Run Example 7 (GEMM All-Scatter) and report benchmark results - #29
Draft
JoseSantosAMD with Copilot wants to merge 1 commit into
Draft
Run Example 7 (GEMM All-Scatter) and report benchmark results#29JoseSantosAMD with Copilot wants to merge 1 commit into
JoseSantosAMD with Copilot wants to merge 1 commit into
Conversation
Draft
Copilot
AI
changed the title
[WIP] Add intellikit to project
Run Example 7 (GEMM All-Scatter) and report benchmark results
Mar 4, 2026
Copilot stopped work on behalf of
JoseSantosAMD due to an error
March 4, 2026 13:30
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Ran Example 7 (
07_gemm_all_scatter) on 2 AMD Radeon GPU ranks to validate correctness and measure performance of the fused persistent GEMM + all-scatter kernel.Results
Default dimensions — M=8192, N=4608, K=36864, fp16, 2 ranks (304 CUs each):
Smoke test — M=4096, N=4608, K=4096, fp16:
The kernel fuses matrix multiply with cross-GPU scatter in a single persistent kernel — each rank computes its N-shard and scatters results to peers' global buffers in-flight, with no separate communication phase.
✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.