Sandhya Dwarkadas
Department of Computer Science
Rice University
sandhya@cs.rice.edu
Alan L.Cox
Department of Computer Science
Rice University
alc@cs.rice.edu
Willy Zwaenepoel
Department of Computer Science
Rice University
willy@cs.rice.edu
For Water-1728, EP, ILINK, SOR-Zero, and SOR-NonZero, the performance of TreadMarks is within 10%of PVM. For IS-Small, Water-288, Barnes-Hut, 3-D FFT, TSP, and QSORT, differences are on the order of 10%to 30%. Finally, for IS-Large, PVM performs two times better than TreadMarks.
More messages and more data are sent in TreadMarks, explaining the performance differences. This extra communication is caused by 1) the separation of synchronization and data transfer, 2) extra messages to request updates for data by the invalidate protocol used in TreadMarks, 3) false sharing, and 4) diff accumulation for migratory data in TreadMarks.
A postscript version of this paper is available at ftp://cs.rice.edu/public/TreadMarks/papers/sc95.ps.gz, and any of the authors' home page.