Message boards :
Number crunching :
Setting up Linux to crunch CUDA90 and above for Windows users
Message board moderation
Previous · 1 . . . 57 · 58 · 59 · 60 · 61 · 62 · 63 . . . 162 · Next
Author | Message |
---|---|
TBar Send message Joined: 22 May 99 Posts: 5204 Credit: 840,779,836 RAC: 2,768 |
This is from the Mac App and it's about the same with the Linux App. On the BLC Tasks the New App is around 50% Faster than the CUDA 9.0 zi3v App. Well worth the effort to switch. Running on TBarsMacPro.local at Sat Aug 18 16:08:28 2018 --------------------------------------------------- Starting benchmark run... --------------------------------------------------- Listing wu-file(s) in /testWUs : 03my17ab.4903.11519.16.43.91.wu 16fe08aa.12502.25021.6.33.13.wu 18dc09ah.26284.16432.6.33.125.wu blc01_2bit_guppi_58137_29542_HIP45689_002 0.26400.818.21.44.80.vlar.wu blc03_2bit_guppi_58227_18045_HIP66354_0049.27116.0.22.45.226.vlar.wu blc04_2bit_blc04_guppi_58226_25178_DIAG_ PSR_J1935+1616_0007.31720.818.22.45.135.vlar.wu blc04_2bit_guppi_58227_05169_HIP53229_0012.26582.409.21.44.134.vlar.wu blc16_2bit_guppi_58 185_76028_Dw1_off_0033.2471.1636.22.45.95.vlar.wu Listing executable(s) in /APPS : setiathome_x41p_V0.97_x86_64-apple-darwin_cuda91 Listing executable in /REF_APPs : setiathome_x41p_zi3v_x86_64-apple-darwin_cuda91 --------------------------------------------------- Current WU: 03my17ab.4903.11519.16.43.91.wu --------------------------------------------------- Running default app with command : setiathome_x41p_zi3v_x86_64-apple-darwin_cuda91 -nobs -device 0 175.75 real 152.75 user 18.94 sys Elapsed Time: ....................................... 175 seconds --------------------------------------------------- Running app with command : setiathome_x41p_V0.97_x86_64-apple-darwin_cuda91 -nobs -device 0 167.63 real 146.53 user 18.70 sys Elapsed Time : .................................... 168 seconds Speed compared to default : 104 % ----------------- Comparing results Result : Strongly similar, Q= 100.0% --------------------------------------------------- Done with 03my17ab.4903.11519.16.43.91.wu. Current WU: 16fe08aa.12502.25021.6.33.13.wu --------------------------------------------------- Running default app with command : setiathome_x41p_zi3v_x86_64-apple-darwin_cuda91 -nobs -device 0 129.00 real 112.09 user 14.62 sys Elapsed Time: ....................................... 129 seconds --------------------------------------------------- Running app with command : setiathome_x41p_V0.97_x86_64-apple-darwin_cuda91 -nobs -device 0 109.32 real 95.27 user 11.77 sys Elapsed Time : .................................... 110 seconds Speed compared to default : 117 % ----------------- Comparing results Result : Strongly similar, Q= 100.0% --------------------------------------------------- Done with 16fe08aa.12502.25021.6.33.13.wu. Current WU: 18dc09ah.26284.16432.6.33.125.wu --------------------------------------------------- Running default app with command : setiathome_x41p_zi3v_x86_64-apple-darwin_cuda91 -nobs -device 0 125.65 real 109.25 user 14.11 sys Elapsed Time: ....................................... 126 seconds --------------------------------------------------- Running app with command : setiathome_x41p_V0.97_x86_64-apple-darwin_cuda91 -nobs -device 0 106.92 real 93.22 user 11.42 sys Elapsed Time : .................................... 107 seconds Speed compared to default : 117 % ----------------- Comparing results Unmatched signal(s) in R1 at line(s) 393 473 For R1:R2 matched signals only, Q= 100.0% Result : Weakly similar. --------------------------------------------------- Done with 18dc09ah.26284.16432.6.33.125.wu. Current WU: blc01_2bit_guppi_58137_29542_HIP45689_0020.26400.818.21.44.80.vlar.wu --------------------------------------------------- Running default app with command : setiathome_x41p_zi3v_x86_64-apple-darwin_cuda91 -nobs -device 0 293.81 real 256.35 user 34.83 sys Elapsed Time: ....................................... 293 seconds --------------------------------------------------- Running app with command : setiathome_x41p_V0.97_x86_64-apple-darwin_cuda91 -nobs -device 0 191.44 real 165.61 user 23.35 sys Elapsed Time : .................................... 191 seconds Speed compared to default : 153 % ----------------- Comparing results Result : Strongly similar, Q= 100.0% --------------------------------------------------- Done with blc01_2bit_guppi_58137_29542_HIP45689_0020.26400.818.21.44.80.vlar.wu. Current WU: blc03_2bit_guppi_58227_18045_HIP66354_0049.27116.0.22.45.226.vlar.wu --------------------------------------------------- Running default app with command : setiathome_x41p_zi3v_x86_64-apple-darwin_cuda91 -nobs -device 0 299.08 real 261.51 user 34.96 sys Elapsed Time: ....................................... 