Message boards :
Number crunching :
Monitoring inconclusive GBT validations and harvesting data for testing
Message board moderation
Previous · 1 · 2 · 3 · 4 · 5 · 6 · 7 · 8 . . . 36 · Next
Author | Message |
---|---|
jason_gee Send message Joined: 24 Nov 06 Posts: 7489 Credit: 91,093,184 RAC: 0 |
More inconclusives whether they are GBT or Arecibo running the first guppi [you supplied before] against reference Win32 stock CPU, and Cuda50, now; then will manually compare to your CPU result. Could turn out yours is ok or not, we'll see. "Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions. |
Kiska Send message Joined: 31 Mar 12 Posts: 302 Credit: 3,067,762 RAC: 0 |
I am also running CUDA as well, I'll do 4.2 then 5.0 Though it shouldn't have issues, I ran it stock |
jason_gee Send message Joined: 24 Nov 06 Posts: 7489 Credit: 91,093,184 RAC: 0 |
I am also running CUDA as well, I'll do 4.2 then 5.0 Looking at the other hosts in that first one, more than likely it could be one Petri will want, so will confirm and then email it to him. The first host was a broken Cuda, second was your CPU, third was Petri special. (If my CPU + Cuda match it under bench, + yours manually, he'll likely find some useful hints in it) "Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions. |
Kiska Send message Joined: 31 Mar 12 Posts: 302 Credit: 3,067,762 RAC: 0 |
I can run petri special app, manually I just need to know where to download it My manually ran one, according to stderr has the same counts of pulses, etc |
jason_gee Send message Joined: 24 Nov 06 Posts: 7489 Credit: 91,093,184 RAC: 0 |
I can run petri special app, manually I just need to know where to download it For Linux, You'd need to ask Petri (if he's still working on it toward these validation issues he may say no). For Windows, my build's somewhat broken and needs updating, so not an option to go handing out. TBar has a Mac version though. "Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions. |
Kiska Send message Joined: 31 Mar 12 Posts: 302 Credit: 3,067,762 RAC: 0 |
Ok. well anyway I expect my result file and your cpu + cuda to be ~99% similar or even matching. Its too bad I can't get the Windows build..... |
jason_gee Send message Joined: 24 Nov 06 Posts: 7489 Credit: 91,093,184 RAC: 0 |
Ok. well anyway I expect my result file and your cpu + cuda to be ~99% similar or even matching. Its too bad I can't get the Windows build..... I think that'll be the case. Sadly takes 2 hours on crappy CPU here :D (not so long for the Cuda result) [Edit:] Just got Petri's sources updated in svn... one small step at a time "Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions. |
Kiska Send message Joined: 31 Mar 12 Posts: 302 Credit: 3,067,762 RAC: 0 |
No worries, it took 2 hrs on my E3-1230 v3. |
Kiska Send message Joined: 31 Mar 12 Posts: 302 Credit: 3,067,762 RAC: 0 |
|
jason_gee Send message Joined: 24 Nov 06 Posts: 7489 Credit: 91,093,184 RAC: 0 |
got it. Will probably pass out while CPU is still running, but will have multiple ones to compare there. Will probably have enough on that one by the morning to work out if it might be useful to petri, then package everything up to email him. "Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions. |
jason_gee Send message Joined: 24 Nov 06 Posts: 7489 Credit: 91,093,184 RAC: 0 |
Well Kiska's original inconclusive against Petri's older build (on WezH's Linux Machine) confirmed a large amount we knew, and possibly holds some hints for development to sift through, so will bundle up and send to Petri. Note that my Windows zkpr3 test build, which I consider broken, and is already outdated, probably reflects similar characteristics to the Linux one WezH's running, and precedes the last changes in alpha. Probably will get to attempting a revised test build after having a Wisdom tooth pulled later today (we'll see) C:\Users\Jason\Downloads\[alpha]\kiska\Comparison>rescmpv4.exe cuda42_result_fro m_kiska.res ref-setiathome_8.00_windows_intelx86.exe-kiska_guppi.vlar.wu.res Result : Strongly similar, Q= 99.22% C:\Users\Jason\Downloads\[alpha]\kiska\Comparison>rescmpv4.exe jason-result-Luna tics_x41zj_win32_cuda50.exe-kiska_guppi.vlar.wu.res ref-setiathome_8.00_windows_ intelx86.exe-kiska_guppi.vlar.wu.res Result : Strongly similar, Q= 99.22% C:\Users\Jason\Downloads\[alpha]\kiska\Comparison>rescmpv4.exe jason-result-Luna tics_x41zj_win32_cuda50.exe-kiska_guppi.vlar.wu.res cuda42_result_from_kiska.res Result : Strongly similar, Q= 100.0% C:\Users\Jason\Downloads\[alpha]\kiska\Comparison>rescmpv4.exe result-Lunatics_x 41zkpr3_winx64_cuda65.exe-kiska_guppi.vlar.wu.res ref-setiathome_8.00_windows_in telx86.exe-kiska_guppi.vlar.wu.res ----- R1:R2 ------ ----- R2:R1 ------ Tight Good Bad Tight Good Bad Spike 0 0 0 0 0 0 Autocorr 1 1 0 1 1 0 Gaussian 0 0 0 0 0 0 Pulse 3 3 0 3 3 2 Triplet 4 4 0 4 4 0 Best Spike 1 1 0 1 1 0 Best Autocorr 1 1 0 1 1 0 Best Gaussian 1 1 0 1 1 0 Best Pulse 0 0 1 0 0 1 Best Triplet 1 1 0 1 1 0 ---- ---- ---- ---- ---- ---- 12 12 1 12 12 3 Unmatched signal(s) in R1 at line(s) 554 Unmatched signal(s) in R2 at line(s) 383 471 606 Result : Weakly similar. "Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions. |
Jeff Buck Send message Joined: 11 Feb 00 Posts: 1441 Credit: 148,764,870 RAC: 0 |
