Although it seems like some of my WUs complete ok, the majority get Computation Errors.

Any Ideas?

Stderr output

<core_client_version>6.12.34</core_client_version>
<![CDATA[
<message>
Incorrect function. (0x1) - exit code 1 (0x1)
</message>
<stderr_txt>
Error loading Lua script 'astronomy_parameters.txt': [string "number_parameters: 4..."]:1: '<name>' expected near '4'
Error reading astronomy parameters from file 'astronomy_parameters.txt'
Trying old parameters file
Using SSE3 path
Found 1 platform(s)
Platform 0 information:
Name: NVIDIA CUDA
Version: OpenCL 1.1 CUDA 4.0.1
Vendor: NVIDIA Corporation
Extensions: cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_d3d9_sharing cl_nv_d3d10_sharing cl_khr_d3d10_sharing cl_nv_d3d11_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll
Profile: FULL_PROFILE
Using device 0 on platform 0
Found 2 CL device(s)
Device GeForce GTX 295 (NVIDIA Corporation:0x10de) (CL_DEVICE_TYPE_GPU)
Driver version: 280.26
Version: OpenCL 1.0 CUDA
Compute capability: 1.3
Image support: CL_TRUE
Max compute units: 30
Clock frequency: 1476 Mhz
Global mem size: 919994368
Local mem size: 16384
Max const buf size: 65536
Double extension: MW_CL_KHR_FP64
Found a compute capability 1.3 device. Using -cl-nv-maxrregcount=32

Compiler flags:
-cl-mad-enable -cl-no-signed-zeros -cl-strict-aliasing -cl-finite-math-only -cl-nv-verbose -cl-nv-maxrregcount=32 -DDOUBLEPREC=1 -DFAST_H_PROB=1 -DAUX_BG_PROFILE=0 -DNSTREAM=3 -DCONVOLVE=120 -DR0=5.800000000000000 -DSUN_R0=8.500000000000000 -DQ_INV_SQR=3.429355281207133 -DUSE_IMAGES=0

Build status: CL_BUILD_SUCCESS
Build log:


Kernel work group info:
Work group size = 512
Kernel local mem size = 64
Compile work group size = { 0, 0, 0 }
Keeping chunk boundaries as multiples of 1920
Range: { nu_steps = 640, mu_steps = 1600, r_steps = 1400 }
Iteration area: 2240000
Chunk estimate: 146
Num chunks: 146
Added area: 640
Effective area: 2240640
Integration time: 683.318201 s. Average time per iteration = 1067.684689 ms
Integral 0 time = 684.528568 s
Kernel work group info:
Work group size = 512
Kernel local mem size = 64
Compile work group size = { 0, 0, 0 }
Keeping chunk boundaries as multiples of 1920
Range: { nu_steps = 640, mu_steps = 400, r_steps = 1400 }
Iteration area: 560000
Chunk estimate: 37
Num chunks: 37
Added area: 640
Effective area: 560640
Integration time: 311.750670 s. Average time per iteration = 487.110421 ms
Integral 1 time = 312.290463 s
Kernel work group info:
Work group size = 512
Kernel local mem size = 64
Compile work group size = { 0, 0, 0 }
Keeping chunk boundaries as multiples of 1920
Range: { nu_steps = 640, mu_steps = 400, r_steps = 1400 }
Iteration area: 560000
Chunk estimate: 37
Num chunks: 37
Added area: 640
Effective area: 560640
Failed to finish: CL_INVALID_COMMAND_QUEUE
Failed to run nu step: CL_INVALID_COMMAND_QUEUE
Integral 2 time = 51.434438 s
Failed to calculate integral 2
02:39:11 (3196): called boinc_finish

</stderr_txt>
]]>

The latest Nvidia drivers (280.26) seem to have some OpenCL issues. Try 275.33. Not sure if it's the driver's fault or mine yet.

The latest Nvidia drivers (280.26) seem to have some OpenCL issues. Try 275.33. Not sure if it's the driver's fault or mine yet.

Although going to 275.33 has helped, I now get more successful completions, I am still getting 50% error rate.

