Message boards :
News :
SETI@home v8 beta to begin on Tuesday
Message board moderation
Previous · 1 . . . 55 · 56 · 57 · 58 · 59 · 60 · 61 . . . 99 · Next
Author | Message |
---|---|
![]() ![]() Send message Joined: 18 Aug 05 Posts: 2423 Credit: 15,878,738 RAC: 0 ![]() |
In both -v 6 did not work but no need to repeat it currently. News about SETI opt app releases: https://twitter.com/Raistmer |
Send message Joined: 12 Nov 10 Posts: 1149 Credit: 32,460,657 RAC: 1 ![]() |
Didn't really get a chance to check the memory leak, although it was climbing slowly it hadn't got much higher than the 8.12 version I ran yesterday. The task reached only 16.5% and then had the postponed 30s issue and another task started. Previous versions the task reached 35% before glitching. If you want to check the results I'll let both the tasks run to completion. Edit: 2nd task just reached 16.5% and glitched so it looks like it's a repeatable error |
Send message Joined: 30 Dec 13 Posts: 258 Credit: 12,340,341 RAC: 0 ![]() |
Ok, here are -high_perf with the sleep quantum of size 3ms WU true angle range is : 0.429487 https://setiweb.ssl.berkeley.edu/beta//result.php?resultid=24283749 WU true angle range is : 0.429487 https://setiweb.ssl.berkeley.edu/beta//result.php?resultid=24283749 WU true angle range is : 0.008175 https://setiweb.ssl.berkeley.edu/beta//result.php?resultid=24283903 WU true angle range is : 0.008175 https://setiweb.ssl.berkeley.edu/beta//result.php?resultid=24283956 Ok, I'm going to test my own commandlines and headed to bed. If you need anything else let me know and I'll try again when I get up in the morning |
![]() ![]() Send message Joined: 18 Aug 05 Posts: 2423 Credit: 15,878,738 RAC: 0 ![]() |
quantum of 3: Ð’Ñ€ÐµÐ¼Ñ Ð²Ñ‹Ð¿Ð¾Ð»Ð½ÐµÐ½Ð¸Ñ 4 мин. 16 Ñек. Ð’Ñ€ÐµÐ¼Ñ Ð¦ÐŸ 4 мин. 14 Ñек. here some not according to plan %) EDIT: OK, it can be considered as interface flaw. no -use_sleep was provided so no sleep used irregardless of quantum size. I'll add automatic sleep enabling if user attempts to use any of sleep-belonging options. But now please retest with -use_sleep -sleep_quantum 3 News about SETI opt app releases: https://twitter.com/Raistmer |
![]() ![]() Send message Joined: 18 Aug 05 Posts: 2423 Credit: 15,878,738 RAC: 0 ![]() |
that's how Earth globe complicates things. Morning here :) News about SETI opt app releases: https://twitter.com/Raistmer |
Send message Joined: 30 Dec 13 Posts: 258 Credit: 12,340,341 RAC: 0 ![]() |
I'll add automatic sleep enabling if user attempts to use any of sleep-belonging options. But now please retest with -use_sleep -sleep_quantum 3 Ah ok, didn't know they needed to go together. I'll do that then I'm headed to bed. See you tonight, lol |
![]() ![]() Send message Joined: 18 Aug 05 Posts: 2423 Credit: 15,878,738 RAC: 0 ![]() |
please let them run until natural erroring out after many attempts. at least one such task. abort another and givethe link. News about SETI opt app releases: https://twitter.com/Raistmer |
![]() ![]() Send message Joined: 18 Aug 05 Posts: 2423 Credit: 15,878,738 RAC: 0 ![]() |
