OpenCL MB v8.12 issues thread attempt 2


Advanced search

Message boards : Number crunching : OpenCL MB v8.12 issues thread attempt 2
Message board moderation

To post messages, you must log in.

Previous · 1 · 2 · 3 · 4 · 5 · 6 · Next

AuthorMessage
Rasputin42
Volunteer tester

Send message
Joined: 25 Jul 08
Posts: 412
Credit: 5,834,661
RAC: 0
United States
Message 1793414 - Posted: 4 Jun 2016, 16:38:11 UTC - in response to Message 1793362.  

I have tested various sog versions with MBbench 2.10.
All hang at a lunatics test WU PG0395_v8.wu.(with use_sleep enabled)

Here are the last few lines of the stderr.

call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 2225
call 'Setting kernel argument:GetFixedPoT_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 734
call 'Enqueueing kernel:GetFixedPoT_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 760
call 'Setting kernel argument:NormalizePoT_peak_PC_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 792
call 'Enqueueing kernel:NormalizePoT_peak_PC_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 804
call 'Setting kernel argument:GaussFit_kernel_PE_cl' is finished OK in file ..\analyzePoT.cpp near line 1018
call 'Enqueueing kernel:GaussFit_kernel_PE_cl' is finished OK in file ..\analyzePoT.cpp near line 1030
call 'Setting kernel argument:PC_find_triplets_avg_kernel_HD5_cl' is finished OK in file ..\analyzePoT.cpp near line 1602
call 'Enqueueing kernel:PC_find_triplets_avg_kernel_HD5_cl' is finished OK in file ..\analyzePoT.cpp near line 1647
call 'Setting kernel argument:set_mem_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 1795
call 'Enqueueing kernel:set_mem_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 1802
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 2247
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,offset' is finished OK in file ..\analyzePoT.cpp near line 2269
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
ID: 1793414 · Report as offensive
Profile Raistmer
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 16 Jun 01
Posts: 6325
Credit: 106,370,077
RAC: 121
Russia
Message 1793416 - Posted: 4 Jun 2016, 16:44:26 UTC - in response to Message 1793414.  

I have tested various sog versions with MBbench 2.10.
All hang at a lunatics test WU PG0395_v8.wu.(with use_sleep enabled)

Thanks a lot.
Last posted build does the same?
ID: 1793416 · Report as offensive
Rasputin42
Volunteer tester

Send message
Joined: 25 Jul 08
Posts: 412
Credit: 5,834,661
RAC: 0
United States
Message 1793426 - Posted: 4 Jun 2016, 17:10:53 UTC - in response to Message 1793393.  

This one works, but it does not allow parameters(-use_sleep etc.)
ID: 1793426 · Report as offensive
Profile Raistmer
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 16 Jun 01
Posts: 6325
Credit: 106,370,077
RAC: 121
Russia
Message 1793434 - Posted: 4 Jun 2016, 17:54:50 UTC - in response to Message 1793426.  

This one works, but it does not allow parameters(-use_sleep etc.)

Why not?
Post log please.
ID: 1793434 · Report as offensive
Rasputin42
Volunteer tester

Send message
Joined: 25 Jul 08
Posts: 412
Credit: 5,834,661
RAC: 0
United States
Message 1793446 - Posted: 4 Jun 2016, 18:32:43 UTC - in response to Message 1793434.  
Last modified: 4 Jun 2016, 18:35:09 UTC

I repeated it.
Seems to be working now with parameters.
I will let you know, if there is anything unusual.

BTW does "LowPerformanceGPU path: yes" do anything other than setting period _iterations_ num to 500?
ID: 1793446 · Report as offensive
Rasputin42
Volunteer tester

Send message
Joined: 25 Jul 08
Posts: 412
Credit: 5,834,661
RAC: 0
United States
Message 1793456 - Posted: 4 Jun 2016, 19:15:22 UTC
Last modified: 4 Jun 2016, 19:17:52 UTC

Appears to be working (with -use_ sleep).
However, it found some signals, that were not found with the standard lunatics cpu app(AKv8c_r2549_winx86-64_AVXxjfs.exe) and missed some, that the CPU app found.

I don't know, how important that is.
ID: 1793456 · Report as offensive
Profile Raistmer
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 16 Jun 01
Posts: 6325
Credit: 106,370,077
RAC: 121
Russia
Message 1793458 - Posted: 4 Jun 2016, 19:17:23 UTC - in response to Message 1793456.  

Appears to be working (with -use_ sleep).
However, it found some signals, that were not found with the standard lunatics cpu app and missed some, that the CPU app did.

I don't know, how important that is.

Please post logs. Hard to say anything just by observations.
ID: 1793458 · Report as offensive
Profile Raistmer
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 16 Jun 01
Posts: 6325
Credit: 106,370,077
RAC: 121
Russia
Message 1793464 - Posted: 4 Jun 2016, 19:48:49 UTC - in response to Message 1793446.  
Last modified: 4 Jun 2016, 19:49:08 UTC


BTW does "LowPerformanceGPU path: yes" do anything other than setting period _iterations_ num to 500?

