Add NVIDIA A100 optimized meta parameters to bsr_dense_mm #111760
Closed
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
[ghstack-poisoned]
This was referenced Oct 22, 2023
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/111760
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit a9ece3f with merge base 57c7aa1 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
pearu
added
module: performance
As in the title. The figures below illustrate the performance differences of bsr_dense_mm with optimized parameters and bsr_dense_mm with default parameters (GPU: NVIDIA A100-SXM4-80GB). The first figure represents the performance equilibrium point in BSR tensor sparsity at which value bsr_dense_mm have the same performance characteristics as torch.matmul. The second figure represents speedups from using optimized meta parameters in bsr_dense_mm at its performance equilibrium points with respect to bsr_dense_mm with default meta parameters. In sum, this PR speeds up `bsr_dense_mm` about 50 % depending on the bsr tensor shape and blocksize and lowers the performance equilibrium points of BSR tensor sparsity and strided tensor for matmul operations. <img src="https://github.com/pytorch/pytorch/assets/402156/6fe9d35f-dd21-4aa0-bb01-6ee257254453" width="48%"> <img src="https://github.com/pytorch/pytorch/assets/402156/506921c6-3770-4209-ad3d-498d2ae4989d" width="48%"> [ghstack-poisoned]
cpuhrsch
approved these changes
Oct 23, 2023
xuhancn
pushed a commit
to xuhancn/pytorch
that referenced
this pull request
Nov 7, 2023
…1760) As in the title. The figures below illustrate the performance differences of bsr_dense_mm with optimized parameters and bsr_dense_mm with default parameters (GPU: NVIDIA A100-SXM4-80GB). The first figure represents the performance equilibrium point in BSR tensor sparsity at which value bsr_dense_mm have the same performance characteristics as torch.matmul. The second figure represents speedups from using optimized meta parameters in bsr_dense_mm at its performance equilibrium points with respect to bsr_dense_mm with default meta parameters. In sum, this PR speeds up `bsr_dense_mm` about 50 % depending on the bsr tensor shape and blocksize and lowers the performance equilibrium points of BSR tensor sparsity and strided tensor for matmul operations. <img src="https://github.com/pytorch/pytorch/assets/402156/6fe9d35f-dd21-4aa0-bb01-6ee257254453" width="48%"> <img src="https://github.com/pytorch/pytorch/assets/402156/506921c6-3770-4209-ad3d-498d2ae4989d" width="48%"> Pull Request resolved: pytorch#111760 Approved by: https://github.com/cpuhrsch ghstack dependencies: pytorch#110396, pytorch#111470, pytorch#111489
xuhancn
pushed a commit
to xuhancn/pytorch
that referenced
this pull request
Nov 7, 2023
pytorch#111796) Pull Request resolved: pytorch#111796 Approved by: https://github.com/cpuhrsch ghstack dependencies: pytorch#110396, pytorch#111470, pytorch#111489, pytorch#111760
Skylion007
pushed a commit
to Skylion007/pytorch
that referenced
this pull request
Nov 14, 2023
…1760) As in the title. The figures below illustrate the performance differences of bsr_dense_mm with optimized parameters and bsr_dense_mm with default parameters (GPU: NVIDIA A100-SXM4-80GB). The first figure represents the performance equilibrium point in BSR tensor sparsity at which value bsr_dense_mm have the same performance characteristics as torch.matmul. The second figure represents speedups from using optimized meta parameters in bsr_dense_mm at its performance equilibrium points with respect to bsr_dense_mm with default meta parameters. In sum, this PR speeds up `bsr_dense_mm` about 50 % depending on the bsr tensor shape and blocksize and lowers the performance equilibrium points of BSR tensor sparsity and strided tensor for matmul operations. <img src="https://github.com/pytorch/pytorch/assets/402156/6fe9d35f-dd21-4aa0-bb01-6ee257254453" width="48%"> <img src="https://github.com/pytorch/pytorch/assets/402156/506921c6-3770-4209-ad3d-498d2ae4989d" width="48%"> Pull Request resolved: pytorch#111760 Approved by: https://github.com/cpuhrsch ghstack dependencies: pytorch#110396, pytorch#111470, pytorch#111489
Skylion007
pushed a commit
to Skylion007/pytorch
that referenced
this pull request
Nov 14, 2023
pytorch#111796) Pull Request resolved: pytorch#111796 Approved by: https://github.com/cpuhrsch ghstack dependencies: pytorch#110396, pytorch#111470, pytorch#111489, pytorch#111760
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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.
As in the title.
The figures below illustrate the performance differences of bsr_dense_mm with optimized parameters and bsr_dense_mm with default parameters (GPU: NVIDIA A100-SXM4-80GB). The first figure represents the performance equilibrium point in BSR tensor sparsity at which value bsr_dense_mm have the same performance characteristics as torch.matmul. The second figure represents speedups from using optimized meta parameters in bsr_dense_mm at its performance equilibrium points with respect to bsr_dense_mm with default meta parameters.
In sum, this PR speeds up
bsr_dense_mmabout 50 % depending on the bsr tensor shape and blocksize and lowers the performance equilibrium points of BSR tensor sparsity and strided tensor for matmul operations.Stack from ghstack (oldest at bottom):