forked from triton-lang/triton
-
Notifications
You must be signed in to change notification settings - Fork 29
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add performance reference for important matmul kernels #642
Open
zhanglx13
wants to merge
5
commits into
main_perf
Choose a base branch
from
perf_ref
base: main_perf
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
+346
−10
Open
Changes from 1 commit
Commits
Show all changes
5 commits
Select commit
Hold shift + click to select a range
e5601b2
Add performance reference for important matmul kernels
zhanglx13 92a8ae4
add config for fp16
zhanglx13 223a5ab
Add a script to process json files
zhanglx13 995144f
Recover/detect abnormal traces
zhanglx13 d47adce
Fix mfma cnt
zhanglx13 File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains 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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,14 @@ | ||
trans,M,N,K,TFLOPS,us | ||
TN,4864,4096,4096,467.39,349.19 | ||
TN,4864,4096,4160,567.17,292.26 | ||
TN,4864,4096,4224,557.49,301.90 | ||
TN,4864,4096,4288,569.55,299.99 | ||
TN,4864,4096,4097,501.58,325.47 | ||
TN,4864,4096,4098,491.96,331.92 | ||
TN,4864,4096,4100,503.51,324.46 | ||
TN,4864,4096,4104,515.70,317.10 | ||
TN,4864,4096,4112,525.66,311.70 | ||
TN,4864,8192,4096,519.95,627.79 | ||
TN,4864,8192,4160,579.14,572.43 | ||
TN,4864,8192,8192,543.30,1201.6 | ||
TN,4864,8192,8256,563.43,1167.7 |
This file contains 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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,18 @@ | ||
# M // BLOCK_M * N // BLOCK_N % 304 == 0 | ||
## 1 workgroup / CU | ||
- {'M': 4864, 'N': 4096, 'K': 4096, 'rowMajorA': 'T', 'rowMajorB': 'N', 'BLOCK_SIZE_M': 256, 'BLOCK_SIZE_N': 256, 'BLOCK_SIZE_K': 64, 'GROUP_SIZE_M': 4, 'SPLIT_K': 1, 'num_warps': 8, 'num_stages': 0, 'waves_per_eu': 0, 'matrix_instr_nonkdim': 16, 'kpack': 2} | ||
- {'M': 4864, 'N': 4096, 'K': 4160, 'rowMajorA': 'T', 'rowMajorB': 'N', 'BLOCK_SIZE_M': 256, 'BLOCK_SIZE_N': 256, 'BLOCK_SIZE_K': 64, 'GROUP_SIZE_M': 4, 'SPLIT_K': 1, 'num_warps': 8, 'num_stages': 0, 'waves_per_eu': 0, 'matrix_instr_nonkdim': 16, 'kpack': 2} | ||
- {'M': 4864, 'N': 4096, 'K': 4224, 'rowMajorA': 'T', 'rowMajorB': 'N', 'BLOCK_SIZE_M': 256, 'BLOCK_SIZE_N': 256, 'BLOCK_SIZE_K': 64, 'GROUP_SIZE_M': 4, 'SPLIT_K': 1, 'num_warps': 8, 'num_stages': 0, 'waves_per_eu': 0, 'matrix_instr_nonkdim': 16, 'kpack': 2} | ||
- {'M': 4864, 'N': 4096, 'K': 4288, 'rowMajorA': 'T', 'rowMajorB': 'N', 'BLOCK_SIZE_M': 256, 'BLOCK_SIZE_N': 256, 'BLOCK_SIZE_K': 64, 'GROUP_SIZE_M': 4, 'SPLIT_K': 1, 'num_warps': 8, 'num_stages': 0, 'waves_per_eu': 0, 'matrix_instr_nonkdim': 16, 'kpack': 2} | ||
## 1 workgroup / CU masked loadK | ||
- {'M': 4864, 'N': 4096, 'K': 4097, 'rowMajorA': 'T', 'rowMajorB': 'N', 'BLOCK_SIZE_M': 256, 'BLOCK_SIZE_N': 256, 'BLOCK_SIZE_K': 32, 'GROUP_SIZE_M': 4, 'SPLIT_K': 1, 'num_warps': 8, 'num_stages': 0, 'waves_per_eu': 0, 'matrix_instr_nonkdim': 16, 'kpack': 2} | ||