It enables sleep (new build - 1ms, older - 5ms)
ID: 1793464 · Report as offensive
Profile Raistmer
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 16 Jun 01
Posts: 6325
Credit: 106,370,077
RAC: 121
Russia
Message 1793465 - Posted: 4 Jun 2016, 19:50:36 UTC - in response to Message 1793456.  

(AKv8c_r2549_winx86-64_AVXxjfs.exe)

Are you sure it's v8 build? AFAIK Joe's builds were v7 only
ID: 1793465 · Report as offensive
Rasputin42
Volunteer tester

Send message
Joined: 25 Jul 08
Posts: 412
Credit: 5,834,661
RAC: 0
United States
Message 1793472 - Posted: 4 Jun 2016, 20:19:53 UTC - in response to Message 1793465.  
Last modified: 4 Jun 2016, 21:06:42 UTC

Actually it is: MB8_win_x64_AVX_VS2010_r3330.exe

Thanks for the correction.

EDIT: i redid the test with the correct cpu app.
Results are matching.
ID: 1793472 · Report as offensive
Profile Questor Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 3 Sep 04
Posts: 471
Credit: 230,506,401
RAC: 157
United Kingdom
Message 1793656 - Posted: 5 Jun 2016, 11:39:55 UTC - in response to Message 1793362.  
Last modified: 5 Jun 2016, 11:43:42 UTC


Happy to help test with your build when ready - just let me know.
...
It is the ones that hang which are more problematic.


So please try this build:
https://cloud.mail.ru/public/9Fry/DCSkyQm1C
on those types of tasks wich hang with -use_sleep.
Will it hang with this build? If it will hang (-use_sleep enabled) please post ~20 last line of corresponding stderr.
It's debug build so will produce lot of output and can't be used as production one.



With this app and the later posted app - very low CPU usage and no GPU activity (from MSI Afterburner)

With -use_sleep or not. on both GUPPI and nonGUPPI.

Unlikely to be able to post last lines of stderr.txt as completion time not reducing but stderr.txt continues to increase.

No screen lag but little or no processing.

Start of stderr.txt for second app

Running on device number: 0
Priority of worker thread raised successfully
Priority of process adjusted successfully, below normal priority class used
OpenCL platform detected: NVIDIA Corporation
call 'clGetDeviceIDs' is finished OK in file ..\..\..\src\GPU_lock.cpp near line 939
BOINC assigns device 0
Info: BOINC provided OpenCL device ID used
call 'Quering device abilities' is finished OK in file ..\..\..\src\GPU_lock.cpp near line 342
call 'Quering NV device abilities' is finished OK in file ..\..\..\src\GPU_lock.cpp near line 345
call 'Quering device abilities' is finished OK in file ..\..\..\src\GPU_lock.cpp near line 396
call 'clCreateContext' is finished OK in file ..\..\..\src\GPU_lock.cpp near line 1147
call 'Creating Command Queue. (clCreateCommandQueue)' is finished OK in file ..\..\..\src\GPU_lock.cpp near line 1172
call 'Creating Command Queue for writing' is finished OK in file ..\..\..\src\GPU_lock.cpp near line 1177
call 'Creating Command Queue. (clCreateCommandQueue)' is finished OK in file ..\..\..\src\GPU_lock.cpp near line 1184
call 'Creating Command Queue. (clCreateCommandQueue)' is finished OK in file ..\..\..\src\GPU_lock.cpp near line 1189

Build features: SETI8 Non-graphics OpenCL USE_OPENCL_NV OCL_VERBOSE OCL_ZERO_COPY SIGNALS_ON_GPU OCL_CHIRP3 FFTW USE_SSE3 x86
CPUID: Intel(R) Core(TM) i7 CPU 920 @ 2.67GHz

