   52.757
 scf_env_do_scf                      11  5.9    0.000    0.001   44.046   44.046
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.007   36.099   36.100
 velocity_verlet                     10  3.0    0.001    0.001   31.756   31.759
 dbcsr_multiply_generic            2055 12.4    0.103    0.108   23.263   23.477
 qs_scf_new_mos                      99  7.5    0.001    0.001   20.690   20.739
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   20.690   20.739
 ot_scf_mini                         99  9.5    0.002    0.002   19.437   19.476
 multiply_cannon                   2055 13.4    0.244    0.257   17.582   19.133
 multiply_cannon_loop              2055 14.4    0.323    0.337   16.223   16.651
 rebuild_ks_matrix                  110  8.3    0.000    0.000   12.162   12.194
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.014   12.161   12.194
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.769   10.798
 ot_mini                             99 10.5    0.001    0.001   10.589   10.619
 multiply_cannon_multrec           8220 15.4    3.218    4.479    7.629    8.511
 init_scf_loop                       11  6.9    0.000    0.000    7.894    7.895
 mp_waitall_1                    103326 16.6    6.154    7.634    6.154    7.634
 qs_ot_get_derivative                99 11.5    0.001    0.001    6.802    6.841
 sum_up_and_integrate               110 10.3    0.080    0.082    6.672    6.687
 integrate_v_rspace                 110 11.3    0.003    0.003    6.592    6.606
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.518    6.530
 calculate_rho_elec                 110  8.6    0.115    0.115    6.517    6.530
 prepare_preconditioner              11  7.9    0.000    0.000    6.222    6.226
 make_preconditioner                 11  8.9    0.000    0.000    6.222    6.226
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.783    5.863
 init_scf_run                        11  5.9    0.000    0.001    5.543    5.543
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.543    5.543
 dbcsr_mm_accdrv_process          17442 15.9    2.863    4.136    4.282    5.239
 qs_ot_get_p                        110 10.4    0.001    0.001    4.858    4.884
 make_m2s                          4110 13.4    0.039    0.040    4.368    4.639
 make_images                       4110 14.4    0.640    0.696    4.238    4.507
 multiply_cannon_metrocomm3        8220 15.4    0.018    0.018    2.952    4.244
 pw_transfer                       1331 11.6    0.066    0.073    4.140    4.155
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.009    4.031    4.051
 ot_diis_step                        99 11.5    0.012    0.012    3.763    3.764
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    3.666    3.688
 apply_single                       110 13.6    0.000    0.000    3.666    3.688
 grid_integrate_task_list           110 12.3    3.364    3.556    3.364    3.556
 density_rs2pw                      110  9.6    0.004    0.004    3.179    3.550
 qs_ot_p2m_diag                      48 11.0    0.081    0.084    3.491    3.497
 fft_wrap_pw1pw2_140                451 13.1    0.836    0.855    3.441    3.476
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.181    3.181
 cp_fm_cholesky_invert               11 10.9    3.038    3.041    3.038    3.041
 multiply_cannon_sync_h2d          8220 15.4    2.916    2.993    2.916    2.993
 make_images_data                  4110 15.4    0.038    0.043    2.494    2.929
 hybrid_alltoall_any               4261 16.3    0.202    0.874    2.406    2.883
 wfi_extrapolate                     11  7.9    0.001    0.001    2.818    2.818
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    2.691    2.693
 rs_pw_transfer                     902 11.9    0.010    0.011    2.257    2.660
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    2.634    2.641
 cp_fm_diag_elpa_base                48 14.0    2.575    2.601    2.632    2.640
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.635    2.637
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.618    2.621
 fft3d_ps                          1111 14.6    1.150    1.206    2.573    2.583
 calculate_dm_sparse                110  9.5    0.001    0.001    2.552    2.582
 grid_collocate_task_list           110  9.6    2.316    2.576    2.316    2.576
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.280    2.296
 potential_pw2rs                    110 12.3    0.015    0.016    2.159    2.167
 mp_alltoall_d11v                  2046 13.8    1.748    2.064    1.748    2.064
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    1.997    2.020
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.769    1.996
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    1.912    1.926
 jit_kernel_multiply                  9 15.7    1.109    1.760    1.109    1.760
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.728    1.732
 cp_fm_cholesky_decompose            22 10.9    1.713    1.725    1.713    1.725
 mp_allgather_i34                  2055 14.4    0.546    1.674    0.546    1.674
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    1.528    1.656
 dbcsr_complete_redistribute        325 12.2    0.560    0.581    1.484    1.589
 mp_waitany                        9240 13.8    1.102    1.529    1.102    1.529
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.507    1.516
 qs_create_task_list                 11  7.9    0.007    0.008    1.231    1.336
 generate_qs_task_list               11  8.9    0.373    0.443    1.224    1.328
 rs_gather_matrices                 110 12.3    0.323    0.367    0.976    1.282
 rs_pw_transfer_RS2PW_140           121 11.5    0.162    0.166    0.834    1.241
 multiply_cannon_metrocomm1        8220 15.4    0.021    0.022    0.849    1.232
 mp_alltoall_z22v                  1111 16.6    1.188    1.223    1.188    1.223
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.148    1.167
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="208", plot="h2o_128_md", label="(8n/2r/6t)", y=56.944000, yerr=0.000000
PlotPoint: name="209", plot="h2o_128_md_mem", label="(8n/2r/6t)", y=792.909091, yerr=14.393525
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_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               1.330307E+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         9752                    812.
 MP_Sync                52
 MP_Alltoall          1474               16505187.
 MP_SendRecv          2310                 360267.
 MP_ISendRecv         2310                 360267.
 MP_Wait              5214
 MP_ISend             2420                1187840.
 MP_IRecv             2420                1187840.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.018    0.037   87.524   87.524
 qs_mol_dyn_low                       1  2.0    0.003    0.003   87.219   87.228
 qs_forces                           11  3.9    0.009    0.010   87.157   87.158
 qs_energies                         11  4.9    0.001    0.001   82.947   82.952
 scf_env_do_scf                      11  5.9    0.001    0.001   72.972   72.972
 velocity_verlet                     10  3.0    0.001    0.001   55.956   55.962
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.006   44.363   44.364
 init_scf_loop                       11  6.9    0.000    0.000   28.537   28.539
 dbcsr_multiply_generic            2055 12.4    0.118    0.124   28.246   28.325
 prepare_preconditioner              11  7.9    0.000    0.000   26.524   26.530
 make_preconditioner                 11  8.9    0.000    0.000   26.523   26.530
 qs_scf_new_mos                      99  7.5    0.001    0.001   26.062   26.098
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   26.062   26.097
 make_full_inverse_cholesky          11  9.9    0.000    0.000   20.582   25.989
 ot_scf_mini                         99  9.5    0.002    0.002   24.325   24.343
 multiply_cannon                   2055 13.4    0.344    0.362   21.271   22.157
 multiply_cannon_loop              2055 14.4    0.342    0.346   19.502   19.860
 cp_fm_upper_to_full                 70 14.2   12.895   18.579   12.895   18.579
 rebuild_ks_matrix                  110  8.3    0.000    0.001   14.137   14.162
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.013   14.136   14.162
 ot_mini                             99 10.5    0.001    0.001   13.408   13.428
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.769   12.793
 dbcsr_complete_redistribute        325 12.2    1.023    1.056    7.500   10.842
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    6.487    9.827
 multiply_cannon_multrec           8220 15.4    4.405    4.598    9.559    9.657
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    5.926    9.240
 qs_ot_get_derivative                99 11.5    0.001    0.001    8.946    8.968
 mp_alltoall_i22                    605 13.7    5.535    8.890    5.535    8.890
 mp_waitall_1                     84994 16.7    7.373    8.125    7.373    8.125
 qs_rho_update_rho_low              110  7.6    0.001    0.001    7.775    7.815
 calculate_rho_elec                 110  8.6    0.227    0.227    7.775    7.815
 sum_up_and_integrate               110 10.3    0.150    0.151    7.390    7.405
 integrate_v_rspace                 110 11.3    0.004    0.004    7.239    7.254
 qs_ot_get_p                        110 10.4    0.001    0.001    5.764    5.788
 make_m2s                          4110 13.4    0.043    0.043    5.268    5.758
 init_scf_run                        11  5.9    0.000    0.001    5.708    5.709
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.708    5.708
 make_images                       4110 14.4    0.882    0.934    5.079    5.568
 dbcsr_mm_accdrv_process          11614 15.7    3.248    3.589    5.013    5.286
 cp_fm_cholesky_invert               11 10.9    5.181    5.186    5.181    5.186
 pw_transfer                       1331 11.6    0.075    0.076    5.072    5.078
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.576    5.042
 apply_single                       110 13.6    0.000    0.000    4.576    5.042
 fft_wrap_pw1pw2                   1111 12.6    0.009    0.009    4.955    4.961
 multiply_cannon_metrocomm3        8220 15.4    0.018    0.018    4.557    4.947
 ot_diis_step                        99 11.5    0.015    0.015    4.447    4.447
 fft_wrap_pw1pw2_140                451 13.1    1.335    1.341    4.314    4.320
 qs_ot_p2m_diag                      48 11.0    0.151    0.156    4.257    4.264
 multiply_cannon_sync_h2d          8220 15.4    3.948    3.954    3.948    3.954
 density_rs2pw                      110  9.6    0.004    0.004    3.775    3.828
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.810    3.810
 grid_integrate_task_list           110 12.3    3.682    3.753    3.682    3.753
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    3.663    3.667
 hybrid_alltoall_any               4261 16.3    0.258    0.559    2.857    3.596
 make_images_data                  4110 15.4    0.041    0.044    2.881    3.514
 wfi_extrapolate                     11  7.9    0.001    0.001    3.317    3.317
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    2.814    3.253
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.191    3.191
 cp_fm_diag_elpa_base                48 14.0    2.611    2.848    3.189    3.189
 calculate_dm_sparse                110  9.5    0.001    0.001    3.091    3.111
 fft3d_ps                          1111 14.6    1.306    1.323    2.886    2.898
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.837    2.839
 grid_collocate_task_list           110  9.6    2.673    2.687    2.673    2.687
 potential_pw2rs                    110 12.3    0.021    0.022    2.480    2.482
 rs_pw_transfer                     902 11.9    0.011    0.011    2.374    2.411
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.373    2.385
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.351    2.359
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.267    2.268
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    2.186    2.244
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    2.090    2.175
 cp_fm_cholesky_decompose            22 10.9    2.041    2.060    2.041    2.060
 mp_alltoall_d11v                  2046 13.8    1.908    2.005    1.908    2.005
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.968    1.970
 qs_create_task_list                 11  7.9    0.001    0.001    1.880    1.928
 generate_qs_task_list               11  8.9    0.730    0.784    1.880    1.927
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="210", plot="h2o_128_md", label="(8n/1r/12t)", y=87.524000, yerr=0.000000
PlotPoint: name="211", plot="h2o_128_md_mem", label="(8n/1r/12t)", y=1203.000000, yerr=46.567644
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/15/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1430460020736       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1958505086976       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1986244964352       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1992000282624       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2753956716544       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4454954827776       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5444944789504       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5492290093056       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6712799002624       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11613089636352       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15239146475520       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15239146475520       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19911124992000       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        94.228663E+12       0.0%      0.0%    100.0%
 flops max/rank                      1.103326E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6806316384       0.0%      0.0%    100.0%
 number of processed stacks              12044928       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     565.1
 marketing flops                   145.647559E+12
 -------------------------------------------------------------------------------
 # multiplications                           2527
 max memory usage/rank             630.538240E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                10431456
 MPI messages size (bytes):
  total size                         4.526012E+12
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     433.881156E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               65736                        0
       128 < size <=     8192                1232                 10092544
      8192 < size <=    32768             3605352              96403587072
     32768 < size <=   131072             1305088              74666999808
    131072 < size <=  4194304             5190114            3200148350408
   4194304 < size <= 16777216              263934            1154745839544
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4030                  57371.