Also, could you describe what happened with this one: Ð˜Ð¼Ñ 24mr10ac.10953.4975.14.48.235_3 Задача 8711782 Создан 6 Jul 2016, 22:45:55 UTC Отправлен 7 Jul 2016, 15:45:43 UTC Крайний Ñрок отчёта 29 Aug 2016, 19:42:33 UTC Получен 8 Jul 2016, 7:05:08 UTC СоÑтоÑние Ñервера Завершено Результат Ð²Ñ‹Ð¿Ð¾Ð»Ð½ÐµÐ½Ð¸Ñ ÐžÑˆÐ¸Ð±ÐºÐ° вычиÑлений СоÑтоÑние клиента Прервано пользователем Ð¡Ñ‚Ð°Ñ‚ÑƒÑ Ð²Ñ‹Ñ…Ð¾Ð´Ð° 203 (0xcb) EXIT_ABORTED_VIA_GUI ID компьютера 78787 Ð’Ñ€ÐµÐ¼Ñ Ð²Ñ‹Ð¿Ð¾Ð»Ð½ÐµÐ½Ð¸Ñ 9 Ñек. Ð’Ñ€ÐµÐ¼Ñ Ð¦ÐŸ 37 Ñек. СоÑтоÑние проверки Ðеправильный Очки 0.00 ÐŸÐ¸ÐºÐ¾Ð²Ð°Ñ Ð¿Ñ€Ð¾Ð¸Ð·Ð²Ð¾Ð´Ð¸Ñ‚ÐµÐ»ÑŒÐ½Ð¾Ñть уÑтройÑтва, FLOPS 201.60 GFLOPS ВерÑÐ¸Ñ Ð¿Ñ€Ð¸Ð»Ð¾Ð¶ÐµÐ½Ð¸Ñ SETI@home v8 ÐÐ½Ð¾Ð½Ð¸Ð¼Ð½Ð°Ñ Ð¿Ð»Ð°Ñ‚Ñ„Ð¾Ñ€Ð¼Ð° (ГП Intel) Peak working set size 308.91 MB Peak swap size 322.73 MB Peak disk usage 0.01 MB ТекÑÑ‚ протокола <core_client_version>7.6.22</core_client_version> <![CDATA[ <message> aborted by user </message> <stderr_txt> Running on device number: 0 Priority of worker thread raised successfully Priority of process adjusted successfully, below normal priority class used OpenCL platform detected: Intel(R) Corporation BOINC assigns device 0 Info: BOINC provided OpenCL device ID used Build features: SETI8 Non-graphics OpenCL USE_OPENCL_INTEL OCL_SYNCHED OCL_ZERO_COPY OCL_CHIRP3 FFTW USE_SSSE3 x86 CPUID: Intel(R) Core(TM) i5-6500 CPU @ 3.20GHz Cache: L1=64K L2=256K CPU features: FPU TSC PAE CMPXCHG8B APIC SYSENTER MTRR CMOV/CCMP MMX FXSAVE/FXRSTOR SSE SSE2 HT SSE3 SSSE3 FMA3 SSE4.1 SSE4.2 AVX OpenCL-kernels filename : MultiBeam_Kernels_r3484.cl ar=0.429512 NumCfft=195421 NumGauss=1100618090 NumPulse=226435533277 NumTriplet=452838184353 Currently allocated 209 MB for GPU buffers In v_BaseLineSmooth: NumDataPoints=1048576, BoxCarLength=8192, NumPointsInChunk=32768 Windows optimized setiathome_v8 application Based on Intel, Core 2-optimized v8-nographics V5.13 by Alex Kan SSSE3xj Win32 Build 3484 , Ported by : Raistmer, JDWhale SETI8 update by Raistmer OpenCL version by Raistmer, r3484 Number of OpenCL platforms: 1 OpenCL Platform Name: Intel(R) OpenCL Number of devices: 1 Max compute units: 24 Max work group size: 256 Max clock frequency: 1050Mhz Max memory allocation: 390280806 Cache type: Read/Write Cache line size: 64 Cache size: 524288 Global memory size: 1561123226 Constant buffer size: 65536 Max number of constant args: 8 Local memory type: Scratchpad Local memory size: 65536 Queue properties: Out-of-Order: No Name: Intel(R) HD Graphics 530 Vendor: Intel(R) Corporation Driver version: 20.19.15.4326 Version: OpenCL 2.0 Extensions: cl_intel_accelerator cl_intel_advanced_motion_estimation cl_intel_ctz cl_intel_d3d11_nv12_media_sharing cl_intel_dx9_media_sharing cl_intel_motion_estimation cl_intel_simultaneous_sharing cl_intel_subgroups cl_khr_3d_image_writes cl_khr_byte_addressable_store cl_khr_d3d10_sharing cl_khr_d3d11_sharing cl_khr_depth_images cl_khr_dx9_media_sharing cl_khr_fp16 cl_khr_gl_depth_images cl_khr_gl_event cl_khr_gl_msaa_sharing cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_gl_sharing cl_khr_icd cl_khr_image2d_from_buffer cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_mipmap_image cl_khr_mipmap_image_writes cl_khr_spir Work Unit Info: ............... Credit multiplier is : 2.85 WU true angle range is : 0.429512 Used GPU device parameters are: Number of compute units: 24 Single buffer allocation size: 128MB Total device global memory: 1488MB max WG size: 256 local mem type: Real LotOfMem path: no LowPerformanceGPU path: no HighPerformanceGPU path: no period_iterations_num=50 GPU device sync requested... ...GPU device synched Termination request detected or computations are finished. GPU device synched, exiting... </stderr_txt> ]]> News about SETI opt app releases: https://twitter.com/Raistmer |