Cache: L1=64K L2=256K

CPU features: FPU TSC PAE CMPXCHG8B APIC SYSENTER MTRR CMOV/CCMP MMX FXSAVE/FXRSTOR SSE SSE2 HT SSE3 SSSE3 SSE4.1 SSE4.2
OpenCL-kernels filename : MultiBeam_Kernels_r3430.cl
FFT: clFFT_CreatePlan[0] done.
FFT: clFFT_CreatePlan[1] done.
FFT: clFFT_CreatePlan[2] done.
FFT: clFFT_CreatePlan[3] done.
FFT: clFFT_CreatePlan[4] done.
FFT: clFFT_CreatePlan[5] done.
FFT: clFFT_CreatePlan[6] done.
FFT: clFFT_CreatePlan[7] done.
FFT: clFFT_CreatePlan[8] done.
FFT: clFFT_CreatePlan[9] done.
FFT: clFFT_CreatePlan[10] done.
FFT: clFFT_CreatePlan[11] done.
FFT: clFFT_CreatePlan[12] done.
FFT: clFFT_CreatePlan[13] done.
FFT: clFFT_CreatePlan[14] done.
ar=0.008383 NumCfft=123141 NumGauss=0 NumPulse=54144848768 NumTriplet=67127516320
call 's_clCreateBuffer(gpu_DataIn)' is finished OK in file ..\analyzeFuncs.cpp near line 927
call 's_clCreateBuffer(FFTbuf)' is finished OK in file ..\analyzeFuncs.cpp near line 943
call 's_clCreateBuffer(gpu_WorkData)' is finished OK in file ..\analyzeFuncs.cpp near line 950
call 's_clCreateBuffer(gpu_ChirpedData)' is finished OK in file ..\analyzeFuncs.cpp near line 974
call 's_clCreateBuffer(gpu_FFTedData)' is finished OK in file ..\analyzeFuncs.cpp near line 983
call 's_clCreateBuffer(FFTbuf_small)' is finished OK in file ..\analyzeFuncs.cpp near line 996
call 's_clCreateBuffer(gpu_ACTemp)' is finished OK in file ..\analyzeFuncs.cpp near line 1005
call 's_clCreateBuffer(gpu_PowerSpectrum)' is finished OK in file ..\analyzeFuncs.cpp near line 1039
call 's_clCreateBuffer(gpu_GPUState)' is finished OK in file ..\analyzeFuncs.cpp near line 1262
call 's_clCreateBuffer(gpu_PulsePoT_average)' is finished OK in file ..\analyzeFuncs.cpp near line 1283
call 'clCreateBuffer(gpu_gaussian_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 1387
call 'clEnqueueMapBuffer(gpu_gaussian_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 1390
call 'clEnqueueUnmapMemObject(gpu_gaussian_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 1393
call 'clCreateBuffer(gpu_triplet_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 1402
call 'clEnqueueMapBuffer(gpu_triplet_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 1405
call 'clEnqueueUnmapMemObject(gpu_triplet_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 1408
call 'clCreateBuffer(gpu_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 1417
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 1420
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 1423
call 's_clCreateBuffer(gpu_MeanMaxIdx)' is finished OK in file ..\analyzeFuncs.cpp near line 1495
call 'clCreateBuffer(cpu_PowerBin_buf)' is finished OK in file ..\analyzeFuncs.cpp near line 1548
Currently allocated 201 MB for GPU buffers
call 'Creating RepackInput_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1587
call 'Creating FindAutoCorrelation_reduce0_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1594
call 'Creating FindAutoCorrelation_reduce1_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1596
call 'Creating Autocorr_logging_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1600
call 'Creating CalcChirpData_kernel_df64_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1617
call 'Creating GetPowerSpectrum_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1624
call 'Creating Transpose4_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1630
call 'Creating GetFixedPoT_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1632
call 'Creating NormalizePoT_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1634
call 'Creating NormalizePoT_peak_PC_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1636
call 'Creating Gaussian_logging_kernel from program' is finished OK in file ..\analyzeFuncs.cpp near line 1639
call 'Creating GaussFit_SoG_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1643
call 'Creating GaussFit_SoG_kernel_PE_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1645
call 'Creating GaussFit_no_best_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1653
call 'Creating set_mem_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1656
call 'Creating PC_find_triplets_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1663
call 'Creating PC_find_triplets_avg_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1665
call 'Creating PC_find_triplets_avg_kernel_HD5_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1668
call 'Creating PC_find_triplets_kernel_HD5_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1670
call 'Creating PC_find_pulse_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1684
call 'Creating PC_find_pulse_partial_kernel1_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1686
INFO: Creating PC_find_pulse_semi_local_kernel_cl from program ok
call 'Creating PC_find_pulse_f_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1702
call 'Creating PC_find_spike_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1717
call 'Creating Spike_logging_HD5_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1722
call 'Creating Spike_partial_logging_HD5_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1726
call 'Creating PC_find_spike32_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1740
call 'clGetKernelWorkGroupInfo' is finished OK in file ..\analyzeFuncs.cpp near line 1752
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
SSE3xj Win32 Build 3430 , Ported by : Raistmer, JDWhale

SETI8 update by Raistmer

OpenCL version by Raistmer, r3430

Very Verbose OpenCL INFO dumping!

Number of OpenCL platforms: 1


OpenCL Platform Name: NVIDIA CUDA
Number of devices: 1
Max compute units: 15
Max work group size: 1024
Max clock frequency: 1600Mhz
Max memory allocation: 335544320
Cache type: Read/Write
Cache line size: 128
Cache size: 245760
Global memory size: 1342177280
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 570
Vendor: NVIDIA Corporation
Driver version: 365.19
Version: OpenCL 1.1 CUDA
Extensions: 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 cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_d3d9_sharing cl_nv_d3d10_sharing cl_khr_d3d10_sharing cl_nv_d3d11_sharing cl_nv_copy_opts


