Add SSDScratchPadIndicesQueue lookup in frontend #2948
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: D60413116 |
|
This pull request was exported from Phabricator. Differential Revision: D60413116 |
sryap
force-pushed
the
export-D60413116
branch
from
0076919 to
99315d8
Compare
sryap
added a commit
to sryap/FBGEMM
that referenced
this pull request
Aug 12, 2024
Summary: Pull Request resolved: pytorch#2948 X-link: facebookresearch/FBGEMM#50 This diff updates SSD-TBE frontend to use `torch.classes.fbgemm.SSDScratchPadIndicesQueue` for scratch pad lookup (added in D60363607). `SSDScratchPadIndicesQueue` is for storing scratch pad indices (conflict missed indices) from previous iterations. It is used during the L1 cache prefetching step: instead of fetching the missing indices directly from SSD, TBE will lookup the scatch pad index queue first to check whether the missing data is in the scratch pad from the previous iteration. The high-level workflow of the prefetch step in SSD-TBE is shown in the figure below: {F1795380801} https://internalfb.com/excalidraw/EX264055 Reviewed By: ehsanardestani Differential Revision: D60413116
|
This pull request was exported from Phabricator. Differential Revision: D60413116 |
sryap
added a commit
to sryap/FBGEMM
that referenced
this pull request
Aug 12, 2024
Summary: Pull Request resolved: pytorch#2948 X-link: facebookresearch/FBGEMM#50 This diff updates SSD-TBE frontend to use `torch.classes.fbgemm.SSDScratchPadIndicesQueue` for scratch pad lookup (added in D60363607). `SSDScratchPadIndicesQueue` is for storing scratch pad indices (conflict missed indices) from previous iterations. It is used during the L1 cache prefetching step: instead of fetching the missing indices directly from SSD, TBE will lookup the scatch pad index queue first to check whether the missing data is in the scratch pad from the previous iteration. The high-level workflow of the prefetch step in SSD-TBE is shown in the figure below: {F1795380801} https://internalfb.com/excalidraw/EX264055 Reviewed By: ehsanardestani Differential Revision: D60413116
sryap
force-pushed
the
export-D60413116
branch
from
99315d8 to
dafebf8
Compare
|
This pull request was exported from Phabricator. Differential Revision: D60413116 |
sryap
added a commit
to sryap/FBGEMM
that referenced
this pull request
Aug 12, 2024
Summary: Pull Request resolved: pytorch#2948 X-link: facebookresearch/FBGEMM#50 This diff updates SSD-TBE frontend to use `torch.classes.fbgemm.SSDScratchPadIndicesQueue` for scratch pad lookup (added in D60363607). `SSDScratchPadIndicesQueue` is for storing scratch pad indices (conflict missed indices) from previous iterations. It is used during the L1 cache prefetching step: instead of fetching the missing indices directly from SSD, TBE will lookup the scatch pad index queue first to check whether the missing data is in the scratch pad from the previous iteration. The high-level workflow of the prefetch step in SSD-TBE is shown in the figure below: {F1795380801} https://internalfb.com/excalidraw/EX264055 Reviewed By: ehsanardestani Differential Revision: D60413116
sryap
force-pushed
the
export-D60413116
branch
from
dafebf8 to
6260f45
Compare
|
This pull request was exported from Phabricator. Differential Revision: D60413116 |
sryap
added a commit
to sryap/FBGEMM
that referenced
this pull request
Aug 13, 2024
Summary: Pull Request resolved: pytorch#2948 X-link: facebookresearch/FBGEMM#50 This diff updates SSD-TBE frontend to use `torch.classes.fbgemm.SSDScratchPadIndicesQueue` for scratch pad lookup (added in D60363607). `SSDScratchPadIndicesQueue` is for storing scratch pad indices (conflict missed indices) from previous iterations. It is used during the L1 cache prefetching step: instead of fetching the missing indices directly from SSD, TBE will lookup the scatch pad index queue first to check whether the missing data is in the scratch pad from the previous iteration. The high-level workflow of the prefetch step in SSD-TBE is shown in the figure below: {F1795380801} https://internalfb.com/excalidraw/EX264055 Reviewed By: ehsanardestani Differential Revision: D60413116
sryap
force-pushed
the
export-D60413116
branch
from
6260f45 to
56ecc47
Compare
Summary: Pull Request resolved: pytorch#2948 X-link: facebookresearch/FBGEMM#50 This diff updates SSD-TBE frontend to use `torch.classes.fbgemm.SSDScratchPadIndicesQueue` for scratch pad lookup (added in D60363607). `SSDScratchPadIndicesQueue` is for storing scratch pad indices (conflict missed indices) from previous iterations. It is used during the L1 cache prefetching step: instead of fetching the missing indices directly from SSD, TBE will lookup the scatch pad index queue first to check whether the missing data is in the scratch pad from the previous iteration. The high-level workflow of the prefetch step in SSD-TBE is shown in the figure below: {F1795380801} https://internalfb.com/excalidraw/EX264055 Reviewed By: ehsanardestani Differential Revision: D60413116
|
This pull request was exported from Phabricator. Differential Revision: D60413116 |
sryap
force-pushed
the
export-D60413116
branch
from
56ecc47 to
147b04c
Compare
|
This pull request has been merged in 4ae45b7. |
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:
This diff updates SSD-TBE frontend to use
torch.classes.fbgemm.SSDScratchPadIndicesQueuefor scratch padlookup (added in D60363607).
SSDScratchPadIndicesQueueis forstoring scratch pad indices (conflict missed indices) from previous
iterations. It is used during the L1 cache prefetching step: instead
of fetching the missing indices directly from SSD, TBE will lookup the
scatch pad index queue first to check whether the missing data is in
the scratch pad from the previous iteration.
The high-level workflow of the prefetch step in SSD-TBE is shown in
the figure below:
{F1795380801}
https://internalfb.com/excalidraw/EX264055
Differential Revision: D60413116