Send message Joined: 12 Nov 10 Posts: 1149 Credit: 32,460,657 RAC: 1 ![]() |
Also, could you describe what happened with this one: If "7 Jul 2016, 15:45:43 UTC" is the reporting time I'm afraid I left early yesterday so wasn't here when this one was running. Also, as the postpone 30s errors only happened on guppi tasks, I hadn't been monitoring the non-guppi ones. In fact I had aborted most of the ones that I'd received before I left. Edit: Reading a bit further down the log I noticed "EXIT_ABORTED_VIA_GUI", this could have been one I aborted this morning when I started running the new 3484 app. If I can manage to snag another 24mr10ac task today I'll monitor it and report the results. Edit: 2nd task just reached 16.5% and glitched so it looks like it's a repeatable error Will do :-) |
![]() ![]() Send message Joined: 18 Aug 05 Posts: 2423 Credit: 15,878,738 RAC: 0 ![]() |
Thanks. I want to provide full deployment set to Eric before weekend to collect some statistics data on weekend. But with iGPU misbehaving this plan could fail - that's why I would like to fix it before Berkeley's lab closes for weekend ;) So, if you have few already postponed tasks please abort one of them and provide link to result. Also, would be good to just suspend all others and allow BOINC to switch between 1-2 postponed to speedup testing. News about SETI opt app releases: https://twitter.com/Raistmer |
Send message Joined: 12 Nov 10 Posts: 1149 Credit: 32,460,657 RAC: 1 ![]() |
It was flicking between just 2 tasks but I have now aborted one of them http://setiweb.ssl.berkeley.edu/beta/result.php?resultid=24277228 I'll leave the other one to finish and post that link then. I'll keep suspending the task it swaps with to force it back to the one that's 75% so should be able to get a result to you in the next 1/2 hour Edit: Task completed and validated http://setiweb.ssl.berkeley.edu/beta/result.php?resultid=24277138 Also, I suspect that the memory leak problem still exists - it's just masked by the fact that the tasks glitch out more frequently. The memory usage does climb continuously throughout the task run, it then gets reset as the task postpones. The 8.12 tasks I monitored yesterday were pretty stable on their memory usage, perhaps going up by 0.1Mb but then dropping again. These tasks only ever went up on memory usage A slight problem for further testing - I have reached my daily quota of tasks so not being issued with any new ones. I'll suspend the few tasks I have got (all guppi) in case you come up with another version to test |
![]() ![]() Send message Joined: 18 Aug 05 Posts: 2423 Credit: 15,878,738 RAC: 0 ![]() |
Thanks for testing. Yep, new version should come... with complete disabling of all new refinements in PulseFind area for iGPU :/ It can't handle events properly. Seems time to revive my Intel OpenCL forums account and go complain there... News about SETI opt app releases: https://twitter.com/Raistmer |
![]() ![]() Send message Joined: 18 Aug 05 Posts: 2423 Credit: 15,878,738 RAC: 0 ![]() |
