This repository was archived by the owner on Aug 11, 2023. It is now read-only.
Updating the matrix multiplication example #8
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Ruyk commented Nov 24, 2016
Ruyk commented - Host matrix multiplication deals with non-divisible sizes of matrix
- SYCL variant only accepts power-of-two matrix sizes
- Error correction is added to both host and sycl variants
added 4 commits October 12, 2016 16:01
This patch adds some licensing and documentation information for the FindComputeCpp module in order to easily re-distribute the FindComputeCpp file without the rest of the SDK.
* Host matrix multiplication deals with non-divisible sizes of matrix * SYCL variant only accepts power-of-two matrix sizes * Error correction is added to both host and sycl variants
| std::cout << " The order is : " << matSize << std::endl; | ||
| std::cout << " The blockSize is : " << blockSize << std::endl; | ||
| // Make sure the block size is not larger than the mat size | ||
| blockSize = min(matSize, blockSize); |
There was a problem hiding this comment.
This will be cl::sycl::min because of the using statement in this file
| } | ||
| if (!error) { | ||
| std::cout << "Success" << std::endl; | ||
| ; |
| } | ||
| } | ||
| std::cout << "GFLOPs: " << flops << std::endl; | ||
| std::cout << " Output " << std::endl; |
There was a problem hiding this comment.
This will be printed on a line by itself
DuncanMcBain suggested changes Nov 24, 2016
| // Testing | ||
| for (int i = 0; i < matSize; i++) | ||
| for (int j = 0; j < matSize; j++) { | ||
| if (std::fabs(MC[i * matSize + j] - MB[i * matSize + j]) > 1e-8) { |
There was a problem hiding this comment.
Can we replace this with something like the sample from here? Sounds pedantic, but I'm worried that for larger numbers (say ~100) that will be spuriously false, or that for small numbers it will be incorrectly true.
There was a problem hiding this comment.
This was there before my latest changes, so I rather not change it in this patch.
There was a problem hiding this comment.
Oh, it was? My bad, I'll add it myself then, rather than be a hypocrite! But in a separate merge request. Thanks very much!
added 2 commits November 24, 2016 16:34
* Clang-format matrix multiply * Added missing std:: to min
* Removed extra ;
DuncanMcBain approved these changes Nov 24, 2016
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
2 participants
Add this suggestion to a batch that can be applied as a single commit. This suggestion is invalid because no changes were made to the code. Suggestions cannot be applied while the pull request is closed. Suggestions cannot be applied while viewing a subset of changes. Only one suggestion per line can be applied in a batch. Add this suggestion to a batch that can be applied as a single commit. Applying suggestions on deleted lines is not supported. You must change the existing code in this line in order to create a valid suggestion. Outdated suggestions cannot be applied. This suggestion has been applied or marked resolved. Suggestions cannot be applied from pending reviews. Suggestions cannot be applied on multi-line comments. Suggestions cannot be applied while the pull request is queued to merge. Suggestion cannot be applied right now. Please check back later.