Seti@Home optimized science apps and information
Optimized Seti@Home apps => Windows => GPU crunching => Topic started by: Raistmer on 28 Jan 2011, 05:38:48 pm
-
App requirements (the same as for released OpenCL ATI AstroPulse):
ATI Stream SDK 2.2 and higher (current version is 2.3) installed, Catalyst 10.7 and higher, HD4xxx(look know issues for more detailed info) and higher GPU.
EDIT: With latest Catalyst (10.12 APP) drivers SDK is unneeded.
Command line parameter that application supports
-period_iterations_num <N> splits single longest PulseFind kernes call on N calls
-period_iterations_num 1 (default value)
If you see lags in GUI or even driver restarts - add this parameter with value >1 (integer numbers).
-instances_per_device <N> allows to run N app instances per single device
-instances_per_device 1 (default value)
-hp will instruct application to rise its priority class to high. Useful when host under high non-BOINC loads. Also useful if BOINc client itself imposes high load on CPU.
app_info section:
<app>
<name>setiathome_enhanced</name>
</app>
<file_info>
<name>MB_6.10_win_SSE3_ATI_r177.exe</name>
<executable/>
</file_info>
<file_info>
<name>MultiBeam_Kernels.cl</name>
<executable/>
</file_info>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>610</version_num>
<platform>windows_intelx86</platform>
<avg_ncpus>0.05</avg_ncpus>
<max_ncpus>0.05</max_ncpus>
<plan_class>ati13ati</plan_class>
<cmdline>-period_iterations_num 2 -instances_per_device 1</cmdline>
<flops>20987654321</flops>
<file_ref>
<file_name>MB_6.10_win_SSE3_ATI_r177.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>MultiBeam_Kernels.cl</file_name>
<copy_file/>
</file_ref>
<coproc>
<type>ATI</type>
<count>1</count>
</coproc>
</app_version>
Known issues:
- App will not work correctly with HD43xx GPUs and possibly other models who have max workgroup size of 128 instead of 256 (this can be checked with CLInfo sample from SDK)
- Double check if your config (GPU+driver) has OpenCL support in case of mobility GPU. Ask ATi for OpenCL support if not.
If you want to use few app instances per GPU change -instances_per_device param value and don't forget to change <count> field in app_info too to inform BOINC.
-Currently HD5 version only partially compatible with HD6xxx GPUs, probably, due to unmature drivers. It tested as working on HD6970, but there are sporadic driver restarts possible.
Also, there is additional binary placed in archive: MB_6.10_win_SSE3_ATI_HD5_r177.exe
It uses same CL file as usual version and designed for HD5xxx and higher GPUs. I would like to say great THANK YOU to SubSpace who provided countless profiler data from his HD5870 while I worked on HD5xxx kernels.
I have no HD5xxx-compatible hardware and w/o his help this secondary build hardly appear.
Also, I thank all alpha and beta testers who took participation in app checking and whole Lunatics crew for continuous support.
-
Snif :(
Found out that the ATI 4550 has a Max Workgroup size less than 256...
Here is the output from ClInfo:
C:\Program Files\ATI Stream\bin\x86>CLInfo.exe
Number of platforms: 1
Platform Profile: FULL_PROFILE
Platform Version: OpenCL 1.1 ATI-Stream-v2.3 (451
)
Platform Name: ATI Stream
Platform Vendor: Advanced Micro Devices, Inc.
Platform Extensions: cl_khr_icd cl_amd_event_callbac
k cl_amd_offline_devices
Platform Name: ATI Stream
Number of devices: 2
Device Type: CL_DEVICE_TYPE_GPU
Device ID: 4098
Max compute units: 2
Max work items dimensions: 3
Max work items[0]: 128
Max work items[1]: 128
Max work items[2]: 128
Max work group size: 128
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: 0
Native vector width short: 0
Native vector width int: 0
Native vector width long: 0
Native vector width float: 0
Native vector width double: 0
Max clock frequency: 650Mhz
Address bits: 32
Max memory allocation: 134217728
Image support: No
Max size of kernel argument: 1024
Alignment (bits) of base address: 32768
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: 536870912
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Global
Local memory size: 16384
Kernel Preferred work group size multiple: 32
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: 01B4A40C
Name: ATI RV710
Vendor: Advanced Micro Devices, Inc.