Here is quick replacement for alpha testing. New rev will come after. https://cloud.mail.ru/public/KNvM/vpWcArF6F News about SETI opt app releases: https://twitter.com/Raistmer |
Send message Joined: 12 Nov 10 Posts: 1149 Credit: 32,460,657 RAC: 1 ![]() |
Downloaded and running v3485. Early indications - memory has been stable for a couple of minutes now - fingers crossed :-) Edit: 20 mins in and still looking good. The task has gone past 16.5% and is still running. Even better the memory usage has followed that of v81.2, ie it has dropped 20Mb since the task started. What's more, it happened even earlier in the task. v8.12 memory usage dropped somewhere between 20% and 25% progress. v3485 dropped around 10% progress |
![]() ![]() Send message Joined: 18 Aug 05 Posts: 2423 Credit: 15,878,738 RAC: 0 ![]() |
Thanks. I'll do commit and full rebuild then. News about SETI opt app releases: https://twitter.com/Raistmer |
Send message Joined: 12 Nov 10 Posts: 1149 Credit: 32,460,657 RAC: 1 ![]() |
Task now approaching 50% complete which means it's gone past the 35% glitch point in one of the earlier versions.. :) Edit: Task completed and validated http://setiweb.ssl.berkeley.edu/beta/result.php?resultid=24276753 The first 3% was done with 3484 (this was the task the other one swapped to so you will see a few stops and starts under 3484), but the task then finished with 3485. Another task is now running which will be entirely 3485 but I have suspended the other tasks in case there is anything else to test :-) |
![]() ![]() Send message Joined: 18 Aug 05 Posts: 2423 Credit: 15,878,738 RAC: 0 ![]() |
Here is new set of binaries (r3486): https://cloud.mail.ru/public/A7yG/k8yoZrFvr Please test. For all but iGPU only cosmetic change - no need to provide -use_sleep directly if some of options from sleep set defined. News about SETI opt app releases: https://twitter.com/Raistmer |
Send message Joined: 12 Nov 10 Posts: 1149 Credit: 32,460,657 RAC: 1 ![]() |
First Intel GPU task completed and validated http://setiweb.ssl.berkeley.edu/beta/result.php?resultid=24276839 Not sure if this is anything to worry about but it does contain the following errors in the log: INFO: can't open binary kernel file: D:\BOINC\Data/projects/setiweb.ssl.berkeley.edu_beta\MultiBeam_Kernels_r3486.cl_IntelRHDGraphics530.bin_V7_2019154326, continue with recompile... Info : Building Program (binary, clBuildProgram):main kernels: OK code 0 INFO: binary kernel file created WARNING: can't open binary kernel file for oclFFT plan: D:\BOINC\Data/projects/setiweb.ssl.berkeley.edu_beta\MB_clFFTplan_IntelRHDGraphics530_524288_gr64_lr8_wg64_tw3_ls1024_bn16_cw16_r3486.bin_2019154326, continue with recompile... WARNING: can't open binary kernel file for oclFFT plan: D:\BOINC\Data/projects/setiweb.ssl.berkeley.edu_beta\MB_clFFTplan_IntelRHDGraphics530_8_gr64_lr8_wg64_tw3_ls1024_bn16_cw16_r3486.bin_2019154326, continue with recompile... WARNING: can't open binary kernel file for oclFFT plan: D:\BOINC\Data/projects/setiweb.ssl.berkeley.edu_beta\MB_clFFTplan_IntelRHDGraphics530_16_gr64_lr8_wg64_tw3_ls1024_bn16_cw16_r3486.bin_2019154326, continue with recompile... WARNING: can't open binary kernel file for oclFFT plan: D:\BOINC\Data/projects/setiweb.ssl.berkeley.edu_beta\MB_clFFTplan_IntelRHDGraphics530_32_gr64_lr8_wg64_tw3_ls1024_bn16_cw16_r3486.bin_2019154326, continue with