Stderr output

<core_client_version>6.12.33</core_client_version>
<![CDATA[
<message>
Incorrect function. (0x1) - exit code 1 (0x1)
</message>
<stderr_txt>
Error loading Lua script 'astronomy_parameters.txt': [string "number_parameters: 4..."]:1: '<name>' expected near '4'
Error reading astronomy parameters from file 'astronomy_parameters.txt'
Trying old parameters file
Using SSE3 path
Found 1 platform(s)
Platform 0 information:
Name: NVIDIA CUDA
Version: OpenCL 1.0 CUDA 4.0.1
Vendor: NVIDIA Corporation
Extensions: cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_d3d9_sharing cl_nv_d3d10_sharing cl_khr_d3d10_sharing cl_nv_d3d11_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll
Profile: FULL_PROFILE
Using device 0 on platform 0
Found 1 CL device(s)
Device GeForce GTX 260 (NVIDIA Corporation:0x10de) (CL_DEVICE_TYPE_GPU)
Driver version: 275.33
Version: OpenCL 1.0 CUDA
Compute capability: 1.3
Image support: CL_TRUE
Max compute units: 27
Clock frequency: 1408 Mhz
Global mem size: 883228672
Local mem size: 16384
Max const buf size: 65536
Double extension: MW_CL_KHR_FP64
Found a compute capability 1.3 device. Using -cl-nv-maxrregcount=32

Compiler flags:
-cl-mad-enable -cl-no-signed-zeros -cl-strict-aliasing -cl-finite-math-only -cl-nv-verbose -cl-nv-maxrregcount=32 -DDOUBLEPREC=1 -DFAST_H_PROB=1 -DAUX_BG_PROFILE=0 -DNSTREAM=2 -DCONVOLVE=120 -DR0=29.830428334172062 -DSUN_R0=8.500000000000000 -DQ_INV_SQR=9.412153878997035 -DUSE_IMAGES=0

Build status: CL_BUILD_SUCCESS
Build log:

ptxas info : Compiling entry function 'mu_sum_kernel' for 'sm_13'
ptxas info : Used 30 registers, 336+0 bytes lmem, 48+16 bytes smem, 22 bytes cmem[0], 60 bytes cmem[1], 4 bytes cmem[2], 4 bytes cmem[3], 4 bytes cmem[4], 4 bytes cmem[5], 4 bytes cmem[6]
Kernel work group info:
Work group size = 512
Kernel local mem size = 64
Compile work group size = { 0, 0, 0 }
Keeping chunk boundaries as multiples of 1728
Range: { nu_steps = 640, mu_steps = 1600, r_steps = 1400 }
Iteration area: 2240000
Chunk estimate: 163
Num chunks: 163
Added area: 1216
Effective area: 2241216
Integration time: 563.813601 s. Average time per iteration = 880.958752 ms
Integral 0 time = 564.994666 s
Likelihood time = 2.348108 s
Non-finite result
Failed to calculate likelihood
<background_integral> 0.000054630029497 </background_integral>
<stream_integral> 818.416014116782890 10.920919621834059 </stream_integral>
<background_likelihood> -1.#IND00000000000 </background_likelihood>
<stream_only_likelihood> 1.#QNAN0000000000 1.#QNAN0000000000 </stream_only_likelihood>
<search_likelihood> -3.324976656157873 </search_likelihood>
<search_application> milkywayathome_client separation 0.82 Windows x86_64 double OpenCL </search_application>
07:27:16 (4332): called boinc_finish

</stderr_txt>
]]>

Try 266.58 instead, CUDA 4.0 is the most likely culprit.

---

Try 266.58 instead, CUDA 4.0 is the most likely culprit.

Tried 266.58 and still getting errors, I really want to donate to this project, but only half my WUs seem to be successful.

