This document shows the current support matrix for the latest ComputeCpp Community Edition. The table below indicates the different operating systems and devices supported.
- A Yes in the Supported column means Codeplay has tested this internally and actively supports the platform combination.
- A No in the Supported column means Codeplay has tested that combination and we know the reasons for it not working with ComputeCpp.
- A Not tested in the Supported column means Codeplay has reports of users having support but we cannot reproduce it.
- A With limitations in the Supported column means that there are some limitations due to platform or driver issues.
Other combinations may work, but Codeplay does not actively support them. We are glad to receive feedback on other platforms that may work. Please, read carefully the different notes organised per platform for details on setting up ComputeCpp.
Table 1. Support Matrix
|Operating System||OpenCL Platform||Device||Supported||CL_DRIVER_VERSION||Notes|
|Ubuntu 16.04 64bit||AMD®||GPU||Not Tested||N/A||AMD-4, GCC-1|
|Ubuntu 16.04 64bit||Intel®||CPU||Yes||126.96.36.199||INTEL-1, GCC, INTEL-3|
|Ubuntu 16.04 64bit||Intel®||GPU||With limitations||19.13.12717||INTEL-1|
|Ubuntu 16.04 64bit||NVIDIA®||GPU||With limitations||CUDA 9.0.194||PTX Experimental Support-1|
|Ubuntu 18.04 64bit||Intel®||CPU||Yes||188.8.131.52||INTEL-1, GCC, INTEL-3|
|Ubuntu 18.04 64bit||Intel®||GPU||With limitations||19.13.12717||INTEL-1|
|CentOS 7.2 64 bit||Intel®||CPU||Yes||184.108.40.206||Intel-1, Intel-4|
|CentOS 7.2 64 bit||Intel®||GPU||With limitations||18.28.0||Intel-2|
[GCC-1] GCC Versions
Ubuntu 16.04 64bit version of ComputeCpp has been built with GCC 5.4
Ubuntu 18.04 64bit version of ComputeCpp has been built with GCC 7
[INTEL-1] Intel® OpenCL platform driver for CPU devices
The supported driver version is 18.1, and can be found at OpenCL™ Runtimes for Intel® Processors under the Intel® Xeon® Processors OR Intel® Core™ Processors Section.
[INTEL-2] Intel® OpenCL platform driver for GPU devices
The supported Intel® Neo driver can be found at Intel® Graphics Compute Runtime for OpenCL(TM). Replaces Beignet for Gen8 (Broadwell) and beyond (64-bit). Please make sure to read the Release Notes of the driver and the documentation regarding the installation to ensure the combination
[INTEL-3] Intel® CPU OpenCL Device SSE4.1 Requirement
The Intel® OpenCL CPU Runtime requires SSE4.1 support:
- If the Intel® OpenCL CPU device does not support SSE4.1, an OpenCL error will be thrown during execution.
- A typical error is a failure to create an OpenCL context (
- Beware that some virtualization environments do not expose SSE instructions by default.
- Please refer to the documentation of your virtualization solution for instructions on how to enable vectorization support.
[AMD-1] AMD® OpenCL Platform driver for GPU devices
The latest AMD® OpenCL Platform driver for GPU with SPIR support can be downloaded from AMD website. Ubuntu 16.04 does not support the fglrx drivers because the OS relies on newer kernels (version number higher than 3.19). Although the new amdgpu-pro drivers are available for Ubuntu 16.04, they only support SPIR 1.2 on the Fury series of GPU. If you need to use Vega+, please, contact AMD® regarding the status of their SPIR-V consumer. Community feedback reports that amdgpu-pro driver version 17.40 supports SPIR.
[AMD-2] AMD® OpenCL Platform SPIR support
The fglrx (Crimson Edition 15.12) driver only works for older Linux kernels (3.19 or lower). The amd-gpupro version of the driver for newer version of the Linux kernel only supports SPIR on the Fury series of GPUs.
[AMD-3] AMD® OpenCL Platform driver on Ubuntu
For Ubuntu, please download and install all of the packages from the download page, e.g.:
- Video Driver for Graphics Accelerators
- Minimal Video Driver for Graphics Accelerators (Non-X Support)
- Video Driver for Graphics Accelerators Devel Files (OGL, OCL)
[NVIDIA-1] NVIDIA® PTX Support
This release contains experimental PTX support. This allows ComputeCpp to work on top of NVIDIA GPUs. However, as this is experimental this platform doesn’t fully support all SYCL features yet. Use of half, images, and most OpenCL builtin functions will cause issues.
AMD is a registered trademark of Advanced Micro Devices, Inc. Intel is a trademark of Intel Corporation or its subsidiaries in the U.S. and/or other countries. NVIDIA and CUDA are registered trademarks of NVIDIA Corporation