ATI 6970 MultiBeam Crashes Drivers in XP
Message boards :
SETI@home Enhanced :
ATI 6970 MultiBeam Crashes Drivers in XP
Message board moderation
| Author | Message |
|---|---|
|
Send message Joined: 2 Jul 13 Posts: 505 Credit: 5,019,318 RAC: 0 
|
Just installed the PowerColor 6970 in this Host and found it crashes both XP drivers with MB r2489, r2033, and r1817. The card works fine in Vista with Cat 13.12 and Ubuntu with Cat 14.6. It seems to be building the Binaries and then crashes with; Error in mb oclFFT_2: -34 ERROR: OpenCL kernel/call 'non-strip fft' call failed (-34) in file ..\analyzeFuncs.cpp near line 3813. Waiting 30 sec before restart... Ideas? ID: 53086 ·  |
|
Send message Joined: 2 Jul 13 Posts: 505 Credit: 5,019,318 RAC: 0
|
Is there any hope getting this to work or should I make other plans for the tasks on this host? I had planned on testing the 'new' 6970 in XP... ID: 53100 · |
|
Send message Joined: 2 Jul 13 Posts: 505 Credit: 5,019,318 RAC: 0
|
Too weird. In My XP; Error in mb oclFFT_2: -34 In a Mac; Error in mb oclFFT_2: -49 http://lunatics.kwsn.net/10-alternate-hardware-platforms/osx-multibeam-opencl-question.msg57737.html#msg57737 Well, I tried the non-HD5 version MB7_win_x86_SSE_OpenCL_ATi_r2489.exe, but, I get the same error; Error in mb oclFFT_2: -34 At least it didn't Crash the machine with the HD4 version... ID: 53102 · |
 Raistmer Send message Joined: 18 Aug 05 Posts: 2423 Credit: 15,878,738 RAC: 0 
|
#define CL_INVALID_CONTEXT -34 #define CL_INVALID_ARG_INDEX -49 As I understand OS X "-49" issue in debugging now for some of builds. Where you got OS X build? News about SETI opt app releases: https://twitter.com/Raistmer ID: 53103 · |
|
Raistmer Send message Joined: 18 Aug 05 Posts: 2423 Credit: 15,878,738 RAC: 0
|
Just installed the PowerColor 6970 in this Host and found it crashes both XP drivers with MB r2489, r2033, and r1817. The card works fine in Vista with Cat 13.12 and Ubuntu with Cat 14.6. It seems to be building the Binaries and then crashes with; try this one: https://dl.dropboxusercontent.com/u/60381958/MB7_win_x86_SSE_OpenCL_ATi_HD5_r2760.7z News about SETI opt app releases: https://twitter.com/Raistmer ID: 53104 · |
|
Send message Joined: 2 Jul 13 Posts: 505 Credit: 5,019,318 RAC: 0
|
I don't have the OSX build referenced at Lunatics. I'm getting the -34 error in Win XP with my 'new' 6970. I noticed the similarities in the OSX & XP Errors when I went to track down your last known location. It would be nice to have a OSX MB build though, I have a Mac that hasn't had any work going on 3 weeks now. try this one: https://dl.dropboxusercontent.com/u/60381958/MB7_win_x86_SSE_OpenCL_ATi_HD5_r2760.7z I'm not getting the OpenCL Error with this one but it crashes the AMD driver after about 90 seconds. I have to reboot to get the App to work again. Work Unit Info: ID: 53105 · |
|
Raistmer Send message Joined: 18 Aug 05 Posts: 2423 Credit: 15,878,738 RAC: 0
|
try: -sbs 64 -period_iterations_num 100 -cpu_lock News about SETI opt app releases: https://twitter.com/Raistmer ID: 53106 · |
|
Send message Joined: 2 Jul 13 Posts: 505 Credit: 5,019,318 RAC: 0
|
try: -sbs 64 -period_iterations_num 100 -cpu_lock It works for about a minute, then crashes the ATI driver. I've begun downgrading the driver while keeping AMD App 831.4. I think I remember someone saying it might work around Cat 11.7...or maybe that was with AstroPulse... ID: 53107 · |