 MP_Allreduce        11154                    793.
 MP_Sync                87
 MP_Alltoall          2242                3013135.
 MP_SendRecv         24510                  18752.
 MP_ISendRecv        24510                  18752.
 MP_Wait             42802
 MP_ISend            16140                 108019.
 MP_IRecv            16140                 108019.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.017    0.032  210.585  210.587
 qs_mol_dyn_low                       1  2.0    0.004    0.007  209.996  210.009
 qs_forces                           11  3.9    0.009    0.048  209.876  209.878
 qs_energies                         11  4.9    0.001    0.001  204.144  204.166
 scf_env_do_scf                      11  5.9    0.001    0.001  187.290  187.294
 scf_env_do_scf_inner_loop          118  6.6    0.003    0.008  166.318  166.320
 velocity_verlet                     10  3.0    0.002    0.011  126.491  126.493
 dbcsr_multiply_generic            2527 12.6    0.178    0.181  125.537  125.932
 qs_scf_new_mos                     118  7.6    0.001    0.001  125.284  125.577
 qs_scf_loop_do_ot                  118  8.6    0.001    0.001  125.283  125.577
 ot_scf_mini                        118  9.6    0.003    0.004  118.565  118.857
 multiply_cannon                   2527 13.6    0.246    0.270  101.991  103.317
 multiply_cannon_loop              2527 14.6    2.087    2.159   99.713  100.953
 ot_mini                            118 10.6    0.001    0.002   66.117   66.404
 multiply_cannon_multrec          60648 15.6   33.628   35.499   41.779   43.497
 qs_ot_get_derivative               118 11.6    0.001    0.002   41.206   41.512
 rebuild_ks_matrix                  129  8.3    0.001    0.001   34.438   34.724
 qs_ks_build_kohn_sham_matrix       129  9.3    0.015    0.017   34.437   34.723
 mp_waitall_1                    269254 16.5   28.944   32.045   28.944   32.045
 qs_ks_update_qs_env                129  7.6    0.001    0.001   30.902   31.180
 qs_ot_get_p                        129 10.4    0.001    0.001   30.234   30.563
 multiply_cannon_sync_h2d         60648 15.6   27.769   29.270   27.769   29.270
 apply_preconditioner_dbcsr         129 12.6    0.000    0.001   24.497   25.289
 apply_single                       129 13.6    0.001    0.001   24.496   25.289
 ot_diis_step                       118 11.6    0.008    0.010   24.673   24.674
 qs_ot_p2m_diag                      83 11.4    0.079    0.092   23.435   23.503
 cp_dbcsr_syevd                      83 12.4    0.005    0.005   20.918   20.920
 init_scf_loop                       11  6.9    0.000    0.001   20.889   20.890
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002   19.279   19.511
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   17.878   17.908
 cp_fm_diag_elpa_base                83 14.4   17.805   17.850   17.873   17.905
 multiply_cannon_metrocomm3       60648 15.6    0.114    0.120   15.859   17.815
 prepare_preconditioner              11  7.9    0.000    0.000   16.189   16.252
 make_preconditioner                 11  8.9    0.000    0.000   16.189   16.252
 make_full_inverse_cholesky          11  9.9    0.000    0.000   15.402   15.612
 sum_up_and_integrate               129 10.3    0.090    0.108   14.716   14.732
 integrate_v_rspace                 129 11.3    0.004    0.004   14.626   14.643
 make_m2s                          5054 13.6    0.106    0.115   14.090   14.535
 qs_rho_update_rho_low              129  7.7    0.001    0.002   14.248   14.380
 calculate_rho_elec                 129  8.7    0.047    0.065   14.248   14.379
 make_images                       5054 14.6    0.406    0.425   13.910   14.364
 init_scf_run                        11  5.9    0.000    0.001   12.634   12.635
 scf_env_initial_rho_setup           11  6.9    0.000    0.001   12.634   12.634
 density_rs2pw                      129  9.7    0.006    0.007    7.410   10.701
 rs_pw_transfer                    1054 12.0    0.017    0.019    6.190    9.498
 mp_sum_l                          8010 12.9    8.181    9.311    8.181    9.311
 cp_fm_cholesky_invert               11 10.9    9.269    9.277    9.269    9.277
 wfi_extrapolate                     11  7.9    0.001    0.001    9.254    9.254
 calculate_dm_sparse                129  9.5    0.001    0.001    8.546    8.629
 qs_ot_get_derivative_taylor         41 13.0    0.001    0.001    8.427    8.544
 dbcsr_mm_accdrv_process         125468 16.2    3.088    3.296    7.705    8.283
 pw_transfer                       1559 11.6    0.076    0.091    8.065    8.256
 fft_wrap_pw1pw2                   1301 12.7    0.011    0.013    7.860    8.055
 qs_ot_get_orbitals                 118 10.6    0.001    0.001    7.943    8.009
 make_images_data                  5054 15.6    0.068    0.076    6.960    7.966
 multiply_cannon_metrocomm1       60648 15.6    0.091    0.095    6.213    7.788
 grid_integrate_task_list           129 12.3    7.125    7.570    7.125    7.570
 hybrid_alltoall_any               5240 16.5    0.295    2.282    6.078    7.402
 fft_wrap_pw1pw2_140                527 13.2    1.289    1.333    6.791    7.001
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.003    6.799    6.809
 mp_waitany                       16140 13.9    2.780    6.172    2.780    6.172
 mp_alltoall_d11v                  2423 14.1    4.428    6.033    4.428    6.033
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.913    5.986
 grid_collocate_task_list           129  9.7    4.716    5.977    4.716    5.977
 fft3d_ps                          1301 14.7    2.154    2.816    5.598    5.938
 rs_pw_transfer_RS2PW_140           140 11.5    0.285    0.307    2.195    5.501
 potential_pw2rs                    129 12.3    0.009    0.011    4.946    4.977
 cp_fm_cholesky_decompose            22 10.9    4.706    4.719    4.706    4.719
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="400", plot="h2o_256_md", label="(8n/12r/1t)", y=210.587000, yerr=0.000000
PlotPoint: name="401", plot="h2o_256_md_mem", label="(8n/12r/1t)", y=595.545455, yerr=6.050750
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/16/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1410023282688       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1924145348608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1957871443968       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1963544850432       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2714615709696       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4377645416448       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5350455508992       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5395653328896       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6594687401984       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11444707676160       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15019188129792       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15019188129792       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19624853225472       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        92.796579E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.166472E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6705500928       0.0%      0.0%    100.0%
 number of processed stacks               5925696       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1131.6
 marketing flops                   143.508480E+12
 -------------------------------------------------------------------------------
 # multiplications                           2485
 max memory usage/rank             839.000064E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 2385600
 MPI messages size (bytes):
  total size                         4.069300E+12
  min size                           0.000000E+00
  max size                          17.653760E+06
  average size                       1.705776E+06
 MPI breakdown and total messages size (bytes):
             size <=      128               14916                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768               70188               2295595008
     32768 < size <=   131072              716032              54973693952
    131072 < size <=  4194304             1363760            1386318135296
   4194304 < size <= 16777216              153648            1453843137296
  16777216 < size                           67056            1171888537600
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3997                  58290.
 MP_Allreduce        11071                    960.
 MP_Sync                86
 MP_Alltoall          1955                5616370.
 MP_SendRecv         11938                  47072.
 MP_ISendRecv        11938                  47072.
 MP_Wait             25718
 MP_ISend            11660                 212488.
