Windows S5R4 SSE2 power App 6.05 available

John Clark
John Clark
Joined: 4 May 07
Posts: 1,087
Credit: 3,143,193
RAC: 0

RE: RE: RE: A SSE2 App

Message 86530 in response to message 86522

Quote:
Quote:
Quote:

A SSE2 App for Windows can be found on the Power User's Apps page.

For this App to run your CPU must support SSE2 instructions.

Following an idea from Holger Pletsch which he got during the S4 results processing we are currently examining a way to reduce the computing power needed to search a certain area of parameter space. Also a bug in the current search code has been found and fixed, the effect this bug actually has on the results is also still under investigation. Currently it looks rather likely that this would at least affect the validation on Einstein@home, i.e. old and new Apps can't be run at the same time. BTW this bug fix is one reason for using the new build process.

If at least one of these issues applies, we will most likely cut the current S5R4 run short and start a new run "S5R5" with new Apps and a new workunit design (using the same data files, though). I'd consider it unlikely that I'll bring out new official "buggy" S5R4 Apps (6.05 is definitely an exception). Estimated timeframe for S5R5 (or a final decision on not to do it) is a few weeks (2-4). I'd expect S5R5 Windows Apps to have a similar switching mechanism like the current S5R4 Linux Apps (x87, SSE, SSe2), switching between three Apps that all have been built using the new process. BM

Looks like I had better get off my butt, with the other project, and return to EAH so I do not miss the roll out of the S5R5 units, and client.

Shih-Tzu are clever, cuddly, playful and rule!! Jack Russell are feisty!

RandyC
RandyC
Joined: 18 Jan 05
Posts: 3,628
Credit: 111,139,797
RAC: 0

RE: Looks like I had

Message 86531 in response to message 86530

Quote:

Looks like I had better get off my butt, with the other project, and return to EAH so I do not miss the roll out of the S5R5 units, and client.

You still have 2-4 weeks before they even make the decision, much less implement it.

Seti Classic Final Total: 11446 WU.

Bernd Machenschalk
Bernd Machenschalk
Moderator
Administrator
Joined: 15 Oct 04
Posts: 4,027
Credit: 215,294,896
RAC: 64,074

RE: RE: Looks like I had

Message 86532 in response to message 86531

Quote:
Quote:

Looks like I had better get off my butt, with the other project, and return to EAH so I do not miss the roll out of the S5R5 units, and client.

You still have 2-4 weeks before they even make the decision, much less implement it.

I'm not sure about that. Once all the details has been decided, the implementation should take only a few days.

BM

BM

Arion
Arion
Joined: 20 Mar 05
Posts: 147
Credit: 1,626,747
RAC: 0

RE: So the answer to your

Message 86533 in response to message 86528

Quote:
So the answer to your question is that (for 6.05) you wont be seeing any extra versions of the science app that have _0 or _1 etc tags in their name. I trust you did confirm the capabilities of your CPU before you threw version 6.05 into the mix? :-).

Thanks for the explaination on the data files. I knew I had no more work to process so dropping the app_info.txt file in (without modeification) shouldn't have been a problem of mid unit changeover. I was concerned that those files were going to be a fly in the ointment.

As to the -0 or -1 extension to the exe I wasn't sure I read it right and was double checking. I didn't think it was supposed to be there if I had SSE2. Forgot about the switching mech.

And Of Course I know what my AMD 64 x2-6400 has in it.

I appreciate your help with my questions. The mid-August changeover seems so long ago and dealing with an app_info.txt was still new to me even then.

Richard Haselgrove
Richard Haselgrove
Joined: 10 Dec 05
Posts: 2,040
Credit: 688,926,747
RAC: 944,180

RE: ... The mid-August

Message 86534 in response to message 86533

Quote:
... The mid-August changeover seems so long ago and dealing with an app_info.txt was still new to me even then.


Just so long as you spell it app_info.xml...

Arion
Arion
Joined: 20 Mar 05
Posts: 147
Credit: 1,626,747
RAC: 0

RE: I'm not sure about

Message 86535 in response to message 86532

Quote:

I'm not sure about that. Once all the details has been decided, the implementation should take only a few days.

BM

I'm didn't bother to wait for my cache of wu's from the other project empty, I just started this right up and they'll go 50/50 because of my settings. No problem with deadlines either. I have to admit it felt strange to NOT have any einstein@home work for the past few weeks.

Arion
Arion
Joined: 20 Mar 05
Posts: 147
Credit: 1,626,747
RAC: 0

RE: RE: ... The

Message 86536 in response to message 86534

Quote:
Quote:
... The mid-August changeover seems so long ago and dealing with an app_info.txt was still new to me even then.

Just so long as you spell it app_info.xml...

Yes... Whew.... Thanks..

Thunder
Thunder
Joined: 18 Jan 05
Posts: 138
Credit: 46,754,541
RAC: 0

Threw this on a variety of

Threw this on a variety of machines... everything from an older Celeron 2 Ghz (supports SSE2 though) to a AMD TL-34 to a Xeon 5335 (with a smattering of P4D's, P4(ht) and Athlon64's to boot). Used Gary's app_info.xml (except that I botched it on the TL-34 and trashed one result... sigh), and everything appears to be working fine.

I'll watch them all for validation and report back when I see good/bad news. :)

RandyC
RandyC
Joined: 18 Jan 05
Posts: 3,628
Credit: 111,139,797
RAC: 0

First pure result on my X2

First pure result on my X2 4600+ (5% OC): 36,777.27 secs (seq #46).

The previous quickest result (same datapak) on this machine was 44,335.50 sec.

I burned three WUs in the change over, but the last successful result from 6.04 on this datapak ran 48,086.31 secs (seq #53), so you can see the seq #s were fairly close together.

Seti Classic Final Total: 11446 WU.

Winterknight
Winterknight
Joined: 4 Jun 05
Posts: 482
Credit: 189,813,804
RAC: 113,052

Timings for Q6600 @ 3GHz,

Timings for Q6600 @ 3GHz, host 252515
[pre]App Freq_# Time
6.05 1048.00_870 23409.77
6.05 1048.00_871 23242.78

6.04 1048.00_872 28542.67
6.04 1048.00_873 28555.72
6.04 1048.00_874 28670.89
6.04 1048.00_875 28919.98
6.04 1048.00_876 29238.28
6.04 1048.00_877 29019.34
6.04 1048.00_878 28719.38
6.04 1048.00_879 29181.73

6.05 1048.05_894 24986.44
6.05 1048.05_895 24422.92
[/pre]

All units validated and granted credit.
The computer is my normal in-use computer so timings will be affected by computer usage.

edit] these figures would suggest 6.05 takes about 82% of time to process unit compared to 6.04.
[edit

Comment viewing options

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