AmigaONE benchmark - Important

[ksk]

These are from a Finnish Amiga forum...

A1G3@733:
[Feb 18 10:34:17 UTC] OGR: using core #0 (GARSP 5.13 PPC-scalar).
[Feb 18 10:34:37 UTC] OGR: Benchmark for core #0 (GARSP 5.13 PPC-scalar)
0.00:00:16.78 [8,680,916 nodes/sec]

600MHz:
[Feb 17 14:24:36 UTC] OGR: using core #0 (GARSP 5.13 PPC-scalar).
[Feb 17 14:24:56 UTC] OGR: Benchmark for core #0 (GARSP 5.13 PPC-scalar)
0.00:00:16.55 [7,120,713 nodes/sec]

Athlon XP 1800+ native:
[Feb 17 10:46:36 UTC] OGR: using core #1 (GARSP 5.13-B).
[Feb 17 10:46:55 UTC] OGR: Benchmark for core #1 (GARSP 5.13-B)
0.00:00:16.71 [11,750,304 nodes/sec]

Athlon XP 1800+ & WinUAE:
[Feb 17 11:10:44 UTC] OGR: using core #3 (GARSP 5.13 68040).
[Feb 17 11:11:03 UTC] OGR: Benchmark for core #3 (GARSP 5.13 68040)
0.00:00:16.18 [2,201,927 nodes/sec]

But in the end, those results have very little relevance in real life apps.

[ksk]

@EntilZha

Please, the OS release ... quckly, please, please ...  :-x  :-P

[ksk]

>I'm living in the real world - which one are you living in?  

Loosen up a bit. This is just FUN stuff, nothing more.

Have a red&white pill.   :-D

[ksk]

This should be interesting:
http://www.math.wm.edu/~cahunter/NASA_G4_Study.pdf

[ksk]

Has anyone yet run SPECmark, Bytemark or any other little tougher tests?

How does the L2 and L3 cache show up in those benchmarks?

Amiga 68k benchmarks in PPCLinux UAE would be also nice...

[ksk]

mips_proc wrote:

Really AmigaONE G4-800Mhz wins over P4 2,6Ghz, this without level3 cache?

if it where only true...
...

But it IS true. On those tiny little tings, like OGR/RC5.  ;-)

[ksk]

Bytemark test on the A1G3SE by some happy A1 user:
http://personal.inet.fi/cool/pekosbil/a1benchmarks.htm

[ksk]

Hammer wrote:

ksk wrote:
Has anyone yet run SPECmark, Bytemark or any other little tougher tests?

How does the L2 and L3 cache show up in those benchmarks?

Just get some late model Power Macintosh’s benchmarks.

After bbrv's recent hints about A1G4XE's pathetic performance, I want to see benchmarks run on the A1. (but also benchmarks run on MOL should be ok)


BTW: I think this benchmark digs out some possible memory bus bottlenecs: http://www.netlib.org/linpack/

The JAVA version: http://www.netlib.org/benchmark/linpackjava/


(some a bit offtopic PPC 970 talk that I just saw)

[ksk]

Hammer wrote:
...
For OpenSSL benchmarks refer to
http://www.macosxhints.com/article.php?story=20020113045343563

 :-o  :-o  :-o  :-o  :-?

[ksk]

Hammer wrote:

After bbrv's recent hints about A1G4XE's pathetic performance,

Any numbers?

No.
Just that Peg1G3@600 "performs better than" A1G4XE.

 I want to see benchmarks run on the A1. (but also benchmarks run on MOL should be ok)

What for? Does Pegy run "AmigaOS 4.0"?

Nope.
But I love using AmigaOS and I have load of AOS3.x apps.
I want to continue using AmigaOS like OS.
Peg1 with MOS is one of the options.

“AmigaOS 3.9” compatibility can be obtain via the cheaper X86 based solutions (still waiting for Berniethlon).

I woud like to get rid of my noisy x86 kludge HW.
But yes, Umilator would be also one option, if it existed.

The JAVA version: http://www.netlib.org/benchmark/linpackjava/

Dependant on the Java virtual machine.  Good for benchmarking between Java VMs btw.

But when using identical JVM, it's also good for benchmarking system performance, right?

**************
Update:

Example of Linpack results on x86:
http://www.tech-report.com/reviews/2002q4/athlonxp-2800/index.x?pg=3

I would love to see A1G4XE somewhere between those graphs...
http://www.tech-report.com/reviews/2001q2/pentium4-1.7/index.x?pg=4

[ksk]

post gone to bitheaven...

[ksk]

Now A1SE and A1XE tested side by side:
http://personal.inet.fi/cool/pekosbil/a1benchmarks.htm

Soon also on pegasos....

(please notice that those test are not done by me (so, all credits to Pekka, please ;-) ) and that they are no way scientificly accurate, but they should give some rough hints about the performance)

( after recompiling with motorolla math libraries, it seems that PPC performance jumped up 300% in some cases)  :-)

[ksk]

While Pekka is waiting for the results of peg1, is there anywhere a pegasos benchmark page?

[ksk]

More results:

http://personal.inet.fi/cool/pekosbil/a1benchmarks.htm

(do not give me the credit of those benchmarks, please, I'm not the author)

Also pegasos results exist, but some of them will not be published untill a few unclear bits are sorted out.

( UPDATE: Also Pegasos results exist now.  More tests are in development (most likely also with Altivec). )

regards
 ksk