|
Raistmer Send message Joined: 18 Aug 05 Posts: 2423 Credit: 15,878,738 RAC: 0
|
try this one and send stderr.txt to me https://www.dropbox.com/s/tgyh22pvt8s3rok/MB7_win_x86_SSE_OpenCL_ATi_HD5_r2760_verbose.7z?dl=0 News about SETI opt app releases: https://twitter.com/Raistmer ID: 53108 · |
|
Send message Joined: 2 Jul 13 Posts: 505 Credit: 5,019,318 RAC: 0
|
It finished one here, http://setiathome.berkeley.edu/result.php?resultid=3837810797 Run time: 21 min 47 sec CPU time: 20 min 42 sec The Run Time is just a little long but the CPU time is terrible. It's using a full CPU and it's Red in SIV indicating Kernel thrashing. I removed the gpu lock for the next task and set it to sbs 256, but it appears to be the same with the next task as the first. It still crashed the driver with Cat 11.10, but seems to work with Cat 11.9 with AMD App 831.4. Second one, http://setiathome.berkeley.edu/result.php?resultid=3837810748 ID: 53109 · |
|
Raistmer Send message Joined: 18 Aug 05 Posts: 2423 Credit: 15,878,738 RAC: 0
|
it's debug build, no sense to look at completion times ... News about SETI opt app releases: https://twitter.com/Raistmer ID: 53110 · |
|
Raistmer Send message Joined: 18 Aug 05 Posts: 2423 Credit: 15,878,738 RAC: 0
|
It finished one here, http://setiathome.berkeley.edu/result.php?resultid=3837810797 I lost track what build is working for you. Links to 2 results are not for verbose build. Did they obtained with non-verbose r2760? And what did you did to stop driver crash for it then, explain your results, please. News about SETI opt app releases: https://twitter.com/Raistmer ID: 53111 · |
|
Send message Joined: 2 Jul 13 Posts: 505 Credit: 5,019,318 RAC: 0
|
I just ran the verbose build long enough to generate the file. The original r2760 build cured the OpenCL Error. I began to remember other people posting about having to use earlier drivers to get their 6970 to work so I began downgrading drivers. The driver crashes stopped with Cat 11.9 and AMD APP 831.4. I'm still getting annoying screen lag and the app is thrashing a full cpu core. I just installed AMD APP 851.4 and everything looks the same so far; http://setiathome.berkeley.edu/result.php?resultid=3837810799 11/23/2014 7:47:21 AM | | Starting BOINC client version 7.2.42 for windows_intelx86 11/23/2014 7:47:21 AM | | CUDA: NVIDIA GPU 0: GeForce 8800 GT (driver version 266.58, CUDA version 3.2, compute capability 1.1, 512MB, 467MB available, 544 GFLOPS peak) 11/23/2014 7:47:21 AM | | CAL: ATI GPU 0: AMD Radeon HD 6900 series (Cayman) (CAL version 1.4.1546, 2048MB, 2032MB available, 6758 GFLOPS peak) 11/23/2014 7:47:21 AM | | OpenCL: NVIDIA GPU 0: GeForce 8800 GT (driver version 266.58, device version OpenCL 1.0 CUDA, 512MB, 467MB available, 544 GFLOPS peak) 11/23/2014 7:47:21 AM | | OpenCL: AMD/ATI GPU 0: AMD Radeon HD 6900 series (Cayman) (driver version CAL 1.4.1546, device version OpenCL 1.1 AMD-APP (851.4), 2048MB, 2032MB available, 6758 GFLOPS peak) 11/23/2014 7:47:21 AM | | OpenCL CPU: Intel(R) Core(TM)2 Quad CPU Q9400 @ 2.66GHz (OpenCL driver vendor: Advanced Micro Devices, Inc., driver version 2.0, device version OpenCL 1.1 AMD-APP (851.4)) 11/23/2014 7:47:21 AM | | OS: Microsoft Windows XP: Professional x86 Edition, Service Pack 3, (05.01.2600.00) Platform Name: AMD Accelerated Parallel Processing