 MP_IRecv            11660                 212488.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.051    0.090  190.645  190.646
 qs_mol_dyn_low                       1  2.0    0.003    0.004  190.150  190.164
 qs_forces                           11  3.9    0.004    0.005  190.067  190.069
 qs_energies                         11  4.9    0.008    0.030  183.144  183.156
 scf_env_do_scf                      11  5.9    0.001    0.001  166.568  166.578
 scf_env_do_scf_inner_loop          116  6.6    0.003    0.008  133.238  133.242
 velocity_verlet                     10  3.0    0.001    0.001  119.378  119.380
 dbcsr_multiply_generic            2485 12.5    0.187    0.193   96.361   97.530
 qs_scf_new_mos                     116  7.6    0.001    0.001   93.300   93.793
 qs_scf_loop_do_ot                  116  8.6    0.001    0.001   93.299   93.792
 ot_scf_mini                        116  9.6    0.004    0.005   88.528   89.063
 multiply_cannon                   2485 13.5    0.469    0.521   76.529   80.668
 multiply_cannon_loop              2485 14.5    1.240    1.280   73.548   76.528
 ot_mini                            116 10.6    0.001    0.001   49.479   49.960
 mp_waitall_1                    212858 16.6   24.506   37.825   24.506   37.825
 multiply_cannon_multrec          29820 15.5   21.706   27.132   31.240   36.825
 rebuild_ks_matrix                  127  8.3    0.001    0.001   33.238   33.706
 qs_ks_build_kohn_sham_matrix       127  9.3    0.017    0.019   33.237   33.705
 init_scf_loop                       11  6.9    0.005    0.038   33.235   33.239
 qs_ks_update_qs_env                127  7.6    0.001    0.001   29.795   30.219
 prepare_preconditioner              11  7.9    0.000    0.001   28.752   28.844
 make_preconditioner                 11  8.9    0.000    0.002   28.752   28.844
 qs_ot_get_derivative               116 11.6    0.001    0.002   27.629   28.155
 make_full_inverse_cholesky          11  9.9    0.000    0.001   27.417   27.955
 multiply_cannon_metrocomm3       29820 15.5    0.090    0.095   15.796   27.803
 apply_preconditioner_dbcsr         127 12.6    0.000    0.000   21.910   23.053
 apply_single                       127 13.6    0.001    0.001   21.910   23.052
 qs_ot_get_p                        127 10.4    0.001    0.002   21.104   21.720
 ot_diis_step                       116 11.6    0.014    0.014   21.675   21.678
 multiply_cannon_sync_h2d         29820 15.5   19.028   21.367   19.028   21.367
 cp_fm_cholesky_invert               11 10.9   16.929   16.942   16.929   16.942
 qs_ot_p2m_diag                      82 11.4    0.186    0.213   16.342   16.380
 make_m2s                          4970 13.5    0.093    0.100   14.149   15.415
 make_images                       4970 14.5    1.155    1.338   13.936   15.204
 cp_dbcsr_syevd                      82 12.4    0.006    0.006   15.200   15.201
 sum_up_and_integrate               127 10.3    0.115    0.134   14.824   14.862
 integrate_v_rspace                 127 11.3    0.004    0.004   14.709   14.752
 qs_rho_update_rho_low              127  7.7    0.001    0.001   14.195   14.225
 calculate_rho_elec                 127  8.7    0.088    0.105   14.194   14.224
 cp_fm_diag_elpa                     82 13.4    0.000    0.001   12.074   12.108
 cp_fm_diag_elpa_base                82 14.4   11.818   11.899   12.068   12.105
 init_scf_run                        11  5.9    0.000    0.001   11.640   11.642
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   11.640   11.641
 qs_ot_get_derivative_diag           76 12.4    0.002    0.002   10.784   11.164
 multiply_cannon_metrocomm4       27335 15.5    0.104    0.119    3.729   10.450
 make_images_data                  4970 15.5    0.064    0.072    8.578   10.115
 mp_irecv_dv                      68888 16.3    3.529   10.056    3.529   10.056
 density_rs2pw                      127  9.7    0.007    0.007    7.522    9.978
 dbcsr_mm_accdrv_process          61726 16.2    4.445    5.488    8.998    9.584
 hybrid_alltoall_any               5155 16.4    0.341    1.516    7.335    9.502
 pw_transfer                       1535 11.6    0.086    0.097    8.869    8.935
 fft_wrap_pw1pw2                   1281 12.7    0.011    0.012    8.645    8.714
 wfi_extrapolate                     11  7.9    0.001    0.001    8.475    8.475
 rs_pw_transfer                    1038 11.9    0.014    0.016    5.861    8.330
 fft_wrap_pw1pw2_140                519 13.2    1.325    1.345    7.607    7.689
 grid_integrate_task_list           127 12.3    7.133    7.563    7.133    7.563
 cp_fm_cholesky_decompose            22 10.9    6.955    7.025    6.955    7.025
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    6.198    6.916
 calculate_dm_sparse                127  9.5    0.001    0.001    6.426    6.578
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.118    6.127
 fft3d_ps                          1281 14.7    2.787    2.959    5.973    6.037
 grid_collocate_task_list           127  9.7    4.745    5.900    4.745    5.900
 mp_sum_l                          7884 12.9    3.922    5.672    3.922    5.672
 qs_ot_get_orbitals                 116 10.6    0.001    0.001    5.312    5.387
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.246    5.372
 potential_pw2rs                    127 12.3    0.016    0.019    5.086    5.120
 mp_waitany                       11660 13.9    2.510    5.030    2.510    5.030
 mp_alltoall_d11v                  2401 14.1    4.210    4.922    4.210    4.922
 rs_pw_transfer_RS2PW_140           138 11.5    0.348    0.378    2.108    4.565
 mp_allgather_i34                  2485 14.5    1.568    4.527    1.568    4.527
 mp_sum_d                          4449 12.1    2.691    4.126    2.691    4.126
 dbcsr_complete_redistribute        393 12.7    0.780    0.879    3.181    4.040
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    3.858    3.914
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="402", plot="h2o_256_md", label="(8n/6r/2t)", y=190.646000, yerr=0.000000
PlotPoint: name="403", plot="h2o_256_md_mem", label="(8n/6r/2t)", y=799.000000, yerr=3.384456
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/17/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1410023282688       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1924145348608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1957871443968       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1963544850432       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2714615709696       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4377645416448       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5350455508992       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5395653328896       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6594687401984       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11444707676160       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15019188129792       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15019188129792       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19624853225472       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        92.796579E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.906045E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6705500928       0.0%      0.0%    100.0%
 number of processed stacks               3951168       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1697.1
 marketing flops                   143.507742E+12
 -------------------------------------------------------------------------------
 # multiplications                           2485
 max memory usage/rank             943.972352E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                 1033760
 MPI messages size (bytes):
  total size                         2.695213E+12
  min size                           0.000000E+00
  max size                          26.214400E+06
  average size                       2.607194E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 264                  8650752
     32768 < size <=   131072              279168              36591108096
    131072 < size <=  4194304              654272             987691483136
   4194304 < size <= 16777216               65184             925172905552
  16777216 < size                           28448             745747251200
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4003                  58198.
 MP_Allreduce        11085                   1000.
 MP_Sync                86
 MP_Alltoall          1700                9383497.
 MP_SendRecv          7874                  75008.
 MP_ISendRecv         7874                  75008.
 MP_Wait             21654
 MP_ISend            11660                 275234.
 MP_IRecv            11660                 275234.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.045    0.066  177.470  177.471
 qs_mol_dyn_low                       1  2.0    0.003    0.003  176.983  176.995
 qs_forces                           11  3.9    0.004    0.005  176.313  176.319
 qs_energies                         11  4.9    0.001    0.001  169.617  169.628
 scf_env_do_scf                      11  5.9    0.001    0.001  153.957  153.958
 scf_env_do_scf_inner_loop          116  6.6    0.003    0.008  118.547  118.547
 velocity_verlet                     10  3.0    0.001    0.002  113.642  113.662
 dbcsr_multiply_generic            2485 12.5    0.177    0.182   81.268   82.351
 qs_scf_new_mos                     116  7.6    0.001    0.001   80.136   80.483
 qs_scf_loop_do_ot                  116  8.6    0.001    0.001   80.135   80.482
 ot_scf_mini                        116  9.6    0.003    0.004   76.027   76.395
 multiply_cannon                   2485 13.5    0.495    0.511   61.284   66.065
 multiply_cannon_loop              2485 14.5    0.857    0.889   58.384   60.790
 ot_mini                            116 10.6    0.001    0.001   42.485   42.871
 init_scf_loop                       11  6.9    0.000    0.000   35.301   35.302
 mp_waitall_1                    169034 16.6   25.569   34.975   25.569   34.975
 rebuild_ks_matrix                  127  8.3    0.001    0.001   30.870   31.281
 qs_ks_build_kohn_sham_matrix       127  9.3    0.017    0.023   30.870   31.281
 prepare_preconditioner              11  7.9    0.000    0.000   31.217   31.266
 make_preconditioner                 11  8.9    0.000    0.000   31.217   31.266
 make_full_inverse_cholesky          11  9.9    0.000    0.000   28.829   30.240
 qs_ks_update_qs_env                127  7.6    0.001    0.001   27.722   28.103
 multiply_cannon_multrec          19880 15.5   13.315   16.428   21.898   24.943
 multiply_cannon_metrocomm3       19880 15.5    0.058    0.060   15.505   24.787
 qs_ot_get_derivative               116 11.6    0.001    0.002   22.700   23.060
 apply_preconditioner_dbcsr         127 12.6    0.000    0.000   19.940   21.000
 apply_single                       127 13.6    0.001    0.001   19.939   21.000
 ot_diis_step                       116 11.6    0.017    0.018   19.679   19.680
 qs_ot_get_p                        127 10.4    0.001    0.001   19.017   19.463
 multiply_cannon_sync_h2d         19880 15.5   14.014   15.900   14.014   15.900
 make_m2s                          4970 13.5    0.082    0.088   14.992   15.740
 make_images                       4970 14.5    1.169    1.258   14.758   15.506
 qs_ot_p2m_diag                      82 11.4    0.262    0.269   14.795   14.811
 sum_up_and_integrate               127 10.3    0.131    0.144   14.757   14.787
 integrate_v_rspace                 127 11.3    0.004    0.004   14.626   14.653
 cp_fm_cholesky_invert               11 10.9   14.594   14.603   14.594   14.603
 qs_rho_update_rho_low              127  7.7    0.001    0.001   14.517   14.547
 calculate_rho_elec                 127  8.7    0.131    0.146   14.517   14.546
 cp_dbcsr_syevd                      82 12.4    0.005    0.006   13.764   13.765
 cp_fm_diag_elpa                     82 13.4    0.000    0.000   10.686   10.695
 cp_fm_diag_elpa_base                82 14.4   10.267   10.421   10.682   10.691
 init_scf_run                        11  5.9    0.000    0.001   10.584   10.584
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   10.584   10.584
 make_images_data                  4970 15.5    0.058    0.066    9.364   10.530
 hybrid_alltoall_any               5155 16.4    0.433    1.982    8.084    9.829
 density_rs2pw                      127  9.7    0.006    0.007    7.317    9.338
 multiply_cannon_metrocomm4       17395 15.5    0.062    0.072    3.468    9.235
 qs_ot_get_derivative_diag           76 12.4    0.002    0.002    8.892    9.170
 pw_transfer                       1535 11.6    0.086    0.102    8.987    9.082
 mp_irecv_dv                      49801 16.2    3.347    8.992    3.347    8.992
 fft_wrap_pw1pw2                   1281 12.7    0.010    0.012    8.764    8.864
 dbcsr_mm_accdrv_process          41158 16.2    4.288    4.675    8.045    8.150
 fft_wrap_pw1pw2_140                519 13.2    1.403    1.434    7.737    7.851
 grid_integrate_task_list           127 12.3    7.213    7.708    7.213    7.708
 wfi_extrapolate                     11  7.9    0.001    0.001    7.523    7.523
 cp_fm_cholesky_decompose            22 10.9    7.505    7.523    7.505    7.523
 rs_pw_transfer                    1038 11.9    0.013    0.015    5.366    7.394
 cp_fm_upper_to_full                104 14.8    5.697    7.236    5.697    7.236
 dbcsr_complete_redistribute        393 12.7    1.169    1.197    4.541    6.324
 fft3d_ps                          1281 14.7    2.719    2.939    5.903    5.974
 grid_collocate_task_list           127  9.7    4.943    5.871    4.943    5.871
 calculate_dm_sparse                127  9.5    0.001    0.001    5.707    5.823
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.443    5.448
 mp_alltoall_d11v                  2401 14.1    4.360    5.214    4.360    5.214
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    4.543    5.210
 copy_fm_to_dbcsr                   208 11.6    0.002    0.002    3.345    5.122
 potential_pw2rs                    127 12.3    0.021    0.024    4.876    4.895
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.545    4.712
 mp_allgather_i34                  2485 14.5    1.437    4.579    1.437    4.579
 mp_waitany                       11660 13.9    2.390    4.501    2.390    4.501
 mp_sum_l                          7884 12.9    3.181    4.499    3.181    4.499
 transfer_fm_to_dbcsr                11  9.9    0.020    0.030    2.369    4.085
 qs_ot_get_orbitals                 116 10.6    0.001    0.001    4.021    4.061
 rs_pw_transfer_RS2PW_140           138 11.5    0.328    0.345    1.933    3.960
 mp_alltoall_i22                    712 14.1    1.965    3.858    1.965    3.858
 qs_energies_init_hamiltonians       11  5.9    0.003    0.005    3.795    3.796
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    3.648    3.692
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="404", plot="h2o_256_md", label="(8n/4r/3t)", y=177.471000, yerr=0.000000
PlotPoint: name="405", plot="h2o_256_md_mem", label="(8n/4r/3t)", y=896.636364, yerr=9.441424
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/18/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1430454546432       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1975684956160       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1986255912960       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1992006770688       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2753958699008       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4454954827776       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5444944789504       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5492290093056       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6712799002624       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11613065416704       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15239182565376       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15239182565376       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19911132921856       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        94.245913E+12       0.0%      0.0%    100.0%
 flops max/rank                      4.387845E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6806580192       0.0%      0.0%    100.0%
 number of processed stacks               6033792       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1128.1
 marketing flops                   145.664755E+12
 -------------------------------------------------------------------------------
 # multiplications                           2535
 max memory usage/rank               1.141416E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1155960
 MPI messages size (bytes):
  total size                         2.039892E+12
  min size                           0.000000E+00
  max size                          17.653760E+06
  average size                       1.764674E+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              323584              36561747968
    131072 < size <=  4194304              723224             792350162944
   4194304 < size <= 16777216               70800             669922351760
  16777216 < size                           30960             541065216000
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4041                  57660.
