Use PyTorch's p2p access enable function #2000
Closed
Conversation
This file contains hidden or 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 canceled.
|
|
This pull request was exported from Phabricator. Differential Revision: D49021817 |
banitag1
pushed a commit
to banitag1/FBGEMM
that referenced
this pull request
Sep 7, 2023
Summary: We split the diff after adding a needed lazy cuda init call in enable p2p access function. Diff 1: D48939723 [PyTorch] Add the lazy init call for p2p access function *Prior context* cudaEnablePeerAccess only enables cross device access for memory allocated with cudaMalloc. When using other cuda APIs such cuMemMap, peer access is managed differently. expandable_segments:True in PyTorch uses cuMemMap, so code that just calls cudaEnablePeerAccess is not sufficient to enable cross-device copies. This patch switching the p2p access enabling functions to use PyTorchs `get_p2p_access` which lets its allocator figure out how to correctly enable p2p access for that memory. In the normal case (expandable_segments:False), this code performs exactly the same cuda calls as before. Differential Revision: D49021817
banitag1
force-pushed
the
export-D49021817
branch
from
3892929 to
cc7cd60
Compare
|
This pull request was exported from Phabricator. Differential Revision: D49021817 |
banitag1
pushed a commit
to banitag1/FBGEMM
that referenced
this pull request
Sep 7, 2023
Summary: We split the diff after adding a needed lazy cuda init call in enable p2p access function. Diff 1: D48939723 [PyTorch] Add the lazy init call for p2p access function *Prior context* cudaEnablePeerAccess only enables cross device access for memory allocated with cudaMalloc. When using other cuda APIs such cuMemMap, peer access is managed differently. expandable_segments:True in PyTorch uses cuMemMap, so code that just calls cudaEnablePeerAccess is not sufficient to enable cross-device copies. This patch switching the p2p access enabling functions to use PyTorchs `get_p2p_access` which lets its allocator figure out how to correctly enable p2p access for that memory. In the normal case (expandable_segments:False), this code performs exactly the same cuda calls as before. Differential Revision: D49021817
banitag1
force-pushed
the
export-D49021817
branch
from
cc7cd60 to
1059020
Compare
|
This pull request was exported from Phabricator. Differential Revision: D49021817 |
banitag1
force-pushed
the
export-D49021817
branch
from
1059020 to
433a510
Compare
banitag1
pushed a commit
to banitag1/FBGEMM
that referenced
this pull request
Sep 12, 2023
Summary: We split the diff after adding a needed lazy cuda init call in enable p2p access function. Diff 1: D48939723 [PyTorch] Add the lazy init call for p2p access function *Prior context* cudaEnablePeerAccess only enables cross device access for memory allocated with cudaMalloc. When using other cuda APIs such cuMemMap, peer access is managed differently. expandable_segments:True in PyTorch uses cuMemMap, so code that just calls cudaEnablePeerAccess is not sufficient to enable cross-device copies. This patch switching the p2p access enabling functions to use PyTorchs `get_p2p_access` which lets its allocator figure out how to correctly enable p2p access for that memory. In the normal case (expandable_segments:False), this code performs exactly the same cuda calls as before. Reviewed By: zdevito Differential Revision: D49021817
|
This pull request was exported from Phabricator. Differential Revision: D49021817 |
banitag1
pushed a commit
to banitag1/FBGEMM
that referenced
this pull request
Sep 12, 2023
Summary: We split the diff after adding a needed lazy cuda init call in enable p2p access function. Diff 1: D48939723 [PyTorch] Add the lazy init call for p2p access function *Prior context* cudaEnablePeerAccess only enables cross device access for memory allocated with cudaMalloc. When using other cuda APIs such cuMemMap, peer access is managed differently. expandable_segments:True in PyTorch uses cuMemMap, so code that just calls cudaEnablePeerAccess is not sufficient to enable cross-device copies. This patch switching the p2p access enabling functions to use PyTorchs `get_p2p_access` which lets its allocator figure out how to correctly enable p2p access for that memory. In the normal case (expandable_segments:False), this code performs exactly the same cuda calls as before. Reviewed By: zdevito Differential Revision: D49021817
