3eda60a031
* static: Enable true rccl static library build
Rccl uses `-fgpu-rdc` to compile, which requires a specialized link command in order to produce a true static library.
When "linking" with `amdclang++`, you need to use `--emit-static-lib` and `--hip-link` to get a static library with all gpu code generated. Subsequent links with binaries do not need any special flags to generate gpu code.`
Building a static library:
```
$ cmake -DROCM_PATH=$ROCM_PATH -DCMAKE_PREFIX_PATH=$ROCM_PATH -DCMAKE_BUILD_TYPE=Release -DBUILD_SHARED_LIBS=off -DCMAKE_POSITION_INDEPENDENT_CODE=on -DAMDGPU_TARGETS=gfx942 -DCMAKE_CXX_COMPILER=$ROCM_PATH/lib/llvm/bin/amdclang++ -DCMAKE_C_COMPILER=$ROCM_PATH/lib/llvm/bin/amdclang .. 2>&1 | tee -a /tmp/build.txt
-- Could NOT find GTest (missing: GTEST_LIBRARY GTEST_INCLUDE_DIR GTEST_MAIN_LIBRARY) (Required is at least version "1.11")
-- Checking for ROCm support for GPU targets: gfx942
-- Compiling for gfx942
-- Could NOT find GTest (missing: GTEST_LIBRARY GTEST_INCLUDE_DIR GTEST_MAIN_LIBRARY) (Required is at least version "1.11")
-- ROCM_PATH found: /opt/rocm
-- Compiling with amdclang++
-- HIP compiler: clang
-- HIP runtime: rocclr
-- amdclang++ executable: /opt/rocm/llvm/bin/amdclang++
-- amdclang++ version: 18.0.0git
-- hipconfig executable: /opt/rocm/bin/hipconfig
-- amdclang++ HIP version: 6.2.41133
-- ROCm version: 6.2.0
...
$ make -j 32
[ 0%] Updating git_version.cpp if necessary
-- Updating git_version.cpp
[ 0%] Built target git_version_check
[ 0%] Hipifying src/transport/shm.cc -> /home/skarlage/local/rccl/build/hipify/src/transport/shm.cc
[ 0%] Hipifying src/bootstrap.cc -> /home/skarlage/local/rccl/build/hipify/src/bootstrap.cc
[ 0%] Hipifying src/channel.cc -> /home/skarlage/local/rccl/build/hipify/src/channel.cc
[ 1%] Hipifying src/device/all_reduce.h -> /home/skarlage/local/rccl/build/hipify/src/device/all_reduce.h
[ 1%] Hipifying src/device/broadcast.h -> /home/skarlage/local/rccl/build/hipify/src/device/broadcast.h
[ 1%] Hipifying src/device/all_gather.h -> /home/skarlage/local/rccl/build/hipify/src/device/all_gather.h
[ 1%] Hipifying src/device/common.cu -> /home/skarlage/local/rccl/build/hipify/src/device/common.cu.cpp
[ 1%] Hipifying src/debug.cc -> /home/skarlage/local/rccl/build/hipify/src/debug.cc
[ 1%] Hipifying src/device/alltoall_pivot.h -> /home/skarlage/local/rccl/build/hipify/src/device/alltoall_pivot.h
[ 1%] Hipifying src/device/network/unpack/unpack.h -> /home/skarlage/local/rccl/build/hipify/src/device/network/unpack/unpack.h
[ 4%] Hipifying src/collectives.cc -> /home/skarlage/local/rccl/build/hipify/src/collectives.cc
[ 4%] Hipifying src/device/msccl_kernel_impl.h -> /home/skarlage/local/rccl/build/hipify/src/device/msccl_kernel_impl.h
[ 4%] Hipifying src/device/network/unpack/unpack_defs.h -> /home/skarlage/local/rccl/build/hipify/src/device/network/unpack/unpack_defs.h
[ 4%] Hipifying src/device/op128.h -> /home/skarlage/local/rccl/build/hipify/src/device/op128.h
[ 4%] Hipifying src/device/onerank.cu -> /home/skarlage/local/rccl/build/hipify/src/device/onerank.cu.cpp
[ 4%] Hipifying src/device/common.h -> /home/skarlage/local/rccl/build/hipify/src/device/common.h
