Difference between revisions of "Benchmarking: HPL CUDA Accelerated for Linux64"

From Define Wiki
Jump to navigation Jump to search
(Created page with "== Requirements == - CUDA 5.0 <br> - Intel MKL <br> - OpenMPI <br> - Tesla GPUs")
 
m
Line 1: Line 1:
 
== Requirements ==
 
== Requirements ==
 
- CUDA 5.0 <br>
 
- CUDA 5.0 <br>
 +
- GNU Compilers <br>
 
- Intel MKL <br>
 
- Intel MKL <br>
- OpenMPI <br>
+
- OpenMPI (Configured from computenode and compiled with GNU compilers <br>
 
- Tesla GPUs
 
- Tesla GPUs
 +
 +
== Download ==
 +
Download CUDA Accelerated Linpack for Linux64 (hpl-2.0_FERMI_v15.gz) from NVIDIA Developer Portal
 +
untar hpl-2.0_FERMI_v15.gz
 +
cd hpl-2.0_FERMI_v15
 +
Edit Make.CUDA
 +
# ----------------------------------------------------------------------
 +
# - HPL Directory Structure / HPL library ------------------------------
 +
# ----------------------------------------------------------------------
 +
TOPdir = /shared/apps/linpack/hpl-2.0_FERMI_v15
 +
.
 +
.
 +
# ----------------------------------------------------------------------
 +
# - Linear Algebra library (BLAS) -----------------------------
 +
# ----------------------------------------------------------------------
 +
LAdir        = /shared/apps/intel/mkl/lib/intel64
 +
LAinc        = -I/shared/apps/cuda/cuda-5.0/include
 +
LAlib = -L$(TOPdir)/src/cuda -ldgemm -L/shared/apps/cuda/cuda-5.0/lib64 -lcublas -lcuda -lcudart -L$(LAdir) -  lmkl_intel_lp64 -lmkl_gnu_thread -lmkl_core
 +
.
 +
.
 +
# ----------------------------------------------------------------------
 +
# - Compilers / linkers - Optimization flags ---------------------------
 +
# ----------------------------------------------------------------------
 +
CC      = mpicc
 +
CCFLAGS = $(HPL_DEFS) -fomit-frame-pointer -O3 -funroll-loops -W -Wall -fopenmp
 +
== Environment ==
 +
This is to make sure that you don't have any issues in compiling HPL on your system because they have hard-coded in the /usr/local/cuda/ directory as the default directory in all of their makefiles. You can go through them all and change it, but it is just easier to create a link to where you have it installed.
 +
cd /usr/local
 +
ln -s /shared/apps/cuda/cuda-5.0 cuda
 +
== Build ==
 +
module load cuda/5.0
 +
module load openmpi/1.6.3-gpu
 +
make arch=CUDA

Revision as of 06:52, 20 February 2013

Requirements

- CUDA 5.0
- GNU Compilers
- Intel MKL
- OpenMPI (Configured from computenode and compiled with GNU compilers
- Tesla GPUs

Download

Download CUDA Accelerated Linpack for Linux64 (hpl-2.0_FERMI_v15.gz) from NVIDIA Developer Portal

untar hpl-2.0_FERMI_v15.gz
cd hpl-2.0_FERMI_v15

Edit Make.CUDA

# ----------------------------------------------------------------------
# - HPL Directory Structure / HPL library ------------------------------
# ----------------------------------------------------------------------
TOPdir = /shared/apps/linpack/hpl-2.0_FERMI_v15
.
.
# ----------------------------------------------------------------------
# - Linear Algebra library (BLAS) -----------------------------
# ----------------------------------------------------------------------
LAdir        = /shared/apps/intel/mkl/lib/intel64
LAinc        = -I/shared/apps/cuda/cuda-5.0/include
LAlib = -L$(TOPdir)/src/cuda -ldgemm -L/shared/apps/cuda/cuda-5.0/lib64 -lcublas -lcuda -lcudart -L$(LAdir) -   lmkl_intel_lp64 -lmkl_gnu_thread -lmkl_core
.
.
# ----------------------------------------------------------------------
# - Compilers / linkers - Optimization flags ---------------------------
# ----------------------------------------------------------------------
CC      = mpicc
CCFLAGS = $(HPL_DEFS) -fomit-frame-pointer -O3 -funroll-loops -W -Wall -fopenmp

Environment

This is to make sure that you don't have any issues in compiling HPL on your system because they have hard-coded in the /usr/local/cuda/ directory as the default directory in all of their makefiles. You can go through them all and change it, but it is just easier to create a link to where you have it installed.

cd /usr/local
ln -s /shared/apps/cuda/cuda-5.0 cuda

Build

module load cuda/5.0
module load openmpi/1.6.3-gpu
make arch=CUDA