Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of GraphSearch.
In this paper we evaluate the use of software distributed shared memory (DSM) on a message passing machine as the target for a parallelizing compiler. We compare this approach to compiler-generated message passing, hand-coded software DSM and hand-coded message passing. For this comparison, we use six applications: four that are regular and two that are irregular: Our results are gathered on an 8-node IBM SP/2 using the TreadMarks software DSM system. We use the APR shared-memory (SPF) compiler to generate the shared memory-programs and the APR XHPF compiler to generate message passing programs. The hand-coded message passing programs run with the IBM PVMe optimized message passing library. On the regular programs, both the compiler-generated and the hand-coded message passing outperform the SPF/TreadMarks combination: the compiler-generated message passing by 5.5% to 40%, and the hand-coded message passing by 7.5% to 49%. On the irregular programs, the SPF/TreadMarks combination outperforms the compiler-generated message passing by 38% and 89%, and only slightly underperforms the hand-coded message passing, differing by 4.4% and 16%. We also identify the factors that account for the performance differences, estimate their relative importance, and describe methods to improve the performance
Loading
Loading
Loading
Loading
Loading
,
Sandhya Dwarkadas, Willy Zwaenepoel
Sandhya Dwarkadas, Willy Zwaenepoel