Driver version: CAL 1.4.1016
Profile: FULL_PROFILE
Version: OpenCL 1.0 ATI-Stream-v2.3 (451
)
Extensions: cl_khr_gl_sharing cl_amd_device
_attribute_query
Also strangely, when I have my GeForce active (display monitor enabled) CLInfo stops after listing the Nvidia details:
C:\Program Files\ATI Stream\bin\x86>CLInfo.exe
Number of platforms: 2
Platform Profile: FULL_PROFILE
Platform Version: OpenCL 1.0 CUDA 3.2.1
Platform Name: NVIDIA CUDA
Platform Vendor: NVIDIA Corporation
Platform Extensions: cl_khr_byte_addressable_store c
l_khr_icd cl_khr_gl_sharing cl_nv_d3d9_sharing cl_nv_compiler_options cl_nv_devi
ce_attribute_query cl_nv_pragma_unroll
Platform Profile: FULL_PROFILE
Platform Version: OpenCL 1.1 ATI-Stream-v2.3 (451
)
Platform Name: ATI Stream
Platform Vendor: Advanced Micro Devices, Inc.
Platform Extensions: cl_khr_icd cl_amd_event_callbac
k cl_amd_offline_devices
Platform Name: NVIDIA CUDA
Number of devices: 1
Device Type: CL_DEVICE_TYPE_GPU
Device ID: 4318
Max compute units: 4
Max work items dimensions: 3
Max work items[0]: 512
Max work items[1]: 512
Max work items[2]: 64
Max work group size: 512
Preferred vector width char: 1
Preferred vector width short: 1
Preferred vector width int: 1
Preferred vector width long: 1
Preferred vector width float: 1
Preferred vector width double: 0
ERROR: clgetDeviceInfo(-30)
Could this be another 'friendly' behavior between Nvidia and AMD?
-
Max workgroup <256 issue will be fixed in next release.
About NV/ATi interoperability better to write on ATi (cause CLInfo is ATi stuff) forums. It's their job to fix.
I created thread on ATi forum: http://forums.amd.com/devforum/messageview.cfm?catid=390&threadid=147129&enterthread=y
-
Here is the output from ClInfo:
ERROR: clgetDeviceInfo(-30)
Could this be another 'friendly' behavior between Nvidia and AMD?
Please, try to run modded CLinfo version attached to this post
-
Modded CLinfo works fine:
Number of platforms: 2
Platform Profile: FULL_PROFILE
Platform Version: OpenCL 1.0 CUDA 3.2.1
Platform Name: NVIDIA CUDA
Platform Vendor: NVIDIA Corporation
Platform Extensions: cl_khr_byte_addressable_store c
l_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
Platform Profile: FULL_PROFILE
Platform Version: OpenCL 1.1 ATI-Stream-v2.3 (451
)
Platform Name: ATI Stream
Platform Vendor: Advanced Micro Devices, Inc.
Platform Extensions: cl_khr_icd cl_amd_event_callbac
k cl_amd_offline_devices cl_khr_d3d10_sharing
Platform Name: NVIDIA CUDA
Number of devices: 1
Device Type: CL_DEVICE_TYPE_GPU
Device ID: 4318
Max compute units: 7
Max work items dimensions: 3
Max work items[0]: 1024
Max work items[1]: 1024
Max work items[2]: 64
Max work group size: 1024
Preferred vector width char: 1
Preferred vector width short: 1
Preferred vector width int: 1
Preferred vector width long: 1
Preferred vector width float: 1
Preferred vector width double: 1
Max clock frequency: 1600Mhz
Address bits: 14757395255531667488
Max memory allocation: 260423680
Image support: Yes
Max number of images read arguments: 128
Max number of images write arguments: 8
Max image 2D width: 4096
Max image 2D height: 32768
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: 4352
Alignment (bits) of base address: 4096
Minimum alignment (bytes) for any datatype: 128
Single precision floating point capability
Denorms: Yes
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: Read/Write
Cache line size: 128
Cache size: 114688
Global memory size: 1041694720
Constant buffer size: 65536
Max number of constant args: 9
Local memory type: Scratchpad
Local memory size: 49152
Error correction support: 0
Profiling timer resolution: 1000
Device endianess: Little
Available: Yes
Compiler available: Yes
Execution capabilities:
Execute OpenCL kernels: Yes
Execute native function: No
Queue properties:
Out-of-Order: Yes
Profiling : Yes
Platform ID: 003E0D78
Name: GeForce GTX 460
Vendor: NVIDIA Corporation
Driver version: 266.58
Profile: FULL_PROFILE
Version: OpenCL 1.0 CUDA
Extensions: cl_khr_byte_addressable_store c
l_khr_icd cl_khr_gl_sharing cl_nv_d3d9_sharing cl_nv_d3d10_sharing cl_khr_d3d10_
sharing cl_nv_d3d11_sharing cl_nv_compiler_options cl_nv_device_attribute_query
cl_nv_pragma_unroll cl_khr_global_int32_base_atomics cl_khr_global_int32_extend
ed_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics c
l_khr_fp64
Platform Name: ATI Stream
Number of devices: 2
Device Type: CL_DEVICE_TYPE_GPU
Device ID: 4098
Max compute units: 10
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
Max clock frequency: 850Mhz
Address bits: 32
Max memory allocation: 134217728
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: 32768
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: 536870912
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Scratchpad
Local memory size: 32768
Error correction support: 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: 0344A40C
Name: Juniper
Vendor: Advanced Micro Devices, Inc.