Work Unit Info:
...............
Credit multiplier is : 2.85
WU true angle range is : 0.008383
call 'clEnqueueMapBuffer(gpu_GPUState)' is finished OK in file ..\analyzeFuncs.cpp near line 2099
call 'clEnqueueUnmapMemObject(gpu_GPUState)' is finished OK in file ..\analyzeFuncs.cpp near line 2131
call 'clWriteBuffer(gpu_DataIn)' is finished OK in file ..\analyzeFuncs.cpp near line 2946
call 's_clCreateBuffer(gpu_t_funct_cache)' is finished OK in file ..\analyzeFuncs.cpp near line 1918
call 's_clCreateBuffer(gpu_pulsefind_settings)' is finished OK in file ..\analyzeFuncs.cpp near line 1925
call 'clWriteBuffer(gpu_pulsefind_settings)' is finished OK in file ..\analyzeFuncs.cpp near line 1930
call 'clWriteBuffer(gpu_t_funct_cache)' is finished OK in file ..\analyzeFuncs.cpp near line 1946
INFO: After initialize_pulse_find_cl
Used GPU device parameters are:
Number of compute units: 15
Single buffer allocation size: 128MB
Total device global memory: 1280MB
max WG size: 1024
local mem type: Real
FERMI path used: yes
LotOfMem path: yes
LowPerformanceGPU path: no
period_iterations_num=50
call 'Setting kernel argument:CalcChirpData_kernel2_cl' is finished OK in file ..\analyzeFuncs.cpp near line 590
call 'Setting kernel argument:GetPowerSpectrum_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 592
call 'Setting kernel argument:PC_find_spike_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 635
call 'Setting kernel argument:Spike_logging_HD5_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 652
call 'Setting kernel argument:Spike_partial_logging_HD5_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 660
call 'Setting kernel argument:Transpose4_kernel_cl(PoT)' is finished OK in file ..\analyzeFuncs.cpp near line 761
call 'Setting kernel argument:PC_find_triplets_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 766
call 'Setting kernel argument:PC_find_triplets_avg_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 770
call 'Setting kernel argument:PC_find_triplets_avg_kernel_HD5_cl' is finished OK in file ..\analyzeFuncs.cpp near line 776
call 'Setting kernel argument:PC_find_triplets_kernel_HD5_cl' is finished OK in file ..\analyzeFuncs.cpp near line 780
call 'Setting kernel argument:PC_find_pulse_f_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 791
call 'Setting kernel argument:PC_find_pulse_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 800
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 810
call 'Setting kernel argument:RepackInput_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 818
call 'Setting kernel argument:FindAutoCorrelation_reduce0_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 827
call 'Setting kernel argument:FindAutoCorrelation_reduce1_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 843
call 'Setting kernel argument:Autocorr_logging_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 851
INFO: After SetupKernelArgs
INFO: Freeing local variables.
call 'Setting kernel argument:CalcChirpData_kernel2_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4359
call 'Enqueueing kernel:CalcChirpData_kernel2_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4374
call ' oclFFT2: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 609
call 'non-strip fft' is finished OK in file ..\analyzeFuncs.cpp near line 4488
INFO: oclFFT done no strip. fftlen=8, NumBlockFfts=131072, chirplen=1048576
call 'Enqueueing kernel:GetPowerSpectrum_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4524
Spike search (main) omitted due to too small FFT size==8
call 'Setting kernel argument: Spike_logging_HD5_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4890
call 'clEnqueueNDRangeKernel(cq,Spike_logging_HD5_kernel_cl)' is finished OK in file ..\analyzeFuncs.cpp near line 4909
call 'clEnqueueMapBuffer(gpu_GPUState)' is finished OK in file ..\analyzeFuncs.cpp near line 2172
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 2225
call 'Setting kernel argument:Transpose4_kernel_cl(pulse)' is finished OK in file ..\analyzePoT.cpp near line 3990
call 'Enqueueing kernel:Transpose4_kernel_cl(pulse)' is finished OK in file ..\analyzePoT.cpp near line 4003
call 'ReadBuffer(gpu_WorkData->tPowerSpectrum)' is finished OK in file ..\analyzePoT.cpp near line 4030
need_pulse_cpu_processing=0;need_triplet_cpu_processing=1;ThisPoT=1;last_bin=8;
PulseSearchBinStart=8;PulseSearchBinStop=0;TripletSearchBinStart=1;TripletSearchBinStop=8
Doing find_triplets() on CPU, ThisPoT=1, PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=2, PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=3, PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=4, PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=5, PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=6, PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=7, PulsePoTNum=1
call 'clEnqueueMapBuffer(gpu_GPUState)' is finished OK in file ..\analyzeFuncs.cpp near line 2172
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 2225
call ' oclFFT2: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 609
call 'non-strip fft' is finished OK in file ..\analyzeFuncs.cpp near line 4488
INFO: oclFFT done no strip. fftlen=16, NumBlockFfts=65536, chirplen=1048576
call 'Enqueueing kernel:GetPowerSpectrum_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4524
Spike search (main) omitted due to too small FFT size==16
call 'Setting kernel argument: Spike_logging_HD5_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4890
call 'clEnqueueNDRangeKernel(cq,Spike_logging_HD5_kernel_cl)' is finished OK in file ..\analyzeFuncs.cpp near line 4909
call 'clEnqueueMapBuffer(gpu_GPUState)' is finished OK in file ..\analyzeFuncs.cpp near line 2172
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 2225
call 'Setting kernel argument:PC_find_triplets_avg_kernel_HD5_cl' is finished OK in file ..\analyzePoT.cpp near line 1455
call 'Enqueueing kernel:PC_find_triplets_kernel_HD5_cl' is finished OK in file ..\analyzePoT.cpp near line 1498
call 'clEnqueueMapBuffer(gpu_triplet_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 3913
call 'clEnqueueUnmapMemObject(gpu_triplet_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 3935
call 'Setting kernel argument:Transpose4_kernel_cl(pulse)' is finished OK in file ..\analyzePoT.cpp near line 3990
call 'Enqueueing kernel:Transpose4_kernel_cl(pulse)' is finished OK in file ..\analyzePoT.cpp near line 4003
call 'ReadBuffer(gpu_WorkData->tPowerSpectrum)' is finished OK in file ..\analyzePoT.cpp near line 4030
need_pulse_cpu_processing=0;need_triplet_cpu_processing=1;ThisPoT=4;last_bin=8;
PulseSearchBinStart=16;PulseSearchBinStop=0;TripletSearchBinStart=4;TripletSearchBinStop=8
Doing find_triplets() on CPU, ThisPoT=4, PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=5, PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=6, PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=7, PulsePoTNum=1