Number of devices: 2
Device Type: CL_DEVICE_TYPE_GPU
Device ID: 4098
Board name: AMD Radeon HD 6900 Series
Max compute units: 24
Max work items dimensions: 3
Max work items[0]: 256
Max work items[1]: 256
Max work items[2]: 256
Max work group size: 256
Preferred vector width char: 16
Preferred vector width short: 8
Preferred vector width int: 4
Preferred vector width long: 2
Preferred vector width float: 4
Preferred vector width double: 0
Native vector width char: 16
Native vector width short: 8
Native vector width int: 4
Native vector width long: 2
Native vector width float: 4
Native vector width double: 0
Max clock frequency: 880Mhz
Address bits: 32
Max memory allocation: 268435456
Image support: Yes
Max number of images read arguments: 128
Max number of images write arguments: 8
Max image 2D width: 8192
Max image 2D height: 8192
Max image 3D width: 2048
Max image 3D height: 2048
Max image 3D depth: 2048
Max samplers within kernel: 16
Max size of kernel argument: 1024
Alignment (bits) of base address: 2048
Minimum alignment (bytes) for any datatype: 128
Single precision floating point capability
Denorms: No
Quiet NaNs: Yes
Round to nearest even: Yes
Round to zero: Yes
Round to +ve and infinity: Yes
IEEE754-2008 fused multiply-add: Yes
Cache type: None
Cache line size: 0
Cache size: 0
Global memory size: 1073741824
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Scratchpad
Local memory size: 32768
Kernel Preferred work group size multiple: 64
Error correction support: 0
Unified memory for Host and Device: 0
Profiling timer resolution: 1
Device endianess: Little
Available: Yes
Compiler available: Yes
Execution capabilities:
Execute OpenCL kernels: Yes
Execute native function: No
Queue properties:
Out-of-Order: No
Profiling : Yes
Platform ID: 0206A4F4
Name: Cayman
Vendor: Advanced Micro Devices, Inc.
Device OpenCL C version: OpenCL C 1.1
Driver version: CAL 1.4.1546
Profile: FULL_PROFILE
Version: OpenCL 1.1 AMD-APP (851.4)
Extensions: cl_amd_fp64 cl_khr_global_int32
_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomi
cs cl_khr_local_int32_extended_atomics cl_khr_3d_image_writes cl_khr_byte_addres
sable_store cl_khr_gl_sharing cl_ext_atomic_counters_32 cl_amd_device_attribute_
query cl_amd_vec3 cl_amd_printf cl_amd_media_ops cl_amd_popcntID: 53112 · |
|
Send message Joined: 2 Jul 13 Posts: 505 Credit: 5,019,318 RAC: 0
|
Well, I decided to try to remove the CPU thrashing by trying a different driver. More crashes. The crash list; Cat 12.1 APP 851.4 Crash Cat 12.1 APP 831.4 Crash Cat 11.12 APP 851.4 Crash Cat 11.12 APP 831.4 Crash Cat 11.10 APP 831.4 Crash Cat 11.9 APP 831.4 Good Cat 11.9 APP 851.4 Good Cat 11.8 APP 851.4 Crash Cat 11.7 APP 851.4 Crash I may have missed a couple So, I ran the Display Driver Uninstaller and Installed Cat 11.9. Of course r2760 will not work with SDK 2.5, so I used r1843. No OpenCL Error, No Crash. But I still get LAG and 100% core Thrashing. I also get better times, http://setiathome.berkeley.edu/result.php?resultid=3837792468 http://setiathome.berkeley.edu/result.php?resultid=3837810773 11/23/2014 3:02:17 PM | | Starting BOINC client version 7.2.42 for windows_intelx86 11/23/2014 3:02:17 PM | | CUDA: NVIDIA