299 seconds --------------------------------------------------- Running app with command : setiathome_x41p_V0.97_x86_64-apple-darwin_cuda91 -nobs -device 0 195.45 real 170.45 user 22.57 sys Elapsed Time : .................................... 195 seconds Speed compared to default : 153 % ----------------- Comparing results Result : Strongly similar, Q= 100.0% --------------------------------------------------- Done with blc03_2bit_guppi_58227_18045_HIP66354_0049.27116.0.22.45.226.vlar.wu. Current WU: blc04_2bit_blc04_guppi_58226_25178_DIAG_PSR_J1935+1616_0007.31720.818.22.45.135.vlar.wu --------------------------------------------------- Running default app with command : setiathome_x41p_zi3v_x86_64-apple-darwin_cuda91 -nobs -device 0 8.33 real 5.06 user 1.18 sys Elapsed Time: ....................................... 8 seconds --------------------------------------------------- Running app with command : setiathome_x41p_V0.97_x86_64-apple-darwin_cuda91 -nobs -device 0 9.37 real 6.15 user 1.11 sys Elapsed Time : .................................... 9 seconds Speed compared to default : 88 % ----------------- Comparing results Result : Strongly similar, Q= 100.0% --------------------------------------------------- Done with blc04_2bit_blc04_guppi_58226_25178_DIAG_PSR_J1935+1616_0007.31720.818.22.45.135.vlar.wu. Current WU: blc04_2bit_guppi_58227_05169_HIP53229_0012.26582.409.21.44.134.vlar.wu --------------------------------------------------- Running default app with command : setiathome_x41p_zi3v_x86_64-apple-darwin_cuda91 -nobs -device 0 23.81 real 18.63 user 3.04 sys Elapsed Time: ....................................... 24 seconds --------------------------------------------------- Running app with command : setiathome_x41p_V0.97_x86_64-apple-darwin_cuda91 -nobs -device 0 23.10 real 18.37 user 2.61 sys Elapsed Time : .................................... 23 seconds Speed compared to default : 104 % ----------------- Comparing results Result : Strongly similar, Q= 99.99% --------------------------------------------------- Done with blc04_2bit_guppi_58227_05169_HIP53229_0012.26582.409.21.44.134.vlar.wu. Current WU: blc16_2bit_guppi_58185_76028_Dw1_off_0033.2471.1636.22.45.95.vlar.wu --------------------------------------------------- Running default app with command : setiathome_x41p_zi3v_x86_64-apple-darwin_cuda91 -nobs -device 0 357.79 real 315.15 user 39.94 sys Elapsed Time: ....................................... 358 seconds --------------------------------------------------- Running app with command : setiathome_x41p_V0.97_x86_64-apple-darwin_cuda91 -nobs -device 0 222.99 real 192.91 user 27.60 sys Elapsed Time : .................................... 223 seconds Speed compared to default : 160 % ----------------- Comparing results Unmatched signal(s) in R1 at line(s) 373 469 For R1:R2 matched signals only, Q= 100.0% Result : Weakly similar. --------------------------------------------------- Done with blc16_2bit_guppi_58185_76028_Dw1_off_0033.2471.1636.22.45.95.vlar.wu. Done with Benchmark run! |
JohnDK Send message Joined: 28 May 00 Posts: 1222 Credit: 451,243,443 RAC: 1,127 |
Yes the new app is fast, used the cpu2gpu script and had 1000 WUs and it ran dry just around when the outage was over. Really could use the ability to get more WUs every Tuesday... Well waiting for new work :) |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
Still haven't snagged any work today from the servers after the outage. Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
petri33 Send message Joined: 6 Jun 02 Posts: 1668 Credit: 623,086,772 RAC: 156 |
Hi, I do not want to laugh, but ... I just hit accidentally 'remove' at projects tab (forgot my reading glasses). I meant to hit No New Tasks and then Update. Am I stupid or what am I? Old! I have my app_info and app_config, but I have to make a new host. The servers are slow to send initialization files.... I lost 600+ tasks that were not reported yet after the outage. Blah! To overcome Heisenbergs: "You can't always get what you want / but if you try sometimes you just might find / you get what you need." -- Rolling Stones |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
Sorry to hear your misfortune Petri. I think we all have done "fat-finger" goof-ups before. Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
petri33 Send message Joined: 6 Jun 02 Posts: 1668 Credit: 623,086,772 RAC: 156 |
Sorry to hear your misfortune Petri. I think we all have done "fat-finger" goof-ups before. After all my fat-fingeredness did not cause any major harm. The BOINC and seti system recognized my machine and I'm back with the same host ID. All I lost was 600 WUs and the credit history on the statistics tab. Luckily the history is on WOW and FreeDC. No real damage. :) To overcome Heisenbergs: "You can't always get what you want / but if you try sometimes you just might find / you get what you need." -- Rolling Stones |
