Beta version 24.6 - Athlon users wanted - Page 10

Uncwilly · 2004-12-21, 07:55

Quote:

Originally Posted by Prime95

It matched!

I hope that mine did.

I have watched for an update to the status page so I can check.

(This is the first time that I have actually worried about going to the effort to check.)

markr · 2004-12-21, 10:19

Just submitted 13204339; it matched to the (partly obscured) result I found in a cleared.txt!

sdbardwick · 2004-12-21, 13:51

Quote:

Originally Posted by stippix

Xyzzy could you tell me how you got all these different FFT-length.

I'm not Xyzzy, but I can quote him

Quote:

Originally Posted by Xyzzy

please put "FullBench=1" in prime.ini...

delta_t · 2004-12-21, 22:54

Quote:

Originally Posted by Prime95

It matched!

Excellent. A few more DC's and could we feel comfortable to run 24.6 of first time LL tests?

sdbardwick · 2004-12-22, 03:33

Two more DC completed:

UID: sdbardwick/Dual_MP_1, M13091987 is not prime. Res64: 538761BF506Bxxxx. Wa1: 4FBEC629,8870607,00000000
UID: sdbardwick/Dual_MP_0, M13091473 is not prime. Res64: 78D6F8752E17xxxx. Wa1: 408F554E,6147157,00000000

patrik · 2004-12-22, 12:14

I've got a feeling that errors are more likely to occur near the high end of an FFT range (and I don't mean the reproducible errors). Has anyone made some statistics about that? So at least those of you Athlons owners who overclock and get a hotter computer should perhaps try to get hold of a few exponents below 12.83M to double-check.

Would this also be something to consider when confirming that v24.6 works correctly? I don't know.

Prime95 · 2004-12-22, 15:29

Quote:

Originally Posted by sdbardwick

Two more DC completed:

UID: sdbardwick/Dual_MP_1, M13091987 is not prime. Res64: 538761BF506Bxxxx.
UID: sdbardwick/Dual_MP_0, M13091473 is not prime. Res64: 78D6F8752E17xxxx.

Two more matches. Feel free to use 24.6 to test whatever you'd like.

Uncwilly · 2004-12-22, 17:35

Quote:

Originally Posted by Uncwilly

Finished and reported a DC done ~50% with v24.6 on an athalon.

[Thu Dec 16 16:15:45 2004]
UID: Team_Inspector/uncwilly, M13328993 is not prime. Res64: xxxxxxxxxxxxxxxx. Wa1: xxxxxxxx,xxxxxxxx,00000000

res blocked out by me.

Found in cleared.txt

Maybe I will finally look at doing a 33M....

delta_t · 2004-12-28, 19:38

Hello George, thanks for the new 24.6 for FreeBSD.
Here's the benches for a dual Athlon MP server running FreeBSD 5.2

Old v23.5
AMD Athlon(tm) MP 2000+
CPU speed: 1666.05 MHz
CPU features: RDTSC, CMOV, PREFETCH, MMX, SSE
L1 cache size: 64 KB
L2 cache size: 256 KB
L1 cache line size: 64 bytes
L2 cache line size: 64 bytes
L1 TLBS: 32
L2 TLBS: 256
Prime95 version 23.5, RdtscTiming=1
Best time for 384K FFT length: 37.857 ms.
Best time for 448K FFT length: 43.859 ms.
Best time for 512K FFT length: 47.066 ms.
Best time for 640K FFT length: 62.214 ms.
Best time for 768K FFT length: 74.421 ms.
Best time for 896K FFT length: 88.771 ms.
Best time for 1024K FFT length: 99.729 ms.
Best time for 1280K FFT length: 133.427 ms.
Best time for 1536K FFT length: 157.636 ms.
Best time for 1792K FFT length: 195.026 ms.
Best time for 2048K FFT length: 221.948 ms.