 MP_Allreduce        11179                   1079.
 MP_Sync                88
 MP_Alltoall          1724               12509527.
 MP_SendRecv          5934                  75008.
 MP_ISendRecv         5934                  75008.
 MP_Wait             22612
 MP_ISend            15064                 244788.
 MP_IRecv            15064                 244788.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.034    0.047  190.849  190.850
 qs_mol_dyn_low                       1  2.0    0.003    0.003  190.447  190.460
 qs_forces                           11  3.9    0.004    0.004  189.790  189.797
 qs_energies                         11  4.9    0.001    0.001  182.565  182.574
 scf_env_do_scf                      11  5.9    0.001    0.001  165.816  165.824
 velocity_verlet                     10  3.0    0.001    0.001  127.112  127.138
 scf_env_do_scf_inner_loop          118  6.6    0.003    0.008  118.885  118.886
 qs_scf_new_mos                     118  7.6    0.001    0.001   80.821   81.134
 qs_scf_loop_do_ot                  118  8.6    0.001    0.001   80.820   81.133
 dbcsr_multiply_generic            2535 12.6    0.187    0.194   79.606   80.600
 ot_scf_mini                        118  9.6    0.003    0.004   76.292   76.576
 multiply_cannon                   2535 13.6    0.562    0.599   54.979   58.163
 multiply_cannon_loop              2535 14.6    1.203    1.228   51.303   53.518
 init_scf_loop                       11  6.9    0.000    0.000   46.808   46.809
 ot_mini                            118 10.6    0.001    0.001   42.579   42.863
 prepare_preconditioner              11  7.9    0.000    0.000   42.674   42.705
 make_preconditioner                 11  8.9    0.000    0.000   42.674   42.705
 make_full_inverse_cholesky          11  9.9    0.011    0.023   36.249   41.228
 multiply_cannon_multrec          30420 15.6   14.095   19.534   26.076   31.268
 rebuild_ks_matrix                  129  8.3    0.001    0.001   30.300   30.627
 qs_ks_build_kohn_sham_matrix       129  9.3    0.017    0.020   30.300   30.626
 mp_waitall_1                    149508 16.7   17.493   27.885   17.493   27.885
 qs_ks_update_qs_env                129  7.6    0.001    0.001   27.301   27.592
 qs_ot_get_derivative               118 11.6    0.001    0.002   22.693   22.989
 make_m2s                          5070 13.6    0.099    0.102   20.287   21.331
 make_images                       5070 14.6    1.955    2.247   19.977   21.020
 qs_ot_get_p                        129 10.4    0.001    0.001   19.879   20.202
 apply_preconditioner_dbcsr         129 12.6    0.000    0.001   19.196   20.016
 apply_single                       129 13.6    0.001    0.001   19.195   20.015
 ot_diis_step                       118 11.6    0.018    0.019   19.769   19.771
 cp_fm_upper_to_full                106 14.8   11.498   16.886   11.498   16.886
 cp_fm_cholesky_invert               11 10.9   16.496   16.505   16.496   16.505
 qs_ot_p2m_diag                      84 11.4    0.347    0.395   15.756   15.809
 multiply_cannon_metrocomm3       30420 15.6    0.048    0.051    6.604   15.264
 sum_up_and_integrate               129 10.3    0.141    0.153   14.977   15.003
 integrate_v_rspace                 129 11.3    0.004    0.004   14.836   14.866
 qs_rho_update_rho_low              129  7.7    0.001    0.001   14.815   14.849
 calculate_rho_elec                 129  8.7    0.177    0.194   14.815   14.848
 cp_dbcsr_syevd                      84 12.4    0.005    0.006   14.452   14.454
 dbcsr_complete_redistribute        397 12.7    1.499    1.614    9.045   12.760
 multiply_cannon_sync_h2d         30420 15.6   11.743   12.712   11.743   12.712
 make_images_data                  5070 15.6    0.063    0.068   10.912   12.669
 dbcsr_mm_accdrv_process          62852 16.2    7.406    8.425   11.546   12.154
 hybrid_alltoall_any               5257 16.5    0.531    2.242    9.822   11.927
 copy_fm_to_dbcsr                   210 11.7    0.001    0.002    7.655   11.374
 cp_fm_diag_elpa                     84 13.4    0.000    0.000   11.317   11.332
 cp_fm_diag_elpa_base                84 14.4   10.333   10.667   11.311   11.325
 init_scf_run                        11  5.9    0.000    0.001   10.857   10.858
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   10.857   10.858
 transfer_fm_to_dbcsr                11  9.9    0.001    0.006    6.402   10.057
 qs_ot_get_derivative_diag           78 12.4    0.002    0.002    9.422    9.634
 pw_transfer                       1559 11.6    0.088    0.101    9.301    9.387
 mp_alltoall_i22                    720 14.1    5.579    9.273    5.579    9.273
 fft_wrap_pw1pw2                   1301 12.7    0.010    0.011    9.072    9.164
 density_rs2pw                      129  9.7    0.006    0.007    7.136    8.554
 fft_wrap_pw1pw2_140                527 13.2    1.572    1.608    8.059    8.156
 grid_integrate_task_list           129 12.3    7.560    7.880    7.560    7.880
 wfi_extrapolate                     11  7.9    0.001    0.001    7.747    7.747
 cp_fm_cholesky_decompose            22 10.9    7.581    7.735    7.581    7.735
 multiply_cannon_metrocomm4       25350 15.6    0.081    0.094    2.885    7.330
 mp_irecv_dv                      76889 16.2    2.733    7.051    2.733    7.051
 rs_pw_transfer                    1054 12.0    0.013    0.015    4.837    6.346
 calculate_dm_sparse                129  9.5    0.001    0.001    6.206    6.311
 mp_alltoall_d11v                  2429 14.1    4.992    6.262    4.992    6.262
 fft3d_ps                          1301 14.7    2.859    2.944    5.971    6.041
 grid_collocate_task_list           129  9.7    5.189    5.923    5.189    5.923
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.431    5.483
 potential_pw2rs                    129 12.3    0.023    0.024    4.673    4.692
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    4.349    4.435
 qs_energies_init_hamiltonians       11  5.9    0.000    0.001    4.404    4.405
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.343    4.400
 qs_ot_get_orbitals                 118 10.6    0.001    0.001    4.213    4.267
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="406", plot="h2o_256_md", label="(8n/3r/4t)", y=190.850000, yerr=0.000000
PlotPoint: name="407", plot="h2o_256_md_mem", label="(8n/3r/4t)", y=1083.000000, yerr=14.572702
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/19/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420239992832       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528891191296       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514751E+12       0.0%      0.0%    100.0%
 flops max/rank                      5.865088E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755938624       0.0%      0.0%    100.0%
 number of processed stacks               1960712       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    3445.7
 marketing flops                   144.579337E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank               1.485533E+09
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  240672
 MPI messages size (bytes):
  total size                         1.331455E+12
  min size                           0.000000E+00
  max size                          52.428800E+06
  average size                       5.532237E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                 132                  8650752
    131072 < size <=  4194304              113904              59718500352
   4194304 < size <= 16777216              104976             550376570880
  16777216 < size                           20208             721350092304
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         8931                     51.
 MP_Alltoall          9654                 799394.
 MP_ISend            40068                2102572.
 MP_IRecv            40068                2101675.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3992                  58352.
 MP_Allreduce        11057                   1167.
 MP_Sync                87
 MP_Alltoall          1712               18838210.
 MP_SendRecv          3840                 122880.
 MP_ISendRecv         3840                 122880.
 MP_Wait             16122
 MP_ISend            10680                 423556.
