[Feat] use host-pinned memory with dual CPU/device addresses for transport buffers#1024
Merged
mag1c-h merged 1 commit intoJun 17, 2026
Merged
Conversation
yumingyue624
requested review from
FangRun2,
Infinite666,
Tarrei,
Wwwzff,
flesher0813,
mag1c-h and
ygwpz
as code owners
Infinite666
reviewed
Jun 12, 2026
Infinite666
reviewed
Jun 12, 2026
Infinite666
reviewed
Jun 12, 2026
ygwpz
reviewed
Jun 13, 2026
ygwpz
reviewed
Jun 13, 2026
ygwpz
reviewed
Jun 13, 2026
ygwpz
reviewed
Jun 13, 2026
ygwpz
reviewed
Jun 13, 2026
ygwpz
reviewed
Jun 13, 2026
yumingyue624
force-pushed
the
adapt_connection
branch
4 times, most recently
from
88298b3 to
c5cfef8
Compare
ygwpz
reviewed
Jun 16, 2026
ygwpz
reviewed
Jun 16, 2026
yumingyue624
force-pushed
the
adapt_connection
branch
3 times, most recently
from
fba4e10 to
548365b
Compare
Infinite666
reviewed
Jun 16, 2026
Infinite666
reviewed
Jun 16, 2026
yumingyue624
force-pushed
the
adapt_connection
branch
from
548365b to
933a8fa
Compare
Infinite666
reviewed
Jun 16, 2026
yumingyue624
force-pushed
the
adapt_connection
branch
from
933a8fa to
3d19404
Compare
Infinite666
reviewed
Jun 16, 2026
yumingyue624
force-pushed
the
adapt_connection
branch
3 times, most recently
from
59a10dd to
02f205c
Compare
Infinite666
previously approved these changes
Jun 16, 2026
yumingyue624
force-pushed
the
adapt_connection
branch
from
02f205c to
566a729
Compare
Infinite666
previously approved these changes
Jun 16, 2026
mag1c-h
reviewed
Jun 16, 2026
yumingyue624
force-pushed
the
adapt_connection
branch
from
566a729 to
d925f83
Compare
mag1c-h
reviewed
Jun 16, 2026
…r transport buffers ## Purpose Switch ASU send/flag buffers from plain host memory to host-pinned memory so that CPU code packs SQEs through the local mapping while HCOMM/RDMA uses the device-visible mapping of the same allocation. ## Modifications 1. BufferManager: allocate host-pinned memory via aclrtMallocHost + aclrtHostRegisterV2, obtain device pointer via aclrtHostGetDevicePointer. ScatterGatherEntry gains device_addr. RegisterMemory uses device address for host-pinned regions. 2. AsuTransportImpl: send/flag buffers use HOST_PINNED instead of HOST. 3. asu_submit_flow: pass device_addr to SendIoBatch. 4. sqe_request: use flagBuffer.device_addr for response_buffer_addr. 5. Move IsTransportBufferReady from asu_submit_flow to buffer_manager. 6. Tests: added host-pinned dual-address and device_addr assertions. ## Test - buffer_manager_test: HostPinnedRegistersDeviceAddress. - asu_submit_flow_test: BuildSubBatchSendBuffersUsesHostPinnedDeviceAddresses. - sqe_request_test: packed response address matches device_addr.
yumingyue624
force-pushed
the
adapt_connection
branch
from
d925f83 to
4a2de05
Compare
mag1c-h
approved these changes
Jun 17, 2026
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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.
Purpose
Switch ASU send/flag buffers from plain host memory to host-pinned
memory so that CPU code packs SQEs through the local mapping while
HCOMM/RDMA uses the device-visible mapping of the same allocation.
Modifications
aclrtHostRegisterV2, obtain device pointer via
aclrtHostGetDevicePointer. ScatterGatherEntry gains device_addr.
RegisterMemory uses device address for host-pinned regions.
Test