Fix MIArchVgpr=1 + LSU=2 + SK and fix grouped gemm solution selection#345
Merged
Conversation
AlexBrownAMD
requested review from
bethune-bryant,
bstefanuk,
davidd-amd,
eidenyoshida,
mahmoodw,
pghysels and
yoichiyoshida
bnemanich
previously approved these changes
Jun 23, 2025
aliry95amd
previously approved these changes
Jun 23, 2025
KKyang
previously approved these changes
Jun 23, 2025
AlexBrownAMD
dismissed stale reviews from KKyang, aliry95amd, and bnemanich
via
c2f6613
jichangjichang
approved these changes
Jun 24, 2025
Contributor
|
gfx908 got tox errors. |
Merged
bnemanich
approved these changes
Jun 24, 2025
assistant-librarian Bot
pushed a commit
to ROCm/hipBLASLt
that referenced
this pull request
Jun 24, 2025
Fix MIArchVgpr=1 + LSU=2 + SK and fix grouped gemm solution selection (#345) Fix incorrect assembly code in the fixup step for stream-k when LSU=2 and MIArchVgpr=1 causing results to be reordered. This fixes issues with the test: *nightly_matmul_deepbench_f16_rf16_rf16_rf16_rf32_r_NN_576_128_12544_1_576_12544_0_576_576_1* Also fix an issue in grouped gemm solution selection that would cause a div by 0 fault. This fixes the test: *pre_checkin_matmul_groupedgemm_zero_n_f16_rf16_rf16_rf16_rf32_r_NT_127_127_127_1_127_127_0_127_127_1_GG7*
AlexBrownAMD
added a commit
to AlexBrownAMD/rocm-libraries
that referenced
this pull request
Jun 24, 2025
…ROCm#345) Fix incorrect assembly code in the fixup step for stream-k when LSU=2 and MIArchVgpr=1 causing results to be reordered. This fixes issues with the test: *nightly_matmul_deepbench_f16_rf16_rf16_rf16_rf32_r_NN_576_128_12544_1_576_12544_0_576_576_1* Also fix an issue in grouped gemm solution selection that would cause a div by 0 fault. This fixes the test: *pre_checkin_matmul_groupedgemm_zero_n_f16_rf16_rf16_rf16_rf32_r_NT_127_127_127_1_127_127_0_127_127_1_GG7*
AlexBrownAMD
added a commit
to AlexBrownAMD/rocm-libraries
that referenced
this pull request
Jun 27, 2025
…ROCm#345) Fix incorrect assembly code in the fixup step for stream-k when LSU=2 and MIArchVgpr=1 causing results to be reordered. This fixes issues with the test: *nightly_matmul_deepbench_f16_rf16_rf16_rf16_rf32_r_NN_576_128_12544_1_576_12544_0_576_576_1* Also fix an issue in grouped gemm solution selection that would cause a div by 0 fault. This fixes the test: *pre_checkin_matmul_groupedgemm_zero_n_f16_rf16_rf16_rf16_rf32_r_NT_127_127_127_1_127_127_0_127_127_1_GG7*
evetsso
pushed a commit
to evetsso/rocm-libraries
that referenced
this pull request
Dec 31, 2025
…ashot_091825 Merge rahulc/develop_snpashot_091825 to gfx1250 after solver migration PR#192
3 tasks
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
5 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.
Fix incorrect assembly code in the fixup step for stream-k when LSU=2 and MIArchVgpr=1 causing results to be reordered. This fixes issues with the test:
nightly_matmul_deepbench_f16_rf16_rf16_rf16_rf32_r_NN_576_128_12544_1_576_12544_0_576_576_1
Also fix an issue in grouped gemm solution selection that would cause a div by 0 fault. This fixes the test:
pre_checkin_matmul_groupedgemm_zero_n_f16_rf16_rf16_rf16_rf32_r_NT_127_127_127_1_127_127_0_127_127_1_GG7