قم بتثبيت إصدار GPL من HPL مع OpenBLAS

تثبيت حزمة MODULES

$ yum install environment-modules
$ mcedit /etc/modulefailes/test/v1.0
  #%Module1.0
  proc ModulesHelp { } {
    global version
      puts stderr "Modulefile for test v1.0"
      }
      set version v1.0
      module-whatis "Modulefile for test v1.0"
      # Our environment
      setenv MAINDIR /nfs/software/test/v1.0
      prepend-path PATH $env(MAINDIR)/bin
      prepend-path C_INCLUDE_PATH $env(MAINDIR)/include
      prepend-path CPLUS_INCLUDE_PATH $env(MAINDIR)/include
      prepend-path LIBRARY_PATH $env(MAINDIR)/lib64
      prepend-path LD_LIBRARY_PATH $env(MAINDIR)/lib64

تحقق من ملفات الوحدة

$ cat check-modulefiles
  #!/bin/sh
  ModulePath=$1
  MainDir=$(cat $ModulePath | grep "setenv MAINDIR" | cut -f7 -d " ")
  ListOfPaths=$(cat $ModulePath | grep path | cut -f7 -d " ")
  #Replace MainDir setenv in modulefile
  ListOfPaths=$(echo $ListOfPaths | sed "s@\$env(MAINDIR)@$MainDir@g")
  for u in $ListOfPaths; do
    ls -la $u 1> /dev/null 2> /dev/null;
    printf "%60s %4d\n" $u $?;
  done
$ chmod +x check-modulefiles
$ ./check-modulefiles /etc/modulefiles/test/v1.0
  /nfs/software/test/v1.0/bin            0
  /nfs/software/test/v1.0/include        0
  /nfs/software/test/v1.0/include        0
  /nfs/software/test/v1.0/lib64          0
  /nfs/software/test/v1.0/lib64          0

أوامر إدارة الوحدة النمطية

$ module avail
$ module add cuda/v10.1
$ nvcc –version
  Cuda compilation tools, release 10.1, V10.1.168
$ module switch cuda/v10.1 cuda/v9.2
$ nvcc –version
  Cuda compilation tools, release 9.2, V9.2.88
$ module list
$ module rm cuda/v9.2

تثبيت CUDA

$ chmod +x cuda_9.2.run
$ ./cuda_9.2.run
  Do you accept the previously read EULA? accept
  Install the CUDA 9.2 Toolkit? yes
  Enter Toolkit Location: /nfs/software/cuda/v9.2
  Do you want to install a symbolic link at /usr/local/cuda? no
  Install the CUDA 9.2 Samples? no
$ cat /etc/modulefiles/cuda/v9.2
  #%Module1.0
  proc ModulesHelp { } {
    global version
      puts stderr "Modulefile for cuda v9.2"
      }
      set version v9.2
      module-whatis "Modulefile for cuda v9.2"
      # Our environment
      setenv MAINDIR /nfs/software/cuda/v9.2
      prepend-path PATH $env(MAINDIR)/bin
      prepend-path C_INCLUDE_PATH $env(MAINDIR)/include
      prepend-path CPLUS_INCLUDE_PATH $env(MAINDIR)/include
      prepend-path LIBRARY_PATH $env(MAINDIR)/lib64/stubs
      prepend-path LIBRARY_PATH $env(MAINDIR)/lib64
      prepend-path LD_LIBRARY_PATH $env(MAINDIR)/lib64/stubs
      prepend-path LD_LIBRARY_PATH $env(MAINDIR)/lib64
  $ module add cuda/v9.2
  $ nvcc --version
  Cuda compilation tools, release 9.2, V9.2.148