banitag1
force-pushed
the
export-D49021817
branch
from
433a510 to
3bc6a09
Compare
|
This pull request was exported from Phabricator. Differential Revision: D49021817 |
banitag1
pushed a commit
to banitag1/FBGEMM
that referenced
this pull request
Sep 12, 2023
Summary: We split the diff after adding a needed lazy cuda init call in enable p2p access function. Diff 1: D48939723 [PyTorch] Add the lazy init call for p2p access function *Prior context* cudaEnablePeerAccess only enables cross device access for memory allocated with cudaMalloc. When using other cuda APIs such cuMemMap, peer access is managed differently. expandable_segments:True in PyTorch uses cuMemMap, so code that just calls cudaEnablePeerAccess is not sufficient to enable cross-device copies. This patch switching the p2p access enabling functions to use PyTorchs `get_p2p_access` which lets its allocator figure out how to correctly enable p2p access for that memory. In the normal case (expandable_segments:False), this code performs exactly the same cuda calls as before. Reviewed By: zdevito Differential Revision: D49021817
banitag1
force-pushed
the
export-D49021817
branch
from
3bc6a09 to
aa6971c
Compare
|
This pull request was exported from Phabricator. Differential Revision: D49021817 |
banitag1
pushed a commit
to banitag1/FBGEMM
that referenced
this pull request
Sep 12, 2023
Summary: We split the diff after adding a needed lazy cuda init call in enable p2p access function. Diff 1: D48939723 [PyTorch] Add the lazy init call for p2p access function *Prior context* cudaEnablePeerAccess only enables cross device access for memory allocated with cudaMalloc. When using other cuda APIs such cuMemMap, peer access is managed differently. expandable_segments:True in PyTorch uses cuMemMap, so code that just calls cudaEnablePeerAccess is not sufficient to enable cross-device copies. This patch switching the p2p access enabling functions to use PyTorchs `get_p2p_access` which lets its allocator figure out how to correctly enable p2p access for that memory. In the normal case (expandable_segments:False), this code performs exactly the same cuda calls as before. Reviewed By: zdevito Differential Revision: D49021817
banitag1
force-pushed
the
export-D49021817
branch
from
aa6971c to
86bf244
Compare
|
This pull request was exported from Phabricator. Differential Revision: D49021817 |
Summary: We split the diff after adding a needed lazy cuda init call in enable p2p access function. Diff 1: D48939723 [PyTorch] Add the lazy init call for p2p access function *Prior context* cudaEnablePeerAccess only enables cross device access for memory allocated with cudaMalloc. When using other cuda APIs such cuMemMap, peer access is managed differently. expandable_segments:True in PyTorch uses cuMemMap, so code that just calls cudaEnablePeerAccess is not sufficient to enable cross-device copies. This patch switching the p2p access enabling functions to use PyTorchs `get_p2p_access` which lets its allocator figure out how to correctly enable p2p access for that memory. In the normal case (expandable_segments:False), this code performs exactly the same cuda calls as before. Reviewed By: zdevito Differential Revision: D49021817
banitag1
force-pushed
the
export-D49021817
branch
from
86bf244 to
71609f9
Compare
|
This pull request was exported from Phabricator. Differential Revision: D49021817 |
1 similar comment
|
This pull request was exported from Phabricator. Differential Revision: D49021817 |
|
This pull request has been merged in 14cf6f2. |
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 split the diff after adding a needed lazy cuda init call in enable p2p access function.
Diff 1: D48939723
[PyTorch] Add the lazy init call for p2p access function
Prior context
cudaEnablePeerAccess only enables cross device access for memory allocated with cudaMalloc. When using other cuda APIs such cuMemMap, peer access is managed differently.
expandable_segments:True in PyTorch uses cuMemMap, so code that just calls cudaEnablePeerAccess is not sufficient to enable cross-device copies. This patch switching the p2p access enabling functions
to use PyTorchs
get_p2p_accesswhich lets its allocator figure out how to correctly enable p2p access for that memory.In the normal case (expandable_segments:False), this code performs exactly the same cuda calls as before.
Differential Revision: D49021817