GPU 0: GeForce 8800 GT (driver version 266.58, CUDA version 3.2, compute capability 1.1, 512MB, 468MB available, 544 GFLOPS peak) 11/23/2014 3:02:17 PM | | CAL: ATI GPU 0: AMD Radeon HD 6900 series (Cayman) (CAL version 1.4.1546, 2048MB, 2032MB available, 6758 GFLOPS peak) 11/23/2014 3:02:17 PM | | OpenCL: NVIDIA GPU 0: GeForce 8800 GT (driver version 266.58, device version OpenCL 1.0 CUDA, 512MB, 468MB available, 544 GFLOPS peak) 11/23/2014 3:02:17 PM | | OpenCL: AMD/ATI GPU 0: AMD Radeon HD 6900 series (Cayman) (driver version CAL 1.4.1546, device version OpenCL 1.1 AMD-APP-SDK-v2.5 (732.1), 2048MB, 2032MB available, 6758 GFLOPS peak) 11/23/2014 3:02:17 PM | | OpenCL CPU: Intel(R) Core(TM)2 Quad CPU Q9400 @ 2.66GHz (OpenCL driver vendor: Advanced Micro Devices, Inc., driver version 2.0, device version OpenCL 1.1 AMD-APP-SDK-v2.5 (732.1)) 11/23/2014 3:02:17 PM | | OS: Microsoft Windows XP: Professional x86 Edition, Service Pack 3, (05.01.2600.00) ID: 53113 · |
|
Send message Joined: 2 Jul 13 Posts: 505 Credit: 5,019,318 RAC: 0
|
I lost track what build is working for you... So, what next? Do you want me to load Cat 11.12, the verbose build, let it crash, then send you the stderr.txt? How does your 6970 work in XP? Mine is the one currently at NewEgg, it's pretty much an ATI reference card, AFAIK. ID: 53114 · |
|
Raistmer Send message Joined: 18 Aug 05 Posts: 2423 Credit: 15,878,738 RAC: 0
|
I lost track what build is working for you... Well, I use HD6950 and use Vista for it, not XP. Your findings definitely mean it's driver issue, hardly we can fix AMD driver. You could try to run verbose build under driver that you would want to use for production build but can't because of crash. If verbose build would crash too it will give some info regarding where crash occurs. But I'm quite sceptical about this. Verbose build hardly crash in such conditions. EDIT: Also, you could try to run this build (under both your current working and not working but desirable drivers) to compare its behavior with usual build: https://www.dropbox.com/s/hapkv5rflrodnvj/MB7_win_x86_SSE_OpenCL_ATi_HD5_r2760_SYNCHED.7z?dl=0 News about SETI opt app releases: https://twitter.com/Raistmer ID: 53116 · |
|
Send message Joined: 2 Jul 13 Posts: 505 Credit: 5,019,318 RAC: 0
|
...Also, you could try to run this build (under both your current working and not working but desirable drivers) to compare its behavior with usual build: https://www.dropbox.com/s/hapkv5rflrodnvj/MB7_win_x86_SSE_OpenCL_ATi_HD5_r2760_SYNCHED.7z?dl=0 That one still doesn't like SDK 2.5; ERROR: unsupported OpenCL runtime version: OpenCL 1.1 AMD-APP-SDK-v2.5 (732.1). Please update drivers! Exiting... I installed the complete Cat 11.12 and as soon as the Binaries were built it crashed the driver. Nothing strange; Running on device number: 0
Maximum single buffer size set to:256MB
Number of period iterations for PulseFind set to:80
CPU affinity adjustment enabled
GPUlock enabled. Use -instances_per_device N switch to provide number of instances to run if BOINC is configured to launch few tasks per device.
Priority of worker thread raised successfully
Priority of process adjusted successfully, below normal priority class used
OpenCL platform detected: NVIDIA Corporation
OpenCL platform detected: Advanced Micro Devices, Inc.
