S41.xx Observation Thread

Akos Fekete
Akos Fekete
Joined: 13 Nov 05
Posts: 560
Credit: 4,510,638
RAC: 0
Topic 191154

S41 uses SSE and CMOV extensions to improve the calculation performance.

SSE/CMOV compatibles: Pentium-III, AthlonXP and newer processors.

comments:
- Spitfire and Thunderbird cores don't support SSE.
- Nehemiah doesn't support CMOV.

Kratylos
Kratylos
Joined: 23 Nov 05
Posts: 28
Credit: 1,550,025
RAC: 0

S41.xx Observation Thread

First WU with mixed work D41.12/S41.06 is valid.
S41.06 is faster as D41.12.

Nightbird
Nightbird
Joined: 17 Feb 05
Posts: 79
Credit: 561,723
RAC: 0

A "pure" Wu S41.06 Athlon 64

A "pure" Wu S41.06
Athlon 64 - 3200 + / Win2k SP4 - 1024 mb memory
wu z1_1174

3503 sec to 3556 sec with S40.12 (~ 0h 59 min)
2,561.84 sec !! (0h 42 min 41 sec) with S41.06 and for this first wu

edit :
the second wu :
2,541.78 sec ! (0h 42 min 21 sec)



[

Higgi
Higgi
Joined: 4 Jun 05
Posts: 19
Credit: 8,168,519
RAC: 0

WU about 1396

WU about 1396 cycles:

D41.12 - 0:43:25
S41.06 - 0:38:05
@Opteron 144@2,32GHz

Great job!

Nightbird
Nightbird
Joined: 17 Feb 05
Posts: 79
Credit: 561,723
RAC: 0

My Barton 2800+ (running

My Barton 2800+ (running under Millenium) is faster
wu r1_1213 :
with S39L -> 4207 sec to 4900 sec
with S39L + S41.06 -> first wu -> 3,892.96 sec (1h04min52sec) ; wu valid and credits

with S41.06 -> second wu r1_1213.0 -> 2,970.00 sec !!! (0h49min30sec)

[

MRAO
MRAO
Joined: 7 May 05
Posts: 33
Credit: 13,515,409
RAC: 9,106

Pentium M 2.0GHz, XP

Pentium M 2.0GHz, XP SP2:
40.12 3560 - 3595 ish spread 41.06 first 3014 all on z1_1055.5_3xx_...
Pentium 4 Prescott 2.8GHz, XP SP2:
40.12 4699 - 4701 ish spread 41.06 first 3640 all on z1_1255.5_12xx_...

neither yet validated though. Super stuff akosf!

Udo
Udo
Joined: 19 May 05
Posts: 203
Credit: 8,945,570
RAC: 0

Pentium M 1.6GHz, XP

Pentium M 1.6GHz, XP SP2:
40.12: 1416 to 1454 sec.
41.06: 1082 to 1120 sec. (only 2 results but both validated and got credits!)
all on z1_0248.0__14xx...
thats over 20% faster!

Edit: 3rd result validated with S41.06 after 1130 sec. CPU time.

Udo

archae86
archae86
Joined: 6 Dec 05
Posts: 2,819
Credit: 3,281,688,471
RAC: 2,558,358

Continuing my practice of

Continuing my practice of retesting the same archived WU on my Gallatin (Northwood-descended P4 EE running 3.2 GHz HT):

S40.12 39:05
S40.04 32:13
C41.00 41:26
C41.01 55:55
C41.00 41:11 (retry)
S41.06 34:27

So I see S41.06 as much faster than the unfortunate S40.12 on this machine, but still not so fast as the S40.04 it currently runs. I'll try S41.06 on my other machines, and if it looks more promising on them, retry on this machine with another work unit and more carefully controlled conditions.

Joachim Schmidt
Joachim Schmidt
Joined: 19 Feb 05
Posts: 35
Credit: 391,050
RAC: 0

Athlon 64 3000+ D41.12:

Athlon 64 3000+

D41.12: 3220 seconds -- some invalid
S41.06: 2980 seconds -- not yet validated

greets

[Sleeper]
[Sleeper]
Joined: 28 Feb 05
Posts: 10
Credit: 112,524
RAC: 0

6 WUs worked without

6 WUs worked without errors
3 WUs valid
3 WUs pendings

this 6 WUs faster than D41.12 :D

Great Job and big Thx. :D

Edit:
WUs pasted :P

MarkF
MarkF
Joined: 12 Apr 05
Posts: 393
Credit: 1,516,715
RAC: 0

[Sleeper]: What CPU(s) types

[Sleeper]:
What CPU(s) types are you using?

Comment viewing options

Select your preferred way to display the comments and click "Save settings" to activate your changes.