call 'clEnqueueMapBuffer(gpu_GPUState)' is finished OK in file ..\analyzeFuncs.cpp near line 2172
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 2225
call ' oclFFT2: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 609
call 'non-strip fft' is finished OK in file ..\analyzeFuncs.cpp near line 4488
INFO: oclFFT done no strip. fftlen=32, NumBlockFfts=32768, chirplen=1048576
call 'Enqueueing kernel:GetPowerSpectrum_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4524
call 'Setting kernel argument: PC_find_spike_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4725
call 'Enqueueing kernel:PC_find_spike_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4740
call 'Setting kernel argument: Spike_partial_logging_HD5_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4745
call 'clEnqueueNDRangeKernel(cq,Spike_partial_logging_HD5_kernel_cl)' is finished OK in file ..\analyzeFuncs.cpp near line 4766
call 'clEnqueueMapBuffer(gpu_GPUState)' is finished OK in file ..\analyzeFuncs.cpp near line 2172
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 2225
call 'Setting kernel argument:PC_find_triplets_avg_kernel_HD5_cl' is finished OK in file ..\analyzePoT.cpp near line 1602
call 'Enqueueing kernel:PC_find_triplets_avg_kernel_HD5_cl' is finished OK in file ..\analyzePoT.cpp near line 1647
call 'Setting kernel argument:set_mem_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 1795
call 'Enqueueing kernel:set_mem_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 1802
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 2247
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,offset' is finished OK in file ..\analyzePoT.cpp near line 2269
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'clEnqueueMapBuffer(gpu_triplet_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 3913
call 'clEnqueueUnmapMemObject(gpu_triplet_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 3935
call 'Setting kernel argument:Transpose4_kernel_cl(pulse)' is finished OK in file ..\analyzePoT.cpp near line 3990
call 'Enqueueing kernel:Transpose4_kernel_cl(pulse)' is finished OK in file ..\analyzePoT.cpp near line 4003
call 'ReadBuffer(gpu_WorkData->tPowerSpectrum)' is finished OK in file ..\analyzePoT.cpp near line 4030
need_pulse_cpu_processing=1;need_triplet_cpu_processing=1;ThisPoT=1;last_bin=32;
PulseSearchBinStart=0;PulseSearchBinStop=32;TripletSearchBinStart=12;TripletSearchBinStop=28
Doing find_pulse() on CPU,ThisPoT=1,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=2,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=3,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=4,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=5,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=6,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=7,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=8,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=9,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=10,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=11,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=12, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=12,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=13, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=13,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=14, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=14,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=15, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=15,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=16, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=16,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=17, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=17,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=18, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=18,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=19, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=19,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=20, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=20,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=21, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=21,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=22, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=22,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=23, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=23,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=24, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=24,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=25, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=25,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=26, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=26,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=27, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=27,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=28,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=29,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=30,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=31,PulsePoTNum=1
call 'clEnqueueMapBuffer(gpu_GPUState)' is finished OK in file ..\analyzeFuncs.cpp near line 2172
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 2225
call ' oclFFT2: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 609
call 'non-strip fft' is finished OK in file ..\analyzeFuncs.cpp near line 4488
INFO: oclFFT done no strip. fftlen=64, NumBlockFfts=16384, chirplen=1048576
call 'Enqueueing kernel:GetPowerSpectrum_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4524
call 'Setting kernel argument: PC_find_spike_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4725
call 'Enqueueing kernel:PC_find_spike_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4740
call 'Setting kernel argument: Spike_partial_logging_HD5_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4745
call 'clEnqueueNDRangeKernel(cq,Spike_partial_logging_HD5_kernel_cl)' is finished OK in file ..\analyzeFuncs.cpp near line 4766
call 'clEnqueueMapBuffer(gpu_GPUState)' is finished OK in file ..\analyzeFuncs.cpp near line 2172
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 2225
call 'Setting kernel argument:PC_find_triplets_avg_kernel_HD5_cl' is finished OK in file ..\analyzePoT.cpp near line 1602
call 'Enqueueing kernel:PC_find_triplets_avg_kernel_HD5_cl' is finished OK in file ..\analyzePoT.cpp near line 1647
call 'Setting kernel argument:set_mem_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 1795
call 'Enqueueing kernel:set_mem_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 1802
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 2247