recompile... WARNING: can't open binary kernel file for oclFFT plan: D:\BOINC\Data/projects/setiweb.ssl.berkeley.edu_beta\MB_clFFTplan_IntelRHDGraphics530_64_gr64_lr8_wg64_tw3_ls1024_bn16_cw16_r3486.bin_2019154326, continue with recompile... WARNING: can't open binary kernel file for oclFFT plan: D:\BOINC\Data/projects/setiweb.ssl.berkeley.edu_beta\MB_clFFTplan_IntelRHDGraphics530_128_gr64_lr8_wg64_tw3_ls1024_bn16_cw16_r3486.bin_2019154326, continue with recompile... WARNING: can't open binary kernel file for oclFFT plan: D:\BOINC\Data/projects/setiweb.ssl.berkeley.edu_beta\MB_clFFTplan_IntelRHDGraphics530_256_gr64_lr8_wg64_tw3_ls1024_bn16_cw16_r3486.bin_2019154326, continue with recompile... WARNING: can't open binary kernel file for oclFFT plan: D:\BOINC\Data/projects/setiweb.ssl.berkeley.edu_beta\MB_clFFTplan_IntelRHDGraphics530_512_gr64_lr8_wg64_tw3_ls1024_bn16_cw16_r3486.bin_2019154326, continue with recompile... WARNING: can't open binary kernel file for oclFFT plan: D:\BOINC\Data/projects/setiweb.ssl.berkeley.edu_beta\MB_clFFTplan_IntelRHDGraphics530_1024_gr64_lr8_wg64_tw3_ls1024_bn16_cw16_r3486.bin_2019154326, continue with recompile... WARNING: can't open binary kernel file for oclFFT plan: D:\BOINC\Data/projects/setiweb.ssl.berkeley.edu_beta\MB_clFFTplan_IntelRHDGraphics530_2048_gr64_lr8_wg64_tw3_ls1024_bn16_cw16_r3486.bin_2019154326, continue with recompile... WARNING: can't open binary kernel file for oclFFT plan: D:\BOINC\Data/projects/setiweb.ssl.berkeley.edu_beta\MB_clFFTplan_IntelRHDGraphics530_4096_gr64_lr8_wg64_tw3_ls1024_bn16_cw16_r3486.bin_2019154326, continue with recompile... WARNING: can't open binary kernel file for oclFFT plan: D:\BOINC\Data/projects/setiweb.ssl.berkeley.edu_beta\MB_clFFTplan_IntelRHDGraphics530_8192_gr64_lr8_wg64_tw3_ls1024_bn16_cw16_r3486.bin_2019154326, continue with recompile... WARNING: can't open binary kernel file for oclFFT plan: D:\BOINC\Data/projects/setiweb.ssl.berkeley.edu_beta\MB_clFFTplan_IntelRHDGraphics530_16384_gr64_lr8_wg64_tw3_ls1024_bn16_cw16_r3486.bin_2019154326, continue with recompile... WARNING: can't open binary kernel file for oclFFT plan: D:\BOINC\Data/projects/setiweb.ssl.berkeley.edu_beta\MB_clFFTplan_IntelRHDGraphics530_32768_gr64_lr8_wg64_tw3_ls1024_bn16_cw16_r3486.bin_2019154326, continue with recompile... WARNING: can't open binary kernel file for oclFFT plan: D:\BOINC\Data/projects/setiweb.ssl.berkeley.edu_beta\MB_clFFTplan_IntelRHDGraphics530_65536_gr64_lr8_wg64_tw3_ls1024_bn16_cw16_r3486.bin_2019154326, continue with recompile... WARNING: can't open binary kernel file for oclFFT plan: D:\BOINC\Data/projects/setiweb.ssl.berkeley.edu_beta\MB_clFFTplan_IntelRHDGraphics530_131072_gr64_lr8_wg64_tw3_ls1024_bn16_cw16_r3486.bin_2019154326, continue with recompile... |
![]() Send message Joined: 18 Jan 06 Posts: 1038 Credit: 18,734,730 RAC: 0 ![]() |
First Intel GPU task completed and validated Where does it say "error" ? I can't find it ! _\|/_ U r s |
Send message Joined: 12 Nov 10 Posts: 1149 Credit: 32,460,657 RAC: 1 ![]() |
Sorry, I thought the warnings possibly indicated an error somewhere. If I saw a log like that on something I'd done, I'd be thinking I had to find a solution ... I presume not in this case, so all well and good |
©2023 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.