Driver version: CAL 1.4.900
Profile: FULL_PROFILE
Version: OpenCL 1.1 ATI-Stream-v2.3 (451
)
Extensions: cl_khr_global_int32_base_atomic
s cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_lo
cal_int32_extended_atomics cl_khr_3d_image_writes cl_khr_byte_addressable_store
cl_khr_gl_sharing cl_amd_device_attribute_query cl_amd_printf cl_amd_media_ops c
l_amd_popcnt cl_khr_d3d10_sharing
Device Type: CL_DEVICE_TYPE_CPU
Device ID: 4098
Max compute units: 2
Max work items dimensions: 3
Max work items[0]: 1024
Max work items[1]: 1024
Max work items[2]: 1024
Max work group size: 1024
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
Max clock frequency: 4143Mhz
Address bits: 32
Max memory allocation: 536870912
Image support: No
Max size of kernel argument: 4096
Alignment (bits) of base address: 1024
Minimum alignment (bytes) for any datatype: 128
Single precision floating point capability
Denorms: Yes
Quiet NaNs: Yes
Round to nearest even: Yes
Round to zero: Yes
Round to +ve and infinity: Yes
IEEE754-2008 fused multiply-add: No
Cache type: Read/Write
Cache line size: 64
Cache size: 32768
Global memory size: 1073741824
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Global
Local memory size: 32768
Error correction support: 0
Profiling timer resolution: 247
Device endianess: Little
Available: Yes
Compiler available: Yes
Execution capabilities:
Execute OpenCL kernels: Yes
Execute native function: Yes
Queue properties:
Out-of-Order: No
Profiling : Yes
Platform ID: 0344A40C
Name: Intel(R) Core(TM)2 Duo CPU
E8500 @ 3.16GHz
Vendor: GenuineIntel
Driver version: 2.0
Profile: FULL_PROFILE
Version: OpenCL 1.1 ATI-Stream-v2.3 (451
)
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_byte_addressable_store cl_khr_gl_s
haring cl_ext_device_fission cl_amd_device_attribute_query cl_amd_media_ops cl_a
md_popcnt cl_amd_printf cl_khr_d3d10_sharing
Claggy
-
works as well for me with the modified CLinfo.
It lists all devices correctly.
C:\Program Files\ATI Stream\bin\x86>CLInfo_no_OCL1_1.exe
Number of platforms: 2
Platform Profile: FULL_PROFILE
Platform Version: OpenCL 1.0 CUDA 3.2.1
Platform Name: NVIDIA CUDA
Platform Vendor: NVIDIA Corporation
Platform Extensions: cl_khr_byte_addressable_store c
l_khr_icd cl_khr_gl_sharing cl_nv_d3d9_sharing cl_nv_compiler_options cl_nv_devi
ce_attribute_query cl_nv_pragma_unroll
Platform Profile: FULL_PROFILE
Platform Version: OpenCL 1.1 ATI-Stream-v2.3 (451
)
Platform Name: ATI Stream
Platform Vendor: Advanced Micro Devices, Inc.