 MP_IRecv            10680                 423556.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.019    0.034  187.577  187.578
 qs_mol_dyn_low                       1  2.0    0.003    0.003  187.141  187.153
 qs_forces                           11  3.9    0.004    0.004  186.693  186.700
 qs_energies                         11  4.9    0.001    0.001  178.916  178.930
 scf_env_do_scf                      11  5.9    0.001    0.001  160.901  160.905
 velocity_verlet                     10  3.0    0.001    0.001  122.724  122.750
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.008  121.594  121.595
 qs_scf_new_mos                     117  7.6    0.001    0.001   81.670   81.778
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   81.670   81.778
 ot_scf_mini                        117  9.6    0.003    0.004   77.161   77.230
 dbcsr_multiply_generic            2507 12.6    0.182    0.194   75.548   75.956
 multiply_cannon                   2507 13.6    0.582    0.625   54.722   58.523
 multiply_cannon_loop              2507 14.6    0.449    0.460   49.915   50.777
 ot_mini                            117 10.6    0.001    0.001   40.885   40.964
 init_scf_loop                       11  6.9    0.000    0.000   39.150   39.151
 prepare_preconditioner              11  7.9    0.000    0.000   35.178   35.211
 make_preconditioner                 11  8.9    0.000    0.000   35.178   35.211
 mp_waitall_1                    125778 16.7   26.748   33.816   26.748   33.816
 make_full_inverse_cholesky          11  9.9    0.017    0.027   33.034   33.340
 rebuild_ks_matrix                  128  8.3    0.001    0.001   30.668   30.773
 qs_ks_build_kohn_sham_matrix       128  9.3    0.017    0.018   30.668   30.772
 qs_ks_update_qs_env                128  7.6    0.001    0.001   27.763   27.857
 qs_ot_get_p                        128 10.4    0.001    0.001   23.290   23.399
 qs_ot_get_derivative               117 11.6    0.001    0.002   20.984   21.057
 multiply_cannon_multrec          10028 15.6   10.437   14.127   17.734   20.742
 cp_fm_cholesky_invert               11 10.9   20.200   20.207   20.200   20.207
 ot_diis_step                       117 11.6    0.020    0.022   19.829   19.829
 apply_preconditioner_dbcsr         128 12.6    0.000    0.000   19.443   19.602
 apply_single                       128 13.6    0.001    0.001   19.443   19.601
 make_m2s                          5014 13.6    0.067    0.071   16.942   19.452
 qs_ot_p2m_diag                      83 11.4    0.496    0.504   19.124   19.151
 make_images                       5014 14.6    2.305    2.759   16.635   19.145
 multiply_cannon_metrocomm3       10028 15.6    0.023    0.025   11.756   18.387
 cp_dbcsr_syevd                      83 12.4    0.005    0.006   17.837   17.842
 qs_rho_update_rho_low              128  7.7    0.001    0.001   16.168   16.224
 calculate_rho_elec                 128  8.7    0.259    0.270   16.167   16.223
 sum_up_and_integrate               128 10.3    0.181    0.191   15.790   15.835
 integrate_v_rspace                 128 11.3    0.004    0.004   15.609   15.662
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   14.296   14.304
 cp_fm_diag_elpa_base                83 14.4   13.997   14.125   14.287   14.295
 make_images_data                  5014 15.6    0.051    0.060   10.171   12.869
 hybrid_alltoall_any               5200 16.5    0.848    3.857    9.864   12.405
 multiply_cannon_sync_h2d         10028 15.6   11.593   11.939   11.593   11.939
 init_scf_run                        11  5.9    0.000    0.001   11.017   11.017
 scf_env_initial_rho_setup           11  6.9    0.002    0.003   11.016   11.017
 pw_transfer                       1547 11.6    0.087    0.098    9.877    9.924
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.011    9.649    9.705
 cp_fm_cholesky_decompose            22 10.9    9.240    9.364    9.240    9.364
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002    8.619    8.667
 fft_wrap_pw1pw2_140                523 13.2    1.918    1.955    8.372    8.430
 density_rs2pw                      128  9.7    0.006    0.006    7.517    8.405
 grid_integrate_task_list           128 12.3    7.745    8.291    7.745    8.291
 multiply_cannon_metrocomm1       10028 15.6    0.029    0.029    5.168    7.980
 wfi_extrapolate                     11  7.9    0.001    0.001    7.943    7.943
 dbcsr_mm_accdrv_process          20762 16.1    2.676    3.398    6.931    7.581
 mp_allgather_i34                  2507 14.6    3.011    7.172    3.011    7.172
 mp_alltoall_d11v                  2415 14.1    5.528    6.282    5.528    6.282
 calculate_dm_sparse                128  9.5    0.001    0.001    6.171    6.268
 fft3d_ps                          1291 14.7    2.762    2.842    6.117    6.178
 grid_collocate_task_list           128  9.7    5.468    6.137    5.468    6.137
 rs_pw_transfer                    1046 11.9    0.013    0.013    5.094    5.978
 dbcsr_complete_redistribute        395 12.7    2.137    2.191    5.476    5.922
 qs_energies_init_hamiltonians       11  5.9    0.005    0.008    5.319    5.321
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.296    5.315
 potential_pw2rs                    128 12.3    0.027    0.027    5.054    5.082
 multiply_cannon_metrocomm4        7521 15.6    0.023    0.027    1.872    4.248
 mp_irecv_dv                      28860 15.9    1.838    4.180    1.838    4.180
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.112    4.137
 copy_fm_to_dbcsr                   209 11.7    0.001    0.002    3.531    3.880
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    3.560    3.869
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    3.816    3.841
 copy_dbcsr_to_fm                   186 11.8    0.004    0.004    3.733    3.834
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    3.805    3.817
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="408", plot="h2o_256_md", label="(8n/2r/6t)", y=187.578000, yerr=0.000000
PlotPoint: name="409", plot="h2o_256_md_mem", label="(8n/2r/6t)", y=1396.090909, yerr=35.640770
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/20/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1399803918336       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1906965479424       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1943685697536       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1949312876544       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2694948675584       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4338990710784       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5303210868736       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5347334946816       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6535631601664       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11360512217088       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       14909202468864       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       14909202468864       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19481731219456       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        92.080533E+12       0.0%      0.0%    100.0%
 flops max/rank                     11.516853E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6655091424       0.0%      0.0%    100.0%
 number of processed stacks               1931936       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    3444.8
 marketing flops                   142.438295E+12
 -------------------------------------------------------------------------------
 # multiplications                           2464
 max memory usage/rank               3.151057E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                   98560
 MPI messages size (bytes):
  total size                         1.118682E+12
  min size                           0.000000E+00
  max size                         104.857600E+06
  average size                      11.350261E+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               44368              34435235840
   4194304 < size <= 16777216               43616             373376942080
  16777216 < size                            9960             710866973136
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4030                  58743.
 MP_Allreduce        11152                   1503.
 MP_Sync                87
 MP_Alltoall          1688               36934176.
 MP_SendRecv          1764                 218624.
 MP_ISendRecv         1764                 218624.
 MP_Wait              9654
 MP_ISend             6312                1080635.
 MP_IRecv             6312                1080635.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.060    0.075  313.749  313.750
 qs_mol_dyn_low                       1  2.0    0.003    0.003  312.846  313.097
 qs_forces                           11  3.9    0.004    0.004  312.713  312.717
 qs_energies                         11  4.9    0.001    0.001  303.187  303.198
 scf_env_do_scf                      11  5.9    0.001    0.001  280.189  280.202
 velocity_verlet                     10  3.0    0.001    0.001  223.440  223.448
 scf_env_do_scf_inner_loop          115  6.6    0.003    0.008  149.009  149.012
 init_scf_loop                       11  6.9    0.000    0.000  130.916  130.921
 prepare_preconditioner              11  7.9    0.000    0.000  125.818  125.848
 make_preconditioner                 11  8.9    0.000    0.000  125.818  125.848
 make_full_inverse_cholesky          11  9.9    0.037    0.039  101.257  122.827
 qs_scf_new_mos                     115  7.6    0.001    0.001   97.553   97.806
 qs_scf_loop_do_ot                  115  8.6    0.001    0.001   97.553   97.805
 ot_scf_mini                        115  9.6    0.003    0.004   92.774   92.893
 dbcsr_multiply_generic            2464 12.5    0.209    0.222   84.263   85.265
 cp_fm_upper_to_full                105 14.8   53.587   77.104   53.587   77.104
 multiply_cannon                   2464 13.5    0.698    0.763   57.824   59.269
 multiply_cannon_loop              2464 14.5    0.468    0.475   53.933   56.467
 ot_mini                            115 10.6    0.001    0.001   45.972   46.142
 dbcsr_complete_redistribute        395 12.7    3.967    4.013   30.432   43.484
 copy_fm_to_dbcsr                   209 11.7    0.001    0.002   26.938   39.941
 rebuild_ks_matrix                  126  8.3    0.001    0.001   38.585   38.790
 qs_ks_build_kohn_sham_matrix       126  9.3    0.017    0.017   38.584   38.790
 transfer_fm_to_dbcsr                11  9.9    0.032    0.033   24.514   37.294
 cp_fm_cholesky_invert               11 10.9   36.915   36.923   36.915   36.923
 qs_ks_update_qs_env                126  7.6    0.001    0.001   35.407   35.592
 mp_alltoall_i22                    712 14.1   22.305   35.485   22.305   35.485
 mp_waitall_1                    101902 16.8   28.428   34.133   28.428   34.133
 qs_ot_get_p                        126 10.4    0.001    0.001   31.414   31.542
 qs_ot_p2m_diag                      83 11.4    0.879    0.884   26.918   26.969
 qs_ot_get_derivative               115 11.6    0.002    0.002   25.854   25.990
 cp_dbcsr_syevd                      83 12.4    0.006    0.006   24.997   24.999
 make_m2s                          4928 13.5    0.074    0.076   20.929   22.031
 make_images                       4928 14.5    3.713    3.828   20.456   21.562
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   21.319   21.319
 cp_fm_diag_elpa_base                83 14.4   16.789   18.484   21.314   21.314
 qs_rho_update_rho_low              126  7.7    0.001    0.001   21.236   21.256
 calculate_rho_elec                 126  8.7    0.474    0.474   21.235   21.255
 multiply_cannon_metrocomm3        9856 15.5    0.023    0.025   18.105   20.528
 sum_up_and_integrate               126 10.3    0.317    0.321   20.129   20.204
 ot_diis_step                       115 11.6    0.022    0.022   20.050   20.050
 integrate_v_rspace                 126 11.3    0.004    0.004   19.812   19.889
 apply_preconditioner_dbcsr         126 12.6    0.000    0.000   19.021   19.534
 apply_single                       126 13.6    0.001    0.001   19.021   19.533
 multiply_cannon_multrec           9856 15.5   10.376   12.099   17.735   17.826
 multiply_cannon_sync_h2d          9856 15.5   15.412   15.426   15.412   15.426
 make_images_data                  4928 15.5    0.057    0.062   11.230   13.512
 hybrid_alltoall_any               5114 16.4    1.289    2.989   11.041   13.299
 init_scf_run                        11  5.9    0.000    0.001   12.898   12.898
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   12.897   12.898
 pw_transfer                       1523 11.6    0.091    0.091   12.149   12.166
 fft_wrap_pw1pw2                   1271 12.7    0.011    0.011   11.913   11.928
 cp_fm_cholesky_decompose            22 10.9   10.699   10.722   10.699   10.722
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002   10.496   10.612
 fft_wrap_pw1pw2_140                515 13.2    3.027    3.050   10.450   10.471
 mp_alltoall_d11v                  2399 14.1    8.870    9.788    8.870    9.788
 wfi_extrapolate                     11  7.9    0.001    0.001    9.618    9.618
 dbcsr_mm_accdrv_process          20422 16.0    3.754    5.478    7.124    8.963
 density_rs2pw                      126  9.7    0.005    0.005    8.715    8.880
 grid_integrate_task_list           126 12.3    8.474    8.664    8.474    8.664
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    8.004    8.005
 fft3d_ps                          1271 14.7    2.794    2.817    7.061    7.104
 calculate_dm_sparse                126  9.5    0.001    0.001    6.673    6.824
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.539    6.606
 grid_collocate_task_list           126  9.7    6.345    6.413    6.345    6.413
 rs_scatter_matrices                137  9.7    3.656    4.698    6.159    6.388
 copy_dbcsr_to_fm                   186 11.8    0.004    0.004    6.220    6.327
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="410", plot="h2o_256_md", label="(8n/1r/12t)", y=313.750000, yerr=0.000000
PlotPoint: name="411", plot="h2o_256_md_mem", label="(8n/1r/12t)", y=2843.090909, yerr=163.250758
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_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               1.259344E+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         3139                   6114.