Started out as a gray and dismal morning here, so I decided to see if I could use the current Inconclusives in my own local DB to programmatically generate some sort of formatted list that could possibly be useful to those of you doing the research and testing in this area. Here's a sampling of WUs from my initial stab at it: Workunit 2213859925 The full list (in html format, with WU and Task links) is available in a cloud file, if anyone wants to take a further look. These are all just WUs that one of my own hosts is involved in, either already with an Inconclusive result, or in my queue waiting to run as a tiebreaker. I notice that there are already a few that have been resolved, just in the few hours since my DB was updated. Let me know if this is at all useful. Meantime, the sun is now out (albeit through a high smoky haze) and it's lunchtime. |
Kiska Send message Joined: 31 Mar 12 Posts: 302 Credit: 3,067,762 RAC: 0 |
I guess thats a start, but however we would prefer the datafile so we could get some sample results match and see how similar they are. Example:
Workunit Datafile Workunit 2237343062 Workunit Datafile Workunit 2213859925 Workunit Datafile |
Jeff Buck Send message Joined: 11 Feb 00 Posts: 1441 Credit: 148,764,870 RAC: 0 |
I guess thats a start, but however we would prefer the datafile so we could get some sample results match and see how similar they are. Sure, but there are over 100 Workunits in that list and it's likely that only a very few of them might be useful for this testing. That's why I included the signal counts in the summary and embedded links for each work unit and task. That way, those who know better than I what it is specifically that they're looking for can more easily winnow down the potential testing candidates and only retrieve those particular WU files from the server. The one thing I will attempt to do this evening is to replace those "Anonymous platform" IDs with more specific app identifiers wherever I can. Unfortunately, there's not a consistent format for that info in the Stderrs. |
jason_gee Send message Joined: 24 Nov 06 Posts: 7489 Credit: 91,093,184 RAC: 0 |
Yeah choices of which task and result files would be good to dig for and poke at, will probably come down to the individual problems, and how Richard+Raistmer plan to look at them. For Cuda mysteries I prefer lab condition runs with actual files, while that's just my approach and some others may not need that, depending. Many can be ruled out as flaky hosts/GPUs pretty easily (with stock Cuda). In the case of Petri Special, we already have a good headstart with the one Pulses example currently under the microscope, because the result files say more than the stderr prints. Probably we'll be looking for more after some things have been nailed down with that, but extensive collection for the Cuda special builds probably won't be necessary short term. "Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions. |
Jeff Buck Send message Joined: 11 Feb 00 Posts: 1441 Credit: 148,764,870 RAC: 0 |
Okay, I've tweaked the format of my listing a bit, replacing the "Anonymous platform" designations with, hopefully, more specific app descriptions. I've also identified which Work Units are guppis. The latest file is available from this link. (Unfortunately, Amazon's cloud drive apparently gets all screwed up when one tries to replace an existing file, so the link in my earlier post no longer seems to be valid.) Examples of the slightly altered format: Workunit 2243574106 Task 5111259127 (S=7, A=0, P=5, T=0, G=1) v8.12 (opencl_intel_gpu_sah) windows_intelx86 Task 5111259128 (S=8, A=0, P=5, T=0, G=0) x41zi (baseline v8), Cuda 5.00 Workunit 2244749285 (guppi) Task 5113705190 (S=2, A=0, P=8, T=2, G=0) AVXxj Win64 Build 3330 Task 5113705191 (S=2, A=0, P=11, T=2, G=0) v8.12 (opencl_intel_gpu_sah) windows_intelx86 Many can be ruled out as flaky hosts/GPUs pretty easily (with stock Cuda). That's one of the reasons I figured that a listing showing the signal counts for each task would help to more easily weed out the "off the rails" hosts, without having to download the WU files or otherwise dig any deeper. |
Kiska Send message Joined: 31 Mar 12 Posts: 302 Credit: 3,067,762 RAC: 0 |
Again an excellent time to see if we get some resends |
W-K 666 Send message Joined: 18 May 99 Posts: 19012 Credit: 40,757,560 RAC: 67 |
Is this the type of thing you are investigating. blc5_2bit_guppi_57403_68833_HIP11048_OFF_0003.20883.416.21.44.64.vlar I have completed _4, but not reported yet. Network activity suspended. |
Kiska Send message Joined: 31 Mar 12 Posts: 302 Credit: 3,067,762 RAC: 0 |
Yes please upload both result and datafile for analysis, if possible pm me with your email so I can add you to my google drive authorised edit list, so you can upload the results and data |
W-K 666 Send message Joined: 18 May 99 Posts: 19012 Credit: 40,757,560 RAC: 67 |
Yes please upload both result and datafile for analysis, if possible pm me with your email so I can add you to my google drive authorised edit list Do you need my to copy and send you any files still on my computer. edit] We seem to have got crossed up, PM sent |
©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.