Message boards :
Number crunching :
Inconclusive Work Units Running AP Ver 6
Message board moderation
Author | Message |
---|---|
cliff Send message Joined: 16 Dec 07 Posts: 625 Credit: 3,590,440 RAC: 0 |
I've just got an invalid AP6 GPU, its WU 964420018 Here's the error report:- Hope its of some use.. Still on my tasks page.. so hasnt been purged as yet.. <core_client_version>6.12.34</core_client_version> <![CDATA[ <stderr_txt> Number of app instances per device setted to:1 DATA_CHUNK_UNROLL setted to:2 FFA thread block override value:2048 FFA thread fetchblock override value:1024 Maximum single buffer size setted to:128MB Running on device number: 1 DATA_CHUNK_UNROLL at default:2 Priority of worker thread raised successfully Priority of process adjusted successfully, below normal priority class used OpenCL platform detected: NVIDIA Corporation BOINC assigns 1 device, slots 1 to 1 (including) will be checked Used slot is 1; Used GPU device parameters are: Number of compute units: 7 Single buffer allocation size: 128MB max WG size: 1024 Build features: Non-graphics OpenCL USE_OPENCL_NV COMBINED_DECHIRP_KERNEL FFTW USE_INCREASED_PRECISION USE_SSE3 x86 CPUID: AMD FX(tm)-6100 Six-Core Processor Cache: L1=64K L2=2048K CPU features: FPU TSC PAE CMPXCHG8B APIC SYSENTER MTRR CMOV/CCMP MMX FXSAVE/FXRSTOR SSE SSE2 HT SSE3 AstroPulse v. 6.00 Non-graphics FFTW USE_CONVERSION_OPT USE_SSE3 Windows x86 rev 560, 6.00 match, by Raistmer with support of Lunatics.kwsn.net team. SSE3 OpenCL version by Raistmer ffa threshold mods by Joe Segur SSE3 dechirping by JDWhale Combined dechirp kernel by Frizz Number of OpenCL platforms: 1 OpenCL Platform Name: NVIDIA CUDA Number of devices: 2 Max compute units: 7 Max work group size: 1024 Max clock frequency: 1620Mhz Max memory allocation: 268435456 Cache type: Read/Write Cache line size: 128 Cache size: 114688 Global memory size: 1073741824 Constant buffer size: 65536 Max number of constant args: 9 Local memory type: Scratchpad Local memory size: 49152 Queue properties: Out-of-Order: Yes Name: GeForce GTX 560 Vendor: NVIDIA Corporation Driver version: 285.62 Version: OpenCL 1.1 CUDA Extensions: cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_d3d9_sharing cl_nv_d3d10_sharing cl_khr_d3d10_sharing cl_nv_d3d11_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_fp64 Max compute units: 7 Max work group size: 1024 Max clock frequency: 1620Mhz Max memory allocation: 268435456 Cache type: Read/Write Cache line size: 128 Cache size: 114688 Global memory size: 1073741824 Constant buffer size: 65536 Max number of constant args: 9 Local memory type: Scratchpad Local memory size: 49152 Queue properties: Out-of-Order: Yes Name: GeForce GTX 560 Vendor: NVIDIA Corporation Driver version: 285.62 Version: OpenCL 1.1 CUDA Extensions: cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_d3d9_sharing cl_nv_d3d10_sharing cl_khr_d3d10_sharing cl_nv_d3d11_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_fp64 INFO: can't open binary kernel file, continue with recompile... Info : Building Program (source, clBuildProgram):main kernels: OK code 0 INFO: binary kernel file created WARNING: can't open binary kernel file for oclFFT plan, continue with recompile... Termination request detected. GPU device synched, awaiting termination... Number of app instances per device setted to:1 DATA_CHUNK_UNROLL setted to:4 FFA thread block override value:2048 FFA thread fetchblock override value:1024 Maximum single buffer size setted to:128MB Running on device number: 1 DATA_CHUNK_UNROLL at default:4 Priority