SPEC Releases MPI Benchmark Suite
The Standard Performance Evaluation Corp. (SPEC) has released a benchmark suite that measures the performance of parallel computing systems and clusters running Message-Passing Interface (MPI) applications.
SPEC MPI2007 provides performance metrics that can be used to compare different hardware architectures (SMP, NUMA, clusters) and interconnects, processors, memory hierarchy, compilers, and MPI implementations. It tests performance based on actual end-user applications, instead of synthetic workloads or parallelized versions of sequential benchmarks.
SPEC MPI2007 was developed by SPEC members AMD, Argonne National Lab, Fujitsu-Siemens, Hewlett-Packard, IBM, Intel, QLogic, SGI, Sun, and the University of Dresden. It supports a wide range of 32- and 64-bit architectures, and is portable across Linux, UNIX and Windows operating systems. A medium-sized data set in SPEC MPI2007 scales up to 512 processors, and SPEC is working on larger data sets.
Two metrics are provided by SPEC MPI2007: A base metric for users who prefer the relative simplicity of a single-step build process, and a peak metric for those who want to experiment with different compilers and compiler flags to achieve the best performance. Performance measurement is normalized against a reference system to produce a “bigger-is-better” metric. The current reference system is an eight-node cluster of Celestica A2210 systems, each with dual AMD Opteron processors, connected by a TCP (GigE) interconnect.
SPEC MPI2007 is available immediately for $800 on DVD.
Source: Standard Performance Evaluation Corp.
Write a comment below. No registration needed!