mmonnin Send message Joined: 8 Jun 17 Posts: 58 Credit: 10,176,849 RAC: 0 |
I would estimate that it is 50% faster overall than zi3v app. Wow dang. I renamed it as the cuda90 file name and dropped it in. Now I just need some tasks on the 1070 and 1070Ti. The 970 on another PC has tasks though. |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
Be careful with the different 0.97 applications. There is an exclusive Pascal compiled version. And there is another version compiled for Maxwell cards. Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
mmonnin Send message Joined: 8 Jun 17 Posts: 58 Credit: 10,176,849 RAC: 0 |
Be careful with the different 0.97 applications. There is an exclusive Pascal compiled version. And there is another version compiled for Maxwell cards. There is? Both cards work with the above app and are much faster. This only only has Maxwell 0.97 and Sierra 0.97 http://www.arkayn.us/lunatics/ Edit: Ugh as someone that doesn't run SETI all the time this is what makes it so frustrating. Info is all over the place. Someone else posted a link to a separate place in another thread. https://setiathome.berkeley.edu/forum_thread.php?id=83246&postid=1950636#1950636 Or info is hidden somewhere of a 600 page thread. |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
Petri posted a direct link to both versions in an earlier post in this thread. Those links are from TBar's compilation. I think the Sierra designation might be for Pascal. You would have to read the docs in the file. Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
mmonnin Send message Joined: 8 Jun 17 Posts: 58 Credit: 10,176,849 RAC: 0 |
Thanks for the updated apps. It's a shame these aren't default. Even a few invalids is worth the tremendous output increase. |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
Yes these apps are beta versions and only should be run by beta testers who are familiar with their development, their flaws and how to properly install them and test with them. Not for general public release. And certainly not ready for Main. Unless the apps get tested for a year and pass approval by the Seti administrators AND someone comes up with an automatic installer like the Lunatics installer for the SoG app, I don't see these in general release. The installation of the apps has to be bulletproof and "idiot" proof and at the level of the general computer user that knows how to use a computer but has no clue of how it works and cares less so, but wants to do scientific search for E.T. on the desktop. We are a long way from that day. Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
Sorry to hear your misfortune Petri. I think we all have done "fat-finger" goof-ups before. . . and for me just as recently ... . . but life goes on, . . Just read your later message, good news ... Stephen :( |
mmonnin Send message Joined: 8 Jun 17 Posts: 58 Credit: 10,176,849 RAC: 0 |
Yes these apps are beta versions and only should be run by beta testers who are familiar with their development, their flaws and how to properly install them and test with them. Not for general public release. And certainly not ready for Main. Unless the apps get tested for a year and pass approval by the Seti administrators AND someone comes up with an automatic installer like the Lunatics installer for the SoG app, I don't see these in general release. The installation of the apps has to be bulletproof and "idiot" proof and at the level of the general computer user that knows how to use a computer but has no clue of how it works and cares less so, but wants to do scientific search for E.T. on the desktop. We are a long way from that day. BOINC would do the 'install' just like any other app on any project. Select Seti in the dropdown in BM and done. Since it would come from the project the app_info would not be required and we'd all download the executable just like the current SETI provided app. Just 2 files are required now. SETI could even put the Lunatics options right there in Project Preferences. Some projects have multiple versions and PCs download the plan class versions their PCs can support based off the CPU info. If one app runs a bit faster then more tasks for that app will download. Asteroids on CPUs for example has multiple SSE and AVX versions. Depending on the CPU arch implementation one may run faster than the other even if a CPU supports the 'fastest'. Same can be done here. Tweaking with the command lines is up to the user of course. |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
