Add MSCCLPP user buffer registration APIs and integrate with RCCL (#1477)

* ext-src: add MSCCLPP memory registration APIs

* update mem-reg patch with mscclpp helper routine to check if buffer is registered

* RCCL integration of MSCCL++ user-buffer registration APIs

* only include mscclpp_nccl header if ENABLE_MSCCLPP is defined

* ext-src: update mscclpp mem-reg patch

* add helper routine to patch

* check handle before MSCCL++ deregister

* fix typo to replace send buff with recv buff

* in case of no mscclpp registration, dduring deRegister call, ont fall back to rccl deRegister which will return an error

* Apply suggestions from code review

Whitespace suggestions and reducing diffs to avoid future merge conflicts

Co-authored-by: corey-derochie-amd <161367113+corey-derochie-amd@users.noreply.github.com>

* rename helper functions and change their return type

* set RCCL user-buffer registration to occur if attempting MSCCL++ registration with a buffer in managed memory

---------

Co-authored-by: isaki001 <Ioannis.Sakiotis@amd.com>
Co-authored-by: isaki001 <36317038+isaki001@users.noreply.github.com>
Co-authored-by: corey-derochie-amd <161367113+corey-derochie-amd@users.noreply.github.com>
This commit is contained in:
Nusrat Islam
2025-01-14 08:20:24 -06:00
zatwierdzone przez GitHub
rodzic 3fee623d5a
commit e9b6bbca8a
6 zmienionych plików z 215 dodań i 9 usunięć
+19 -7
Wyświetl plik
@@ -68,14 +68,20 @@ if(ENABLE_MSCCLPP)
WORKING_DIRECTORY ${MSCCLPP_SOURCE}
)
execute_process(
COMMAND git apply ${CMAKE_CURRENT_SOURCE_DIR}/ext-src/read-allred.patch
WORKING_DIRECTORY ${MSCCLPP_SOURCE}
COMMAND git apply ${CMAKE_CURRENT_SOURCE_DIR}/ext-src/read-allred.patch
WORKING_DIRECTORY ${MSCCLPP_SOURCE}
)
execute_process(
COMMAND git apply ${CMAKE_CURRENT_SOURCE_DIR}/ext-src/mscclpp_ibv_access_relaxed_ordering.patch
WORKING_DIRECTORY ${MSCCLPP_SOURCE}
)
execute_process(
COMMAND git apply ${CMAKE_CURRENT_SOURCE_DIR}/ext-src/mem-reg.patch
WORKING_DIRECTORY ${MSCCLPP_SOURCE}
)
message(STATUS "Building mscclpp only for gfx942.")
mscclpp_cmake_arg(CMAKE_PREFIX_PATH)
@@ -102,17 +108,23 @@ if(ENABLE_MSCCLPP)
find_package(mscclpp_nccl REQUIRED)
execute_process(
COMMAND git apply --reverse ${CMAKE_CURRENT_SOURCE_DIR}/ext-src/cpx.patch
WORKING_DIRECTORY ${MSCCLPP_SOURCE}
)
execute_process(
COMMAND git apply --reverse ${CMAKE_CURRENT_SOURCE_DIR}/ext-src/read-allred.patch
COMMAND git apply --reverse ${CMAKE_CURRENT_SOURCE_DIR}/ext-src/cpx.patch
WORKING_DIRECTORY ${MSCCLPP_SOURCE}
)
execute_process(
COMMAND git apply --reverse ${CMAKE_CURRENT_SOURCE_DIR}/ext-src/read-allred.patch
WORKING_DIRECTORY ${MSCCLPP_SOURCE}
)
execute_process(
COMMAND git apply --reverse ${CMAKE_CURRENT_SOURCE_DIR}/ext-src/mscclpp_ibv_access_relaxed_ordering.patch
WORKING_DIRECTORY ${MSCCLPP_SOURCE}
)
execute_process(
COMMAND git apply --reverse ${CMAKE_CURRENT_SOURCE_DIR}/ext-src/mem-reg.patch
WORKING_DIRECTORY ${MSCCLPP_SOURCE}
)
endif()
execute_process(COMMAND objcopy