[ 6%] Hipifying src/device/prims_ll.h -> /home/skarlage/local/rccl/build/hipify/src/device/prims_ll.h
[ 6%] Hipifying src/device/primitives.h -> /home/skarlage/local/rccl/build/hipify/src/device/primitives.h
[ 6%] Hipifying src/device/prims_ll128.h -> /home/skarlage/local/rccl/build/hipify/src/device/prims_ll128.h
[ 6%] Hipifying src/device/reduce.h -> /home/skarlage/local/rccl/build/hipify/src/device/reduce.h
[ 7%] Hipifying src/device/common_kernel.h -> /home/skarlage/local/rccl/build/hipify/src/device/common_kernel.h
[ 7%] Hipifying src/device/reduce_scatter.h -> /home/skarlage/local/rccl/build/hipify/src/device/reduce_scatter.h
[ 7%] Hipifying src/device/sendrecv.h -> /home/skarlage/local/rccl/build/hipify/src/device/sendrecv.h
[ 7%] Hipifying src/device/prims_simple.h -> /home/skarlage/local/rccl/build/hipify/src/device/prims_simple.h
[ 7%] Hipifying src/enqueue.cc -> /home/skarlage/local/rccl/build/hipify/src/enqueue.cc
[ 7%] Hipifying src/device/reduce_kernel.h -> /home/skarlage/local/rccl/build/hipify/src/device/reduce_kernel.h
[ 7%] Hipifying src/graph/connect.cc -> /home/skarlage/local/rccl/build/hipify/src/graph/connect.cc
[ 7%] Hipifying src/graph/rings.h -> /home/skarlage/local/rccl/build/hipify/src/graph/rings.h
[ 8%] Hipifying src/graph/rings.cc -> /home/skarlage/local/rccl/build/hipify/src/graph/rings.cc
[ 8%] Hipifying src/graph/rome_models.cc -> /home/skarlage/local/rccl/build/hipify/src/graph/rome_models.cc
[ 8%] Hipifying src/graph/rome_models.h -> /home/skarlage/local/rccl/build/hipify/src/graph/rome_models.h
[ 8%] Hipifying src/graph/paths.cc -> /home/skarlage/local/rccl/build/hipify/src/graph/paths.cc
[ 9%] Hipifying src/graph/search.cc -> /home/skarlage/local/rccl/build/hipify/src/graph/search.cc
[ 9%] Hipifying src/graph/topo.cc -> /home/skarlage/local/rccl/build/hipify/src/graph/topo.cc
...
[100%] Linking CXX static library librccl.a
Elapsed time: 270 s. (time), 0.00046 s. (clock)
Elapsed time: 0 s. (time), 0.000342 s. (clock)
[100%] Built target rccl
```
Static rccl exists:
```
$ file librccl.a
librccl.a: current ar archive
```
* Fix up tests Cmake for static builds
We also need to fix up the tests CMakeLists.txt to:
* Remove the unused `BUILD_STATIC` option
* Use `SHARED_LIBS` as a definition of whether we're building static or
not.
[ROCm/rccl commit: bdf9544c81]
101 regels
3.7 KiB
CMake
101 regels
3.7 KiB
CMake
# Copyright (c) 2019-2021 Advanced Micro Devices, Inc. All rights reserved.
|
|
# Modifications Copyright (c) Microsoft Corporation. Licensed under the MIT License.
|
|
|
|
cmake_minimum_required(VERSION 2.8.12)
|
|
|
|
if(BUILD_TESTS)
|
|
|
|
option(OPENMP_TESTS_ENABLED "Enable OpenMP for unit tests" OFF)
|
|
|
|
message("Building rccl unit tests (Installed in /test/rccl-UnitTests)")
|
|
|
|
find_package(hsa-runtime64 PATHS /opt/rocm )
|
|
if(${hsa-runtime64_FOUND})
|
|
message("hsa-runtime64 found @ ${hsa-runtime64_DIR} ")
|
|
else()
|
|
message("find_package did NOT find hsa-runtime64, finding it the OLD Way")
|
|
message("Looking for header files in ${ROCR_INC_DIR}")
|
|
message("Looking for library files in ${ROCR_LIB_DIR}")
|
|
|
|
# Search for ROCr header file in user defined locations
|
