I have a notebook with an AMD Ryzen 5 2500U (with integrated Radeon Vega 8 mobile GPU) processor and use Ubuntu 18.04.2. I would like to run some OpenCL calculations with C++ on the CPU and GPU. My problem is that I'm not sure how OpenCL can recognize the CPU.
I have installed AMDGPU-PRO from the AMD website and the AMD APP SDK 3.0. After I run clinfo I get the following output:
Number of platforms 2
Platform Name Clover
Platform Vendor Mesa
Platform Version OpenCL 1.1 Mesa 18.2.8
Platform Profile FULL_PROFILE
Platform Extensions cl_khr_icd
Platform Extensions function suffix MESA
Platform Name AMD Accelerated
Parallel Processing
Platform Vendor Advanced Micro Devices, Inc.
Platform Version OpenCL 2.1 AMD-APP (2671.3)
Platform Profile FULL_PROFILE
Platform Extensions cl_khr_icd cl_amd_event_callback cl_amd_offline_devices
Platform Host timer resolution 1ns
Platform Extensions function suffix AMD
Platform Name Clover
Number of devices 1
Device Name AMD RAVEN (DRM 3.26.0, 4.18.0-16-generic, LLVM 7.0.0)
Device Vendor AMD
Device Vendor ID 0x1002
Device Version OpenCL 1.1 Mesa 18.2.8
Driver Version 18.2.8
Device OpenCL C Version OpenCL C 1.1
Device Type GPU
Device Profile FULL_PROFILE
Device Available Yes
Compiler Available Yes
Max compute units 8
Max clock frequency 1100MHz
Max work item dimensions 3
Max work item sizes 256x256x256
Max work group size 256
Preferred work group size multiple 64
Preferred / native vector sizes
char 16 / 16
short 8 / 8
int 4 / 4
long 2 / 2
half 8 / 8 (cl_khr_fp16)
float 4 / 4
double 2 / 2 (cl_khr_fp64)
Half-precision Floating-point support (cl_khr_fp16)
...
Platform Name AMD Accelerated Parallel Processing
Number of devices 1
Device Name gfx902
Device Vendor Advanced Micro Devices, Inc.
Device Vendor ID 0x1002
Device Version OpenCL 1.2 AMD-APP (2671.3)
Driver Version 2671.3 (PAL,HSAIL)
Device OpenCL C Version OpenCL C 1.2
Device Type GPU
Device Board Name (AMD) Unknown AMD GPU
Device Topology (AMD) PCI-E, 05:00.0
Device Profile FULL_PROFILE
.......
NULL platform behavior
clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...) No platform
clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...) No platform
clCreateContext(NULL, ...) [default] No platform
clCreateContext(NULL, ...) [other] Success [MESA]
clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT) Success (1)
Platform Name Clover
Device Name AMD RAVEN (DRM 3.26.0, 4.18.0-16-generic, LLVM 7.0.0)
clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU) No devices found in platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU) Success (1)
Platform Name Clover
Device Name AMD RAVEN (DRM 3.26.0, 4.18.0-16-generic, LLVM 7.0.0)
clCreateContextFromType(NULL, CL_DEVICE_TYPE_ACCELERATOR) No devices found in platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_CUSTOM) No devices found in platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_ALL) Success (1)
Platform Name Clover
Device Name AMD RAVEN (DRM 3.26.0, 4.18.0-16-generic, LLVM 7.0.0)
The first platform Clover with Device AMD RAVEN (DRM 3.26.0, 4.18.0-16-generic, LLVM 7.0.0) has the Device type GPU and the second platform with Device gfx902 also seems to be the GPU of my system.
So my question is: What do I have to install so that OpenCL also recognizes the CPU of my system?
Thanks for helping!
Using the CPU with OpenCL requires a CPU-capable OpenCL implementation, naturally. In particular POCL should be available. AMD seems to have abandoned their CPU OpenCL implementation, and Intel claims theirs is only for their brand of processors.
By the way, mixing OpenCL implementations for the same device (such as Clover and APP) may give surprising results should something try to autodistribute work to all devices. It should be fine if you can specify which devices to use.