This article contains a growing compendium of commonly accessible or downloadable code that can be run on Intel® Xeon Phi™ Coprocessors.
If you have completed an upstream promotion of a community code, please post a thread on the Intel® Many Integrated Core Architecture Forum to let us know, so that we can update this list.
Do you want to receive updates when new codes are posted? Click on the 'Subscribe' button at the bottom of this page to be notified when this document gets updated.
|Code (in Alphabetical order)||Description||Segment||Where to download||Install recipe (if needed)|
|GEMM, STREAM, Linpack||GEMM and Linpack both exercise basic dense matrix operations targeting floating point performance on the coprocessor. STREAM is a test of memory bandwidth targeting GDDR memory performance.||Academic||These benchmarks can be obtained when downloading the Intel® MPSS-- these are included in optionally installed performance packages that will put the benchmarks and related documentation into /opt/intel/mic/perf on the 2.x version of the MPSS or /usr/share/micperf if using an MPSS 3.1.* release||
Intel(R) MPSS 2.1 users: Follow guidance from Chapter 5 of the Intel® MPSS Readme on installation and configuration.
Intel(R) MPSS 3.1 users: Follow guidance from Chapter 4 of the MPSS_Users_Guide on installation and configuration
For STREAM, if you prefer to download source yourself, compilation and optimization recipe is here
|LBS3D||Simulation tools for multiphase flows based on the free energy Lattice Boltzmann Method (LBM), important for Computational Fluid Dynamics. The code allows for the simulation of quasi-incompressible two-phase flows, and uses multiphase models that allow for large density ratios.||Manufacturing||http://code.google.com/p/mplabs/||
Follow compilation instructions at http://code.google.com/p/mplabs/wiki/Using_LBS3D
(Also reference whitepaper:https://www.xsede.org/documents/271087/
Self-contained, stand-alone mini-application which encapsulates the most significant performance characteristics (generation, assembly, solution) of an implicit finite element method application in C++ code. The physical domain is a three-dimensional box modeled by hexahedral elements (sometimes called “brick” elements). The box is discretized as a structured grid but treated as unstructured. The domain is decomposed for parallel execution using recursive coordinate bisection (RCB).
|Academic||http://www.mantevo.org > Download||
Follow guidance from this MiniFE Case Study to understand what flags/options to use to run MiniFE on host, coprocessor, or both
A version of HMMER, a hidden Markov model for analyzing protein sequences. In this version, two routines, hmmsearch and hmmpfam have been modified to use MPI for parallelism.
|Academic||See this recipe for compilation and optimization|
The Scalable Heterogeneous Computing Benchmark Suite (SHOC https://github.com/vetter/shoc-mic#readme) may be used for measuring performance and stability of Coprocessor based systems. The benchmark has been ported to support Intel® Xeon Phi™ using offload programming constructs implemented in the Intel® Compiler that is available as part of Intel® Composer XE 2013 package.
|Academic||See this recipe for configuration and compilation|
|WRF||The Weather Research and Forecasting (WRF) model is a numerical weather prediction system designed to serve atmospheric research and operational forecasting needs. WRF is used by academic atmospheric scientists, forecast teams at operational centers, application scientists, etc. Please see http://www.wrf-model.org/index.php for more details about WRF.||Weather, Academic||http://www.mmm.ucar.edu/wrf/users/
|See this recipe for configuration and compilation|