Home Go Up

Benchmarks

Machine Description

SUN HPC 10000
Machine Type SUN HPC 10000
Number of Processors 64
Tests used 10, 28, 32 and 64
Processor Speed (MHz) 400
Memory Installed (Gbytes) 64
Operating System SunOS Release 5.7

Problem Description

Code Used FMS Example 11
Matrix Sparsity Full
Matrix Symmetry Symmetric and Nonsymmetric
Data Type 16 Byte Complex
Number of Equations Various
Number of Vectors 1

Results

Date Started 6/30/99 6/30/99 7/6/99 7/6/99 7/9/99
Number of processors 10 28 32 64 64
Memory for FMS (Gbytes) 56.0 56.0 18.7 18.7 4.0
Number of Equations 10,000 50,000 50,000 100,000 100,000
Matrix Symmetry Nonsymmetric
(with pivoting)		 Nonsymmetric
(with Pivoting)		 Nonsymmetric
(with Pivoting)		 Nonsymmetric
(with Pivoting)		 Symmetric
Matrix Storage Size (Gbytes) 2.42 54.20 55.75 180.50 84.76
File Location Memory Memory Disk Disk Disk
Factoring CPU Time (Hr:Min:Sec) 1:19:30 162:13:14 156:29:15 1234:37:55 587:42:34
Factoring Wall Time (Hr:Min:Sec) 9:02 6:23:00 5:36:50 22:44:06 10:35:17
I/O Wait Time (Hr:Min:Sec) 0 0 5:00 18:05 1:31
Megaflops per Processor 559 571 592 600 630
Overall Megaflops 4,919 14,505 16,493 32,582 34,980
Parellel Speedup 8.8 out of 10 25.4 out of 28 27.9 out of 32 54.3 out of 64 55.5 out of 64

NOTES:

  1. CPU Time is the total amount of User and System time used by all processors.
  2. Wall Time is the elapsed time measured on a dedicated machine. This includes the time spent processing and any time spent waiting for I/O to complete.
  3. I/O Wait Time is the total time spent waiting for I/O to complete that is not overlapped by asynchronous I/O. This is included in Wall Time.
  4. Megaflops per Processor is the theoretical number of floating point operations performed, divided by the CPU time.
  5. Overall Megaflops is the theoretical number of floating point operations performed, divided by the Wall Time.
  6. Parallel Speedup is overall increase in performance due to parallel processing.

Home Go Up
Copyright © 1999 Multipath Corporation