Hi John,
Here are some STREAM results from the Sun Ultra I. The
tests were run by Tore Ottem at Skriverik A/S in Oslo.
Regards,
Paul
Forwarded message:
> From toreo@breim.sdata.no Wed Nov 29 11:01:06 1995
> Date: Wed, 29 Nov 1995 11:00:49 +0100
> From: toreo@breim.sdata.no (Tore Ottem)
> Message-Id: <199511291000.LAA15395@slagen.sdata.no>
> To: Paul.Budgell@nrsc.no
> Subject: Re: STREAM benchmark
> X-Sun-Charset: US-ASCII
> X-Charset: LATIN1
> X-Char-Esc: 29
>
> Paul,
>
> I tried a few things with stream this morning. I ran the program as
> a fixed priority real time process. This makes the process king of the
> mountain. It's never preempted and will go on uninterupted for as long as it
> takes. This is one of the nice things you can do in SOLARIS 2 ;-)
> This makes for slightly better results. Compiler flags are the same.
> Still the 45 Mb case.
>
> Forward these to McCalpin if you want to.
>
> Regards,
> ToreO....
>
> 1) 45 Mb. case, array size 2000000
> ==================================
>
> Machine : Ultra I/170 Creator.
> Processor: UltraSPARC I @ 167Mhz
> Memory : 128 Mb.
> Compiler : SPARCompiler FORTRAN 77 V4.0
> Flags : -fast -O5 -xtarget=ultra1/170 -xarch=v8plus
> Other : Run as fixed priority real time process.
> (priocntl -c RT -e stream)
>
> ----------------------------------------------
> Double precision appears to have 16 digits of accuracy
> Assuming 8 bytes per DOUBLE PRECISION word
> ----------------------------------------------
> Array size = 2000000
> Offset = 0
> The total memory requirement is 45 MB
> You are running each test 10 times
> The *best* time for each test is used
> ----------------------------------------------------
> Your clock granularity/precision appears to be 22 microseconds
> The tests below will each take a time on the order
> of 89631 microseconds
> (= 4074 clock ticks)
> Increase the size of the arrays if this shows that
> you are not getting at least 20 clock ticks per test.
> ----------------------------------------------------
> WARNING: The above is only a rough guideline.
> For best results, please be sure you know the
> precision of your system timer.
> ----------------------------------------------------
> Function Rate (MB/s) RMS time Min time Max time
> Assignment: 194.1313 0.1649 0.1648 0.1649
> Scaling : 213.6422 0.1498 0.1498 0.1499
> Summing : 221.5109 0.2168 0.2167 0.2168
> SAXPYing : 222.2376 0.2160 0.2160 0.2161
> Sum of a is : 2.3066015625919D+18
> Sum of b is : 4.6132031248564D+17
> Sum of c is : 6.1509375001413D+17
> Note: Nonstandard floating-point mode enabled
> See the Numerical Computation Guide, ieee_sun(3M)
>
-- W. Paul Budgell | e-mail: Paul.Budgell@nrsc.no Nansen Environmental and Remote Sensing Center | phone: +47 55 29 72 88 Edvard Griegsvei 3A | fax: +47 55 20 00 50 5037 Solheimsviken, Norway
This archive was generated by hypermail 2b29 : Tue Apr 18 2000 - 05:23:05 CDT