Platform Extensions: cl_khr_icd cl_amd_event_callbac
k cl_amd_offline_devices
Platform Name: NVIDIA CUDA
Number of devices: 1
Device Type: CL_DEVICE_TYPE_GPU
Device ID: 4318
Max compute units: 4
Max work items dimensions: 3
Max work items[0]: 512
Max work items[1]: 512
Max work items[2]: 64
Max work group size: 512
Preferred vector width char: 1
Preferred vector width short: 1
Preferred vector width int: 1
Preferred vector width long: 1
Preferred vector width float: 1
Preferred vector width double: 0
Max clock frequency: 1500Mhz
Address bits: 14757395255531667488
Max memory allocation: 134217728
Image support: Yes
Max number of images read arguments: 128
Max number of images write arguments: 8
Max image 2D width: 4096
Max image 2D height: 32768
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: 4352
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: 268238848
Constant buffer size: 65536
Max number of constant args: 9
Local memory type: Scratchpad
Local memory size: 16384
Error correction support: 0
Profiling timer resolution: 1000
Device endianess: Little
Available: Yes
Compiler available: Yes
Execution capabilities:
Execute OpenCL kernels: Yes
Execute native function: No
Queue properties:
Out-of-Order: Yes
Profiling : Yes
Platform ID: 003974B8
Name: GeForce 8600 GTS
Vendor: NVIDIA Corporation
Driver version: 260.99
Profile: FULL_PROFILE
Version: OpenCL 1.0 CUDA
Extensions: cl_khr_byte_addressable_store c
l_khr_icd cl_khr_gl_sharing cl_nv_d3d9_sharing cl_nv_compiler_options cl_nv_devi
ce_attribute_query cl_nv_pragma_unroll cl_khr_global_int32_base_atomics cl_khr_
global_int32_extended_atomics
Platform Name: ATI Stream
Number of devices: 2
Device Type: CL_DEVICE_TYPE_GPU
Device ID: 4098
Max compute units: 2
Max work items dimensions: 3
Max work items[0]: 128
Max work items[1]: 128
Max work items[2]: 128
Max work group size: 128
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
Max clock frequency: 650Mhz
Address bits: 32
Max memory allocation: 134217728
Image support: No
Max size of kernel argument: 1024
Alignment (bits) of base address: 32768
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: 536870912
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Global
Local memory size: 16384
Error correction support: 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: 01C0A40C
Name: ATI RV710
Vendor: Advanced Micro Devices, Inc.
Driver version: CAL 1.4.1016
Profile: FULL_PROFILE
Version: OpenCL 1.0 ATI-Stream-v2.3 (451
)
Extensions: cl_khr_gl_sharing cl_amd_device
_attribute_query
Device Type: CL_DEVICE_TYPE_CPU
Device ID: 4098
Max compute units: 4
Max work items dimensions: 3
Max work items[0]: 1024
Max work items[1]: 1024
Max work items[2]: 1024
Max work group size: 1024
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
Max clock frequency: 3200Mhz
Address bits: 32
Max memory allocation: 536870912
Image support: No
Max size of kernel argument: 4096
Alignment (bits) of base address: 1024
Minimum alignment (bytes) for any datatype: 128
Single precision floating point capability
Denorms: Yes
Quiet NaNs: Yes
Round to nearest even: Yes
Round to zero: Yes
Round to +ve and infinity: Yes
IEEE754-2008 fused multiply-add: No
Cache type: Read/Write
Cache line size: 64
Cache size: 32768
Global memory size: 1073741824
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Global
Local memory size: 32768
Error correction support: 0
Profiling timer resolution: 0
Device endianess: Little
Available: Yes
Compiler available: Yes
Execution capabilities:
Execute OpenCL kernels: Yes
Execute native function: Yes
Queue properties:
Out-of-Order: No
Profiling : Yes
Platform ID: 01C0A40C
Name: Intel(R) Core(TM)2 Quad CPU
Q9450 @ 2.66GHz
Vendor: GenuineIntel
Driver version: 2.0
Profile: FULL_PROFILE
Version: OpenCL 1.1 ATI-Stream-v2.3 (451
)
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_byte_addressable_store cl_khr_gl_s
haring cl_ext_device_fission cl_amd_device_attribute_query cl_amd_media_ops cl_a
md_popcnt cl_amd_printf
C:\Program Files\ATI Stream\bin\x86>
-
And just to be different this new clInfo only picks up my 5670 and CPU no NV card:
E:\Downloads>CLInfo_no_OCL1_1.exe
Number of platforms: 1
Platform Profile: FULL_PROFILE
Platform Version: OpenCL 1.1 ATI-Stream-v2.3 (451
)
Platform Name: ATI Stream
Platform Vendor: Advanced Micro Devices, Inc.
Platform Extensions: cl_khr_icd cl_amd_event_callbac
k cl_amd_offline_devices cl_khr_d3d10_sharing
Platform Name: ATI Stream
Number of devices: 2
Device Type: CL_DEVICE_TYPE_GPU
Device ID: 4098
Max compute units: 5
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
Max clock frequency: 850Mhz
Address bits: 32
Max memory allocation: 134217728
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: 32768
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: 536870912
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Scratchpad
Local memory size: 32768
Error correction support: 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: 02D1A40C
Name: Redwood
Vendor: Advanced Micro Devices, Inc.
