Message boards :
Number crunching :
Optimised AP v5.00 - initial release
Message board moderation
Previous · 1 . . . 4 · 5 · 6 · 7 · 8 · 9 · Next
Author | Message |
---|---|
samuel7 Send message Joined: 2 Jan 00 Posts: 47 Credit: 2,194,240 RAC: 0 |
My task tiebreaking v4 and v5 results finished with 64,238.98 seconds and validated along with the v5 result but not with the v4 result. Commiserations to user konusv. Because I'm in a position to choose which application to use by modifying app_info, I'll cruch with v4.37 those tasks that only have successful v4 results and all others with v5. |
Zap de Ridder Send message Joined: 9 Jan 00 Posts: 227 Credit: 1,468,844 RAC: 1 |
|
-Bert- Send message Joined: 23 Mar 02 Posts: 152 Credit: 412,754 RAC: 0 |
Hi, I would like to run the newest optimized app too. Before I will do that, I would like to verify a few things here: I will shut down BOINC Copy the following files to my C:\ProgramData\BOINC\projects\setiathome.berkeley.edu folder (I'm using Vista with a SSSE3 capable machine) and overwrite any existing files ap_4.37_SSE3_EPF.exe ap_5.00r69_SSE3.exe libfftw3f-3-1-1a_upx.dll Then I will edit the existing app_info.xml. At this moment it looks like this: <app_info> <app> <name>setiathome_enhanced</name> </app> <file_info> <name>AK_v8_win_SSSE3x.exe</name> <executable/> </file_info> <app_version> <app_name>setiathome_enhanced</app_name> <version_num>528</version_num> <file_ref> <file_name>AK_v8_win_SSSE3x.exe</file_name> <main_program/> </file_ref> </app_version> <app_version> <app_name>setiathome_enhanced</app_name> <version_num>603</version_num> <file_ref> <file_name>AK_v8_win_SSSE3x.exe</file_name> <main_program/> </file_ref> </app_version> <app> <name>astropulse</name> </app> <file_info> <name>ap_4.35rev24b54_SSE3.exe</name> <executable/> </file_info> <file_info> <name>libfftw3f-3-1-1a_upx.dll</name> <executable/> </file_info> <app_version> <app_name>astropulse</app_name> <version_num>435</version_num> <file_ref> <file_name>ap_4.35rev24b54_SSE3.exe</file_name> <main_program/> </file_ref> <file_ref> <file_name>libfftw3f-3-1-1a_upx.dll</file_name> </file_ref> </app_version> <app_version> <app_name>astropulse</app_name> <version_num>436</version_num> <file_ref> <file_name>ap_4.35rev24b54_SSE3.exe</file_name> <main_program/> </file_ref> <file_ref> <file_name>libfftw3f-3-1-1a_upx.dll</file_name> </file_ref> </app_version> </app_info> Now my question. Where exactly do I put the new AP part which looks like this: <app_info> <app> <name>astropulse</name> </app> <file_info> <name>ap_4.37_SSE3_EPF.exe</name> <executable/> </file_info> <file_info> <name>ap_5.00r69_SSE3.exe</name> <executable/> </file_info> <file_info> <name>libfftw3f-3-1-1a_upx.dll</name> <executable/> </file_info> <app_version> <app_name>astropulse</app_name> <version_num>435</version_num> <file_ref> <file_name>ap_4.37_SSE3_EPF.exe</file_name> <main_program/> </file_ref> <file_ref> <file_name>ap_5.00r69_SSE3.exe</file_name> </file_ref> <file_ref> <file_name>libfftw3f-3-1-1a_upx.dll</file_name> </file_ref> </app_version> <app_version> <app_name>astropulse</app_name> <version_num>436</version_num> <file_ref> <file_name>ap_4.37_SSE3_EPF.exe</file_name> <main_program/> </file_ref> <file_ref> <file_name>ap_5.00r69_SSE3.exe</file_name> </file_ref> <file_ref> <file_name>libfftw3f-3-1-1a_upx.dll</file_name> </file_ref> </app_version> <app_version> <app_name>astropulse</app_name> <version_num>500</version_num> <file_ref> <file_name>ap_5.00r69_SSE3.exe</file_name> <main_program/> </file_ref> <file_ref> <file_name>ap_4.37_SSE3_EPF.exe</file_name> </file_ref> <file_ref> <file_name>libfftw3f-3-1-1a_upx.dll</file_name> </file_ref> </app_version> </app_info> Thanks in advance. |