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,offset' is finished OK in file ..\analyzePoT.cpp near line 2269
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'clEnqueueMapBuffer(gpu_triplet_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 3913
call 'clEnqueueUnmapMemObject(gpu_triplet_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 3935
call 'Setting kernel argument:Transpose4_kernel_cl(pulse)' is finished OK in file ..\analyzePoT.cpp near line 3990
call 'Enqueueing kernel:Transpose4_kernel_cl(pulse)' is finished OK in file ..\analyzePoT.cpp near line 4003
call 'ReadBuffer(gpu_WorkData->tPowerSpectrum)' is finished OK in file ..\analyzePoT.cpp near line 4030
need_pulse_cpu_processing=1;need_triplet_cpu_processing=1;ThisPoT=1;last_bin=64;
PulseSearchBinStart=0;PulseSearchBinStop=64;TripletSearchBinStart=12;TripletSearchBinStop=20
Doing find_pulse() on CPU,ThisPoT=1,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=2,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=3,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=4,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=5,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=6,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=7,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=8,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=9,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=10,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=11,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=12, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=12,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=13, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=13,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=14, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=14,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=15, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=15,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=16, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=16,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=17, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=17,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=18, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=18,PulsePoTNum=1
Doing find_triplets() on CPU, ThisPoT=19, PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=19,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=20,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=21,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=22,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=23,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=24,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=25,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=26,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=27,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=28,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=29,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=30,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=31,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=32,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=33,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=34,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=35,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=36,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=37,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=38,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=39,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=40,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=41,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=42,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=43,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=44,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=45,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=46,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=47,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=48,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=49,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=50,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=51,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=52,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=53,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=54,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=55,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=56,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=57,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=58,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=59,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=60,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=61,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=62,PulsePoTNum=1
Doing find_pulse() on CPU,ThisPoT=63,PulsePoTNum=1
call 'clEnqueueMapBuffer(gpu_GPUState)' is finished OK in file ..\analyzeFuncs.cpp near line 2172
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 2225
call ' oclFFT2: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 609
call 'non-strip fft' is finished OK in file ..\analyzeFuncs.cpp near line 4488
INFO: oclFFT done no strip. fftlen=128, NumBlockFfts=8192, chirplen=1048576
call 'Enqueueing kernel:GetPowerSpectrum_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4524
call 'Setting kernel argument: PC_find_spike_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4725
call 'Enqueueing kernel:PC_find_spike_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4740
call 'Setting kernel argument: Spike_partial_logging_HD5_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4745
call 'clEnqueueNDRangeKernel(cq,Spike_partial_logging_HD5_kernel_cl)' is finished OK in file ..\analyzeFuncs.cpp near line 4766
call 'clEnqueueMapBuffer(gpu_GPUState)' is finished OK in file ..\analyzeFuncs.cpp near line 2172
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 2225
call 'Setting kernel argument:PC_find_triplets_avg_kernel_HD5_cl' is finished OK in file ..\analyzePoT.cpp near line 1602
call 'Enqueueing kernel:PC_find_triplets_avg_kernel_HD5_cl' is finished OK in file ..\analyzePoT.cpp near line 1647
call 'Setting kernel argument:set_mem_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 1795
call 'Enqueueing kernel:set_mem_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 1802
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 2247
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,offset' is finished OK in file ..\analyzePoT.cpp near line 2269
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2424
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 2464
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2300
call 'Enqueueing kernel:PC_find_pulse_partial_kernel_cl,pass 3' is finished OK in file ..\analyzePoT.cpp near line 2324