- {'M': 4864, 'N': 4096, 'K': 4098, 'rowMajorA': 'T', 'rowMajorB': 'N', 'BLOCK_SIZE_M': 256, 'BLOCK_SIZE_N': 256, 'BLOCK_SIZE_K': 32, 'GROUP_SIZE_M': 4, 'SPLIT_K': 1, 'num_warps': 8, 'num_stages': 0, 'waves_per_eu': 0, 'matrix_instr_nonkdim': 16, 'kpack': 2} | ||
- {'M': 4864, 'N': 4096, 'K': 4100, 'rowMajorA': 'T', 'rowMajorB': 'N', 'BLOCK_SIZE_M': 256, 'BLOCK_SIZE_N': 256, 'BLOCK_SIZE_K': 32, 'GROUP_SIZE_M': 4, 'SPLIT_K': 1, 'num_warps': 8, 'num_stages': 0, 'waves_per_eu': 0, 'matrix_instr_nonkdim': 16, 'kpack': 2} | ||
- {'M': 4864, 'N': 4096, 'K': 4104, 'rowMajorA': 'T', 'rowMajorB': 'N', 'BLOCK_SIZE_M': 256, 'BLOCK_SIZE_N': 256, 'BLOCK_SIZE_K': 32, 'GROUP_SIZE_M': 4, 'SPLIT_K': 1, 'num_warps': 8, 'num_stages': 0, 'waves_per_eu': 0, 'matrix_instr_nonkdim': 16, 'kpack': 2} | ||
- {'M': 4864, 'N': 4096, 'K': 4112, 'rowMajorA': 'T', 'rowMajorB': 'N', 'BLOCK_SIZE_M': 256, 'BLOCK_SIZE_N': 256, 'BLOCK_SIZE_K': 32, 'GROUP_SIZE_M': 4, 'SPLIT_K': 1, 'num_warps': 8, 'num_stages': 0, 'waves_per_eu': 0, 'matrix_instr_nonkdim': 16, 'kpack': 2} | ||
|
||
## 2 workgroups / CU | ||
- {'M': 4864, 'N': 8192, 'K': 4096, 'rowMajorA': 'T', 'rowMajorB': 'N', 'BLOCK_SIZE_M': 256, 'BLOCK_SIZE_N': 256, 'BLOCK_SIZE_K': 64, 'GROUP_SIZE_M': 4, 'SPLIT_K': 1, 'num_warps': 8, 'num_stages': 0, 'waves_per_eu': 0, 'matrix_instr_nonkdim': 16, 'kpack': 2} | ||
- {'M': 4864, 'N': 8192, 'K': 4160, 'rowMajorA': 'T', 'rowMajorB': 'N', 'BLOCK_SIZE_M': 256, 'BLOCK_SIZE_N': 256, 'BLOCK_SIZE_K': 64, 'GROUP_SIZE_M': 4, 'SPLIT_K': 1, 'num_warps': 8, 'num_stages': 0, 'waves_per_eu': 0, 'matrix_instr_nonkdim': 16, 'kpack': 2} | ||
- {'M': 4864, 'N': 8192, 'K': 8192, 'rowMajorA': 'T', 'rowMajorB': 'N', 'BLOCK_SIZE_M': 256, 'BLOCK_SIZE_N': 256, 'BLOCK_SIZE_K': 64, 'GROUP_SIZE_M': 4, 'SPLIT_K': 1, 'num_warps': 8, 'num_stages': 0, 'waves_per_eu': 0, 'matrix_instr_nonkdim': 16, 'kpack': 2} | ||
- {'M': 4864, 'N': 8192, 'K': 8256, 'rowMajorA': 'T', 'rowMajorB': 'N', 'BLOCK_SIZE_M': 256, 'BLOCK_SIZE_N': 256, 'BLOCK_SIZE_K': 64, 'GROUP_SIZE_M': 4, 'SPLIT_K': 1, 'num_warps': 8, 'num_stages': 0, 'waves_per_eu': 0, 'matrix_instr_nonkdim': 16, 'kpack': 2} |
This file contains 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
This file contains 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
Oops, something went wrong.
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
what are the purposes of this database file ? are they used to benchmark against the ref.csv ? if that's the case, what if the parameters changed, e.g GROUP_SIZE_M change from 4 to 8 ?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
we may need other database file format if this is a daily/per commit tasks ?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This database.yaml is used as the current best perf config. If you have an optimization that can improve the best perf number and requires a different config, we should update the database.
The main purpose is to catch regression.