#!/bin/bash
##############################################################
#
# HPL-AI Mixed-Precision Benchmark v2.3a  --  March 14, 2021
#
##############################################################
#
# Check out <https://wu-kan.cn/_posts/2021-03-14-HPL-AI/> for
# the full document and the latest information.
#
##############################################################
#
# A quick start to build and run a few tests: ./README

# First the following softwares are required on your system:
# C&C++ compiler, autoconf, autoconf-archive, automake, mpi,
# blas, blaspp
#
# You can easily install and load the requirements via spack
# <https://github.com/spack/spack/releases/tag/v0.16.1>.
#
# I just tested with the followings, while other versions or
# libraries might work as well:

spack unload -a
spack load [email protected]
spack load [email protected]%[email protected]
spack load [email protected]%[email protected]
spack load [email protected]%[email protected]
spack load [email protected]%[email protected]~cxx~cxx_exceptions
spack load [email protected]%[email protected]+openmp~cuda \
    ^[email protected]%[email protected] threads=openmp

# Then boostrap the configuration files by typing:

autoreconf -ivf

# The user is given the opportunity to compile the software
# with some specific compile options:
#
# CPPFLAGS=" -DHPLAI_T_AFLOAT=double "
#
# CPPFLAGS=" -DHPLAI_DEVICE_BLASPP_GEMM "
#
# CPPFLAGS=" -DHPLAI_DEVICE_BLASPP_TRSM "
#
# CPPFLAGS=" -DHPLAI_GEN_BLASPP_GEMM "
#
# CPPFLAGS=" -DHPLAI_GEN_BLASPP_TRSM "
#
# CPPFLAGS=" -DHPLAI_GEN_BLASPP_TRSV "
#
# CPPFLAGS=" -DHPLAI_PMAT_REGEN "
#
# CPPFLAGS=" -DHPL_COPY_L "
#
# CPPFLAGS=" -DHPL_CALL_CBLAS "
#
# CPPFLAGS=" -DHPL_CALL_VSIPL "
# (deperated)
#
# CPPFLAGS=" -DHPL_DETAILED_TIMING "
# (deperated)
#
# To configure the build and prepare for compilation run:

./configure

# Note: to use device blaspp routines, you may need to enable
# CUDA support of blaspp:
#
# spack load [email protected]%[email protected]+openmp+cuda
#
# and then:
#
# ./configure \
#     LIBS=" -lcudart -lcublas " \
#     CPPFLAGS=" -DBLASPP_WITH_CUBLAS \
#         -DHPLAI_DEVICE_BLASPP_GEMM \
#         -DHPLAI_DEVICE_BLASPP_TRSM "

# Then compile:

make -j

# The configuration file must be called HPL.dat.
#
# You can copy the configuration file from the original HPL,
# or create a configuration file anew.
#
# Most of the performance parameters can be tuned.

if true; then
    cp testing/ptest/HPL.dat HPL.dat
else
    cat >HPL.dat <<EOF
HPLinpack benchmark input file
Innovative Computing Laboratory, University of Tennessee
HPL.out      output file name (if any)
6            device out (6=stdout,7=stderr,file)
1            # of problems sizes (N) 
16384 143360 Ns  
1            # of NBs 
384 192 256  NBs 
1            PMAP process mapping (0=Row-,1=Column-major)
1            # of process grids (P x Q)
2 1 4        Ps  
2 4 1        Qs  
16.0         threshold
1            # of panel fact
2 1 0        PFACTs (0=left, 1=Crout, 2=Right)
1            # of recursive stopping criterium
2            NBMINs (>= 1)
1            # of panels in recursion
2            NDIVs
1            # of recursive panel fact.
2 1 0        RFACTs (0=left, 1=Crout, 2=Right)
1            # of broadcast
0            BCASTs (0=1rg,1=1rM,2=2rg,3=2rM,4=Lng,5=LnM)
1            # of lookahead depth
0            DEPTHs (>=0)
0            SWAP (0=bin-exch,1=long,2=mix)
1            swapping threshold
1            L1 in (0=transposed,1=no-transposed) form
1            U  in (0=transposed,1=no-transposed) form
0            Equilibration (0=no,1=yes)
8            memory alignment in double (> 0)
EOF
fi

# Finally run and compare with the original hpl-2.3:

mpiexec -n 4 -x OMP_NUM_THREADS=2 testing/xhpl
mpiexec -n 4 -x OMP_NUM_THREADS=2 testing/xhplai

# If you download HPL-AI via git, you can clean the builds by:

git clean -d -f -q -x

##############################################################
#
# The newest version of HPL-AI is available at
# <https://github.com/wu-kan/HPL-AI/releases>
#
##############################################################
#
# Bugs are tracked at
# <https://github.com/wu-kan/HPL-AI/issues>
#
##############################################################
#
# The souce code of HPL-AI is licensed under `COPYING`.
#
# The souce code of hpl-2.3 is licensed under `COPYRIGHT`.
#
##############################################################