BOINC assigns device 0, slots 0 to 0 (including) will be checked
Used slot is 0; Info: BOINC provided OpenCL device ID used
Info: CPU affinity mask used: 1
Build features: SETI7 Non-graphics OpenCL USE_OPENCL_HD5xxx OCL_SYNCHED OCL_ZERO_COPY OCL_CHIRP3 FFTW AMD specific USE_SSSE3 x86
CPUID: Intel(R) Core(TM)2 Quad CPU Q9400 @ 2.66GHz
Cache: L1=64K L2=3072K
CPU features: FPU TSC PAE CMPXCHG8B APIC SYSENTER MTRR CMOV/CCMP MMX FXSAVE/FXRSTOR SSE SSE2 HT SSE3 SSSE3 SSE4.1
OpenCL-kernels filename : MultiBeam_Kernels_r2760.cl
INFO: can't open binary kernel file: C:\Documents and Settings\All Users\Application Data\BOINC/projects/setiathome.berkeley.edu\MultiBeam_Kernels_r2760.clHD5_Cayman.bin_V7_CAL141646, 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: C:\Documents and Settings\All Users\Application Data\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Cayman_524288_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r2760.bin_CAL141646, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\Documents and Settings\All Users\Application Data\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Cayman_8_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r2760.bin_CAL141646, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\Documents and Settings\All Users\Application Data\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Cayman_16_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r2760.bin_CAL141646, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\Documents and Settings\All Users\Application Data\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Cayman_32_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r2760.bin_CAL141646, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\Documents and Settings\All Users\Application Data\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Cayman_64_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r2760.bin_CAL141646, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\Documents and Settings\All Users\Application Data\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Cayman_128_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r2760.bin_CAL141646, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\Documents and Settings\All Users\Application Data\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Cayman_256_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r2760.bin_CAL141646, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\Documents and Settings\All Users\Application Data\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Cayman_512_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r2760.bin_CAL141646, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\Documents and Settings\All Users\Application Data\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Cayman_1024_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r2760.bin_CAL141646, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\Documents and Settings\All Users\Application Data\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Cayman_2048_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r2760.bin_CAL141646, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\Documents and Settings\All Users\Application Data\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Cayman_4096_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r2760.bin_CAL141646, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\Documents and Settings\All Users\Application Data\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Cayman_8192_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r2760.bin_CAL141646, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\Documents and Settings\All Users\Application Data\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Cayman_16384_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r2760.bin_CAL141646, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\Documents and Settings\All Users\Application Data\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Cayman_32768_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r2760.bin_CAL141646, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\Documents and Settings\All Users\Application Data\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Cayman_65536_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r2760.bin_CAL141646, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\Documents and Settings\All Users\Application Data\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Cayman_131072_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r2760.bin_CAL141646, continue with recompile...
ar=0.442669 NumCfft=192409 NumGauss=1067764990 NumPulse=226319983753 NumTriplet=452747030745
Currently allocated 337 MB for GPU buffers
In v_BaseLineSmooth: NumDataPoints=1048576, BoxCarLength=8192, NumPointsInChunk=32768
Windows optimized S@H v7 application
Based on Intel, Core 2-optimized v8-nographics V5.13 by Alex Kan
SSSE3xj Win32 Build 2760 , Ported by : Raistmer, JDWhale
SETI7 update by Raistmer
OpenCL version by Raistmer, r2760
AMD HD5 version by Raistmer
Number of OpenCL platforms: 2
OpenCL Platform Name: NVIDIA CUDA
Number of devices: 1
Max compute units: 14
Max work group size: 512
Max clock frequency: 1620Mhz
Max memory allocation: 134217728
Cache type: None
Cache line size: 0
Cache size: 0
Global memory size: 536674304
Constant buffer size: 65536
Max number of constant args: 9
Local memory type: Scratchpad
Local memory size: 16384
Queue properties:
Out-of-Order: Yes
Name: GeForce 8800 GT
Vendor: NVIDIA Corporation
Driver version: 266.58
Version: OpenCL 1.0 CUDA
Extensions: cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_d3d9_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
OpenCL Platform Name: AMD Accelerated Parallel Processing
Number of devices: 1
Max compute units: 24
Max work group size: 256
Max clock frequency: 880Mhz
Max memory allocation: 268435456
Cache type: None
Cache line size: 0
Cache size: 0
Global memory size: 1073741824
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Scratchpad
Local memory size: 32768
Queue properties:
Out-of-Order: No
Name: Cayman
Vendor: Advanced Micro Devices, Inc.
Driver version: CAL 1.4.1646
Version: OpenCL 1.1 AMD-APP (831.4)
Extensions: cl_amd_fp64 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_3d_image_writes cl_khr_byte_addressable_store cl_khr_gl_sharing cl_ext_atomic_counters_32 cl_amd_device_attribute_query cl_amd_vec3 cl_amd_printf cl_amd_media_ops cl_amd_popcnt
Work Unit Info:
...............
