deepseek-ai / deepseek-ai/DeepGEMM
TMA selection of get_best_configs in gemm.py
- Dominant language
- Cuda
- Stars
- 7.8k
- Forks
- 1.3k
- Avg merge
- 3d 7h
- Merged PRs (30d)
- 3
Description
```
for i in ('A', 'B') if best_block_m > best_block_n else ('B', 'A'):
if m >= 512 and is_multicast_legal[i]:
best_tma_multicast_config = (2, i == 'A')
break
```
when best_block_m <= best_block_n, I think need to use n instead of m to choose. Need to change to below:
```
for i in ('A', 'B') if best_block_m > best_block_n else ('B', 'A'):
dim_size = m if best_block_m > best_block_n else n
if dim_size >= 512 and is_multicast_legal[i]:
best_tma_multicast_config = (2, i == 'A')
break
```
Contributor guide
No contributing guide indexed for this repository
Research direction
Open gemm.py and locate get_best_configs and the shown TMA multicast-selection block. Trace how best_block_m, best_block_n, m, and n are used, then run the repository’s relevant GEMM or configuration tests if available. Done means the dimension checked for the 512 threshold matches the selected block direction when best_block_m is not greater than best_block_n.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- performance
- Issue type
- Bug
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Clearly specified
- Newbie friendliness
- 45/100