Driver version: CAL 1.4.1016
Profile: FULL_PROFILE
Version: OpenCL 1.1 ATI-Stream-v2.3 (451
)
Extensions: cl_khr_global_int32_base_atomic
s cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_lo
cal_int32_extended_atomics cl_khr_3d_image_writes cl_khr_byte_addressable_store
cl_khr_gl_sharing cl_amd_device_attribute_query cl_amd_printf cl_amd_media_ops c
l_amd_popcnt cl_khr_d3d10_sharing
Device Type: CL_DEVICE_TYPE_CPU
Device ID: 4098
Max compute units: 6
Max work items dimensions: 3
Max work items[0]: 1024
Max work items[1]: 1024
Max work items[2]: 1024
Max work group size: 1024
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
Max clock frequency: 3200Mhz
Address bits: 32
Max memory allocation: 536870912
Image support: No
Max size of kernel argument: 4096
Alignment (bits) of base address: 1024
Minimum alignment (bytes) for any datatype: 128
Single precision floating point capability
Denorms: Yes
Quiet NaNs: Yes
Round to nearest even: Yes
Round to zero: Yes
Round to +ve and infinity: Yes
IEEE754-2008 fused multiply-add: No
Cache type: Read/Write
Cache line size: 64
Cache size: 65536
Global memory size: 1073741824
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Global
Local memory size: 32768
Error correction support: 0
Profiling timer resolution: 319
Device endianess: Little
Available: Yes
Compiler available: Yes
Execution capabilities:
Execute OpenCL kernels: Yes
Execute native function: Yes
Queue properties:
Out-of-Order: No
Profiling : Yes
Platform ID: 02D1A40C
Name: AMD Phenom(tm) II X6 1090T Proc
essor
Vendor: AuthenticAMD
Driver version: 2.0
Profile: FULL_PROFILE
Version: OpenCL 1.1 ATI-Stream-v2.3 (451
)
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_byte_addressable_store cl_khr_gl_s
haring cl_ext_device_fission cl_amd_device_attribute_query cl_amd_media_ops cl_a
md_popcnt cl_amd_printf cl_khr_d3d10_sharing
-
And just to be different this new clInfo only picks up my 5670 and CPU no NV card:
Ghost, does GPU-Z or GpuCapsViewer report OpenCL support on your Nvidia GPU?
Claggy
-
Hi Claggy,
Yes openCL is checked in GPU-z, and the original CLInfo lists the 465 the 5670 and the CPU:
E:\Documents\ATI Stream\samples\opencl\bin\x86>CLInfo.exe
Number of platforms: 2
Platform Profile: FULL_PROFILE
Platform Version: OpenCL 1.1 ATI-Stream-v2.3 (451
)
Platform Name: ATI Stream
Platform Vendor: Advanced Micro Devices, Inc.
Platform Extensions: cl_khr_icd cl_amd_event_callback cl_amd
_offline_devices cl_khr_d3d10_sharing
Platform Profile: FULL_PROFILE
Platform Version: OpenCL 1.0 CUDA 3.2.1
Platform Name: NVIDIA CUDA
Platform Vendor: NVIDIA Corporation
Platform Extensions: cl_khr_byte_addressable_store cl_khr_ic
d 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_pr
agma_unroll
Platform Name: ATI Stream
Number of devices: 2
Device Type: CL_DEVICE_TYPE_GPU
Device ID: 4098
Max compute units: 5
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
Max clock frequency: 850Mhz
Address bits: 32
Max memory allocation: 134217728
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: 32768
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: 536870912
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Scratchpad
Local memory size: 32768
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: 0283A40C
Name: Redwood
Vendor: Advanced Micro Devices, Inc.
Driver version: CAL 1.4.1016
Profile: FULL_PROFILE
Version: OpenCL 1.1 ATI-Stream-v2.3 (451
)
Extensions: cl_khr_global_int32_base_atomic
s cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_lo
cal_int32_extended_atomics cl_khr_3d_image_writes cl_khr_byte_addressable_store
cl_khr_gl_sharing cl_amd_device_attribute_query cl_amd_printf cl_amd_media_ops c
l_amd_popcnt cl_khr_d3d10_sharing
Device Type: CL_DEVICE_TYPE_CPU
Device ID: 4098
Max compute units: 6
Max work items dimensions: 3
Max work items[0]: 1024
Max work items[1]: 1024
Max work items[2]: 1024
Max work group size: 1024
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
Max clock frequency: 3200Mhz
Address bits: 32
Max memory allocation: 536870912
Image support: No
Max size of kernel argument: 4096
Alignment (bits) of base address: 1024
Minimum alignment (bytes) for any datatype: 128
Single precision floating point capability
Denorms: Yes
Quiet NaNs: Yes
Round to nearest even: Yes
Round to zero: Yes
Round to +ve and infinity: Yes
IEEE754-2008 fused multiply-add: No
Cache type: Read/Write
Cache line size: 64
Cache size: 65536
Global memory size: 1073741824
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Global
Local memory size: 32768
Profiling timer resolution: 319
Device endianess: Little
Available: Yes
Compiler available: Yes
Execution capabilities:
Execute OpenCL kernels: Yes
Execute native function: Yes
Queue properties:
Out-of-Order: No
Profiling : Yes
Platform ID: 0283A40C
Name: AMD Phenom(tm) II X6 1090T Proc
essor
Vendor: AuthenticAMD
Driver version: 2.0
Profile: FULL_PROFILE
Version: OpenCL 1.1 ATI-Stream-v2.3 (451
)
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_byte_addressable_store cl_khr_gl_s
haring cl_ext_device_fission cl_amd_device_attribute_query cl_amd_media_ops cl_a
md_popcnt cl_amd_printf cl_khr_d3d10_sharing
Passed!