Stderr output

<core_client_version>6.12.34</core_client_version>
<![CDATA[
<message>
Incorrect function. (0x1) - exit code 1 (0x1)
</message>
<stderr_txt>
Error loading Lua script 'astronomy_parameters.txt': [string "number_parameters: 4..."]:1: '<name>' expected near '4'
Error reading astronomy parameters from file 'astronomy_parameters.txt'
Trying old parameters file
Using SSE3 path
Found 1 platform(s)
Platform 0 information:
Name: NVIDIA CUDA
Version: OpenCL 1.0 CUDA 3.2.1
Vendor: NVIDIA Corporation
Extensions: cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_d3d9_sharing cl_nv_d3d10_sharing cl_khr_d3d10_sharing cl_nv_d3d11_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll
Profile: FULL_PROFILE
Using device 0 on platform 0
Found 2 CL device(s)
Device GeForce GTX 295 (NVIDIA Corporation:0x10de) (CL_DEVICE_TYPE_GPU)
Driver version: 266.58
Version: OpenCL 1.0 CUDA
Compute capability: 1.3
Image support: CL_TRUE
Max compute units: 30
Clock frequency: 1476 Mhz
Global mem size: 919994368
Local mem size: 16384
Max const buf size: 65536
Double extension: MW_CL_KHR_FP64
Found a compute capability 1.3 device. Using -cl-nv-maxrregcount=32

Compiler flags:
-cl-mad-enable -cl-no-signed-zeros -cl-strict-aliasing -cl-finite-math-only -cl-nv-verbose -cl-nv-maxrregcount=32 -DDOUBLEPREC=1 -DFAST_H_PROB=1 -DAUX_BG_PROFILE=0 -DNSTREAM=3 -DCONVOLVE=120 -DR0=8.000000000000000 -DSUN_R0=8.500000000000000 -DQ_INV_SQR=3.783304006281294 -DUSE_IMAGES=0

Build status: CL_BUILD_SUCCESS
Build log:

: Considering profile 'compute_13' for gpu='sm_13' in 'cuModuleLoadDataEx_4'
: Retrieving binary for 'cuModuleLoadDataEx_4', for gpu='sm_13', usage mode=' --verbose --maxrregcount 32 '
: Considering profile 'compute_13' for gpu='sm_13' in 'cuModuleLoadDataEx_4'
: Control flags for 'cuModuleLoadDataEx_4' disable search path
: Ptx binary found for 'cuModuleLoadDataEx_4', architecture='compute_13'
: Ptx compilation for 'cuModuleLoadDataEx_4', for gpu='sm_13', ocg options=' --verbose --maxrregcount 32 '
ptxas info : Compiling entry function 'mu_sum_kernel' for 'sm_13'
ptxas info : Used 31 registers, 484+0 bytes lmem, 48+16 bytes smem, 22 bytes cmem[0], 60 bytes cmem[1], 4 bytes cmem[2], 4 bytes cmem[3], 4 bytes cmem[4], 4 bytes cmem[5], 4 bytes cmem[6]
Kernel work group info:
Work group size = 512
Kernel local mem size = 64
Compile work group size = { 0, 0, 0 }
Keeping chunk boundaries as multiples of 1920
Range: { nu_steps = 640, mu_steps = 1600, r_steps = 1400 }
Iteration area: 2240000
Chunk estimate: 146
Num chunks: 146
Added area: 640
Effective area: 2240640
Failed to finish: CL_INVALID_COMMAND_QUEUE
Failed to run nu step: CL_INVALID_COMMAND_QUEUE
Integral 0 time = 66.026411 s
Failed to calculate integral 0
15:10:24 (3460): called boinc_finish

</stderr_txt>
]]>


Home | My Account | Message Boards


Copyright © 2011 AstroInformatics Group

I shifted to Collatz and 100% are error free under 266.58, but few are successful under milky way.

i use 266.58 no problem at all 4 x gtx 295

Still getting errors on milky way only. Win 7 Pro, Boinc ver 12.33,Nvidia 266.58.

It must me something on this machine. Other machines are fine and I changed video cards from a GTX 285 to a GTX 275 and I am still getting a lot of errors on milky way.