Credit multiplier is : 2.85
WU true angle range is : 0.442669
Used GPU device parameters are:
Number of compute units: 24
Single buffer allocation size: 256MB
Total device global memory: 1024MB
max WG size: 256
local mem type: Real
period_iterations_num=80So I removed the Driver & CCC and installed the Driver from Cat 11.9. It Built new Binaries and is working with the Driver from 11.9 and AMD APP from 11.12. The Screen Lag seems to be less but that may be because it's only working at around 75% GPU load. It was around 85% with SDK 2.5. It's still Thrashing a complete CPU core. At least it validated, http://setiathome.berkeley.edu/result.php?resultid=3837792476 ID: 53120 · |
|
Raistmer Send message Joined: 18 Aug 05 Posts: 2423 Credit: 15,878,738 RAC: 0
|
try verbose build in that combination you saw crash with SYNCHED one. News about SETI opt app releases: https://twitter.com/Raistmer ID: 53121 · |
|
Send message Joined: 2 Jul 13 Posts: 505 Credit: 5,019,318 RAC: 0
|
Well the Verbose build Crashes the driver Too. I have removed the 8800, now it's just the 6970; Running on device number: 0
Maximum single buffer size set to:256MB
Number of period iterations for PulseFind set to:80
CPU affinity adjustment enabled
GPUlock enabled. Use -instances_per_device N switch to provide number of instances to run if BOINC is configured to launch few tasks per device.
Priority of worker thread raised successfully
Priority of process adjusted successfully, below normal priority class used
OpenCL platform detected: Advanced Micro Devices, Inc.
call 'clGetDeviceIDs' is finished OK in file ..\..\..\src\GPU_lock.cpp near line 819
BOINC assigns device 0, slots 0 to 0 (including) will be checked
Used slot is 0; Info: BOINC provided OpenCL device ID used
call 'clCreateContext' is finished OK in file ..\..\..\src\GPU_lock.cpp near line 1003
call 'Creating Command Queue. (clCreateCommandQueue)' is finished OK in file ..\..\..\src\GPU_lock.cpp near line 1028
call 'Creating Command Queue for writing' is finished OK in file ..\..\..\src\GPU_lock.cpp near line 1033
call 'Quering device abilities' is finished OK in file ..\..\..\src\GPU_lock.cpp near line 293
call 'Quering device abilities' is finished OK in file ..\..\..\src\GPU_lock.cpp near line 334
Info: CPU affinity mask used: 1
Build features: SETI7 Non-graphics OpenCL USE_OPENCL_HD5xxx OCL_VERBOSE OCL_ZERO_COPY OCL_CHIRP3 FFTW AMD specific USE_SSSE3 x86
CPUID: Intel(R) Core(TM)2 Quad CPU Q9400 @ 2.66GHz
Cache: L1=64K L2=3072K
CPU features: FPU TSC PAE CMPXCHG8B APIC SYSENTER MTRR CMOV/CCMP MMX FXSAVE/FXRSTOR SSE SSE2 HT SSE3 SSSE3 SSE4.1
OpenCL-kernels filename : MultiBeam_Kernels_r2760.cl
INFO: can't open binary kernel file: C:\Documents and Settings\All Users\Application Data\BOINC/projects/setiathome.berkeley.edu\MultiBeam_Kernels_r2760.clHD5_Cayman.bin_V7_CAL141646, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\Documents and Settings\All Users\Application Data\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Cayman_131072_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r2760.bin_CAL141646, continue with recompile...
call 'clGetProgramInfo' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_setup.cpp near line 775
FFT: clFFT_CreatePlan[14] done.
