Characterizing Application Performance Sensitivity to R esource Contention in Multicore Architectures
Haoqiang H. Jin, Robert T. Hood, Johnny Chang, Jahed Djomehri, Dennis C. Jespersen, Kenichi Taylor, Rupak Biswas, Piyush Mehrotra · 2009
Contention for shared resources in the memory hierarchy can have a profound effect on the performance of applications running on high-end computers based on commodity multicore microprocessors. In this paper we describe a methodology, based on differential performance analysis, to quantify the effect of this contention on parallel applications. In particular, we characterize the contention for a specific shared resource by comparing runs that use different patterns of assigning processes to cores on multicore nodes. We demonstrate our approach with a subset of the HPCC benchmarks and the NAS Parallel Benchmarks running on high-end computing platforms that use four different quad-core microprocessors—Intel Clovertown, Intel Harpertown, AMD Barcelona, and Intel Nehalem-EP. The results help further our understanding of the requirements these codes place on their execution environments and also of each computer’s ability to deliver performance. 1