|
find_path(ROCR_HDR hsa/hsa.h PATHS ${ROCR_INC_DIR} "/opt/rocm" PATH_SUFFIXES include REQUIRED)
|
|
INCLUDE_DIRECTORIES(${ROCR_HDR})
|
|
|
|
# Search for ROCr library file in user defined locations
|
|
find_library(ROCR_LIB ${CORE_RUNTIME_TARGET} PATHS ${ROCR_LIB_DIR} "/opt/rocm" PATH_SUFFIXES lib lib64 REQUIRED)
|
|
endif()
|
|
|
|
if(OPENMP_TESTS_ENABLED)
|
|
find_package(OpenMP REQUIRED)
|
|
endif()
|
|
|
|
include_directories(${GTEST_INCLUDE_DIRS} ./common)
|
|
|
|
# Collect testing framework source files
|
|
set(TEST_SOURCE_FILES
|
|
AllGatherTests.cpp
|
|
AllReduceTests.cpp
|
|
AllToAllTests.cpp
|
|
AllToAllVTests.cpp
|
|
BroadcastTests.cpp
|
|
GatherTests.cpp
|
|
GroupCallTests.cpp
|
|
NonBlockingTests.cpp
|
|
ReduceScatterTests.cpp
|
|
ReduceTests.cpp
|
|
ScatterTests.cpp
|
|
SendRecvTests.cpp
|
|
StandaloneTests.cpp
|
|
common/main.cpp
|
|
common/CollectiveArgs.cpp
|
|
common/EnvVars.cpp
|
|
common/PrepDataFuncs.cpp
|
|
common/PtrUnion.cpp
|
|
common/TestBed.cpp
|
|
common/TestBedChild.cpp
|
|
)
|
|
|
|
add_executable(rccl-UnitTests ${TEST_SOURCE_FILES})
|
|
|
|
## Set rccl-UnitTests include directories
|
|
target_include_directories(rccl-UnitTests PRIVATE ${ROCM_PATH} ${GTEST_INCLUDE_DIRS})
|
|
target_include_directories(rccl-UnitTests PRIVATE ${PROJECT_BINARY_DIR}/include) # for generated rccl.h header
|
|
target_include_directories(rccl-UnitTests PRIVATE ${PROJECT_BINARY_DIR}/hipify/src/include) # for rccl_bfloat16.h
|
|
|
|
## Set rccl-UnitTests compile definitions
|
|
if(LL128_ENABLED)
|
|
target_compile_definitions(rccl-UnitTests PRIVATE ENABLE_LL128)
|
|
endif()
|
|
if(OPENMP_TESTS_ENABLED)
|
|
target_compile_definitions(rccl-UnitTests PRIVATE ENABLE_OPENMP)
|
|
endif()
|
|
target_compile_definitions(rccl-UnitTests PRIVATE ROCM_PATH="${ROCM_PATH}")
|
|
|
|
## Set rccl-UnitTests compile definitions
|
|
if(OPENMP_TESTS_ENABLED)
|
|
target_compile_options(rccl-UnitTests PRIVATE "${OpenMP_CXX_FLAGS}")
|
|
endif()
|
|
|
|
## Set rccl-UnitTests linked libraries
|
|
target_link_libraries(rccl-UnitTests PRIVATE ${GTEST_BOTH_LIBRARIES})
|
|
target_link_libraries(rccl-UnitTests PRIVATE hip::host hip::device hsa-runtime64::hsa-runtime64)
|
|
target_link_libraries(rccl-UnitTests PRIVATE Threads::Threads)
|
|
if(OPENMP_TESTS_ENABLED)
|
|
target_link_libraries(rccl-UnitTests PRIVATE "${OpenMP_CXX_FLAGS}")
|
|
endif()
|
|
|
|
# rccl-UnitTests using static library of rccl requires passing rccl
|
|
# through -l and -L instead of command line input.
|
|
if(BUILD_SHARED_LIBS)
|
|
target_link_libraries(rccl-UnitTests PRIVATE rccl)
|
|
set_property(TARGET rccl-UnitTests PROPERTY INSTALL_RPATH "${CMAKE_INSTALL_PREFIX}/lib;${ROCM_PATH}/lib;${CMAKE_BINARY_DIR}")
|
|
else()
|
|
add_dependencies(rccl-UnitTests rccl)
|
|
target_link_libraries(rccl-UnitTests PRIVATE dl rt numa -lrccl -L${CMAKE_BINARY_DIR} -lrocm_smi64 -L${ROCM_PATH}/lib -L${ROCM_PATH}/rocm_smi/lib)
|
|
endif()
|
|
set_property(TARGET rccl-UnitTests PROPERTY BUILD_RPATH "${CMAKE_BINARY_DIR};${ROCM_PATH}/lib")
|
|
rocm_install(TARGETS rccl-UnitTests COMPONENT tests)
|
|
else()
|
|
message("Not building rccl unit tests")
|
|
endif()
|