ar=0.442669 NumCfft=192409 NumGauss=1067764990 NumPulse=226319983753 NumTriplet=452747030745
call 's_clCreateBuffer(gpu_DataIn)' is finished OK in file ..\analyzeFuncs.cpp near line 802
call 's_clCreateBuffer(FFTbuf)' is finished OK in file ..\analyzeFuncs.cpp near line 818
call 's_clCreateBuffer(gpu_ChirpedData)' is finished OK in file ..\analyzeFuncs.cpp near line 841
call 's_clCreateBuffer(gpu_WorkData)' is finished OK in file ..\analyzeFuncs.cpp near line 853
call 's_clCreateBuffer(gpu_PowerSpectrum)' is finished OK in file ..\analyzeFuncs.cpp near line 886
call 's_clCreateBuffer(gpu_GaussPoT)' is finished OK in file ..\analyzeFuncs.cpp near line 922
call 's_clCreateBuffer(gpu_GaussFitResults)' is finished OK in file ..\analyzeFuncs.cpp near line 933
call 'clCreateBuffer(cpu_GaussFitResults_buf)' is finished OK in file ..\analyzeFuncs.cpp near line 979
call 's_clCreateBuffer(gpu_PoTPrefixSum)' is finished OK in file ..\analyzeFuncs.cpp near line 1038
call 's_clCreateBuffer(gpu_NormMaxPower)' is finished OK in file ..\analyzeFuncs.cpp near line 1044
call 's_clCreateBuffer(gpu_WeakPeaks)' is finished OK in file ..\analyzeFuncs.cpp near line 1050
call 's_clCreateBuffer(gpu_f_weight)' is finished OK in file ..\analyzeFuncs.cpp near line 1057
call 's_clCreateBuffer(gpu_settings)' is finished OK in file ..\analyzeFuncs.cpp near line 1086
call 's_clCreateBuffer(gpu_PulsePoT_average)' is finished OK in file ..\analyzeFuncs.cpp near line 1108
call 'clCreateBuffer(gpu_gaussian_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 1212
call 'clEnqueueMapBuffer(gpu_gaussian_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 1215
call 'clEnqueueUnmapMemObject(gpu_gaussian_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 1218
call 'clCreateBuffer(gpu_triplet_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 1227
call 'clEnqueueMapBuffer(gpu_triplet_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 1230
call 'clEnqueueUnmapMemObject(gpu_triplet_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 1233
call 'clCreateBuffer(gpu_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 1242
call 'clEnqueueMapBuffer(gpu_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 1245
call 'clEnqueueUnmapMemObject(gpu_result_flag)' is finished OK in file ..\analyzeFuncs.cpp near line 1248
call 's_clCreateBuffer(gpu_MeanMaxIdx)' is finished OK in file ..\analyzeFuncs.cpp near line 1320
call 'clCreateBuffer(cpu_MeanMaxIdx_buf)' is finished OK in file ..\analyzeFuncs.cpp near line 1344
call 'clCreateBuffer(cpu_PowerBin_buf)' is finished OK in file ..\analyzeFuncs.cpp near line 1373
Currently allocated 337 MB for GPU buffers
call 'Creating RepackInput_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1411
call 'Creating FindAutoCorrelation_reduce0_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1418
call 'Creating FindAutoCorrelation_reduce1_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1420
call 'Creating CalcChirpData_kernel_df64_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1433
call 'Creating GetPowerSpectrum_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1440
call 'Creating Transpose4_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1446
call 'Creating GetFixedPoT_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1448
call 'Creating NormalizePoT_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1450
call 'Creating NormalizePoT_peak_PC_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1452
call 'Creating GaussFit_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1454
call 'Creating GaussFit_kernel_PE_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1456
call 'Creating GaussFit_no_best_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1463
call 'Creating set_mem_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1465
call 'Creating PC_find_triplets_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1472
call 'Creating PC_find_triplets_avg_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1474
call 'Creating PC_find_pulse_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1486
call 'Creating PC_find_pulse_partial_kernel1_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1488
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 1504
INFO: Creating PC_find_pulse_f_kernel_cl from program ok
call 'Creating PC_find_spike_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1522
INFO: Creating PC_find_spike_kernel_cl from program ok
call 'Creating PC_find_spike_reduce0_kernel_cl from program:' is finished OK in file ..\analyzeFuncs.cpp near line 1527
INFO: Creating PC_find_spike_reduce0_kernel_cl from program ok
call 'Creating PC_find_spike_reduce1_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1532
call 'Creating PC_find_spike32_kernel_cl from program' is finished OK in file ..\analyzeFuncs.cpp near line 1545
In v_BaseLineSmooth: NumDataPoints=1048576, BoxCarLength=8192, NumPointsInChunk=32768
Windows optimized S@H v7 application
...
Very Verbose OpenCL INFO dumping!
......
