| How fast is your system? [message #830] |
Tue, 11 May 1993 11:20  |
sextonm
Messages: 3
Registered: May 1993
|
Junior Member |
|
|
I ran the IDL routines TIME_TEST and GRAPHICS_TIMES on my new
IBM clone. I've posted the results below. I am curious how the
486-66DX2 stackes up against other machines, ie VAX, SGI, SUN... ect.
The IDL documentation has results for several older machines, but
I would like to see some time tests for newer machines.
If interested, try the above named routines on your machine and mail
to me or post the results.
Machine / OS / Ram/cache Comp. Geo. Avg. Graphics Geo. Avg.
486DX2-33/16 VLB Windows,16M, 0k 64 1.88 10.5 2.53
486DX2-33/16 VLB Windows,16M,256k 55 1.65 8.5 1.93
486DX2-66/33 VLB Windows,16M, 0k 36 1.08 6.1 1.47
486DX2-66/33 VLB Windows,16M,256k 33 0.96 5.2 1.21
Matt Sexton sexton@claes.space.lockheed.com
|
|
|
|
| RE: How fast is your system? [message #1029 is a reply to message #830] |
Mon, 24 May 1993 01:05  |
nowicki
Messages: 11
Registered: May 1993
|
Junior Member |
|
|
IDL users:
Following are the numbers for a DEC 3000-400 (Alpha AXP) workstation
with standard graphics, running OpenVMS 1.5FT (Field Test), MOTIF,
and IDL 3.0.1 Sorry it took so long, but just installed IDL.
Don't ask me if these are good numbers, but this machine is fast....
1 0.800000 Empty For loop, 1 million times
2 1.10800 Call empty procedure (1 param) 100,000 times
3 0.849000 Add 100,000 integer scalars and store
4 0.770000 25,000 scalar loops each of 5 ops, 2 =, 1 if)
5 1.09400 Mult 512 by 512 byte by constant and store, 10 times
6 0.0860001 Shift 512 by 512 byte and store, 10 times
7 0.702000 Add constant to 512 x 512 byte array and store, 10 times
8 0.827000 Add two 512 by 512 byte images and store, 10 times
9 0.323000 Mult 512 by 512 floating by constant and store, 10 times
10 0.268000 Add constant to 512 x 512 floating and store, 10 times
11 0.669000 Add two 512 by 512 floating images and store, 10 times
12 0.331000 Invert a 100 by 100 random matrix
13 0.901000 Transpose 256 x 256 byte, FOR loops
14 0.106000 Transpose 256 x 256 byte, row and column ops
15 0.0180000 Transpose 256 x 256 byte, transpose function
16 1.75900 Log of 100,000 numbers, FOR loop
17 0.0870000 Log of 100,000 numbers, vector ops
18 1.75600 Add two 100000 element floating vectors, FOR loop
19 0.0270001 Add two 100000 element floating vectors, vector op
20 0.230000 65536 point real to complex FFT
21 0.120000 Smooth 512 by 512 byte array, 5x5 boxcar
22 0.164000 Smooth 512 by 512 floating array, 5x5 boxcar
23 3.51000 Write and read 10 512 by 512 byte arrays
16.5050 Total Time
0.37042165 Geometric mean, 23 tests.
1 0.326000 Simple plot, 10 times
2 0.331000 vectors
3 0.192000 Polygon filling
4 1.14400 Display 512 x 512 image, 10 times
1.99300 Total Time
0.39236767 Geometric mean, 4 tests.
-Greg
/* Greg Nowicki | Mail Stop 401A | LIDAR Applications Group */
/* NASA Langley Research Center | Hampton, Virginia 23681-0001 */
/* Voice: (804) 864-2713 | FAX: (804) 864-7790 */
/* nowicki@vaxine.larc.nasa.gov | My opinions and mine alone . . . */
|
|
|
|
comp.lang.idl-pvwave archive
Members
Search
Help
Login
Home
