Intel® Math Kernel Library 11.3 Update 4 Developer Guide

Contents of the Intel Optimized MP LINPACK Benchmark

The Intel Optimized MP LINPACK Benchmark includes the entire HPL 2.1 distribution, but with modifications to several files, and files specific to the Intel Optimized MP LINPACK Benchmark. All the files are located in the ./benchmarks/mp_linpack/ subdirectory of the Intel MKL directory. Files specific to the Intel Optimized MP LINPACK Benchmark are listed below.

Directory/File in <mkl directory>/benchmarks/mp_linpack/

Contents

Make.ia32

Sample architecture makefile for processors using the IA-32 architecture.

Make.intel64

Sample architecture makefile for processors using the Intel® 64 architecture and Linux OS.

Make.mic

Sample architecture makefile for native runs on Intel® Xeon Phi™ coprocessors.

HPL.dat

A duplicate of testing/ptest/HPL.dat in the top-level directory.

Prebuilt executables for simple performance testing

bin_intel/intel64/xhpl_intel64

Prebuilt binary for the Intel® 64 architecture statically linked against Intel MPI library‡. The binary accelerates execution by offloading computations to Intel Xeon Phi coprocessors if they are available on the system.

bin_intel/intel64/xhpl_intel64_dynamic

Prebuilt binary for the Intel® 64 architecture dynamically linked against Intel MPI library. The binary accelerates execution by offloading computations to Intel Xeon Phi coprocessors if they are available on the system.

Prebuilt libraries

lib_hybrid/intel64/libhpl_hybrid.a

Prebuilt library with the hybrid version of the Intel Optimized MP LINPACK Benchmark for the Intel® 64 architecture and Intel MPI library.

lib_hybrid/intel64/libhpl_offload.a

Prebuilt library with the offload version of the Intel Optimized MP LINPACK Benchmark for the Intel® 64 architecture and Intel MPI library.

lib_hybrid/mic/libhpl_hybrid.a

Prebuilt library with the hybrid version of the Intel Optimized MP LINPACK Benchmark for native runs on Intel Xeon Phi coprocessors.

Run scripts and examples of input files

bin_intel/intel64/runme_intel64

Sample run script for the Intel® 64 architecture and hybrid offload binary statically linked against Intel MPI library.

bin_intel/intel64/runme_intel64_dynamic

Sample run script for the Intel® 64 architecture and hybrid offload binary dynamically linked against Intel MPI library.

bin_intel/intel64/runme_intel64_prv

A script that sets HPL environment variables based on the number of Intel Xeon Phi coprocessors per MPI process. The script is called by runme_intel64 and runme_intel64_dynamic.

bin_intel/intel64/HPL.dat

Example of an input file for the Intel® 64 architecture and an offload binary.

  

nodeperf.c

Sample utility that tests the DGEMM speed across the cluster.

‡ For a list of supported versions of the Intel MPI Library, see system requirements in the Intel MKL Release Notes.

Optimization Notice

Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.

Notice revision #20110804

Parent topic: Intel® Optimized MP LINPACK Benchmark for Clusters

See Also

High-level Directory Structure