Current end of file


call 'Setting kernel argument:CalcChirpData_kernel2_cl' is finished OK in file ..\analyzeFuncs.cpp near line 3223
call 'Enqueueing kernel:CalcChirpData_kernel2_cl' is finished OK in file ..\analyzeFuncs.cpp near line 3238
call ' oclFFT1: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 570
call ' oclFFT1: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 570
call ' oclFFT1: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 570
call 'in strip fft' is finished OK in file ..\analyzeFuncs.cpp near line 3344
call 'Enqueueing kernel: (strip) GetPowerSpectrum_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 3390
call 'RepackInput_kernel' is finished OK in file ..\autocorr.cpp near line 531
call ' oclFFT1: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 570
call ' oclFFT1: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 570
call ' oclFFT1: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 570
call ' oclFFT1: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 570
call 'autocorr fft' is finished OK in file ..\autocorr.cpp near line 546
call 'FindAutoCorrelation_reduce0_kernel_cl' is finished OK in file ..\autocorr.cpp near line 588
call 'Enqueueing FindAutoCorrelation_reduce1_kernel_cl' is finished OK in file ..\autocorr.cpp near line 620
call 'Setting kernel argument: (strip) PC_find_spike32_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 3557
call 'Enqueueing kernel: (strip) PC_find_spike32_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 3563
call 'Setting kernel argument: (strip) Spike_logging_HD5_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 3568
call 'clEnqueueNDRangeKernel(cq,Spike_logging_HD5_kernel_cl)' is finished OK in file ..\analyzeFuncs.cpp near line 3589
call 'clEnqueueTask(cq,Autocorr_logging_kernel_cl)' is finished OK in file ..\analyzeFuncs.cpp near line 3919
call 'Setting kernel argument:CalcChirpData_kernel2_cl' is finished OK in file ..\analyzeFuncs.cpp near line 3223
call 'Enqueueing kernel:CalcChirpData_kernel2_cl' is finished OK in file ..\analyzeFuncs.cpp near line 3238
call ' oclFFT1: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 570
call ' oclFFT1: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 570
call ' oclFFT1: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 570
call 'in strip fft' is finished OK in file ..\analyzeFuncs.cpp near line 3344
call 'Enqueueing kernel: (strip) GetPowerSpectrum_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 3390
call 'RepackInput_kernel' is finished OK in file ..\autocorr.cpp near line 531
call ' oclFFT1: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 570
call ' oclFFT1: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 570
call ' oclFFT1: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 570
call ' oclFFT1: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 570
call 'autocorr fft' is finished OK in file ..\autocorr.cpp near line 546
call 'FindAutoCorrelation_reduce0_kernel_cl' is finished OK in file ..\autocorr.cpp near line 588
call 'Enqueueing FindAutoCorrelation_reduce1_kernel_cl' is finished OK in file ..\autocorr.cpp near line 620
call 'Setting kernel argument: (strip) PC_find_spike32_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 3557
call 'Enqueueing kernel: (strip) PC_find_spike32_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 3563
call 'Setting kernel argument: (strip) Spike_logging_HD5_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 3568
call 'clEnqueueNDRangeKernel(cq,Spike_logging_HD5_kernel_cl)' is finished OK in file ..\analyzeFuncs.cpp near line 3589
call 'clEnqueueTask(cq,Autocorr_logging_kernel_cl)' is finished OK in file ..\analyzeFuncs.cpp near line 3919
call 'Setting kernel argument:CalcChirpData_kernel2_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4359
call 'Enqueueing kernel:CalcChirpData_kernel2_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4374
call ' oclFFT1: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 570
call ' oclFFT1: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 570
call ' oclFFT1: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 570
call 'non-strip fft' is finished OK in file ..\analyzeFuncs.cpp near line 4488
INFO: oclFFT done no strip. fftlen=32768, NumBlockFfts=32, chirplen=1048576
call 'Enqueueing kernel:GetPowerSpectrum_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4524
call 'Setting kernel argument:PC_find_spike32_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4591
call 'Enqueueing kernel:PC_find_spike32_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4597
call 'Setting kernel argument: Spike_logging_HD5_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 4602
call 'clEnqueueNDRangeKernel(cq,Spike_logging_HD5_kernel_cl)' is finished OK in file ..\analyzeFuncs.cpp near line 4623
call 'Setting kernel argument:PC_find_triplets_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 1533
call 'Enqueueing kernel:PC_find_triplets_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 1562
call 'clEnqueueMapBuffer(gpu_triplet_result_flag)' is finished OK in file ..\analyzePoT.cpp near line 3913
GPU Users Group



ID: 1793656 · Report as offensive
Rasputin42
Volunteer tester

Send message
Joined: 25 Jul 08
Posts: 412
Credit: 5,834,661
RAC: 0
United States
Message 1793660 - Posted: 5 Jun 2016, 12:06:54 UTC

With this app and the later posted app - very low CPU usage and no GPU activity (from MSI Afterburner)


I have to disagree.

It takes a minute or so for the GPU to pick up, but then the GPU utilization is good.(maybe set -period_ iterations_num lower e.g. 20, to increase GPU utilization)

The important thing is, that the tasks, that with all previous versions got stuck (with -use_sleep), are running now.
ID: 1793660 · Report as offensive
Rasputin42
Volunteer tester

Send message
Joined: 25 Jul 08
Posts: 412
Credit: 5,834,661
RAC: 0
United States
Message 1793730 - Posted: 5 Jun 2016, 19:29:06 UTC
Last modified: 5 Jun 2016, 19:31:26 UTC

I have notice, that setting the -period_iterations number to 1 crashes the driver in some cases.

