Skip to content

Batched GEMM for fp16#79

Merged
asroy merged 16 commits into
developfrom
batched_gemm
Feb 11, 2022
Merged

Batched GEMM for fp16#79
asroy merged 16 commits into
developfrom
batched_gemm

Conversation

@zjing14
Copy link
Copy Markdown
Contributor

@zjing14 zjing14 commented Feb 7, 2022

  • Added a batched GEMM kernel
  • Added instances for fp16 with all layouts

@zjing14 zjing14 requested a review from asroy February 8, 2022 00:14
@zjing14 zjing14 changed the title Batched GEMM for fp16 and NN layout Batched GEMM for fp16 Feb 9, 2022
Comment thread host/host_tensor/include/host_gemm.hpp Outdated
@zjing14 zjing14 requested a review from asroy February 10, 2022 02:25
@asroy asroy merged commit b53e9d0 into develop Feb 11, 2022
@junliume junliume deleted the batched_gemm branch October 21, 2023 06:09
assistant-librarian Bot pushed a commit that referenced this pull request Mar 27, 2026
[CK][CK_TILE] Fix CTest parsing to handle all test number
 formats (#5880)

## Motivation
Fix a bug in the smart-build --ctest-only filter that was incorrectly
excluding tests with numbers less than 100.

## Technical Details
The issue was caused by CTest formatting test numbers with variable
spacing based on the number of digits:
  - "Test   `#1`: name (3 spaces for tests 1-9)"
  - "Test  `#79`: name (2 spaces for tests 10-99)"
  - "Test `#100`: name (1 space for tests 100+)"

The previous code used `line.strip().startswith("Test #")` which only
matched tests with a single space (i.e., test numbers >= 100).

This caused tests like ck_tile_unit_sequence (Test #79) to be excluded
from smart-build test selection, resulting in CTest failures when the
binary wasn't built.

Solution: Replace string matching with a regex pattern that handles
all spacing variations: r'^\s*Test\s+#\d+:\s*(.+)$'

## Test Plan
Tested with test numbers from 1 to 12345.

## Test Result
  - Before: 48 tests selected (only tests #100+)
  - After: 146 tests selected (all CTest-registered tests)

## Submission Checklist

- [x ] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
hyoon1 pushed a commit to hyoon1/composable_kernel that referenced this pull request Mar 29, 2026
…880)

## Motivation
Fix a bug in the smart-build --ctest-only filter that was incorrectly
excluding tests with numbers less than 100.

## Technical Details
The issue was caused by CTest formatting test numbers with variable
spacing based on the number of digits:
  - "Test   `ROCm#1`: name (3 spaces for tests 1-9)"
  - "Test  `ROCm#79`: name (2 spaces for tests 10-99)"
  - "Test `ROCm#100`: name (1 space for tests 100+)"

The previous code used `line.strip().startswith("Test #")` which only
matched tests with a single space (i.e., test numbers >= 100).

This caused tests like ck_tile_unit_sequence (Test ROCm#79) to be excluded
from smart-build test selection, resulting in CTest failures when the
binary wasn't built.

Solution: Replace string matching with a regex pattern that handles
all spacing variations: r'^\s*Test\s+#\d+:\s*(.+)$'

## Test Plan
Tested with test numbers from 1 to 12345.

## Test Result
  - Before: 48 tests selected (only tests ROCm#100+)
  - After: 146 tests selected (all CTest-registered tests)



## Submission Checklist

- [x ] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants