Optimize FBGEMM Triton MX4 Dequantize #2837
Closed
Conversation
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
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
|
This pull request was exported from Phabricator. Differential Revision: D59661776 |
|
This pull request was exported from Phabricator. Differential Revision: D59661776 |
jwfromm
added a commit
to jwfromm/FBGEMM
that referenced
this pull request
Jul 12, 2024
Summary: Pull Request resolved: pytorch#2837 We previously had to use python to unravel values from exponents and feed them to triton as two separate tensors. This introduced a lot of overhead as it introduced large copies. This diff does a bunch of fancy indexing to directly operate on a tensor with mixed elements and exponents. The result is that triton dequantize is now slightly faster than the cuda kernel. My hope is that this allows us to standardize on a single implementation. I think we could probably do something similar during quantize to get a significant speedup as well. ``` INFO:root:input size: 1073741824 group size: 32 INFO:root:Start to benchmark ... INFO:root:Start to benchmark ... input_size=1073741824 MX4 quantized time per iter: 7563us input_size=1073741824 MX4 dequantized time per iter: 2756us INFO:root:Start to benchmark ... INFO:root:Start to benchmark ... input_size=1073741824 MX4 triton quantized time per iter: 5110us input_size=1073741824 MX4 triton dequantized time per iter: 2417us INFO:root:Start to benchmark ... INFO:root:Start to benchmark ... input_size=1073741824 FP8 quantized time per iter: 6274us input_size=1073741824 FP8 dequantized time per iter: 4223us ``` Reviewed By: sryap Differential Revision: D59661776
jwfromm
force-pushed
the
export-D59661776
branch
from
6d84c06
to
11069b7
Compare
|
This pull request was exported from Phabricator. Differential Revision: D59661776 |
jwfromm
added a commit
to jwfromm/FBGEMM
that referenced
this pull request
Jul 12, 2024
Summary: Pull Request resolved: pytorch#2837 We previously had to use python to unravel values from exponents and feed them to triton as two separate tensors. This introduced a lot of overhead as it introduced large copies. This diff does a bunch of fancy indexing to directly operate on a tensor with mixed elements and exponents. The result is that triton dequantize is now slightly faster than the cuda kernel. My hope is that this allows us to standardize on a single implementation. I think we could probably do something similar during quantize to get a significant speedup as well. ``` INFO:root:input size: 1073741824 group size: 32 INFO:root:Start to benchmark ... INFO:root:Start to benchmark ... input_size=1073741824 MX4 quantized time per iter: 7563us input_size=1073741824 MX4 dequantized time per iter: 2756us INFO:root:Start to benchmark ... INFO:root:Start to benchmark ... input_size=1073741824 MX4 triton quantized time per iter: 5110us input_size=1073741824 MX4 triton dequantized time per iter: 2417us INFO:root:Start to benchmark ... INFO:root:Start to benchmark ... input_size=1073741824 FP8 quantized time per iter: 6274us input_size=1073741824 FP8 dequantized time per iter: 4223us ``` Reviewed By: sryap Differential Revision: D59661776
jwfromm
force-pushed
the
export-D59661776
branch
from
11069b7
to
2e38cc2
Compare
added 2 commits
July 12, 2024 13:04
) Summary: X-link: facebookresearch/FBGEMM#20 Pull Request resolved: pytorch#2816 As noted in [this doc](https://docs.google.com/document/d/156Du0hBRH6umG_i-OrYC574XhpQMUU5SJYG0RTS2tTg/edit#heading=h.akfcp7xpg8cr), using a ceiling round for scale calculation does a better job of not truncating some mantissa bits. This diff switches triton's floor rounding to ceil rounding. Note that currently mx4_test doesnt pass as the cuda kernel now has different behavior than triton. Once we rebase this diff onto a similar change to the cuda kernel, we should see exact matching outputs again. Differential Revision: D59527463 Reviewed By: jianyuh
Summary: Pull Request resolved: pytorch#2836 Rather than try to reshape inputs to 2D matrices with each thread operating on one row, this refactor uses 1D inputs and has each thread operate on an offset of the array. The main benefit of this is that it avoid ragged tensors where we cant divide an input into even sized rows. This should enable us to be compatible with more shapes. Differential Revision: D59653809 Reviewed By: sryap
|
This pull request was exported from Phabricator. Differential Revision: D59661776 |
jwfromm
added a commit
to jwfromm/FBGEMM
that referenced
this pull request
Jul 12, 2024
Summary: Pull Request resolved: pytorch#2837 We previously had to use python to unravel values from exponents and feed them to triton as two separate tensors. This introduced a lot of overhead as it introduced large copies. This diff does a bunch of fancy indexing to directly operate on a tensor with mixed elements and exponents. The result is that triton dequantize is now slightly faster than the cuda kernel. My hope is that this allows us to standardize on a single implementation. I think we could probably do something similar during quantize to get a significant speedup as well. ``` INFO:root:input size: 1073741824 group size: 32 INFO:root:Start to benchmark ... INFO:root:Start to benchmark ... input_size=1073741824 MX4 quantized time per iter: 7563us input_size=1073741824 MX4 dequantized time per iter: 2756us INFO:root:Start to benchmark ... INFO:root:Start to benchmark ... input_size=1073741824 MX4 triton quantized time per iter: 5110us input_size=1073741824 MX4 triton dequantized time per iter: 2417us INFO:root:Start to benchmark ... INFO:root:Start to benchmark ... input_size=1073741824 FP8 quantized time per iter: 6274us input_size=1073741824 FP8 dequantized time per iter: 4223us ``` Reviewed By: sryap Differential Revision: D59661776
jwfromm
force-pushed
the
export-D59661776
branch
from
2e38cc2
to
ffa268f
Compare
Summary: Pull Request resolved: pytorch#2837 We previously had to use python to unravel values from exponents and feed them to triton as two separate tensors. This introduced a lot of overhead as it introduced large copies. This diff does a bunch of fancy indexing to directly operate on a tensor with mixed elements and exponents. The result is that triton dequantize is now slightly faster than the cuda kernel. My hope is that this allows us to standardize on a single implementation. I think we could probably do something similar during quantize to get a significant speedup as well. ``` INFO:root:input size: 1073741824 group size: 32 INFO:root:Start to benchmark ... INFO:root:Start to benchmark ... input_size=1073741824 MX4 quantized time per iter: 7563us input_size=1073741824 MX4 dequantized time per iter: 2756us INFO:root:Start to benchmark ... INFO:root:Start to benchmark ... input_size=1073741824 MX4 triton quantized time per iter: 5110us input_size=1073741824 MX4 triton dequantized time per iter: 2417us INFO:root:Start to benchmark ... INFO:root:Start to benchmark ... input_size=1073741824 FP8 quantized time per iter: 6274us input_size=1073741824 FP8 dequantized time per iter: 4223us ``` Reviewed By: sryap Differential Revision: D59661776
|
This pull request was exported from Phabricator. Differential Revision: D59661776 |
jwfromm
force-pushed
the
export-D59661776
branch
from
ffa268f
to
c680732
Compare
|
This pull request has been merged in 215bab4. |
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.
Summary:
We previously had to use python to unravel values from exponents and feed them to triton as two separate tensors. This introduced a lot of overhead as it introduced large copies.
This diff does a bunch of fancy indexing to directly operate on a tensor with mixed elements and exponents. The result is that triton dequantize is now slightly faster than the cuda kernel. My hope is that this allows us to standardize on a single implementation.
I think we could probably do something similar during quantize to get a significant speedup as well.
Reviewed By: sryap
Differential Revision: D59661776