) Success ĬlCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT) Success (1) Platform Name CloverĬlCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU) No devices found in platformĬlCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU) Success (1) Platform Name CloverĬlCreateContextFromType(NULL, CL_DEVICE_TYPE_ACCELERATOR) No devices found in platformĬlCreateContextFromType(NULL, CL_DEVICE_TYPE_CUSTOM) No devices found in platformĬlCreateContextFromType(NULL, CL_DEVICE_TYPE_ALL) Success (1) Platform Name Clover ) No platformĬlGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL. Platform Name AMD Accelerated Parallel Processingĭevice Vendor Advanced Micro Devices, Inc.ĭevice Version OpenCL 1.2 AMD-APP (2671.3)ĬlGetPlatformInfo(NULL, CL_PLATFORM_NAME. Half-precision Floating-point support (cl_khr_fp16) Platform Version OpenCL 2.1 AMD-APP (2671.3)Ĭl_amd_event_callback cl_amd_offline_devicesĭevice Name AMD RAVEN (DRM 3.26.0, 4.18.0-16-generic, LLVM 7.0.0) Platform Vendor Advanced Micro Devices, Inc. After I run clinfo I get the following output: Do not decide one or another just because of the speed. If you are planing to write a GPU based app and just want to know wich one you should choose. There are not proper benchmarks, because simply can't compare different hardware and architectures. I have installed amdgpu-pro from the amd website and the AMD APP SDK 3.0. Generally speaking OpenCL and CUDA get the same performance.
My problem is that I'm not sure how opencl can recognize the cpu. I would like to run some OpenCL calculations with C++ on the CPU and GPU. I have a notebook with an AMD Ryzen 5 2500u (with integrated radeon vega 8 mobile GPU) processor and use Ubuntu 18.04.2.
0 kommentar(er)