Stderr output

<core_client_version>6.12.33</core_client_version>
<![CDATA[
<message>
Incorrect function. (0x1) - exit code 1 (0x1)
</message>
<stderr_txt>
Error loading Lua script 'astronomy_parameters.txt': [string "number_parameters: 4..."]:1: '<name>' expected near '4'
Error reading astronomy parameters from file 'astronomy_parameters.txt'
Trying old parameters file
Using SSE3 path
Found 1 platform(s)
Platform 0 information:
Name: NVIDIA CUDA
Version: OpenCL 1.0 CUDA 3.2.1
Vendor: NVIDIA Corporation
Extensions: cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_d3d9_sharing cl_nv_d3d10_sharing cl_khr_d3d10_sharing cl_nv_d3d11_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll
Profile: FULL_PROFILE
Using device 0 on platform 0
Found 1 CL device(s)
Device GeForce GTX 275 (NVIDIA Corporation:0x10de) (CL_DEVICE_TYPE_GPU)
Driver version: 266.58
Version: OpenCL 1.0 CUDA
Compute capability: 1.3
Image support: CL_TRUE
Max compute units: 30
Clock frequency: 1404 Mhz
Global mem size: 915800064
Local mem size: 16384
Max const buf size: 65536
Double extension: MW_CL_KHR_FP64
Found a compute capability 1.3 device. Using -cl-nv-maxrregcount=32

Compiler flags:
-cl-mad-enable -cl-no-signed-zeros -cl-strict-aliasing -cl-finite-math-only -cl-nv-verbose -cl-nv-maxrregcount=32 -DDOUBLEPREC=1 -DFAST_H_PROB=1 -DAUX_BG_PROFILE=0 -DNSTREAM=2 -DCONVOLVE=120 -DR0=7.143159167262644 -DSUN_R0=8.500000000000000 -DQ_INV_SQR=2.825765961912116 -DUSE_IMAGES=0

Build status: CL_BUILD_SUCCESS
Build log:

: Considering profile 'compute_13' for gpu='sm_13' in 'cuModuleLoadDataEx_4'
: Retrieving binary for 'cuModuleLoadDataEx_4', for gpu='sm_13', usage mode=' --verbose --maxrregcount 32 '
: Considering profile 'compute_13' for gpu='sm_13' in 'cuModuleLoadDataEx_4'
: Control flags for 'cuModuleLoadDataEx_4' disable search path
: Ptx binary found for 'cuModuleLoadDataEx_4', architecture='compute_13'
: Ptx compilation for 'cuModuleLoadDataEx_4', for gpu='sm_13', ocg options=' --verbose --maxrregcount 32 '
ptxas info : Compiling entry function 'mu_sum_kernel' for 'sm_13'
ptxas info : Used 30 registers, 336+0 bytes lmem, 48+16 bytes smem, 22 bytes cmem[0], 60 bytes cmem[1], 4 bytes cmem[2], 4 bytes cmem[3], 4 bytes cmem[4], 4 bytes cmem[5], 4 bytes cmem[6]
Kernel work group info:
Work group size = 512
Kernel local mem size = 64
Compile work group size = { 0, 0, 0 }
Keeping chunk boundaries as multiples of 1920
Range: { nu_steps = 640, mu_steps = 1600, r_steps = 1400 }
Iteration area: 2240000
Chunk estimate: 146
Num chunks: 146
Added area: 640
Effective area: 2240640
Integration time: 511.316939 s. Average time per iteration = 798.932718 ms
Integral 0 time = 512.492557 s
star points: No such file or directory
Failed to read star points item
Failed to read star points file
Failed to calculate likelihood
<background_integral> 0.000710532391470 </background_integral>
<stream_integral> 780.534422071872200 1918.594803171270100 </stream_integral>
<background_likelihood> 1.#QNAN0000000000 </background_likelihood>
<stream_only_likelihood> 1.#QNAN0000000000 1.#QNAN0000000000 </stream_only_likelihood>
<search_likelihood> 1.#QNAN0000000000 </search_likelihood>
<search_application> milkywayathome_client separation 0.82 Windows x86_64 double OpenCL </search_application>
18:37:15 (4332): called boinc_finish

</stderr_txt>
]]>


Home | My Account | Message Boards


Copyright © 2011 AstroInformatics Group