Not so simple on Linux though. On Windows, the environment is a known factor and all support structures are assumed to be in place. So, yes, the project sends you the application that works on 100% of Windows computers. On Linux, there is no standardized environment and so there are too many variables that affect the supporting software that the application needs. I am familiar with the woes that Linux users have over at GPUGrid.net in trying to get the standard Linux app working that the servers send out. If the gcc package isn't installed, the application doesn't run. The users come to the forums asking why everything works fine on their Windows computers so why doesn't the project work on the Linux computers. Since the special app needs a minimum Nvidia driver level, the servers would have to probe a host system for the compatible environment. If all the servers look for is the driver version, the installation will fail since the Linux driver ships with separate packages for the base graphics drivers, the CUDA drivers and the OpenCL drivers. Any one or all missing will cause the application to fail. If the special app source code is somehow ported over to Windows, then the project should be able to automatically send the special application to a host and have an almost 100% chance of it working on first startup. Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
OK, try this in Ubuntu 14.04 (And Others); . . Well colour me tickled pink. . . I am most impressed. On the GTX1050ti run times have reduced from the previous 4.6 min for Arecibo norms, 4.9 to 5.5 mins for various forms of GBT tasks up to 9.6 mins for Arecibo VLARS down to the current 3.1 mins for Arecibo norms, 3.2 to 3.8 mins for most GBT tasks except for the slow Blc14's we have had lately that take a massive 4.1 mins then up to 6.2 mins for the Arecibo VLARs. The increase comes to about 1.475 times what it used to be. Definitely a worthwhile development. Well done guys, many thanks to TBar and Petri. A genius of an app there Petri. . . On the GTX970s well ..... Just about everything takes just about 2 mins. I haven't seen a VLAR go through yet but that will be the fly in the ointment. Everything else is 1.9 to 2.1 mins :) . . I have read that there is no advantage in using the -nobs parameter but what about the pfp 32 setting? Stephen ?? Stephen :) |
Tom M Send message Joined: 28 Nov 02 Posts: 5124 Credit: 276,046,078 RAC: 462 |
I was wondering if I could find the equivalent for GPU-Z for Linux. Here is a "couple" of ideas: https://askubuntu.com/questions/5417/how-to-get-the-gpu-info A terminal command of: nvidia-settings brings up a nice Gui display including the gpu loading. It looks like it will display it for each card. Tom A proud member of the OFA (Old Farts Association). |
Tom M Send message Joined: 28 Nov 02 Posts: 5124 Credit: 276,046,078 RAC: 462 |
I have been wondering for a while if the baseline (suggested) command line parameters from the SOG readme would make a difference on my processing. I have just inserted this " <cmdline>-sbs 192 -spike_fft_thresh 2048 -tune 1 64 1 4</cmdline>" into my app_info.xml file on one machine. The first thing I noticed is the cpu load is varying much more. It has hit 5% briefly. Stay tune for more stupid experiments... This is with 1 cpu dedicated to the gpu. I am also successfully using the app_config.xml file to control how much cpu I dedicate to my gpu(s). Tom A proud member of the OFA (Old Farts Association). |
Mike Send message Joined: 17 Feb 01 Posts: 34258 Credit: 79,922,639 RAC: 80 |
Doesn`t work at all. OpenCL values for cuda app. With each crime and every kindness we birth our future. |
Brent Norman Send message Joined: 1 Dec 99 Posts: 2786 Credit: 685,657,289 RAC: 835 |
I have been wondering for a while if the baseline (suggested) command line parameters from the SOG readme would make a difference on my processing. I have just inserted this " <cmdline>-sbs 192 -spike_fft_thresh 2048 -tune 1 64 1 4</cmdline>" into my app_info.xml file on one machine.You stderr file shows this: <core_client_version>7.4.44</core_client_version> <![CDATA[ <stderr_txt> bad arg: -sbs bad arg: 192 bad arg: -spike_fft_thresh bad arg: 2048 bad arg: -tune bad arg: 1 bad arg: 64 bad arg: 1 bad arg: 4 setiathome_CUDA: Found 1 CUDA device(s): Device 1: GeForce GTX 750 Ti, 2000 MiB, regsPerBlock 65536 computeCap 5.0, multiProcs 5 pciBusID = 1, pciSlotID = 0 In cudaAcc_initializeDevice(): Boinc passed DevPref 1 setiathome_CUDA: CUDA Device 1 specified, checking... Device 1: GeForce GTX 750 Ti is okay SETI@home using CUDA accelerated device GeForce GTX 750 Ti Unroll autotune 5. Overriding Pulse find periods per launch. Parameter -pfp set to 5 setiathome v8 enhanced x41p_zi3v, Cuda 9.00 special Modifications done by petri33, compiled by TBarPETRI, we need a special error code for this type of input. |
©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.