New v24.6
AMD Athlon(tm) MP 2000+
CPU speed: 1665.55 MHz
CPU features: RDTSC, CMOV, PREFETCH, MMX, SSE
L1 cache size: 64 KB
L2 cache size: 256 KB
L1 cache line size: 64 bytes
L2 cache line size: 64 bytes
L1 TLBS: 32
L2 TLBS: 256
Prime95 version 24.6, RdtscTiming=1
Best time for 512K FFT length: 39.372 ms.
Best time for 640K FFT length: 53.396 ms.
Best time for 768K FFT length: 64.537 ms.
Best time for 896K FFT length: 78.601 ms.
Best time for 1024K FFT length: 87.601 ms.
Best time for 1280K FFT length: 115.550 ms.
Best time for 1536K FFT length: 138.869 ms.
Best time for 1792K FFT length: 167.507 ms.
Best time for 2048K FFT length: 188.409 ms.

delta_t · 2004-12-28, 20:53

Here's a FreeBSD 5.3 server running on a Duron:

Old v23.5
AMD Duron(tm) Processor
CPU speed: 758.42 MHz
CPU features: RDTSC, CMOV, PREFETCH, MMX
L1 cache size: 64 KB
L2 cache size: 64 KB
L1 cache line size: 64 bytes
L2 cache line size: 64 bytes
L1 TLBS: 24
L2 TLBS: 256
Prime95 version 23.5, RdtscTiming=1
Best time for 384K FFT length: 77.363 ms.
Best time for 448K FFT length: 92.205 ms.
Best time for 512K FFT length: 99.708 ms.
Best time for 640K FFT length: 135.671 ms.
Best time for 768K FFT length: 167.202 ms.
Best time for 896K FFT length: 206.504 ms.
Best time for 1024K FFT length: 236.810 ms.
Best time for 1280K FFT length: 319.626 ms.
Best time for 1536K FFT length: 403.229 ms.
Best time for 1792K FFT length: 484.322 ms.
Best time for 2048K FFT length: 552.427 ms.

New v24.6
AMD Duron(tm) Processor
CPU speed: 758.15 MHz
CPU features: RDTSC, CMOV, PREFETCH, MMX
L1 cache size: 64 KB
L2 cache size: 64 KB
L1 cache line size: 64 bytes
L2 cache line size: 64 bytes
L1 TLBS: 24
L2 TLBS: 256
Prime95 version 24.6, RdtscTiming=1
Best time for 512K FFT length: 85.308 ms.
Best time for 640K FFT length: 117.577 ms.
Best time for 768K FFT length: 146.089 ms.
Best time for 896K FFT length: 190.425 ms.
Best time for 1024K FFT length: 241.382 ms.
Best time for 1280K FFT length: 292.387 ms.
Best time for 1536K FFT length: 351.645 ms.
Best time for 1792K FFT length: 417.955 ms.
Best time for 2048K FFT length: 471.501 ms.

biwema · 2004-12-29, 19:49

I also played around with Prime95 vers 24.6 on Sierpinski factoring:

P4, 2.66GHz 512M DDR ram

using
PFactor=67607,2,9102371,1,48.5,1.75 ...
1024k FFT

vers 24.0.1
B1=60000, 660000: 117 minutes

vers 24.6
B1=55000, 632500: 185 minutes (varying quite a bit)

The new version seems to be quite a bit slower. Are there any changes in the implementation?

Similar Threads
Thread	Thread Starter	Forum	Replies	Last Post
LLR beta Version 3.8.13 (deprecated)	Jean Penné	Software	111	2015-01-26 21:41
Prime95 beta version 28.3	Prime95	Software	68	2014-02-23 05:42
Beta version 24.12 available	Prime95	Software	33	2005-06-14 13:19
Early Beta of version 24.11	Prime95	Software	113	2005-05-24 17:05
Beta version of PRP	Prime95	PSearch	15	2004-09-17 19:21

2004-12-21, 10:19	#101
markr "Mark" Feb 2003 Sydney 3·191 Posts	Just submitted 13204339; it matched to the (partly obscured) result I found in a cleared.txt!

2004-12-22, 03:33	#104
sdbardwick Aug 2002 North San Diego County 5×137 Posts	Two more DC completed: UID: sdbardwick/Dual_MP_1, M13091987 is not prime. Res64: 538761BF506Bxxxx. Wa1: 4FBEC629,8870607,00000000 UID: sdbardwick/Dual_MP_0, M13091473 is not prime. Res64: 78D6F8752E17xxxx. Wa1: 408F554E,6147157,00000000

2004-12-22, 12:14	#105
patrik "Patrik Johansson" Aug 2002 Uppsala, Sweden 425₁₀ Posts	I've got a feeling that errors are more likely to occur near the high end of an FFT range (and I don't mean the reproducible errors). Has anyone made some statistics about that? So at least those of you Athlons owners who overclock and get a hotter computer should perhaps try to get hold of a few exponents below 12.83M to double-check. Would this also be something to consider when confirming that v24.6 works correctly? I don't know.

