HomeGo Up

CRAY SV1 Supercomputer

Machine Description

Model Number SV1
Number of Processors 16 and 32
Processor Type 300 Mhz
Memory Installed (Gbytes) 32
Memory used by FMS (Gbytes) 14
Operating System Unicos

Problem and Results

Code Used Example 11
Matrix Sparsity Full
Matrix Symmetry Nonsymmetric with pivoting
Data Type 16-byte Complex

Results

Date Started 08/12/2001 08/04/2001 08/11/2001 08/11/2001 08/11/2001
Number of Equations 15,000 50,000 15,000 50,000 100,000
Number of Processors 16 16 32 32 32
Matrix Storage Size (Gbytes) 4 43 5 43 170
File Location Memory Disk Memory Disk Disk
Factoring CPU Time (Days::Hr:Min:Sec) 2:56:53 4::09:58:59 2:59:33 4::10:32:47 36::08:15:19
Factoring Wall Time (Days::Hr:Min:Sec) 13:34 8:23:10 8:43 5:17:32 1::08:23:34
I/O Wait Time (Days::Hr:Min:Sec) Incore <1 Incore <1 <1
Megaflops per Processor 848 873 835 869 849
Overall Megaflops 11,052 11,041 17,222 17,497 22,868
Parellel Speedup 13.0 out of 16 12.6 out of 16 20.6 out of 32 20.0 out of 32 26.9 out of 32

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.
  4. Megaflops per Processor is the theoretical number of floating point operations performed, divided by the CPU Time.
  5. Overall Megaflops is the total number of floating point operations performed, divided by the Wall Time.
  6. Parallel Speedup is the ratio of CPU Time divided by Wall Time.


HomeGo Up
Copyright © 2001 Multipath Corporation