of worker thread raised successfully Priority of process adjusted successfully, below normal priority class used OpenCL platform detected: NVIDIA Corporation BOINC assigns 1 device, slots 1 to 1 (including) will be checked Used slot is 1; Used GPU device parameters are: Number of compute units: 7 Single buffer allocation size: 128MB max WG size: 1024 Build features: Non-graphics OpenCL USE_OPENCL_NV COMBINED_DECHIRP_KERNEL FFTW USE_INCREASED_PRECISION USE_SSE3 x86 CPUID: AMD FX(tm)-6100 Six-Core Processor Cache: L1=64K L2=2048K CPU features: FPU TSC PAE CMPXCHG8B APIC SYSENTER MTRR CMOV/CCMP MMX FXSAVE/FXRSTOR SSE SSE2 HT SSE3 ### Restart at 0.00 percent. Info : Building Program (binary, clBuildProgram):main kernels: OK code 0 Termination request detected. GPU device synched, awaiting termination... Number of app instances per device setted to:1 DATA_CHUNK_UNROLL setted to:4 FFA thread block override value:2048 FFA thread fetchblock override value:1024 Maximum single buffer size setted to:128MB Running on device number: 0 DATA_CHUNK_UNROLL at default:4 Priority of worker thread raised successfully Priority of process adjusted successfully, below normal priority class used OpenCL platform detected: NVIDIA Corporation BOINC assigns 0 device, slots 0 to 0 (including) will be checked Used slot is 0; Used GPU device parameters are: Number of compute units: 7 Single buffer allocation size: 128MB max WG size: 1024 Build features: Non-graphics OpenCL USE_OPENCL_NV COMBINED_DECHIRP_KERNEL FFTW USE_INCREASED_PRECISION USE_SSE3 x86 CPUID: AMD FX(tm)-6100 Six-Core Processor Cache: L1=64K L2=2048K CPU features: FPU TSC PAE CMPXCHG8B APIC SYSENTER MTRR CMOV/CCMP MMX FXSAVE/FXRSTOR SSE SSE2 HT SSE3 ### Restart at 7.21 percent. Info : Building Program (binary, clBuildProgram):main kernels: OK code 0 Termination request detected. GPU device synched, awaiting termination... Number of app instances per device setted to:1 DATA_CHUNK_UNROLL setted to:4 FFA thread block override value:2048 FFA thread fetchblock override value:1024 Maximum single buffer size setted to:128MB Running on device number: 0 DATA_CHUNK_UNROLL at default:4 Priority of worker thread raised successfully Priority of process adjusted successfully, below normal priority class used OpenCL platform detected: NVIDIA Corporation BOINC assigns 0 device, slots 0 to 0 (including) will be checked Used slot is 0; Used GPU device parameters are: Number of compute units: 7 Single buffer allocation size: 128MB max WG size: 1024 Build features: Non-graphics OpenCL USE_OPENCL_NV COMBINED_DECHIRP_KERNEL FFTW USE_INCREASED_PRECISION USE_SSE3 x86 CPUID: AMD FX(tm)-6100 Six-Core Processor Cache: L1=64K L2=2048K CPU features: FPU TSC PAE CMPXCHG8B APIC SYSENTER MTRR CMOV/CCMP MMX FXSAVE/FXRSTOR SSE SSE2 HT SSE3 ### Restart at 10.81 percent. Info : Building Program (binary, clBuildProgram):main kernels: OK code 0 Termination request detected. GPU device synched, awaiting termination... Number of app instances per device setted to:1 DATA_CHUNK_UNROLL setted to:4 FFA thread block override value:2048 FFA thread fetchblock override value:1024 Maximum single buffer size setted to:128MB Running on device number: 1 DATA_CHUNK_UNROLL at default:4 Priority of worker thread raised successfully Priority of process adjusted successfully, below normal priority class used OpenCL platform detected: NVIDIA Corporation BOINC assigns 1 device, slots 1 to 1 (including) will be checked Used slot is 1; Used GPU device parameters are: Number of compute units: 7 Single buffer allocation size: 128MB