Platform Name: NVIDIA CUDA
Number of devices: 1
Device Type: CL_DEVICE_TYPE_GPU
Device ID: 4318
Max compute units: 11
Max work items dimensions: 3
Max work items[0]: 1024
Max work items[1]: 1024
Max work items[2]: 64
Max work group size: 1024
Preferred vector width char: 1
Preferred vector width short: 1
Preferred vector width int: 1
Preferred vector width long: 1
Preferred vector width float: 1
Preferred vector width double: 1
Max clock frequency: 1215Mhz
Address bits: 32
Max memory allocation: 260456448
Image support: Yes
Max number of images read arguments: 128
Max number of images write arguments: 8
Max image 2D width: 4096
Max image 2D height: 32768
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: 4352
Alignment (bits) of base address: 4096
Minimum alignment (bytes) for any datatype: 128
Single precision floating point capability
Denorms: Yes
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: Read/Write
Cache line size: 128
Cache size: 180224
Global memory size: 1041825792
Constant buffer size: 65536
Max number of constant args: 9
Local memory type: Scratchpad
Local memory size: 49152
Profiling timer resolution: 1000
Device endianess: Little
Available: Yes
Compiler available: Yes
Execution capabilities:
Execute OpenCL kernels: Yes
Execute native function: No
Queue properties:
Out-of-Order: Yes
Profiling : Yes
Platform ID: 003A0D88
Name: GeForce GTX 465
Vendor: NVIDIA Corporation
Driver version: 266.58
Profile: FULL_PROFILE
Version: OpenCL 1.0 CUDA
Extensions: cl_khr_byte_addressable_store c
l_khr_icd cl_khr_gl_sharing cl_nv_d3d9_sharing cl_nv_d3d10_sharing cl_khr_d3d10_
sharing cl_nv_d3d11_sharing cl_nv_compiler_options cl_nv_device_attribute_query
cl_nv_pragma_unroll cl_khr_global_int32_base_atomics cl_khr_global_int32_extend
ed_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics c
l_khr_fp64
Passed!
-
Hi Claggy,
Yes openCL is checked in GPU-z, and the original CLInfo lists the 465 the 5670 and the CPU:
Your platform order is the other way round to mine and benool's, probably the difference here,
[Edit: that reminds me, after looking at Benool's driver version, must try Cat 11.2]
Claggy
-
Your platform order is the other way round to mine and benool's, probably the difference here,
Claggy
If thats set by the order the cards are in the motherboard then that would make sense.
I have to have the ATI in slot 0 then the nvidia in slot 1 otherwise one or the other doesn't get picked up
IIRC you have yours the other way round; nvidia first then ATI?
Ghost
-
Your platform order is the other way round to mine and benool's, probably the difference here,
Claggy
If thats set by the order the cards are in the motherboard then that would make sense.
I have to have the ATI in slot 0 then the nvidia in slot 1 otherwise one or the other doesn't get picked up
IIRC you have yours the other way round; nvidia first then ATI?
Ghost
Yep, NV first, ATI 2nd, then i have to use that workaround to stop Boinc's ATI apps crashing, wonder since Benool's order is the same as mine,
and he's running CAL 1.4.1016, if that problem has been fixed in the latest drivers, Back soon,
Claggy
-
Your platform order is the other way round to mine and benool's, probably the difference here,
Claggy
If thats set by the order the cards are in the motherboard then that would make sense.
I have to have the ATI in slot 0 then the nvidia in slot 1 otherwise one or the other doesn't get picked up
IIRC you have yours the other way round; nvidia first then ATI?
Ghost
The Nvidia and ATI in the same host issue is now fixed with Cat 11.2, no workaround needed anymore, ;D ;D ;D
Microsoft Windows [Version 6.1.7600]
Copyright (c) 2009 Microsoft Corporation. All rights reserved.