 MP_Sync                 4
 MP_Alltoall            54               27522563.
 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    0.039    0.252   85.503   85.515
 qs_energies                          1  2.0    0.000    0.000   84.690   84.705
 ls_scf                               1  3.0    0.000    0.000   83.807   83.821
 dbcsr_multiply_generic             111  6.7    0.015    0.016   72.418   72.609
 multiply_cannon                    111  7.7    0.017    0.020   55.870   57.268
 multiply_cannon_loop               111  8.7    0.214    0.228   52.438   54.016
 ls_scf_main                          1  4.0    0.000    0.000   52.457   52.458
 density_matrix_trs4                  2  5.0    0.002    0.003   47.013   47.091
 ls_scf_init_scf                      1  4.0    0.000    0.002   28.394   28.399
 ls_scf_init_matrix_S                 1  5.0    0.000    0.002   27.173   27.226
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   25.019   25.040
 mp_waitall_1                     11031 10.9   21.455   24.664   21.455   24.664
 multiply_cannon_multrec           2664  9.7    8.244    9.023   15.650   17.432
 multiply_cannon_sync_h2d          2664  9.7   14.164   15.946   14.164   15.946
 make_m2s                           222  7.7    0.009    0.011   12.957   13.496
 make_images                        222  8.7    0.101    0.111   12.935   13.476
 multiply_cannon_metrocomm1        2664  9.7    0.010    0.011    9.021   12.900
 make_images_data                   222  9.7    0.005    0.006    7.514    8.045
 dbcsr_mm_accdrv_process           4760 10.4    0.507    0.635    7.022    7.967
 multiply_cannon_metrocomm3        2664  9.7    0.010    0.011    5.251    7.569
 hybrid_alltoall_any                227 10.6    0.219    1.836    6.472    7.435
 dbcsr_mm_accdrv_process_sort      4760 11.4    6.316    7.215    6.316    7.215
 calculate_norms                   4752  9.8    5.635    6.247    5.635    6.247
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.809    4.950
 mp_sum_l                           887  5.1    3.257    4.462    3.257    4.462
 multiply_cannon_metrocomm4        2442  9.7    0.012    0.015    2.064    3.579
 mp_irecv_dv                       6231 10.9    2.047    3.553    2.047    3.553
 arnoldi_extremal                     4  6.8    0.000    0.001    3.394    3.415
 arnoldi_normal_ev                    4  7.8    0.001    0.003    3.394    3.415
 build_subspace                      16  8.4    0.009    0.012    3.301    3.304
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    2.268    3.216
 make_images_sizes                  222  9.7    0.000    0.000    0.710    3.207
 mp_alltoall_i44                    222 10.7    0.710    3.207    0.710    3.207
 ls_scf_post                          1  4.0    0.000    0.000    2.955    2.970
 ls_scf_store_result                  1  5.0    0.000    0.000    2.771    2.813
 dbcsr_special_finalize             555  9.7    0.005    0.006    2.374    2.750
 dbcsr_merge_single_wm              555 10.7    0.458    0.591    2.365    2.742
 make_images_pack                   222  9.7    2.209    2.644    2.211    2.646
 dbcsr_matrix_vector_mult           304  9.0    0.006    0.013    2.397    2.625
 dbcsr_sort_data                    658 11.4    2.165    2.467    2.165    2.467
 dbcsr_matrix_vector_mult_local     304 10.0    2.055    2.446    2.057    2.448
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.358    2.417
 buffer_matrices_ensure_size        222  8.7    1.758    2.084    1.758    2.084
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.805    1.810
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.796    1.800
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.005    1.796    1.800
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="500", plot="h2o_32_nrep3_ls", label="(8n/12r/1t)", y=85.515000, yerr=0.000000
PlotPoint: name="501", plot="h2o_32_nrep3_ls_mem", label="(8n/12r/1t)", y=1131.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_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               2.082009E+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         3138                  10075.
 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    0.051    0.156   91.983   91.991
 qs_energies                          1  2.0    0.000    0.000   91.242   91.256
 ls_scf                               1  3.0    0.000    0.001   89.900   89.912
 dbcsr_multiply_generic             111  6.7    0.015    0.016   75.537   75.863
 multiply_cannon                    111  7.7    0.028    0.040   53.413   57.211
 ls_scf_main                          1  4.0    0.000    0.005   55.190   55.191
 multiply_cannon_loop               111  8.7    0.117    0.123   50.115   53.070
 density_matrix_trs4                  2  5.0    0.002    0.010   49.377   49.582
 ls_scf_init_scf                      1  4.0    0.006    0.017   31.140   31.141
 ls_scf_init_matrix_S                 1  5.0    0.004    0.015   29.891   30.004
 mp_waitall_1                      9105 10.9   21.259   29.797   21.259   29.797
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.457   27.472
 multiply_cannon_multrec           1332  9.7   13.138   16.619   22.448   27.095
 multiply_cannon_metrocomm3        1332  9.7    0.007    0.008   11.727   20.764
 make_m2s                           222  7.7    0.008    0.009   15.509   16.241
 make_images                        222  8.7    1.583    1.973   15.479   16.210
 dbcsr_mm_accdrv_process           4041 10.4    0.286    0.447    8.913   10.415
 dbcsr_mm_accdrv_process_sort      4041 11.4    8.507    9.993    8.507    9.993
 make_images_data                   222  9.7    0.004    0.005    8.877    9.943
 hybrid_alltoall_any                227 10.6    0.521    2.482    8.268    9.491
 mp_sum_l                           887  5.1    5.333    8.263    5.333    8.263
 multiply_cannon_metrocomm4        1221  9.7    0.007    0.008    3.204    7.753
 mp_irecv_dv                       3311 11.0    3.184    7.686    3.184    7.686
 calculate_norms                   2376  9.8    6.004    6.656    6.004    6.656
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    4.138    6.505
 multiply_cannon_sync_h2d          1332  9.7    4.813    5.780    4.813    5.780
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.036    5.215
 arnoldi_extremal                     4  6.8    0.000    0.001    4.788    4.806
 arnoldi_normal_ev                    4  7.8    0.001    0.005    4.788    4.806
 build_subspace                      16  8.4    0.014    0.021    4.529    4.533
 ls_scf_post                          1  4.0    0.001    0.006    3.569    3.583
 dbcsr_matrix_vector_mult           304  9.0    0.010    0.022    3.192    3.430
 ls_scf_store_result                  1  5.0    0.000    0.000    3.220    3.345
 dbcsr_matrix_vector_mult_local     304 10.0    2.740    3.225    2.742    3.227
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.004    1.284    2.875
 ls_scf_dm_to_ks                      2  5.0    0.000    0.017    2.670    2.772
 mp_allgather_i34                   111  8.7    0.988    2.439    0.988    2.439
 make_images_pack                   222  9.7    2.030    2.431    2.032    2.433
 dbcsr_sort_data                    436 11.2    1.841    2.083    1.841    2.083
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.893    1.895
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.881    1.882
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.003    1.881    1.882
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="502", plot="h2o_32_nrep3_ls", label="(8n/6r/2t)", y=91.991000, yerr=0.000000
PlotPoint: name="503", plot="h2o_32_nrep3_ls_mem", label="(8n/6r/2t)", y=1743.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_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               2.723021E+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         3138                  10896.
 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    0.038    0.068   93.791   93.793
 qs_energies                          1  2.0    0.000    0.000   93.022   93.025
 ls_scf                               1  3.0    0.000    0.001   91.601   91.605
 dbcsr_multiply_generic             111  6.7    0.016    0.017   75.918   76.201
 ls_scf_main                          1  4.0    0.000    0.002   57.257   57.263
 multiply_cannon                    111  7.7    0.045    0.165   52.727   57.069
 multiply_cannon_loop               111  8.7    0.101    0.106   49.122   52.775
 density_matrix_trs4                  2  5.0    0.002    0.003   51.251   51.436
 mp_waitall_1                      7281 11.0   23.077   32.947   23.077   32.947
 ls_scf_init_scf                      1  4.0    0.000    0.002   30.808   30.812
 ls_scf_init_matrix_S                 1  5.0    0.000    0.001   29.486   29.553
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.106   27.115
 multiply_cannon_multrec            888  9.7   12.680   15.297   21.278   24.498
 multiply_cannon_metrocomm3         888  9.7    0.004    0.004   10.928   22.339
 make_m2s                           222  7.7    0.007    0.008   16.688   17.989
 make_images                        222  8.7    1.979    2.298   16.649   17.952
 hybrid_alltoall_any                227 10.6    0.623    2.874    8.972   10.443
 make_images_data                   222  9.7    0.004    0.005    9.347   10.393
 dbcsr_mm_accdrv_process           3754 10.4    0.240    0.411    8.137    9.362
 dbcsr_mm_accdrv_process_sort      3754 11.4    7.767    8.951    7.767    8.951
 mp_sum_l                           887  5.1    4.945    8.364    4.945    8.364
 multiply_cannon_sync_h2d           888  9.7    6.033    7.686    6.033    7.686
 multiply_cannon_metrocomm4         777  9.7    0.004    0.005    2.471    7.032
 mp_irecv_dv                       2335 11.1    2.456    6.993    2.456    6.993
 multiply_cannon_metrocomm1         888  9.7    0.003    0.003    3.425    6.932
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.778    6.556
 arnoldi_extremal                     4  6.8    0.005    0.016    5.278    5.290
 arnoldi_normal_ev                    4  7.8    0.004    0.018    5.273    5.289
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.867    5.070
 build_subspace                      16  8.4    0.014    0.020    4.967    4.973
 calculate_norms                   1584  9.8    4.314    4.642    4.314    4.642
 dbcsr_matrix_vector_mult           304  9.0    0.009    0.021    3.501    3.835
 mp_allgather_i34                   111  8.7    1.433    3.710    1.433    3.710
 dbcsr_matrix_vector_mult_local     304 10.0    3.014    3.584    3.016    3.586
 ls_scf_post                          1  4.0    0.000    0.001    3.535    3.540
 ls_scf_store_result                  1  5.0    0.000    0.000    3.279    3.363
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.904    3.003
 dbcsr_sort_data                    325 11.1    1.902    2.216    1.902    2.216
 make_images_pack                   222  9.7    1.815    2.125    1.818    2.128
 make_images_sizes                  222  9.7    0.000    0.000    0.996    2.082
 mp_alltoall_i44                    222 10.7    0.996    2.081    0.996    2.081
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.011    2.013
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.992    1.994
 qs_ks_build_kohn_sham_matrix         3  8.3    0.004    0.013    1.992    1.994
 dbcsr_data_release                9322 10.9    1.306    1.990    1.306    1.990
 dbcsr_finalize                     304  7.8    0.027    0.032    1.628    1.920
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="504", plot="h2o_32_nrep3_ls", label="(8n/4r/3t)", y=93.793000, yerr=0.000000
PlotPoint: name="505", plot="h2o_32_nrep3_ls_mem", label="(8n/4r/3t)", y=2192.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_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               3.379110E+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         3138                  13030.
