论文信息 - Message-Passing Performance of Various Computers

Message-Passing Performance of Various Computers

This report compares the performance of di erent computer systems for basic message passing. Latency and bandwidth are measured on Convex, Cray, Fujitsu, IBM, Intel, KSR, Meiko, nCUBE, NEC, SGI, and TMC multiprocessors. Communication performance is contrasted with the computational power of each system. The comparison includes both shared and distributed memory computers as well as networked workstation clusters.

Jack J. Dongarra | Thomas H. Dunigan

[1] W HockneyRoger. The communication challenge for MPP , 1994 .

[2] Anthony J. G. Hey,et al. The genesis distributed memory benchmarks. Part 2: COMMS1, TRANS1, FFT1 and QCD2 benchmarks on the suprenum and IPSC/860 computers , 1995, Concurr. Pract. Exp..

[3] Michael W. Berry,et al. Public international benchmarks for parallel computers: PARKBENCH committee: Report-1 , 1994 .

[4] Chris R. Jesshope,et al. Parallel Computers 2: Architecture, Programming and Algorithms , 1981 .

[5] T. H. Dunigan,et al. Early experiences and performance of the Intel Paragon , 1994 .

[6] Jack J. Dongarra,et al. Performance of various computers using standard linear equations software in a FORTRAN environment , 1988, CARN.

[7] Roger W. Hockney,et al. Performance parameters and benchmarking of supercomputers , 1991, Parallel Comput..

[8] Jack Dongarra,et al. Pvm: A Users' Guide and Tutorial for Network Parallel Computing , 1994 .

[9] Jack J. Dongarra,et al. Performance of various computers using standard linear equations software in a Fortran environment , 1987, SGNM.