I did an extensive GPU test, and there is no problem.

As a safety precaution, i suggest to set the value as a default to 2 or 3, when LowPerformanceGPU path: yes.

(that was done with this:https://cloud.mail.ru/public/3X4g/HwEhUWHCE Version.)
ID: 1793730 · Report as offensive
Profile Raistmer
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 16 Jun 01
Posts: 6325
Credit: 106,370,077
RAC: 121
Russia
Message 1793731 - Posted: 5 Jun 2016, 19:32:01 UTC - in response to Message 1793730.  

I have notice, that setting the -period_iterations number to 1 crashes the driver in some cases.

I did an extensive GPU test, and there is no problem.

As a safety precaution, i suggest to set the value as a default to 2 or 3, when LowPerformanceGPU path: yes.

For low performance path default is 500. Common default is 50.
There are quite different GPus around so better safe than sorry in defaults. And even with such approach there are edge cases where low-performanxce path not active but NV GPU performance so low that driver crash occurs.
ID: 1793731 · Report as offensive
Rasputin42
Volunteer tester

Send message
Joined: 25 Jul 08
Posts: 412
Credit: 5,834,661
RAC: 0
United States
Message 1793744 - Posted: 5 Jun 2016, 19:59:58 UTC - in response to Message 1793731.  

I understand.
However, for low_performanceGPU option-500 is way way way too slow.
If there is no easy way to find a reasonable compromised setting, these SOG versions will have to be limited to advanced users, that can tweak as required.

BTW. How is determined, if a card is low-performance? Mine is , by any means, a mid range card.
ID: 1793744 · Report as offensive
Profile Raistmer
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 16 Jun 01
Posts: 6325
Credit: 106,370,077
RAC: 121
Russia
Message 1793746 - Posted: 5 Jun 2016, 20:11:33 UTC - in response to Message 1793744.  

by number of CUs
ID: 1793746 · Report as offensive
Stephen "Heretic" Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 20 Sep 12
Posts: 5557
Credit: 192,787,363
RAC: 628
Australia
Message 1794307 - Posted: 8 Jun 2016, 0:52:48 UTC - in response to Message 1793746.  

by number of CUs


. . My GT730 has only 2 CUs so it is low.

. . GTX950 has 6 CUs does that make it midrange?

. . Would 10 CUs be high end?
ID: 1794307 · Report as offensive
Profile Zalster Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 27 May 99
Posts: 5517
Credit: 528,817,460
RAC: 242
United States
Message 1794308 - Posted: 8 Jun 2016, 0:56:47 UTC - in response to Message 1794307.  
Last modified: 8 Jun 2016, 0:57:00 UTC

. . Would 10 CUs be high end?


980TI have 22 CU
Titan X have 24 CU

Just for a reference
ID: 1794308 · Report as offensive
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13732
Credit: 208,696,464
RAC: 304
Australia
Message 1794320 - Posted: 8 Jun 2016, 2:12:34 UTC - in response to Message 1794308.  

Looks like NVidia call them SMM (Maxwell Streaming Muiltiprocessor) or SMX (Streaming Multiprocessor) units, and probably yet another new term for Pascal.

  Model     "Compute Units"

GT 710               1
GT 720/30/40         2
GTX 745              3
GTX 750              4
GTX 750Ti            5
GTX 760              6
GTX 760Ti            7
GTX 770              8
GTX 780             12
GTX 780Ti           15
GTX Titan           14
GTX Titan Black     15
GTX Titan Z       2*15

GTX 950              6
GTX 960              8
GTX 970             13
GTX 980             16
GTX 980Ti           22
GTX Titan X         24

GTX 1070             ?
GTX 1080             ?


The GT/X 600 series had up to 8 (the GTX 659Ti had 4).
The GT/X 500 series had up to 16 (the GTX 560Ti had 8).


Ref
https://en.wikipedia.org/wiki/List_of_Nvidia_graphics_processing_units#GeForce_900_Series
http://docs.nvidia.com/cuda/maxwell-tuning-guide/#smm
http://docs.nvidia.com/cuda/maxwell-compatibility-guide/#abstract
Grant
Darwin NT
ID: 1794320 · Report as offensive
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13732
Credit: 208,696,464
RAC: 304
Australia
Message 1794331 - Posted: 8 Jun 2016, 3:20:16 UTC - in response to Message 1794320.  
Last modified: 8 Jun 2016, 3:20:30 UTC

The GT/X 600 series had up to 8 (the GTX 659Ti had 4).

Make that the GTX 650Ti
Grant
Darwin NT
ID: 1794331 · Report as offensive
Previous · 1 · 2 · 3 · 4 · 5 · 6 · Next

Message boards : Number crunching : OpenCL MB v8.12 issues thread attempt 2


 
©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.