 MP_Sync                 4
 MP_Alltoall            47               30278988.
 MP_SendRecv            69                  86400.
 MP_ISendRecv           69                  86400.
 MP_Wait               531
 MP_ISend              378                 823502.
 MP_IRecv              378                 823753.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.040    0.055   97.451   97.452
 qs_energies                          1  2.0    0.000    0.000   96.772   96.777
 ls_scf                               1  3.0    0.000    0.000   95.120   95.127
 dbcsr_multiply_generic             111  6.7    0.017    0.018   78.722   78.951
 ls_scf_main                          1  4.0    0.000    0.000   59.027   59.029
 multiply_cannon                    111  7.7    0.060    0.214   51.904   55.944
 density_matrix_trs4                  2  5.0    0.002    0.003   52.868   52.998
 multiply_cannon_loop               111  8.7    0.115    0.125   46.950   49.843
 ls_scf_init_scf                      1  4.0    0.000    0.000   32.846   32.848
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   31.586   31.657
 mp_waitall_1                      6369 11.0   23.139   29.602   23.139   29.602
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.002   29.118   29.128
 multiply_cannon_multrec           1332  9.7   14.259   17.146   22.223   25.832
 make_m2s                           222  7.7    0.008    0.009   21.391   22.740
 make_images                        222  8.7    3.150    3.629   21.339   22.690
 multiply_cannon_metrocomm3        1332  9.7    0.003    0.003    9.438   16.585
 make_images_data                   222  9.7    0.004    0.005   11.982   13.531
 hybrid_alltoall_any                227 10.6    0.796    3.767   11.335   12.950
 dbcsr_mm_accdrv_process           3641 10.4    0.237    0.418    7.599    9.143
 dbcsr_mm_accdrv_process_sort      3641 11.4    7.224    8.717    7.224    8.717
 mp_sum_l                           887  5.1    3.847    6.937    3.847    6.937
 multiply_cannon_sync_h2d          1332  9.7    5.487    6.313    5.487    6.313
 multiply_cannon_metrocomm4        1110  9.7    0.004    0.006    2.078    5.998
 mp_irecv_dv                       3229 10.9    2.054    5.918    2.054    5.918
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    2.991    5.485
 arnoldi_extremal                     4  6.8    0.000    0.001    5.296    5.310
 arnoldi_normal_ev                    4  7.8    0.001    0.004    5.296    5.309
 build_subspace                      16  8.4    0.014    0.021    4.959    4.967
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.003    2.547    4.866
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.505    4.673
 calculate_norms                   2376  9.8    4.196    4.564    4.196    4.564
 mp_allgather_i34                   111  8.7    2.074    4.150    2.074    4.150
 dbcsr_matrix_vector_mult           304  9.0    0.010    0.021    3.596    3.912
 dbcsr_matrix_vector_mult_local     304 10.0    3.157    3.686    3.159    3.688
 dbcsr_sort_data                    658 11.4    3.065    3.338    3.065    3.338
 ls_scf_post                          1  4.0    0.000    0.000    3.247    3.252
 dbcsr_special_finalize             555  9.7    0.006    0.007    2.816    3.237
 dbcsr_merge_single_wm              555 10.7    0.533    0.662    2.807    3.228
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    3.065    3.113
 ls_scf_store_result                  1  5.0    0.000    0.000    3.000    3.052
 dbcsr_data_release               10477 10.7    1.596    2.413    1.596    2.413
 dbcsr_finalize                     304  7.8    0.050    0.062    1.802    1.992
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.961    1.962
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="506", plot="h2o_32_nrep3_ls", label="(8n/3r/4t)", y=97.452000, yerr=0.000000
PlotPoint: name="507", plot="h2o_32_nrep3_ls_mem", label="(8n/3r/4t)", y=2773.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_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               4.675895E+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         3129                  15263.
 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    0.058    0.067  100.347  100.349
 qs_energies                          1  2.0    0.000    0.000   99.521   99.527
 ls_scf                               1  3.0    0.000    0.000   97.582   97.589
 dbcsr_multiply_generic             111  6.7    0.017    0.019   78.675   78.917
 ls_scf_main                          1  4.0    0.000    0.000   62.726   62.727
 multiply_cannon                    111  7.7    0.086    0.205   55.638   61.426
 density_matrix_trs4                  2  5.0    0.002    0.003   55.437   55.565
 multiply_cannon_loop               111  8.7    0.070    0.079   51.045   53.073
 mp_waitall_1                      5436 11.0   26.629   32.336   26.629   32.336
 ls_scf_init_scf                      1  4.0    0.000    0.000   31.215   31.221
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   29.884   29.945
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.704   27.721
 multiply_cannon_multrec            444  9.7   14.108   16.608   21.223   24.620
 make_m2s                           222  7.7    0.006    0.007   17.949   20.509
 make_images                        222  8.7    3.732    4.430   17.886   20.447
 multiply_cannon_metrocomm1         444  9.7    0.002    0.002   11.324   16.458
 multiply_cannon_metrocomm3         444  9.7    0.001    0.001    6.100   14.640
 make_images_data                   222  9.7    0.003    0.004   10.004   12.602
 hybrid_alltoall_any                227 10.6    0.791    3.772    9.772   12.228
 multiply_cannon_sync_h2d           444  9.7    6.489    8.850    6.489    8.850
 dbcsr_mm_accdrv_process           3003 10.4    0.187    0.343    6.809    7.938
 dbcsr_mm_accdrv_process_sort      3003 11.4    6.495    7.598    6.495    7.598
 mp_allgather_i34                   111  8.7    2.811    6.979    2.811    6.979
 arnoldi_extremal                     4  6.8    0.000    0.001    5.991    6.008
 arnoldi_normal_ev                    4  7.8    0.002    0.005    5.991    6.007
 mp_sum_l                           887  5.1    3.111    5.722    3.111    5.722
 build_subspace                      16  8.4    0.015    0.019    5.595    5.606
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.640    4.821
 multiply_cannon_metrocomm4         333  9.7    0.001    0.002    1.678    4.494
 mp_irecv_dv                       1241 11.2    1.658    4.465    1.658    4.465
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    2.213    4.443
 dbcsr_matrix_vector_mult           304  9.0    0.011    0.022    4.148    4.339
 dbcsr_matrix_vector_mult_local     304 10.0    3.603    4.046    3.605    4.048
 make_images_sizes                  222  9.7    0.000    0.000    1.272    3.827
 mp_alltoall_i44                    222 10.7    1.271    3.827    1.271    3.827
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    3.652    3.752
 calculate_norms                    792  9.8    3.552    3.705    3.552    3.705
 ls_scf_post                          1  4.0    0.000    0.000    3.640    3.644
 ls_scf_store_result                  1  5.0    0.000    0.000    3.404    3.467
 dbcsr_finalize                     304  7.8    0.062    0.079    2.209    2.292
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.142    2.143
 dbcsr_merge_all                    275  8.9    0.474    0.526    2.056    2.127
 rebuild_ks_matrix                    3  7.3    0.000    0.000    2.109    2.110
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.001    2.109    2.110
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="508", plot="h2o_32_nrep3_ls", label="(8n/2r/6t)", y=100.349000, yerr=0.000000
PlotPoint: name="509", plot="h2o_32_nrep3_ls_mem", label="(8n/2r/6t)", y=3653.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_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               8.813076E+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         3123                  21388.