max WG size: 1024 Build features: Non-graphics OpenCL USE_OPENCL_NV COMBINED_DECHIRP_KERNEL FFTW USE_INCREASED_PRECISION USE_SSE3 x86 CPUID: AMD FX(tm)-6100 Six-Core Processor Cache: L1=64K L2=2048K CPU features: FPU TSC PAE CMPXCHG8B APIC SYSENTER MTRR CMOV/CCMP MMX FXSAVE/FXRSTOR SSE SSE2 HT SSE3 ### Restart at 36.94 percent. Info : Building Program (binary, clBuildProgram):main kernels: OK code 0 single pulses: 4 repetitive pulses: 30 percent blanked: 99.85 class T_remove_radar: total=3.00e+009, N=1, <>=3.00e+009, min=3.00e+009, max=3.00e+009 class T_main_loop_L1: total=3.06e+013, N=69, <>=4.44e+011, min=4.07e+011, max=5.73e+011 class T_FFT_forward: total=5.57e+011, N=282624, <>=1.97e+006, min=8.63e+005, max=1.50e+008 class T_remove_radar_randomize: total=2.64e+013, N=1129944, <>=2.34e+007, min=1.44e+003, max=1.98e+009 class T_build_chirp_table: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000 class T_DataWrite: total=5.05e+011, N=282624, <>=1.79e+006, min=7.59e+005, max=1.50e+008 class T_DataWrite_ns: total=0, N=0, <>=0, min=0 max=0 class T_oclReadBuf: total=1.65e+007, N=282624, <>=5.80e+001, min=3.30e+001, max=1.33e+005 class T_ChirpWrite: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000 class T_ChirpWrite_ns: total=0, N=0, <>=0, min=0 max=0 class T_dechirp: total=6.06e+010, N=282624, <>=2.14e+005, min=1.51e+005, max=6.98e+007 class Dechirp_ns: total=0, N=0, <>=0, min=0 max=0 class Half_ns: total=0, N=0, <>=0, min=0 max=0 class T_PC_single_pulse_kernel_FFA_update: total=3.13e+012, N=282624, <>=1.11e+007, min=5.45e+006, max=3.91e+009 class PC_ns: total=0, N=0, <>=0, min=0 max=0 class T_oclReadBuf: total=1.65e+007, N=282624, <>=5.80e+001, min=3.30e+001, max=1.33e+005 class T_oclWriteBuf: total=5.05e+011, N=282624, <>=1.79e+006, min=7.59e+005, max=1.50e+008 class T_FFT_inverse: total=3.52e+010, N=282624, <>=1.24e+005, min=8.92e+004, max=6.97e+007 class T_ffa: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000 class T_GPU_buffer_read_backs: total=3, N=3, <>=1, min=1 max=1 USE_OPENCL OPENCL_WRITE USE_INCREASED_PRECISION SMALL_CHIRP_TABLE COMBINED_DECHIRP_KERNEL rev 560 08:50:45 (3248): called boinc_finish </stderr_txt> ]]> Regards, Cliff, Been there, Done that, Still no damm T shirt! |
cliff Send message Joined: 16 Dec 07 Posts: 625 Credit: 3,590,440 RAC: 0 |
Two inconclusives now showing:-( http://setiathome.berkeley.edu/workunit.php?wuid=950105434 http://setiathome.berkeley.edu/workunit.php?wuid=967737313 Hope these are of some use.. Cheers, Cliff, Been there, Done that, Still no damm T shirt! |
Richard Haselgrove Send message Joined: 4 Jul 99 Posts: 14650 Credit: 200,643,578 RAC: 874 |
Two inconclusives now showing:-( Excellent. ap_23ja12ab_B2_P1_00018_20120314_18711.wu and ap_28no11aa_B3_P0_00250_20120409_14014.wu preserved for future inspection, should it prove necessary. Thank you. |
Horacio Send message Joined: 14 Jan 00 Posts: 536 Credit: 75,967,266 RAC: 0 |
Two inconclusives now showing:-( I have some more inconclusives, if you want to save them: CPU: http://setiathome.berkeley.edu/workunit.php?wuid=966564164 GPU: (these may not be relevant as I have a GPU that tends to trash some WUs) http://setiathome.berkeley.edu/workunit.php?wuid=969872721 http://setiathome.berkeley.edu/workunit.php?wuid=968914200 http://setiathome.berkeley.edu/workunit.php?wuid=950550098 http://setiathome.berkeley.edu/workunit.php?wuid=968339797 |
Richard Haselgrove Send message Joined: 4 Jul 99 Posts: 14650 Credit: 200,643,578 RAC: 874 |