قم بتثبيت OpenBLAS

$ wget https://github.com/xianyi/OpenBLAS/archive/v0.3.6.tar.gz
$ tar -xzvf v0.3.6.tar.gz
$ cd OpenBLAS-0.3.6
$ mkdir -p /nfs/software/openblas/v0.3.6
$ make -j4
$ make PREFIX=/nfs/software/openblas/v0.3.6/ install
$ ls -la /nfs/software/openblas/v0.3.6/lib/
$ cat /etc/modulefiles/openblas/v0.3.6
  #%Module1.0
  proc ModulesHelp { } {
    global version
      puts stderr "Modulefile for openblas v0.3.6"
      }
      set version v0.3.6
      module-whatis "Modulefile for openblas v0.3.6"
      # Our environment
      setenv MAINDIR /nfs/software/openblas/v0.3.6
      prepend-path PATH $env(MAINDIR)/bin
      prepend-path C_INCLUDE_PATH $env(MAINDIR)/include
      prepend-path CPLUS_INCLUDE_PATH $env(MAINDIR)/include
      prepend-path LIBRARY_PATH $env(MAINDIR)/lib
      prepend-path LD_LIBRARY_PATH $env(MAINDIR)/lib
$ ls -la /nfs/software/openblas/v0.3.6/lib

قم بتثبيت OpenMPI

wget https://download.open-mpi.org/release/open-mpi/v2.1/openmpi-2.1.6.tar.gz
$ tar -xzvf openmpi-2.1.6.tar.gz
$ cd openmpi-2.1.6
$ mkdir -p /nfs/software/openmpi/v2.1.6
$ module add cuda/v9.2
$ ./configure --prefix=/nfs/software/openmpi/v2.1.6/ --with-cuda --enable-static
$ make
$ make install
$ cat /etc/modulefiles/openmpi/v2.1.6
#%Module1.0
proc ModulesHelp { } {
  global version
    puts stderr "Modulefile for openmpi v2.1.6"
    }
    set version v2.1.6
    module-whatis "Modulefile for openmpi v2.1.6"
    # Our environment
    setenv MAINDIR /nfs/software/openmpi/v2.1.6
    prepend-path PATH $env(MAINDIR)/bin
    prepend-path C_INCLUDE_PATH $env(MAINDIR)/include
    prepend-path CPLUS_INCLUDE_PATH $env(MAINDIR)/include
    prepend-path LIBRARY_PATH $env(MAINDIR)/lib
    prepend-path LD_LIBRARY_PATH $env(MAINDIR)/lib
$ module add openmpi/v2.1.6
$ mpirun --version
mpirun (Open MPI) 2.1.6

قم بتثبيت HPL لوحدة معالجة الرسومات

$ module add openmpi/v2.1.6
$ module add cuda/v9.2
$ module add openblas/v0.3.6
$ wget https://developer.download.nvidia.com/assets/cuda/secure/AcceleratedLinpack/hpl-2.0_FERMI_v15.tgz
$ tar -xvf hpl-2.0_FERMI_v15.tgz
$ mv hpl-2.0_FERMI_v15.tgz hpl-2.0
$ cd hpl-2.0

$ cat Make.CUDA
  SHELL        = /bin/sh
  CD           = cd
  CP           = cp
  LN_S         = ln -fs
  MKDIR        = mkdir -p
  RM           = /bin/rm -f
  TOUCH        = touch
  ARCH         = CUDA
  
  TOPdir       = /home/user/hpl-2.0
  INCdir       = $(TOPdir)/include
  BINdir       = $(TOPdir)/bin/$(ARCH)
  LIBdir       = $(TOPdir)/lib/$(ARCH)
  HPLlib       = $(LIBdir)/libhpl.a
  
  MPdir        = /nfs/software/openmpi/v2.1.6
  MPinc        = -I$(MPdir)/include
  MPlib        = -L$(MPdir)/lib -lmpi
  