Leaps-from-Shadows Send message Joined: 11 Aug 08 Posts: 323 Credit: 259,220 RAC: 0 |
Assuming you only have Multibeam 6.03 along with Astropulse 4.36 and/or 5.00 work units on your machine, your new app_info.xml should look like this: <app_info> <app> <name>setiathome_enhanced</name> </app> <file_info> <name>AK_v8_win_SSSE3x.exe</name> <executable/> </file_info> <app_version> <app_name>setiathome_enhanced</app_name> <version_num>603</version_num> <file_ref> <file_name>AK_v8_win_SSSE3x.exe</file_name> <main_program/> </file_ref> </app_version> <app> <name>astropulse</name> </app> <file_info> <name>ap_4.37_SSE3_EPF.exe</name> <executable/> </file_info> <file_info> <name>ap_5.00r69_SSE3.exe</name> <executable/> </file_info> <file_info> <name>libfftw3f-3-1-1a_upx.dll</name> <executable/> </file_info> <app_version> <app_name>astropulse</app_name> <version_num>436</version_num> <file_ref> <file_name>ap_4.37_SSE3_EPF.exe</file_name> <main_program/> </file_ref> <file_ref> <file_name>ap_5.00r69_SSE3.exe</file_name> </file_ref> <file_ref> <file_name>libfftw3f-3-1-1a_upx.dll</file_name> </file_ref> </app_version> <app_version> <app_name>astropulse</app_name> <version_num>500</version_num> <file_ref> <file_name>ap_5.00r69_SSE3.exe</file_name> <main_program/> </file_ref> <file_ref> <file_name>ap_4.37_SSE3_EPF.exe</file_name> </file_ref> <file_ref> <file_name>libfftw3f-3-1-1a_upx.dll</file_name> </file_ref> </app_version> </app_info> Cruiser Gateway GT5692 L-f-S Edition -Phenom X4 9650 CPU -4GB 667MHz DDR2 RAM -500GB SATA HD -Vista x64 SP1 -BOINC 6.2.19 32-bit client -SSE3 optimized 32-bit apps |
-Bert- Send message Joined: 23 Mar 02 Posts: 152 Credit: 412,754 RAC: 0 |
Thanks very much! I switched to the newest app and have seen no problems so far. |
Leaps-from-Shadows Send message Joined: 11 Aug 08 Posts: 323 Credit: 259,220 RAC: 0 |
Cruiser's compiled results so far: Main: 368768645 (Validated) - 0.008021076 credits per CPU second 368768653 (Validated) - 0.008183099 credits per CPU second 368496971 (Pending) - 0.008235288 credits per CPU second 368768654 (Validated) - 0.008136883 credits per CPU second 368768675 (Validated) - 0.008161555 credits per CPU second 368768681 (Validated) - 0.008024405 credits per CPU second 369656439 (Validated) - 0.007830532 credits per CPU second 349739781 (Validated) - 0.008531656 credits per CPU second 369656217 (Pending) - 0.008278782 credits per CPU second 370050505 (Validated) - 0.008334832 credits per CPU second 370050504 (Validated) - 0.008610554 credits per CPU second 368418713 (v4.37, Pending) - 0.006726898 credits per CPU second Beta: 1563494 (Validated) - 0.009484371 credits per CPU second 1565756 (Validated) - 0.009705443 credits per CPU second 1564992 (Validated) - 0.009227865 credits per CPU second 1565745 (Validated) - 0.009846161 credits per CPU second 1565021 (Pending) (Task details) - 0.009777995 credits per CPU second 1565898 (Pending) (Task details) - 0.009551190 credits per CPU second 1628888 (Validated) - 0.009486180 credits per CPU second 1565146 (Validated) - 0.009490379 credits per CPU second For comparison: Shorty Multibeam (16.84 credits): 0.007037046 credits per CPU second Average Multibeam (44.12 credits): 0.008375063 credits per CPU second Long Multibeam (63.86 credits): 0.010619245 credits per CPU second Cruiser Gateway GT5692 L-f-S Edition -Phenom X4 9650 CPU -4GB 667MHz DDR2 RAM -500GB SATA HD -Vista x64 SP1 -BOINC 6.2.19 32-bit client -SSE3 optimized 32-bit apps |