Credit multiplier is : 2.85
WU true angle range is : 0.442669
call 'clWriteBuffer(gpu_DataIn)' is finished OK in file ..\analyzeFuncs.cpp near line 2532
call 'clWriteBuffer(gpu_settings #1)' is finished OK in file ..\analyzeFuncs.cpp near line 1630
call 'clWriteBuffer(gpu_settings #2)' is finished OK in file ..\analyzeFuncs.cpp near line 1632
INFO: After initializeGaussfit_cl
call 's_clCreateBuffer(gpu_t_funct_cache)' is finished OK in file ..\analyzeFuncs.cpp near line 1707
call 's_clCreateBuffer(gpu_pulsefind_settings)' is finished OK in file ..\analyzeFuncs.cpp near line 1714
call 'clWriteBuffer(gpu_pulsefind_settings)' is finished OK in file ..\analyzeFuncs.cpp near line 1719
call 'clWriteBuffer(gpu_t_funct_cache)' is finished OK in file ..\analyzeFuncs.cpp near line 1735
INFO: After initialize_pulse_find_cl
Used GPU device parameters are:
Number of compute units: 24
Single buffer allocation size: 256MB
Total device global memory: 1024MB
max WG size: 256
local mem type: Real
period_iterations_num=80
call 'Setting kernel argument:CalcChirpData_kernel2_cl' is finished OK in file ..\analyzeFuncs.cpp near line 532
call 'Setting kernel argument:GetPowerSpectrum_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 534
call 'Setting kernel argument:PC_find_spike_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 580
call 'Setting kernel argument:GetFixedPoT_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 586
call 'Setting kernel argument:NormalizePoT_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 590
call 'Setting kernel argument:GetFixedPoT_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 595
call 'Setting kernel argument:NormalizePoT_peak_PC_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 601
call 'Setting kernel argument:NormalizePoT_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 606
call 'Setting kernel argument:GaussFit_kernel_PE_cl' is finished OK in file ..\analyzeFuncs.cpp near line 619
call 'Setting kernel argument:GaussFit_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 630
call 'Setting kernel argument:GaussFit_no_best_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 641
call 'Setting kernel argument:NormalizePoT_peak_PC_kernel_cl
' is finished OK in file ..\analyzeFuncs.cpp near line 645
call 'Setting kernel argument:GaussFit_kernel_PE_cl' is finished OK in file ..\analyzeFuncs.cpp near line 650
call 'Setting kernel argument:GaussFit_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 654
call 'Setting kernel argument:GaussFit_no_best_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 658
call 'Setting kernel argument:Transpose4_kernel_cl(PoT)' is finished OK in file ..\analyzeFuncs.cpp near line 661
call 'Setting kernel argument:PC_find_triplets_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 666
call 'Setting kernel argument:PC_find_triplets_avg_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 670
call 'Setting kernel argument:PC_find_pulse_f_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 680
call 'Setting kernel argument:PC_find_pulse_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 689
call 'Setting kernel argument:PC_find_pulse_partial_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 699
call 'Setting kernel argument:FindAutoCorrelation_reduce0_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 710
call 'Setting kernel argument:FindAutoCorrelation_reduce1_kernel_cl' is finished OK in file ..\analyzeFuncs.cpp near line 728
INFO: After SetupKernelArgs
INFO: Freeing local variables.
call 'Setting kernel argument:CalcChirpData_kernel2_cl' is finished OK in file ..\analyzeFuncs.cpp near line 3775
call 'Enqueueing kernel:CalcChirpData_kernel2_cl' is finished OK in file ..\analyzeFuncs.cpp near line 3790
call ' oclFFT2: clEnqueueNDRangeKernel' is finished OK in file ..\..\..\src\OpenCL_FFT\fft_execute.cpp near line 589
call 'non-strip fft' is finished OK in file ..\analyzeFuncs.cpp near line 3901
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 3919
Spike search (main) omitted due to too small FFT size==8
call 'Setting kernel argument:GetFixedPoT_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 639
call 'Enqueueing kernel:GetFixedPoT_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 654
call 'Setting kernel argument:NormalizePoT_peak_PC_kernel_cl' is finished OK in file ..\analyzePoT.cpp near line 686
It stops there.ID: 53122 · |
|
Raistmer Send message Joined: 18 Aug 05 Posts: 2423 Credit: 15,878,738 RAC: 0
|
Hm, it crashes on quite small kernel. I'm afraid that driver can't be used for this app anymore. Stick with r1843 while it produces valid results then consider software upgrading to more compatible environment. News about SETI opt app releases: https://twitter.com/Raistmer ID: 53123 · |
©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.