 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    0.079    0.113  107.665  107.667
 qs_energies                          1  2.0    0.000    0.000  106.236  106.250
 ls_scf                               1  3.0    0.000    0.000  103.328  103.341
 dbcsr_multiply_generic             111  6.7    0.024    0.027   76.721   76.847
 ls_scf_main                          1  4.0    0.000    0.000   65.372   65.374
 density_matrix_trs4                  2  5.0    0.002    0.003   56.072   56.119
 multiply_cannon                    111  7.7    0.165    0.289   49.488   51.341
 multiply_cannon_loop               111  8.7    0.068    0.072   46.126   47.006
 ls_scf_init_scf                      1  4.0    0.000    0.000   34.310   34.311
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   32.696   32.708
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   29.859   29.871
 mp_waitall_1                      4527 11.1   21.598   24.964   21.598   24.964
 make_m2s                           222  7.7    0.007    0.007   23.715   24.556
 make_images                        222  8.7    4.595    5.018   23.605   24.445
 multiply_cannon_multrec            444  9.7   17.892   18.543   22.542   23.170
 hybrid_alltoall_any                227 10.6    1.663    3.622   12.834   15.361
 make_images_data                   222  9.7    0.003    0.004   12.952   15.212
 multiply_cannon_metrocomm3         444  9.7    0.001    0.001   10.071   10.570
 multiply_cannon_sync_h2d           444  9.7    8.850    8.901    8.850    8.901
 arnoldi_extremal                     4  6.8    0.001    0.001    7.347    7.363
 arnoldi_normal_ev                    4  7.8    0.003    0.009    7.346    7.363
 build_subspace                      16  8.4    0.026    0.036    6.781    6.800
 dbcsr_matrix_vector_mult           304  9.0    0.017    0.034    5.413    5.443
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    5.244    5.342
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.005    5.239
 dbcsr_matrix_vector_mult_local     304 10.0    4.862    5.128    4.865    5.131
 dbcsr_mm_accdrv_process           1814 10.4    0.230    0.325    4.486    4.632
 dbcsr_mm_accdrv_process_sort      1814 11.4    4.188    4.321    4.188    4.321
 ls_scf_post                          1  4.0    0.000    0.000    3.646    3.658
 make_images_sizes                  222  9.7    0.000    0.000    1.413    3.462
 mp_alltoall_i44                    222 10.7    1.412    3.462    1.412    3.462
 ls_scf_store_result                  1  5.0    0.000    0.000    3.398    3.412
 calculate_norms                    792  9.8    3.238    3.282    3.238    3.282
 dbcsr_finalize                     304  7.8    0.082    0.090    3.085    3.183
 mp_allgather_i34                   111  8.7    0.979    3.034    0.979    3.034
 dbcsr_merge_all                    275  8.9    0.889    0.916    2.868    2.958
 dbcsr_complete_redistribute          5  7.6    1.429    1.466    2.759    2.891
 qs_energies_init_hamiltonians        1  3.0    0.001    0.001    2.878    2.878
 dbcsr_data_release               12724 10.6    2.317    2.850    2.317    2.850
 matrix_ls_to_qs                      2  6.0    0.000    0.000    2.414    2.544
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.525    2.527
 dbcsr_sort_data                    325 11.1    2.440    2.510    2.440    2.510
 rebuild_ks_matrix                    3  7.3    0.000    0.000    2.458    2.460
 qs_ks_build_kohn_sham_matrix         3  8.3    0.002    0.002    2.458    2.460
 dbcsr_new_transposed                 4  7.5    0.243    0.251    2.354    2.382
 dbcsr_frobenius_norm                74  6.6    2.057    2.135    2.192    2.233
 dbcsr_add_d                        103  6.2    0.000    0.000    2.133    2.207
 dbcsr_add_anytype                  103  7.2    0.859    0.893    2.133    2.207
 mp_alltoall_d11v                    48  9.2    2.096    2.179    2.096    2.179
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="510", plot="h2o_32_nrep3_ls", label="(8n/1r/12t)", y=107.667000, yerr=0.000000
PlotPoint: name="511", plot="h2o_32_nrep3_ls_mem", label="(8n/1r/12t)", y=6838.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa_performance_tests/27/result.log


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

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32        7009386627072       0.0%      0.0%    100.0%
 flops     9 x     9 x    32        7335108845568       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        9866241589248       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        9884108906496       0.0%      0.0%    100.0%
 flops    22 x    22 x    32       13354440523776       0.0%      0.0%    100.0%
 flops    32 x    32 x     9       20607185977344       0.0%      0.0%    100.0%
 flops    32 x    32 x    22       25186560638976       0.0%      0.0%    100.0%
 flops     9 x    32 x    32       28458319085568       0.0%      0.0%    100.0%
 flops    22 x    32 x    32       34782389993472       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       42881542373376       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       55680402235392       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       55680402235392       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       72328573419520       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                       383.054662E+12       0.0%      0.0%    100.0%
 flops max/rank                    733.641090E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                        26899403712       0.0%      0.0%    100.0%
 number of processed stacks             118860288       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     226.3
 marketing flops                   780.439111E+12
 -------------------------------------------------------------------------------
 # multiplications                           1445
 max memory usage/rank             585.879552E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged               102097920
 MPI messages size (bytes):
  total size                        37.227590E+12
  min size                           0.000000E+00
  max size                           4.551360E+06
  average size                     364.626312E+03
 MPI breakdown and total messages size (bytes):
             size <=      128              731472                        0
       128 < size <=     8192            11922720              97670922240
      8192 < size <=    32768            24718992             614677610496
     32768 < size <=   131072            20000256            1970081366016
    131072 < size <=  4194304            42515668           24886801223040
   4194304 < size <= 16777216             2208812            9656099886720
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4640                  76559.
 MP_Allreduce        13232                   2081.
 MP_Sync              1064
 MP_Alltoall          2588              813475758.
 MP_SendRecv        168740                  11136.
 MP_ISendRecv        92040                  11136.
 MP_Wait            102830
 MP_comm_split          40
 MP_ISend            26090                  85106.
 MP_IRecv            37890                  59644.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.046    0.102  285.874  285.877
 qs_mol_dyn_low                       1  2.0    0.003    0.014  284.745  284.766
 qs_forces                            5  3.8    0.023    0.078  284.643  284.646
 qs_energies                          5  4.8    0.002    0.052  281.162  281.231
 scf_env_do_scf                       5  5.8    0.001    0.009  262.046  262.050
 scf_env_do_scf_inner_loop          105  6.6    0.003    0.029  228.196  228.201
 qs_scf_new_mos                     105  7.6    0.001    0.001  178.296  178.574
 qs_scf_loop_do_ot                  105  8.6    0.001    0.001  178.295  178.574
 ot_scf_mini                        105  9.6    0.003    0.012  168.301  168.481
 dbcsr_multiply_generic            1445 12.2    0.135    0.142  138.666  139.490
 multiply_cannon                   1445 13.2    0.277    0.294  117.730  120.835
 velocity_verlet                      4  3.0    0.001    0.007  118.217  118.218
 multiply_cannon_loop              1445 14.2    2.391    2.525  115.269  117.431
 qs_ot_get_p                        112 10.4    0.001    0.001   75.910   76.187
 qs_ot_p2m_diag                      40 11.0    0.020    0.034   64.051   64.154
 ot_mini                            105 10.6    0.001    0.009   61.896   62.019
 cp_dbcsr_syevd                      40 12.0    0.002    0.003   60.673   60.675
 cp_fm_syevd                         40 13.0    0.000    0.001   54.275   54.424
 cp_fm_redistribute_end              40 14.0   24.394   48.687   24.403   48.694
 cp_fm_syevd_base                    40 14.0   24.269   48.561   24.269   48.561
 mp_waitall_1                    488190 16.1   37.392   46.313   37.392   46.313
 multiply_cannon_multrec          69360 15.2   31.640   36.878   39.423   45.047
 qs_ot_get_derivative                55 11.6    0.001    0.001   40.051   40.185
 multiply_cannon_metrocomm3       69360 15.2    0.195    0.208   25.664   35.553
 multiply_cannon_sync_h2d         69360 15.2   30.292   34.621   30.292   34.621
 init_scf_loop                        7  6.6    0.000    0.005   33.800   33.803
 rebuild_ks_matrix                  110  8.4    0.000    0.000   32.980   33.178
 qs_ks_build_kohn_sham_matrix       110  9.4    0.012    0.029   32.980   33.177
 qs_ks_update_qs_env                112  7.6    0.001    0.001   30.236   30.415
 prepare_preconditioner               7  7.6    0.000    0.001   28.203   28.238
 make_preconditioner                  7  8.6    0.000    0.003   28.203   28.238
 qs_rho_update_rho_low              110  7.6    0.001    0.002   23.965   24.279
 calculate_rho_elec                 110  8.6    0.030    0.033   23.964   24.278
 apply_preconditioner_dbcsr          62 12.6    0.000    0.001   23.158   23.383
 apply_single                        62 13.6    0.000    0.000   23.158   23.383
 ot_new_cg_direction                 55 11.6    0.001    0.003   21.144   21.146
 rs_pw_transfer                     690 11.5    0.011    0.013   19.797   21.020
 make_full_inverse_cholesky           7  9.6    0.000    0.015   20.035   20.100
 density_rs2pw                      110  9.6    0.006    0.008   17.521   18.731
 init_scf_run                         5  5.8    0.000    0.001   16.080   16.081
 scf_env_initial_rho_setup            5  6.8    0.001    0.003   16.080   16.081
 qs_ot_get_orbitals                 105 10.6    0.001    0.001   15.141   15.389
 qs_ot_get_derivative_taylor         37 12.8    0.001    0.001   14.326   14.427
 cp_fm_cholesky_invert                7 10.6   13.794   13.815   13.794   13.815
 pw_transfer                       1645 12.4    0.086    0.116   13.182   13.478
 fft_wrap_pw1pw2                   1425 13.5    0.014    0.018   13.037   13.333
 mp_sum_l                          4764 12.2   12.527   13.327   12.527   13.327
 sum_up_and_integrate                60 10.3    0.028    0.032   11.853   11.871
 integrate_v_rspace                  60 11.3    0.002    0.004   11.825   11.843
 calculate_dm_sparse                110  9.5    0.000    0.001   11.624   11.815
 check_diag                          80 13.5    8.590    8.864   11.071   11.228
 fft_wrap_pw1pw2_240                915 15.0    1.227    1.329   10.952   11.217
 qs_vxc_create                      110 10.4    0.003    0.018   11.015   11.072
 cp_dbcsr_sm_fm_multiply             15  9.3    0.001    0.002   10.837   10.854
 qs_ot_get_derivative_diag           18 12.0    0.000    0.000   10.731   10.809
 calculate_first_density_matrix       1  7.0    0.000    0.011   10.636   10.654
 acc_transpose_blocks             69360 15.2    0.359    0.378   10.034   10.572
 cp_dbcsr_sm_fm_multiply_core        15 10.3    0.000    0.000   10.310   10.380
 fft3d_pb                           915 16.0    2.395    2.762    8.967    9.386
 multiply_cannon_metrocomm1       69360 15.2    0.092    0.098    4.597    9.219
 make_m2s                          2890 13.2    0.081    0.089    7.960    8.579
 acc_transpose_blocks_kernels     69360 16.2    0.857    0.902    8.112    8.536
 dbcsr_mm_accdrv_process         154766 15.8    4.003    4.199    7.653    8.491
 make_images                       2890 14.2    0.243    0.262    7.851    8.469
 rs_pw_transfer_RS2PW_30            110 11.6    1.595    1.686    7.274    7.882
 make_full_single_inverse             7  9.6    0.001    0.030    7.811    7.845
 xc_rho_set_and_dset_create         110 12.4    0.080    0.185    7.552    7.807
 potential_pw2rs                     60 12.3    0.003    0.003    7.611    7.656
 jit_kernel_transpose                 5 15.0    7.255    7.652    7.255    7.652
 xc_vxc_pw_create                    60 11.3    0.040    0.093    7.454    7.512
 mp_sendrecv_dv                  168740 12.6    7.097    7.259    7.097    7.259
 xc_pw_derive                       510 13.4    0.006    0.007    6.649    6.719
 mp_alltoall_z22v                  2340 17.7    6.046    6.543    6.046    6.543
 mp_waitany                        7680 13.5    4.615    5.855    4.615    5.855
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="601", plot="h2o_512_md", label="(64n/12r/1t)", y=285.877000, yerr=0.000000
PlotPoint: name="602", plot="h2o_512_md_mem", label="(64n/12r/1t)", y=557.400000, yerr=1.959592
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


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

CommitSHA: a6796a009e3fddc5e6710b248fd74d0bcfe5ccaa
Summary: empty
Status: OK