Aristoteles Doukas Send message Joined: 11 Apr 08 Posts: 1091 Credit: 2,140,913 RAC: 0 |
first AP unit has run 1 hour, 25 to go,hopefully everything goes as should, and no errors. |
Byron S Goodgame Send message Joined: 16 Jan 06 Posts: 1145 Credit: 3,936,993 RAC: 0 |
I think this WU needs to be looked at by someone that can correct it. My first wingman completed the task back on Nov 1 back when they were still supposed to be using 4.36. The problem came when their wingman didn't report and I was assigned. Now we have a 4th wingman, and if things go the way they have been, the guy that did everything he was supposed to do, probably won't get credit for his work. Can someone please fix this if that's the case. |
1mp0£173 Send message Joined: 3 Apr 99 Posts: 8423 Credit: 356,897 RAC: 0 |
Hi, The order doesn't matter. Simply splice the two files together any way you like. Most copy/paste from notepad/wordpad, but whatever you're comfortable with. In the middle of the file, you'll find a closing </app_info> followed by a new opening <app_info> on the next line. Remove those two lines. |
Josef W. Segur Send message Joined: 30 Oct 99 Posts: 4504 Credit: 1,414,761 RAC: 0 |
The order doesn't matter. Not those two! There is conflicting information about which executable to use for astropulse work. Combining all three available optimized AstroPulse versions in one file is neither sensible nor easy. Having two of them designated as both 4.35 and 4.36 is very unlikely to work. In this case, the existing astropulse section should be replaced by the new content. Joe |
Leaps-from-Shadows Send message Joined: 11 Aug 08 Posts: 323 Credit: 259,220 RAC: 0 |
Don't worry guys, I already took care of -Bert-. Already up and running on the new app. Cruiser Gateway GT5692 L-f-S Edition -Phenom X4 9650 CPU -4GB 667MHz DDR2 RAM -500GB SATA HD -Vista x64 SP1 -BOINC 6.2.19 32-bit client -SSE3 optimized 32-bit apps |
1mp0£173 Send message Joined: 3 Apr 99 Posts: 8423 Credit: 356,897 RAC: 0 |
The order doesn't matter. That's what I get for writing SHORT. My suggestion works fine for a genuine AP app_info.xml and a genuine MB ap_info.xml as supplied with the optimized apps themselves. Sorry. |
Byron S Goodgame Send message Joined: 16 Jan 06 Posts: 1145 Credit: 3,936,993 RAC: 0 |
Finished a few AP 5.00 tasks on my Intel E2180 dual core and my AMD64 3800+ and both are showing better crunch times as expected. The AMD went from about 39 hours with the 4.36 to the 36-37 hour range. The Intel seems to be showing a better improvement with the 5.00. It's previous times with 4.36 were in the 42-44 hour range and now are down closer to the AMD, around the 36-38 hour range. With 4.36 there seemed to be a better boost of performance for the AMD. Of course I haven't run enough to say for sure, but with the 5.00, so far it appears to favor Intel again. |
skildude Send message Joined: 4 Oct 00 Posts: 9541 Credit: 50,759,529 RAC: 60 |
"BUMP" seems we have several if not many folks that are not aware of the new ap. and the fact that the new AP app only works with the new 5.0 opt ap In a rich man's house there is no place to spit but his face. Diogenes Of Sinope |
Cosmic_Ocean Send message Joined: 23 Dec 00 Posts: 3027 Credit: 13,516,867 RAC: 13 |
