Message boards :
Number crunching :
Lunatics Windows Installer v0.43 Release Notes
Message board moderation
Previous · 1 · 2 · 3 · 4 · 5 · 6 · 7 . . . 11 · Next
Author | Message |
---|---|
JohnDK Send message Joined: 28 May 00 Posts: 1222 Credit: 451,243,443 RAC: 1,127 |
Thinks t might have something to do with the command line. On the 4GB PC http://setiathome.berkeley.edu/show_host_detail.php?hostid=7283519 I had the problem with this command line -use_sleep -unroll 16 -oclFFT_plan 256 16 256 -ffa_block 16384 -ffa_block_fetch 8192 -tune 1 64 8 1 -tune 2 64 8 1 After changing it to -unroll 16 -ffa_block 10240 -ffa_block_fetch 5120 -use_sleep -tune 1 64 8 1 -tune 2 64 8 1 The problem seems to have gone away. |
Stick Send message Joined: 26 Feb 00 Posts: 100 Credit: 5,283,449 RAC: 5 |
Avast! also freaked out that I was downloading the file. Naturally I ignore the warning of a dangerous file. I use Avast and downloaded both the 32-bit and the 64-bit installers. Strangely enough, Avast did not object to the 64-bit version. |
Mike Send message Joined: 17 Feb 01 Posts: 34255 Credit: 79,922,639 RAC: 80 |
[Which one ? Its probably -unroll 26. Go back to unroll 18. With each crime and every kindness we birth our future. |
Blurf Send message Joined: 2 Sep 06 Posts: 8962 Credit: 12,678,685 RAC: 0 |
[/quote]Can no longer do 2 GPU units at once as I was since installing .43 Thank you-back to where we were. |
JohnDK Send message Joined: 28 May 00 Posts: 1222 Credit: 451,243,443 RAC: 1,127 |
[Which one ? That didn't help, the memory stealing WU keeps on stealing. Pausing it starts another WU which runs normal, unpausing the WU and it's continues stealing. |
Mike Send message Joined: 17 Feb 01 Posts: 34255 Credit: 79,922,639 RAC: 80 |
[Which one ? Reduce ffa_fetch and ffa_fetch_block like you did on your other host. It seems your host can`t cope with sharp timings. With each crime and every kindness we birth our future. |
JohnDK Send message Joined: 28 May 00 Posts: 1222 Credit: 451,243,443 RAC: 1,127 |
Go back to unroll 18. Didn't help either, even tried almost barebone command line, same thing. -unroll 12 -ffa_block 12288 -ffa_block_fetch 6144 -use_sleep It's strange, host runs fine except for a few WUs, think this is the first one on the GTX970 host, seems to me the problem maybe lies with the WU itself. |
Josef W. Segur Send message Joined: 30 Oct 99 Posts: 4504 Credit: 1,414,761 RAC: 0 |
Go back to unroll 18. Although it won't be much help, I downloaded that WU from http://boinc2.ssl.berkeley.edu/sah/download_fanout/143/ap_28jn14aa_B5_P1_00055_20141018_06043.wu and ran it on my AMD A10-4600M APU test laptop with the OpenCL ATI app. The memory usage was under 350 MiB. Of course that's about as different a memory situation as possible with the GPU portion of the APU using system RAM rather than dedicated VRAM, etc. About the only thing in common is that laptop is running Windows 7 64 bit (the Home Premium flavor). The run found 29 Single pulses, 30 Repetitive pulses, and there was 8.8% blanking. That's not a typical WU, but similar WUs aren't very rare either. I can't think of any reason for the task to use an unusual amount of memory, but I'm no expert in how recent NVIDIA drivers deal with memory. The 30 Repetitive pulses were found early at the end of the first large chunk, so before 1% progress. After that the FFAs would no longer be used, so it might be worthwhile to check how quickly the memory usage grows when processing from the beginning. Joe |
DF1DX Send message Joined: 14 Aug 99 Posts: 2 Credit: 2,703,827 RAC: 3 |
IMHO there is a small bug in the installer - APv7_r2559_SSE3_OSX64.zip /Files_to_Install/apv7_install.command in line 24: change sed s/sahv7_install.command// to sed s/apv7_install.command// Many thanks to the team. Jürgen |
Raistmer Send message Joined: 16 Jun 01 Posts: 6325 Credit: 106,370,077 RAC: 121 |
Thinks t might have something to do with the command line. Next time one will see such excessive system memory consumption please catch that particular task and send it to me along with command line options used in task processing. |
juan BFP Send message Joined: 16 Mar 07 Posts: 9786 Credit: 572,710,851 RAC: 3,799 |
I have one who uses more than 1 GB. SETI@home 7.05 astropulse_v7 (opencl_nvidia_100) ap_26jn14aa_B6_P0_00184_20141017_17161.wu_0 00:21:28 (00:00:10) 0,83 61,261 00:43:27 12/11/2014 07:01:51 0,1C + 1NV Suspended by user Juan 2 Command Line: -use_sleep -unroll 16 -oclfft_plan 256 16 256 -ffa_block 16384 -ffa_block_fetch 8192 -tune 1 64 4 1 -tune 2 64 4 1 it´s a 2x780FTW host What else you need? One observation, the core usage rises to allmost 100% when normaly is very low. <edit> another one from the same host, suspended it for now (this one uses 1.7 GB) SETI@home 7.05 astropulse_v7 (opencl_nvidia_100) ap_28jn14aa_B1_P1_00131_20141017_13023.wu_1 00:00:02 (-) 24,00 0,044 01:22:51 12/11/2014 06:46:22 0,1C + 1NV Suspended by user Juan 2 |
Raistmer Send message Joined: 16 Jun 01 Posts: 6325 Credit: 106,370,077 RAC: 121 |
I have one who uses more than 1 GB. I need task itself (binary or link to download binary).