C:\Users\Stephen>C:\Users\Stephen\Downloads\CLInfo_no_OCL1_1\CLInfo_no_OCL1_1.exe
Number of platforms: 2
Platform Profile: FULL_PROFILE
Platform Version: OpenCL 1.0 CUDA 3.2.1
Platform Name: NVIDIA CUDA
Platform Vendor: NVIDIA Corporation
Platform Extensions: cl_khr_byte_addressable_store c
l_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
Platform Profile: FULL_PROFILE
Platform Version: OpenCL 1.1 ATI-Stream-v2.3 (451
)
Platform Name: ATI Stream
Platform Vendor: Advanced Micro Devices, Inc.
Platform Extensions: cl_khr_icd cl_amd_event_callbac
k cl_amd_offline_devices cl_khr_d3d10_sharing
Platform Name: NVIDIA CUDA
Number of devices: 1
Device Type: CL_DEVICE_TYPE_GPU
Device ID: 4318
Max compute units: 7
Max work items dimensions: 3
Max work items[0]: 1024
Max work items[1]: 1024
Max work items[2]: 64
Max work group size: 1024
Preferred vector width char: 1
Preferred vector width short: 1
Preferred vector width int: 1
Preferred vector width long: 1
Preferred vector width float: 1
Preferred vector width double: 1
Max clock frequency: 1600Mhz
Address bits: 14757395255531667488
Max memory allocation: 260423680
Image support: Yes
Max number of images read arguments: 128
Max number of images write arguments: 8
Max image 2D width: 4096
Max image 2D height: 32768
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: 4352
Alignment (bits) of base address: 4096
Minimum alignment (bytes) for any datatype: 128
Single precision floating point capability
Denorms: Yes
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: Read/Write
Cache line size: 128
Cache size: 114688
Global memory size: 1041694720
Constant buffer size: 65536
Max number of constant args: 9
Local memory type: Scratchpad
Local memory size: 49152
Error correction support: 0
Profiling timer resolution: 1000
Device endianess: Little
Available: Yes
Compiler available: Yes
Execution capabilities:
Execute OpenCL kernels: Yes
Execute native function: No
Queue properties:
Out-of-Order: Yes
Profiling : Yes
Platform ID: 02A30C20
Name: GeForce GTX 460
Vendor: NVIDIA Corporation
Driver version: 266.58
Profile: FULL_PROFILE
Version: OpenCL 1.0 CUDA
Extensions: cl_khr_byte_addressable_store c
l_khr_icd cl_khr_gl_sharing cl_nv_d3d9_sharing cl_nv_d3d10_sharing cl_khr_d3d10_
sharing cl_nv_d3d11_sharing cl_nv_compiler_options cl_nv_device_attribute_query
cl_nv_pragma_unroll cl_khr_global_int32_base_atomics cl_khr_global_int32_extend
ed_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics c
l_khr_fp64
Platform Name: ATI Stream
Number of devices: 2
Device Type: CL_DEVICE_TYPE_GPU
Device ID: 4098
Max compute units: 10
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
Max clock frequency: 850Mhz
Address bits: 32
Max memory allocation: 134217728
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: 32768
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: 536870912
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Scratchpad
Local memory size: 32768
Error correction support: 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: 035BA40C
Name: Juniper
Vendor: Advanced Micro Devices, Inc.
Driver version: CAL 1.4.1016
Profile: FULL_PROFILE
Version: OpenCL 1.1 ATI-Stream-v2.3 (451
)
Extensions: cl_khr_global_int32_base_atomic
s cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_lo
cal_int32_extended_atomics cl_khr_3d_image_writes cl_khr_byte_addressable_store
cl_khr_gl_sharing cl_amd_device_attribute_query cl_amd_printf cl_amd_media_ops c
l_amd_popcnt cl_khr_d3d10_sharing
Device Type: CL_DEVICE_TYPE_CPU
Device ID: 4098
Max compute units: 2
Max work items dimensions: 3
Max work items[0]: 1024
Max work items[1]: 1024
Max work items[2]: 1024
Max work group size: 1024
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
Max clock frequency: 4143Mhz
Address bits: 32
Max memory allocation: 536870912
Image support: No
Max size of kernel argument: 4096
Alignment (bits) of base address: 1024
Minimum alignment (bytes) for any datatype: 128
Single precision floating point capability
Denorms: Yes
Quiet NaNs: Yes
Round to nearest even: Yes
Round to zero: Yes
Round to +ve and infinity: Yes
IEEE754-2008 fused multiply-add: No
Cache type: Read/Write
Cache line size: 64
Cache size: 32768
Global memory size: 1073741824
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Global
Local memory size: 32768
Error correction support: 0
Profiling timer resolution: 247
Device endianess: Little
Available: Yes
Compiler available: Yes
Execution capabilities:
Execute OpenCL kernels: Yes
Execute native function: Yes
Queue properties:
Out-of-Order: No
Profiling : Yes
Platform ID: 035BA40C
Name: Intel(R) Core(TM)2 Duo CPU
E8500 @ 3.16GHz
Vendor: GenuineIntel
Driver version: 2.0
Profile: FULL_PROFILE
Version: OpenCL 1.1 ATI-Stream-v2.3 (451
)
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_byte_addressable_store cl_khr_gl_s
haring cl_ext_device_fission cl_amd_device_attribute_query cl_amd_media_ops cl_a
md_popcnt cl_amd_printf cl_khr_d3d10_sharing
Claggy
-
The Nvidia and ATiI in the same host issue is now fixed with Cat 11.2, no workaround needed anymore, ;D ;D ;D
Claggy
I'll try swapping my cards round tomorrow then and see if that makes a difference to the new CLInfo
-
In my case, physical order is ATI first and NVidia in a lower slot.