  LAdir        = /nfs/software/openblas/v0.3.6
  LAinc        = -I$(LAdir)/include
  LAlib        = -L$(TOPdir)/src/cuda -ldgemm -L/nfs/software/cuda/v9.2/lib64 -lcuda -lcudart -lcublas -L$(LAdir)/lib -lopenblas
  F2CDEFS      = -DAdd__ -DF77_INTEGER=int -DStringSunStyle
  HPL_INCLUDES = -I$(INCdir) -I$(INCdir)/$(ARCH) $(LAinc) $(MPinc)
  HPL_LIBS     = $(HPLlib) $(LAlib) $(MPlib)
  HPL_OPTS     =  -DCUDA
  HPL_DEFS     = $(F2CDEFS) $(HPL_OPTS) $(HPL_INCLUDES)
  CC           = mpicc
  CCFLAGS      = -fopenmp -lpthread -fomit-frame-pointer -O3 -funroll-loops $(HPL_DEFS)
  CCNOOPT      = $(HPL_DEFS) -O0 -w
  LINKER       = $(CC)
  LINKFLAGS    = $(CCFLAGS)
  ARCHIVER     = ar
  ARFLAGS      = r
  RANLIB       = echo
  MAKE         = make TOPdir=$(TOPdir)

$ mcedit src/cuda/cuda_dgemm.c
  …
  // handle2 = dlopen ("libmkl_intel_lp64.so", RTLD_LAZY);
  handle2 = dlopen ("libopenblas.so", RTLD_LAZY);
  …
  // dgemm_mkl = (void(*)())dlsym(handle, "dgemm");
  dgemm_mkl = (void(*)())dlsym(handle, "dgemm_");
  …
  // handle = dlopen ("libmkl_intel_lp64.so", RTLD_LAZY);
  handle = dlopen ("libopenblas.so", RTLD_LAZY);
  …
  // mkl_dtrsm = (void(*)())dlsym(handle2, "dtrsm");
  mkl_dtrsm = (void(*)())dlsym(handle2, "dtrsm_");

$ make arch=CUDA
$ cd bin/CUDA
$ export LD_LIBRARY_PATH=/home/user/hpl-2.0/src/cuda/:$LD_LIBRARY_PATH
$ mpirun -np 4 ./xhpl
  ================================================================================
  HPLinpack 2.0  --  High-Performance Linpack benchmark  --   September 10, 2008
  Written by A. Petitet and R. Clint Whaley,  Innovative Computing Laboratory, UTK
  Modified by Piotr Luszczek, Innovative Computing Laboratory, UTK
  Modified by Julien Langou, University of Colorado Denver
  ================================================================================

  An explanation of the input/output parameters follows:
  T/V    : Wall time / encoded variant.
  N      : The order of the coefficient matrix A.
  NB     : The partitioning blocking factor.
  P      : The number of process rows.
  Q      : The number of process columns.
  Time   : Time in seconds to solve the linear system.
  Gflops : Rate of execution for solving the linear system.

  The following parameter values will be used:

  N      :   25000
  NB     :     768
  PMAP   : Row-major process mapping
  P      :       2
  Q      :       2
  PFACT  :    Left
  NBMIN  :       2
  NDIV   :       2
  RFACT  :    Left
  BCAST  :   1ring
  DEPTH  :       1
  SWAP   : Spread-roll (long)
  L1     : no-transposed form
  U      : no-transposed form
  EQUIL  : yes
  ALIGN  : 8 double precision words

  --------------------------------------------------------------------------------

  - The matrix A is randomly generated for each test.
  - The following scaled residual check will be computed:
        ||Ax-b||_oo / ( eps * ( || x ||_oo * || A ||_oo + || b ||_oo ) * N )
  - The relative machine precision (eps) is taken to be               1.110223e-16
  - Computational tests pass if scaled residuals are less than                16.0

  ================================================================================
  T/V                N    NB     P     Q               Time                 Gflops
  --------------------------------------------------------------------------------
  WR10L2L2       25000   768     2     2              16.72              6.232e+02
  --------------------------------------------------------------------------------
  ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)=        0.0019019 ...... PASSED
  ================================================================================

  Finished      1 tests with the following results:
                1 tests completed and passed residual checks,
                0 tests completed and failed residual checks,
                0 tests skipped because of illegal input values.
  --------------------------------------------------------------------------------

  End of Tests.
  ================================================================================