yep, it correlates with my current suspiction where it could be. I expected this issue diminished in APv7 though so need test case to explore. |
HAL9000 Send message Joined: 11 Sep 99 Posts: 6534 Credit: 196,805,888 RAC: 57 |
I have one who uses more than 1 GB. If you do not already have it & need help finding the download path. There is the SETI fanout url generator SETI@home classic workunits: 93,865 CPU time: 863,447 hours Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[ |
Richard Haselgrove Send message Joined: 4 Jul 99 Posts: 14650 Credit: 200,643,578 RAC: 874 |
I have one who uses more than 1 GB. And it works a treat. Both data files are still on the server. http://boinc2.ssl.berkeley.edu/sah/download_fanout/39f/ap_26jn14aa_B6_P0_00184_20141017_17161.wu http://boinc2.ssl.berkeley.edu/sah/download_fanout/2f5/ap_28jn14aa_B1_P1_00131_20141017_13023.wu |
juan BFP Send message Joined: 16 Mar 07 Posts: 9786 Credit: 572,710,851 RAC: 3,799 |
I have one who uses more than 1 GB. UL to my skydrive now and send you the link by PM in few min, sorry for the delay i´m in a diferent country than the host. |
Raistmer Send message Joined: 16 Jun 01 Posts: 6325 Credit: 106,370,077 RAC: 121 |
thanks, got them. @juan BFB - Thanks, no need. I got them from Richard's link already. |
juan BFP Send message Joined: 16 Mar 07 Posts: 9786 Credit: 572,710,851 RAC: 3,799 |
thanks, got them. OK hope that help to fix the problem. If you need more examples or want to test any fix on this host just ask, aparently the problem is very common on this host, latter i will check if that happening on the others. |
BilBg Send message Joined: 27 May 07 Posts: 3720 Credit: 9,385,827 RAC: 0 |
The one in the Joe's post: http://setiathome.berkeley.edu/forum_thread.php?id=75863&postid=1589451#1589451 ... is also still on the server: http://boinc2.ssl.berkeley.edu/sah/download_fanout/143/ap_28jn14aa_B5_P1_00055_20141018_06043.wu  - ALF - "Find out what you don't do well ..... then don't do it!" :)  |
David S Send message Joined: 4 Oct 99 Posts: 18352 Credit: 27,761,924 RAC: 12 |
As previously noted in some thread or other (not sure if it was this one), when I installed .43 on my GPU-only box, I incorrectly installed cuda 50 for MB. At the time, I did not install CPU apps at all, but I did install the AP7 GPU app. It never got any AP7s. Last night, I reinstalled for cuda 42, once again including AP7 for GPU and this time also installing the CPU apps (even though I don't run them -- I figured it didn't hurt anything to install them, since it's disallowed in my prefs). Since I did the reinstall last night, it has downloaded 5 AP7s. I can't really make the case that there's a cause/effect relationship between not installing the CPU apps and not getting any AP7s, but it seems an odd coincidence. David Sitting on my butt while others boldly go, Waiting for a message from a small furry creature from Alpha Centauri. |
juan BFP Send message Joined: 16 Mar 07 Posts: 9786 Credit: 572,710,851 RAC: 3,799 |
@ Raistmer I made some more tests and the problem is aparently related to the -oclfft_plan switch, when you run without the switch the problem dissapears. The same problem apears on others hosts with the same GPU (780FTW) all running Win7 and i see at least one example on a 2x690 host who runs Win Server and on a 670 hosts with win 7. |
©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.