I want to use the AMD A10-7850k to run some HSA(OpenCL2.0) sample.
I download and install the driver : amd-catalyst-omega-14.12-with-dotnet45-win8.1-64bit and 3.0-0-Beta AMD SDK.
When I rebuild the AMD SDK OpenCL sample (ex : SVMBinaryTreeSearch) with Visual Studio 2012 on windows 8.1.
Error msg output:
Unsupported device! Required CL_DEVICE_OPENCL_C_VERSION 2.0 or higher
We can see above that my clinfo GPU device version is OpenCL 2.0 AMD-APP (1642.5) definitely.
But clGetDeviceInfo output deviceVersion is "OpenCL 1.2 AMD-APP (1642.5)". It's weird.
My problem is like :opencl 2.0 borked for the second gpu on a 295x2 ?
But no solution in this thread.
Have any idea?
Thanks.
p.s.the sample not opencl2.0 (ex :HelloWorld ) I can rebuild and run.
clinfo output:
Number of platforms: | 1 | |||
Platform Profile: | FULL_PROFILE | |||
Platform Version: | OpenCL 2.0 AMD-APP (1642.5) | |||
Platform Name: | AMD Accelerated Parallel Processing | |||
Platform Vendor: | Advanced Micro Devices, Inc. | |||
Platform Extensions: | cl_khr_icd cl_khr_d3d10_sharing cl_khr_d3d11_sharing cl_khr_dx9_media_sharing cl_amd_event_callback cl_amd_offline_devices |
Platform Name: | AMD Accelerated Parallel Processing | ||||
Number of devices: | 2 | ||||
Device Type: | CL_DEVICE_TYPE_GPU | ||||
Vendor ID: | 1002h | ||||
Board name: | AMD Radeon(TM) R7 Graphics |
.......................................
Platform ID: | 00007FFE78086B60 | |||||
Name: | Spectre | |||||
Vendor: | Advanced Micro Devices, Inc. | |||||
Device OpenCL C version: | OpenCL C 2.0 | |||||
Driver version: | 1642.5 (VM) | |||||
Profile: | FULL_PROFILE | |||||
Version: | OpenCL 2.0 AMD-APP (1642.5) | |||||
Extensions: | cl_khr_fp64 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_int64_base_atomics cl_khr_int64_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_media_ops2 cl_amd_popcnt cl_khr_d3d10_sharing cl_khr_d3d11_sharing cl_khr_dx9_media_sharing cl_khr_image2d_from_buffer cl_khr_spir cl_khr_subgroups cl_khr_gl_event cl_khr_depth_images |
.......................................
Device Type: | CL_DEVICE_TYPE_CPU | ||||
Vendor ID: | 1002h | ||||
Board name: |
.......................................
Platform ID: | 00007FFE78086B60 | |||||
Name: | AMD A10-7850K Radeon R7, 12 Compute Cores 4C+8G | |||||
Vendor: | AuthenticAMD | |||||
Device OpenCL C version: | OpenCL C 1.2 | |||||
Driver version: | 1642.5 (sse2,avx,fma4) | |||||
Profile: | FULL_PROFILE | |||||
Version: | OpenCL 1.2 AMD-APP (1642.5) | |||||
Extensions: | cl_khr_fp64 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_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_3d_image_writes cl_khr_byte_addressable_store cl_khr_gl_sharing cl_ext_device_fission cl_amd_device_attribute_query cl_amd_vec3 cl_amd_printf cl_amd_media_ops cl_amd_media_ops2 cl_amd_popcnt cl_khr_d3d10_sharing cl_khr_spir cl_khr_gl_event |
Solved! Go to Solution.
Do you see same problem for all OpenCL2.0 sample? or only for SVMBinaryTreeSearch sample?
I don't think you have any issue with multi-GPU. As I can see from your clinfo, there are only two devices: 1 CPU and 1 GPU. Currently, on AMD platform, CPU devices are not detected as OpenCL 2.0 supported devices. So, you'll not be able to run any OpenCL2.0 sample on CPU devices. You should run them on your OpenCL 2.0 supported GPU device. So, my suggestion would to select the proper device before running the OpenCL2.0 sample.
Regards,
Do you see same problem for all OpenCL2.0 sample? or only for SVMBinaryTreeSearch sample?
I don't think you have any issue with multi-GPU. As I can see from your clinfo, there are only two devices: 1 CPU and 1 GPU. Currently, on AMD platform, CPU devices are not detected as OpenCL 2.0 supported devices. So, you'll not be able to run any OpenCL2.0 sample on CPU devices. You should run them on your OpenCL 2.0 supported GPU device. So, my suggestion would to select the proper device before running the OpenCL2.0 sample.
Regards,