atom feed47 messages in org.freebsd.freebsd-stableRe: AMD K6-2 / 550
FromSent OnAttachments
Larry RosenmanJun 27, 2000 8:11 pm 
John BaldwinJun 28, 2000 10:13 pm 
Greg WorkJul 1, 2000 3:53 pm 
Larry RosenmanJul 1, 2000 6:49 pm 
Greg LeheyJul 1, 2000 7:14 pm 
Greg WorkJul 1, 2000 7:17 pm 
Larry RosenmanJul 1, 2000 7:21 pm 
Greg WorkJul 1, 2000 7:22 pm 
Greg LeheyJul 1, 2000 7:31 pm 
Greg LeheyJul 1, 2000 7:33 pm 
Greg LeheyJul 1, 2000 7:35 pm 
Larry RosenmanJul 1, 2000 7:37 pm 
Greg LeheyJul 1, 2000 7:53 pm 
Larry RosenmanJul 1, 2000 8:06 pm 
Bryan LiesnerJul 1, 2000 8:21 pm 
Larry RosenmanJul 1, 2000 8:40 pm 
Greg LeheyJul 1, 2000 8:50 pm 
Larry RosenmanJul 1, 2000 8:56 pm 
Larry RosenmanJul 1, 2000 9:16 pm 
Art Neilson, WH7NJul 1, 2000 11:05 pm 
Coleman KaneJul 1, 2000 11:19 pm 
Greg LeheyJul 2, 2000 12:36 am 
David HellerJul 2, 2000 11:49 am 
Steve O'Hara-SmithJul 3, 2000 1:54 am 
Greg WorkJul 3, 2000 5:42 am 
Greg WorkJul 3, 2000 5:44 am 
Jim KingJul 3, 2000 9:19 am 
Raymond A. WikerJul 3, 2000 11:02 am 
Steve O'Hara-SmithJul 4, 2000 12:26 am 
Jordan K. HubbardJul 4, 2000 1:15 pm 
Larry RosenmanJul 4, 2000 1:20 pm 
Linh PhamJul 4, 2000 1:39 pm 
Joe GrecoJul 4, 2000 7:29 pm 
Paul MurphyJul 4, 2000 7:46 pm 
Greg LeheyJul 4, 2000 8:51 pm 
Joe GrecoJul 4, 2000 9:35 pm 
Coleman KaneJul 4, 2000 10:05 pm 
Ataualpa Albert Carmo BragaJul 4, 2000 11:51 pm 
Mike HardingJul 5, 2000 5:37 am 
Brandon D. ValentineJul 5, 2000 7:21 am 
Coleman KaneJul 5, 2000 8:16 am 
Wilko BulteJul 5, 2000 1:12 pm 
Jeffrey J. MountinJul 5, 2000 6:33 pm 
Coleman KaneJul 6, 2000 8:37 am 
Stefan EsserJul 8, 2000 1:54 pm 
Joe GrecoJul 8, 2000 3:00 pm 
B. K. MinazziJul 9, 2000 7:53 am 
Subject:Re: AMD K6-2 / 550
From:Brandon D. Valentine (ban@looksharp.net)
Date:Jul 5, 2000 7:21:18 am
List:org.freebsd.freebsd-stable

On Wed, 5 Jul 2000, Ataualpa Albert Carmo Braga wrote:

Only more one information about performance. I works at Unicamp university (Brazil), with computational chemistry, and a professor make some real tests (energy and optimize calculations, for example) and got better results for a AMD 700 (Athlon) than with a Pentium 3 850. Than, I think so, the Intel's imperium maybe is close to the end.

You should see the amazing stuff UKY has done with Athlon's on their KLAT2 cluster. They optimized ScaLAPAK to utilize the 3DNow! SIMD Within A Register enhancement and obtained these results:

Rmax=64.459 GFLOPS with Nmax=40,960 (N=40,960, Blocking factor 64, 8x8 grid; LU time 709.98s, sol time 0.78s; residual is 0.000000)

Approximate N1/2 is 32.296 GFLOPS with N=13,824 (Blocking factor 64, 8x8 grid; LU time 54.30s, sol time 0.24s; residual is 0.000000)

Theoretical peak is 179.2 GFLOPS (we'll never see that!)

Machine configuration: 64 Athlon 700MHz with 128MB PC100 CAS2 SDRAM on FIC SD11 motherboards (boot floppy, no hard disk); Flat Neighborhood network implemented using 256 Smartlink 100Mb/s NICs and 9 32-way switches; RedHat Linux 6.0 with 2.2.14 kernel; LAM MPI 6.3.3b1 (with Flat Neighborhood patch); Egcs 2.91.66, G77 0.5.24-19981002, and our 3DNow! SWAR support (http://aggregate.org/SWAR/); ScaLAPACK 1.6; BLACS 1.1; ATLAS 3.0beta (with our 3DNow! code inserted by hand)

Pretty amazing stuff. You can find more info on that cluster at: http://aggregate.org/KLAT2/

To Unsubscribe: send mail to majo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message