Home Go Up

IBM 690

Machine Description

Model Number 690
Processor Type Power4 @ 1.7GHz
Number of Processors 32
Memory Installed 128 Gbytes
Memory Used by FMS 48 Gbytes
Operating System AIX 5.1
ESSL Version 03.03.00.06

Problem Description

Code Used Example 11
Matrix Sparsity Full
Matrix Symmetry Symmetric and Nonsymmetric
Data Type 16-byte Complex
Number of Equations 20,000 to 200,000
Number of Vectors 1
Type of I/O Direct (IOTYPE=2)
Reduced Operation Algorithms None (IALGOR=0)

Results for Complex Symmetric Matrices

Date
Started		 Number of
Equations		 Storage Times (Day::Hr:Min:Sec) Megaflops Parallel
Speedup
Loc. Gbytes CPU Wall I/O Wait CPU Overall
6/27/03 20,000 Mem. 3.8 44:26 1:38 :00 4,002 108,396 27.1
6/27/03 20,000 Disk 3.8 46:29 1:44 :01 3,825 102,151 26.7
6/27/03 40,000 Mem. 21.7 6:02:18 12:31 :00 3,925 113,645 28.9
6/27/03 40,000 Disk 21.7 5:56:34 12:47 :21 3,988 111,265 27.9
6/27/03 60,000 Disk 38.5 20:16:52 41:08 :08 3,944 116,728 29.6
6/27/03 100,000 Disk 121.0 3::19:57:13 3:04:26 03:56 4,028 120,499 29.9
6/28/03 200,000 Disk 380.3 29::20:04:21 23:13:06 10:30 4,138 127,615 30.8

Results for Complex Nonsymmetric Matrices

Date
Started		 Number of
Equations		 Storage Times (Day::Hr:Min:Sec) Megaflops Parallel
Speedup
Loc. Gbytes CPU Wall I/O Wait CPU Overall
6/29/03 20,000 Disk 7.4 1:31:11 3:12 :04 3,900 111,315 28.5
6/29/03 40,000 Disk 43.3 11:29:00 23:13 :24 4,129 122,540 29.7
6/29/03 60,000 Disk 76.9 1::15:04:16 1:17:27 :47 4,095 123,982 30.3
6/29/03 80,000 Disk 120.1 3::19:02:41 2:59:47 3:44 4,166 126,579 30.4
6/29/03 100,000 Disk 242.0 7::11:32:31 5:59:47 12:12 4,126 123,539 29.9

Results for Complex Nonsymmetric Matrices using Pivoting

Date
Started		 Number of
Equations		 Storage Times (Day::Hr:Min:Sec) Megaflops Parallel
Speedup
Loc. Gbytes CPU Wall I/O Wait CPU Overall
6/29/03 20,000 Disk 7.3 1:19:58 3:31 :13 3,680 101,540 27.6
6/29/03 40,000 Disk 27.6 11:47:03 23:41 :42 4,023 120,111 29.9
6/29/03 60,000 Disk 60.0 1::14:30:14 1:15:14 1:31 4,156 127,623 30.7
6/29/03 80,000 Disk 105.2 3::18:37:06 2:57:22 4:07 4,185 128,311 30.7
6/29/03 100,000 Disk 164.4 7::08:17:51 5:51:25 14:22 4,202 126,477 30.1

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 overall increase in performance due to parallel processing.


HomeGo Up
Copyright © Multipath Corporation