Alright, I've got a few 5.00's that have finished crunching at least.. 1068779821 370149106 24 Nov 2008 7:23:52 UTC 1 Dec 2008 11:18:31 UTC Over Success Done 173,537.10 759.33 759.33 1068707588 370115798 24 Nov 2008 4:59:58 UTC 1 Dec 2008 11:18:31 UTC Over Success Done 175,253.60 759.33 pending 1068494274 370015681 23 Nov 2008 22:46:59 UTC 1 Dec 2008 11:18:31 UTC Over Success Done 267,198.90 759.33 759.33 There's three more that haven't reported yet though. On that Opteron rig, there are three that are fairly diverse in their CPU time. One is almost 80 hours, one is in the upper 50s, and the third is in the mid-40s. I was out of town since Tuesday, but as far as I can tell, there were no issues on any of my rigs whilst I was gone. Linux laptop: record uptime: 1511d 20h 19m (ended due to the power brick giving-up) |
Luke Send message Joined: 31 Dec 06 Posts: 2546 Credit: 817,560 RAC: 0 |
|
Cosmic_Ocean Send message Joined: 23 Dec 00 Posts: 3027 Credit: 13,516,867 RAC: 13 |
I'm assuming you're referring to that thread asking everyone to update their opti AP clients to the 5.00r69 one. When this thread was started, r69 was the initial public release, and as far as I know, it is still the current public build. I believe the other thread was to try to get people who were still using v4.xx to move up to v5 so we can get rid of v4 for good and get back to smooth sailing again, given the known issues with v4 and v5 being used for the same WUs. Linux laptop: record uptime: 1511d 20h 19m (ended due to the power brick giving-up) |
Leaps-from-Shadows Send message Joined: 11 Aug 08 Posts: 323 Credit: 259,220 RAC: 0 |
Edit: Errr ... yeah, what Cosmic said. :) Cruiser Gateway GT5692 L-f-S Edition -Phenom X4 9650 CPU -4GB 667MHz DDR2 RAM -500GB SATA HD -Vista x64 SP1 -BOINC 6.2.19 32-bit client -SSE3 optimized 32-bit apps |
Raistmer Send message Joined: 16 Jun 01 Posts: 6325 Credit: 106,370,077 RAC: 121 |
What's all this talk about v5.00r69? Is it different from v5.00? V5r69 is the optimized (much faster) variant of stock V5.00 build. The aim of that thread to remind all users of optimized app to do upgrade. It does not touch users of stock version. Stock version was upgraded automatically. |
Richard Haselgrove Send message Joined: 4 Jul 99 Posts: 14654 Credit: 200,643,578 RAC: 874 |
What's all this talk about v5.00r69? Is it different from v5.00? Cosmic_Ocean is quite right. The initial release of AP v5.00 with which I started this thread is indeed the r69 sub-version, so anyone who installed v5.00 from the links in this thread, or from the newer links in the read-only thread or at Lunatics, is already using the recommended version and doesn't need to upgrade any further. You can see the full revision number in the stderr_txt of any completed AP task: AstroPulse v. 5.00 Non-graphics FFTW USE_CONVERSION_OPT USE_SSE3 [b]Windows x86 rev 69 build 130a[/b] SSE filter by Raistmer with support of Lunatics.kwsn.net team. SSE3 SSE3 dechirping by JDWhale "rev 69 build 130a" gives you an indication of just how much work goes into these optimised applications before they're released. The crew are already up to rev 78, but the thorough testing (another behind-the-scenes job at Lunatics) has revealed that it sometimes doean't validate, so there won't be any new versions for a little while while the gremlins are eradicated. Hats off to Raistmer, Jason, Josef, JD and all for the extremely hard and high-quality work they put into these applications. |
©2024 University of California
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.