OK, these are the WUs I've collected so far. Of course, the sample sizes are still small, but none of the wingmates are showing any signs of errors, or any other inconclusives than the one reported here, for their respective stock applications. Which may suggest we need further testing of the optimised apps. Horatio: CPU r577 against stock ap_05ja12ab_B2_P1_00101_20120407_01310.wu (Intel/Win) Horatio: NV GTX 560 Ti r560 against stock ap_08jn11aa_B5_P1_00343_20120412_19722.wu (Intel/Win) ap_25ja12ad_B3_P1_00044_20120411_05125.wu (Intel/Win) ap_26no11ae_B2_P0_00210_20120315_31464.wu (AMD/Linux) ap_11my11ab_B2_P0_00278_20120409_08996.wu (Intel/Win) Cliff: NV GTX 560 r560 against stock ap_23ja12ab_B2_P1_00018_20120314_18711.wu (Intel/Win) ap_28no11aa_B3_P0_00250_20120409_14014.wu (AMD/Linux) (@ mods, it may be helpful to move these specific reports of individual inconclusive WUs into a thread of their own) |
Richard Haselgrove Send message Joined: 4 Jul 99 Posts: 14650 Credit: 200,643,578 RAC: 874 |
(these may not be relevant as I have a GPU that tends to trash some WUs) May I ask, what makes you say that? And what particular symptom of 'trash'? Obviously, I'm trying to distinguish between hardware and software errors here. |
James Sotherden Send message Joined: 16 May 99 Posts: 10436 Credit: 110,373,059 RAC: 54 |
This thread is for inconclusive work units as suggested by Richard Haselgrove. [/quote] Old James |
Horacio Send message Joined: 14 Jan 00 Posts: 536 Credit: 75,967,266 RAC: 0 |
(these may not be relevant as I have a GPU that tends to trash some WUs) Trashed: the apps gives no run errors, but the results are marked as invalid. I know it's a fact that one GPU is not working perfect, after seeing that most of my invalid results come from the same 560TI GPU in one of my hosts, I've made a little app that reads the results page and save the data and the statistics were that around 30% of the WU reported in a particular day were invalid for that GPU while all the WUs from the other GPU were valid... (Ive changed the PSU recently and the ratio went a little down, Im still testing it, but it takes some time until all the WUs reported on a specific day get validated, and also, the inconclusive/invalids take longer due to they need a 3rd wingman, so is an ongoing test) EDIT: the invalids come from any app, not just APs. Ive also seen some invalids Eisnteins, but as Einstein BRP dont push the GPU as hard as the optimized apps, the failure ratio is much lower. EDIT2: All my inconclusive WUs for the GPU were matched with stock for Intel/Win wingman (V6.01), one of them (ap_08jn11aa_B5_P1_00343_20120412_19722.wu) got a v6.02 as the 3rd wingmate, but Its a Xeon/XP... |
perryjay Send message Joined: 20 Aug 02 Posts: 3377 Credit: 20,676,751 RAC: 0 |
I've got a couple http://setiathome.berkeley.edu/workunit.php?wuid=970100390 and http://setiathome.berkeley.edu/workunit.php?wuid=967816608 I also had one that was a 30/30 that validated with all three of us getting credit but it has already cleared. Other than these, all my AP work both CPU and GPUs have validated. AstroPulse v6 (anonymous platform, CPU) Number of tasks completed 16 Max tasks per day 129 Number of tasks today 0 Consecutive valid tasks 29 Average processing rate 16.150684120093 Average turnaround time 2.73 days AstroPulse v6 (anonymous platform, nvidia GPU) Number of tasks completed 28 Max tasks per day 139 Number of tasks today 0 Consecutive valid tasks 39 Average processing rate 221.98950070936 Average turnaround time 1.91 days PROUD MEMBER OF Team Starfire World BOINC |
Richard Haselgrove Send message Joined: 4 Jul 99 Posts: 14650 Credit: 200,643,578 RAC: 874 |
