- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Can anyone please explain to me how a system handles 2 implementations of opencl.
(For example: intel and nvidia implementations).
How appropriate backend compilers are used in the function clProgramBuild()?
(For example: intel and nvidia implementations).
How appropriate backend compilers are used in the function clProgramBuild()?
Link Copied
1 Reply
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hello Shweta Shree,
This is made possible by the OpenCL ICD. It is documented at: http://www.khronos.org/registry/cl/extensions/khr/cl_khr_icd.txt, here's a quote:
You can read more details in the linked page and by googling "opencl icd".
Eli
This is made possible by the OpenCL ICD. It is documented at: http://www.khronos.org/registry/cl/extensions/khr/cl_khr_icd.txt, here's a quote:
This extension defines a simple mechanism through which the Khronos installable client driver loader (ICD Loader) may expose multiple separate vendor installable client drivers (Vendor ICDs) for OpenCL. An application written against the ICD Loader will be able to access all cl_platform_ids exposed by all vendor implementations with the ICD Loader acting as a demultiplexor.
You can read more details in the linked page and by googling "opencl icd".
Eli
Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page