| Re: time test MacOC [message #11334 is a reply to message #11275] |
Mon, 23 March 1998 00:00  |
harmonic
Messages: 15
Registered: April 1994
|
Junior Member |
|
|
In article <6ekfpv$arl$1@nnrp1.dejanews.com>, uk2@scibernet.com says...
Could you post/send the source for time_test? (If it is freely
distributable). I am curious to compare these benchmarks to O-Matrix.
> Hi Guys,
>
> Here are results from a Dell workstation 333Mz/384Mb Ram running win NT.
> While I love macs and UNIX machines, these numbers are pretty impressive.
> Can anyone supply faster numbers on another platform?
>
> -Pete Riley
>
>
> IDL> time_test
> % Compiled module: TIME_TEST.
> TIME_TEST is obsolete.
> Use the newer, more accurate, TIME_TEST2, contained in this file.
> |TIME_TEST performance for IDL 5.1 Beta 2:
> | OS_FAMILY=Windows, OS=Win32, ARCH=x86
> 1 0.100000 Empty For loop, 1 million times
> 2 0.170000 Call empty procedure (1 param) 100,000 times
> 3 0.110000 Add 100,000 integer scalars and store
> 4 0.0999999 25,000 scalar loops each of 5 ops, 2 =, 1 if)
> 5 0.0400000 Mult 512 by 512 byte by constant and store, 10 times
> 6 0.0300000 Shift 512 by 512 byte and store, 10 times
> 7 0.0510000 Add constant to 512 x 512 byte array and store, 10 times
> 8 0.0800000 Add two 512 by 512 byte images and store, 10 times
> 9 0.180000 Mult 512 by 512 floating by constant and store, 10 times
> 10 0.160000 Add constant to 512 x 512 floating and store, 10 times
> 11 0.221000 Add two 512 by 512 floating images and store, 10 times
> 12 0.0400000 Invert a 100 by 100 random matrix
> 13 0.110000 Transpose 256 x 256 byte, FOR loops
> 14 0.0200000 Transpose 256 x 256 byte, row and column ops
> 15 0.00999999 Transpose 256 x 256 byte, transpose function
> 16 0.230000 Log of 100,000 numbers, FOR loop
> 17 0.0500000 Log of 100,000 numbers, vector ops
> 18 0.231000 Add two 100000 element floating vectors, FOR loop
> 19 0.0100001 Add two 100000 element floating vectors, vector op
> 20 0.0500000 65536 point real to complex FFT
> 21 0.0400000 Smooth 512 by 512 byte array, 5x5 boxcar
> 22 0.0200000 Smooth 512 by 512 floating array, 5x5 boxcar
> 23 0.0500000 Write and read 10 512 by 512 byte arrays
> 2.10300=Total Time, 0.063319051=Geometric mean, 23 tests.
> IDL> time_test2
> |TIME_TEST2 performance for IDL 5.1 Beta 2:
> | OS_FAMILY=Windows, OS=Win32, ARCH=x86
> | Mon Mar 16 16:16:15 1998
> 1 0.190000 Empty For loop, 2000000 times
> 2 0.171000 Call empty procedure (1 param) 100,000 times
> 3 0.110000 Add 100,000 integer scalars and store
> 4 0.0999999 25,000 scalar loops each of 5 ops, 2 =, 1 if)
> 5 0.0500001 Mult 512 by 512 byte by constant and store, 10 times
> 6 0.371000 Shift 512 by 512 byte and store, 100 times
> 7 0.250000 Add constant to 512 x 512 byte array and store, 50 times
--
Beau Paisley / Harmonic Software
Makers of O-Matrix - A High-Performance Data Analysis Environment
http://www.omatrix.com - for free copy of O-Matrix Light
|
|
|
|
comp.lang.idl-pvwave archive
Members
Search
Help
Login
Home
