Proceedings 1997 International Conference on Parallel Architectures and Compilation Techniques (1997)
San Francisco, CA
Nov. 11, 1997 to Nov. 15, 1997
Yuetsu Kodama , Electrotechnical Laboratory
Hirofumi Sakane , Electrotechnical Laboratory
Koike Hanpei , Electrotechnical Laboratory
Mitsuhisa Sato , Electrotechnical Laboratory
Shuichi Sakai , Electrotechnical Laboratory
Yoshinori Yamaguchi , Electrotechnical Laboratory
This report presents empirical results of fine-grain communication on the 80-processor EM-X distributed-memory multiprocessor. EM-X has hardware support for low latency, high throughput fine-grain communication -- this hardware support includes packet generation integrated into the instruction execution pipeline for single-cycle communication overhead, direct memory access for remote references, and rapid context switching for latency tolerance. We study the fine-grain communication performance of integer radix sort, a code with irregular communication, on EM-X, and compare it to the Fujitsu AP1000+ and the Cray Server CS6400. Our experimental results indicate that EM-X achieves high throughput and low overhead for fine-grain communication. Whereas EM-X's communication performance scales perfectly as we increase the number of processors, other coarse-grain message-passing machines exhibit fluctuation and performance degradation for larger configurations due to network contention.
fine-grain communication, parallel radix sort, performance scalability, EM-X
H. Sakane, M. Sato, Y. Kodama, S. Sakai, K. Hanpei and Y. Yamaguchi, "Parallel Execution of Radix Sort Program using Fine-grain Communication," Proceedings 1997 International Conference on Parallel Architectures and Compilation Techniques(PACT), San Francisco, CA, 1997, pp. 136.