On the drivers side Catalyst 11.2 (you were right) and ForceWare 260.99.
OpenCL checkbox is checked in GPUZ for both cards.
-
So what experiment with card swap gave?
Especially interesting what with host where NV GPU disappeared from output...
-
So what experiment with card swap gave?
Especially interesting what with host where NV GPU disappeared from output...
It was where you couldn't run any ATI Brook+ or ATI OpenCL apps standalone (with a Nvidia GPU fitted in the 1st slot),
all offline app runs Crashed, to do any of the Initial AP OpenCL testing i had to remove the Nvidia GPU,
and with Boinc 6.10.56 and earlier, the Boinc client crashed, Boinc 6.10.58 just detects the SIGGEV violation and ignores the ATI GPU,
i've had to use a workaround (renaming two ATI drivers) to get ATI & NV GPU's to work in Boinc,
Ghost and others have had their NV & ATI GPU's fitted the other way round, and it worked in that configuration apparently,
Claggy
-
And now both GPU positions work OK ?
With Cat 11.2 ?
-
And now both GPU positions work OK ?
With Cat 11.2 ?
Yep, it's fixed in my system with NV GPU in 1st slot, ATI in 2nd, not tried the other way round, or tried Cat 11.1,
I think Ghost already had it working the other way round,
Claggy
-
good day to you all,
my first try with MB ATI:
http://setiathome.berkeley.edu/result.php?resultid=1887858163
if could helps, good.
it tooks 26m 41s in a AMD 4770 - 512 RAM the machine infor is in the report.
-
Hi all,
just one small question, why is not a native version for systems running win x64??
(well and if they were optimized form AMD64 that would be great)
-
Seti isnt helped by running in 64 bit mode. Check their forums its been asked and answered there numerous times in the last year alone
-
Seti isnt helped by running in 64 bit mode. Check their forums its been asked and answered there numerous times in the last year alone
But, why not to have the software unified in the same architecture, could be a cosmetic thing, but a unifying way for the near future of x64 o.s. and software ???
it's still early (some more years to come with old build) but we should have been thinking about R.I.P. of x32 buildings
-
Seti isnt helped by running in 64 bit mode. Check their forums its been asked and answered there numerous times in the last year alone
But, why not to have the software unified in the same architecture, could be a cosmetic thing, but a unifying way for the near future of x64 o.s. and software ???
it's still early (some more years to come with old build) but we should have been thinking about R.I.P. of x32 buildings
The main reason - severely limited resourses. Most important - development time.
So only high priority improvements will go at resonable speed.
-
I do have a host, i7-2600+2x HD5870, here are some results, last validated, are ther more, f.i. cmd line
params, last validated MB. (http://setiweb.ssl.berkeley.edu/beta/workunit.php?wuid=3369451)
Also, ran out of AP work, done with rev.516 U=8;Blck=8196; Fetch 4096. Any Unroll above 10,
depending also of card-model, gives inmediat screen lag and is not necessary to keep GPU load
high, ffa_block and ffa_block_fetch, are equally important, but also card dependeble.
Whigh, I say cards, cause, in a lot of cases a 5850 is a 'stripped/or some cores not connected' version,
of the card.
Unfortunatly, GPU load stays low, 0%-31%- long tine zero, then 31%-61%-99%-11%-0.
Which also causes the 5870, to clock down, 850-1200MHz., to 500- 800 and goes back to 157-400,
until anost 'burst'comes along. Times between, those bursts, are also unpredictable(?!)
Also a screen-lag is there, too heavy, compaired to the GPU load, IMHO.
Is there yet another version, that needs, tuning,(testing?) . (Well also slowly recovering fron surgery)
I also still, use your AP ATI rev.516, but ran out of AP's. (Got hundreds or more, well I like them!)