HPC Bechmarks

Benchmarks

Cluster Corp. is experienced in compiling and optimizing benchmarks on a wide variety of platforms for performance runs and internal testing.

The ASCI Purple Benchmarks

The ASCI Purple Benchmarks were designed as are part of the ASCI Purple Request for Proposal (RFP). There are three tiers. Tier 1 includes sPPM, UMT2000, PRESTA, MEMBENCH, PARBENCCH, and SUPER.
http://www.llnl.gov/asci/platforms/purple/rfp/benchmarks/

 

HPC Challenge Benchmark

The HPC Challenge benchmark consists at this time of 7 benchmarks: HPL, STREAM, RandomAccess, PTRANS, FFTE, DGEMM and b_eff Latency/Bandwidth. HPL is the Linpack TPP benchmark. The test stresses the floating point performance of a system. STREAM is a benchmark that measures sustainable memory bandwidth (in GB/s), RandomAccess measures the rate of random updates of memory. PTRANS measures the rate of transfer for larges arrays of data from multiprocessor’s memory. Latency/Bandwidth measures (as the name suggests) latency and bandwidth of communication patterns of increasing complexity between as many nodes as is time-wise feasible.
http://icl.cs.utk.edu/hpcc/

Intel MPI Benchmark (Pallas)

Intel® MPI Benchmarks 2.3 is a comprehensive set of MPI benchmarks, formerly known as Pallas MPI Benchmarks (PMB).
http://www.intel.com/cd/software/products/asmo-na/eng/cluster//clustertoolkit/219848.htm

 

Bounce MPI Benchmark

The Stanford University Bounce (SUbounce) MPI Benchmark tests latency and bandwidth of any MPICH derived implementation. It's a trivial program, easy to 'compile and run' providing human readable results. It's commonly used to verify the MPI F90 interface.
http://www.sourceforge.net/projects/subounce