2004-12-28, 19:38	#108
delta_t Nov 2002 Anchorage, AK 357₁₀ Posts	Hello George, thanks for the new 24.6 for FreeBSD. Here's the benches for a dual Athlon MP server running FreeBSD 5.2 Old v23.5 AMD Athlon(tm) MP 2000+ CPU speed: 1666.05 MHz CPU features: RDTSC, CMOV, PREFETCH, MMX, SSE L1 cache size: 64 KB L2 cache size: 256 KB L1 cache line size: 64 bytes L2 cache line size: 64 bytes L1 TLBS: 32 L2 TLBS: 256 Prime95 version 23.5, RdtscTiming=1 Best time for 384K FFT length: 37.857 ms. Best time for 448K FFT length: 43.859 ms. Best time for 512K FFT length: 47.066 ms. Best time for 640K FFT length: 62.214 ms. Best time for 768K FFT length: 74.421 ms. Best time for 896K FFT length: 88.771 ms. Best time for 1024K FFT length: 99.729 ms. Best time for 1280K FFT length: 133.427 ms. Best time for 1536K FFT length: 157.636 ms. Best time for 1792K FFT length: 195.026 ms. Best time for 2048K FFT length: 221.948 ms. New v24.6 AMD Athlon(tm) MP 2000+ CPU speed: 1665.55 MHz CPU features: RDTSC, CMOV, PREFETCH, MMX, SSE L1 cache size: 64 KB L2 cache size: 256 KB L1 cache line size: 64 bytes L2 cache line size: 64 bytes L1 TLBS: 32 L2 TLBS: 256 Prime95 version 24.6, RdtscTiming=1 Best time for 512K FFT length: 39.372 ms. Best time for 640K FFT length: 53.396 ms. Best time for 768K FFT length: 64.537 ms. Best time for 896K FFT length: 78.601 ms. Best time for 1024K FFT length: 87.601 ms. Best time for 1280K FFT length: 115.550 ms. Best time for 1536K FFT length: 138.869 ms. Best time for 1792K FFT length: 167.507 ms. Best time for 2048K FFT length: 188.409 ms.

2004-12-28, 20:53	#109
delta_t Nov 2002 Anchorage, AK 357₁₀ Posts	Here's a FreeBSD 5.3 server running on a Duron: Old v23.5 AMD Duron(tm) Processor CPU speed: 758.42 MHz CPU features: RDTSC, CMOV, PREFETCH, MMX L1 cache size: 64 KB L2 cache size: 64 KB L1 cache line size: 64 bytes L2 cache line size: 64 bytes L1 TLBS: 24 L2 TLBS: 256 Prime95 version 23.5, RdtscTiming=1 Best time for 384K FFT length: 77.363 ms. Best time for 448K FFT length: 92.205 ms. Best time for 512K FFT length: 99.708 ms. Best time for 640K FFT length: 135.671 ms. Best time for 768K FFT length: 167.202 ms. Best time for 896K FFT length: 206.504 ms. Best time for 1024K FFT length: 236.810 ms. Best time for 1280K FFT length: 319.626 ms. Best time for 1536K FFT length: 403.229 ms. Best time for 1792K FFT length: 484.322 ms. Best time for 2048K FFT length: 552.427 ms. New v24.6 AMD Duron(tm) Processor CPU speed: 758.15 MHz CPU features: RDTSC, CMOV, PREFETCH, MMX L1 cache size: 64 KB L2 cache size: 64 KB L1 cache line size: 64 bytes L2 cache line size: 64 bytes L1 TLBS: 24 L2 TLBS: 256 Prime95 version 24.6, RdtscTiming=1 Best time for 512K FFT length: 85.308 ms. Best time for 640K FFT length: 117.577 ms. Best time for 768K FFT length: 146.089 ms. Best time for 896K FFT length: 190.425 ms. Best time for 1024K FFT length: 241.382 ms. Best time for 1280K FFT length: 292.387 ms. Best time for 1536K FFT length: 351.645 ms. Best time for 1792K FFT length: 417.955 ms. Best time for 2048K FFT length: 471.501 ms.

2004-12-29, 19:49	#110
biwema Mar 2004 17D₁₆ Posts	I also played around with Prime95 vers 24.6 on Sierpinski factoring: P4, 2.66GHz 512M DDR ram using PFactor=67607,2,9102371,1,48.5,1.75 ... 1024k FFT vers 24.0.1 B1=60000, 660000: 117 minutes vers 24.6 B1=55000, 632500: 185 minutes (varying quite a bit) The new version seems to be quite a bit slower. Are there any changes in the implementation?