I've got a couple http://setiathome.berkeley.edu/workunit.php?wuid=970100390 and http://setiathome.berkeley.edu/workunit.php?wuid=967816608 Thanks. Added Perryjay: NV GTS 450 r560 against stock ap_31dc11aa_B2_P0_00024_20120412_03905.wu (Intel/Win) ap_28no11aa_B5_P1_00191_20120409_12666.wu (Intel/Win) to the stock of WUs in captivity. |
perryjay Send message Joined: 20 Aug 02 Posts: 3377 Credit: 20,676,751 RAC: 0 |
Oops, sorry, found my 30/30 that validated. http://setiathome.berkeley.edu/workunit.php?wuid=968344883 FYI, most all of mine have been against stock. I've only had something like one and one running against either Opt CPU or Opt GPU. Haven't really been looking for them though. PROUD MEMBER OF Team Starfire World BOINC |
Richard Haselgrove Send message Joined: 4 Jul 99 Posts: 14650 Credit: 200,643,578 RAC: 874 |
FYI, most all of mine have been against stock. I've only had something like one and one running against either Opt CPU or Opt GPU. Haven't really been looking for them though. Well, the holy grail for all optimised apps is that they validate against stock. Doesn't matter how fast you run, if you get zero science and zero credit at the end of it all! |
cliff Send message Joined: 16 Dec 07 Posts: 625 Credit: 3,590,440 RAC: 0 |
One more inconclusive http://setiathome.berkeley.edu/workunit.php?wuid=954832873 Thats 3 so far in about 1 day:-/ Regards, Cliff, Been there, Done that, Still no damm T shirt! |
Richard Haselgrove Send message Joined: 4 Jul 99 Posts: 14650 Credit: 200,643,578 RAC: 874 |
Caught it, thanks. |
cliff Send message Joined: 16 Dec 07 Posts: 625 Credit: 3,590,440 RAC: 0 |
Hi Richard, From the looks of it all the wingmen are running CPU. So far none of mine seem to have been pure GPU tasks. And there have been other inconclusives besides mine on some. Regards, Cliff, Been there, Done that, Still no damm T shirt! |
Mike Send message Joined: 17 Feb 01 Posts: 34258 Credit: 79,922,639 RAC: 80 |
Richard can you provide some of the the tasks. I will check them on my ATI. With each crime and every kindness we birth our future. |
Richard Haselgrove Send message Joined: 4 Jul 99 Posts: 14650 Credit: 200,643,578 RAC: 874 |
Richard can you provide some of the the tasks. Good idea. If you run them on ATI, I run them on NV, and between us we find someone to run them with stock, we can ask Joe to run a comparator over the result files and work out where (if anywhere) the problem lies. How would you like me to get the files to you, or are you equipped to capture them direct from the fanout? Edit - I've set all 10 mentioned in this thread running with stock on my fastest CPU (Q9300) - may as well start the heavy lifting going while we think about what else needs doing. |
Mike Send message Joined: 17 Feb 01 Posts: 34258 Credit: 79,922,639 RAC: 80 |
Richard can you provide some of the the tasks. Have no Office installed atm. You could send me the links via mail. With each crime and every kindness we birth our future. |
Richard Haselgrove Send message Joined: 4 Jul 99 Posts: 14650 Credit: 200,643,578 RAC: 874 |
Have no Office installed atm. And I'm not sure I have your email atm, after I lost my daily driver with the contact list in a power cut :-( I can do you a PM here, though - that should do it? Edit - PM sent. |
Wiggo Send message Joined: 24 Jan 00 Posts: 34744 Credit: 261,360,520 RAC: 489 |
I have only 1 so far from my Q6600, http://setiathome.berkeley.edu/workunit.php?wuid=968825720. Cheers. |
©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.