maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/openmp/libomptarget/plugins/amdgpu/CMakeLists.txt

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

86 lines
2.7 KiB
CMake
Raw Normal View History

[libomptarget] Implement host plugin for amdgpu [libomptarget] Implement host plugin for amdgpu Replacement for D71384. Primary difference is inlining the dependency on atmi followed by extensive simplification and bugfixes. This is the latest version from https://github.com/ROCm-Developer-Tools/amd-llvm-project/tree/aomp12 with minor patches and a rename from hsa to amdgpu, on the basis that this can't be used by other implementations of hsa without additional work. This will not build unless the ROCM_DIR variable is passed so won't break other builds. That variable is used to locate two amdgpu specific libraries that ship as part of rocm: libhsakmt at https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface libhsa-runtime64 at https://github.com/RadeonOpenCompute/ROCR-Runtime These libraries build from source. The build scripts in those repos are for shared libraries, but can be adapted to statically link both into this plugin. There are caveats. - This works well enough to run various tests and benchmarks, and will be used to support the current clang bring up - It is adequately thread safe for the above but there will be races remaining - It is not stylistically correct for llvm, though has had clang-format run - It has suboptimal memory management and locking strategies - The debug printing / error handling is inconsistent I would like to contribute this pretty much as-is and then improve it in-tree. This would be advantagous because the aomp12 branch that was in use for fixing this codebase has just been joined with the amd internal rocm dev process. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D85742
2020-08-16 06:52:19 +08:00
##===----------------------------------------------------------------------===##
#
# The LLVM Compiler Infrastructure
#
# This file is dual licensed under the MIT and the University of Illinois Open
# Source Licenses. See LICENSE.txt for details.
#
##===----------------------------------------------------------------------===##
#
# Build a plugin for an AMDGPU machine if available.
#
##===----------------------------------------------------------------------===##
################################################################################
[libomptarget][amdgpu] Update plugin CMake to work with latest rocr library
2020-08-27 03:01:42 +08:00
# as of rocm-3.7, hsa is installed with cmake packages and kmt is found via hsa
find_package(hsa-runtime64 QUIET 1.2.0 HINTS ${CMAKE_INSTALL_PREFIX} PATHS /opt/rocm)
if (NOT ${hsa-runtime64_FOUND})
[openmp][libomptarget] Include header from LLVM source tree [openmp][libomptarget] Include header from LLVM source tree The change is to the amdgpu plugin so is unlikely to break anything. The point of contention is whether libomptarget can depend on LLVM. A community discussion was cautiously not opposed yesterday. This introduces a compile time dependency on the LLVM source tree, in this case expressed as skipping the building of the plugin if LLVM_MAIN_INCLUDE_DIR is not set. One the source files will #include llvm/Frontend/OpenMP/OMPGridValues.h, instead of copy&pasting the numbers across. For users that download the monorepo, the llvm tree is already on disk. This will inconvenience users who download only the openmp source as a tar, as they would now also have to download (at least a file or two) from the llvm source, if they want to build the parts of the openmp project that (post this patch) depend on llvm. There was interest expressed in going further - using llvm tools as part of building libomp, or linking against llvm libraries. That seems less clear cut an improvement and worthy of further discussion. This patch seeks only to change policy to support openmp depending on the llvm source tree. Including in the other direction, or using libraries / tools etc, are purposefully out of scope. Reviewers are a best guess at interested parties, please feel free to add others Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D87841
2020-10-15 22:43:39 +08:00
libomptarget_say("Not building AMDGPU plugin: hsa-runtime64 not found")
[libomptarget] Implement host plugin for amdgpu [libomptarget] Implement host plugin for amdgpu Replacement for D71384. Primary difference is inlining the dependency on atmi followed by extensive simplification and bugfixes. This is the latest version from https://github.com/ROCm-Developer-Tools/amd-llvm-project/tree/aomp12 with minor patches and a rename from hsa to amdgpu, on the basis that this can't be used by other implementations of hsa without additional work. This will not build unless the ROCM_DIR variable is passed so won't break other builds. That variable is used to locate two amdgpu specific libraries that ship as part of rocm: libhsakmt at https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface libhsa-runtime64 at https://github.com/RadeonOpenCompute/ROCR-Runtime These libraries build from source. The build scripts in those repos are for shared libraries, but can be adapted to statically link both into this plugin. There are caveats. - This works well enough to run various tests and benchmarks, and will be used to support the current clang bring up - It is adequately thread safe for the above but there will be races remaining - It is not stylistically correct for llvm, though has had clang-format run - It has suboptimal memory management and locking strategies - The debug printing / error handling is inconsistent I would like to contribute this pretty much as-is and then improve it in-tree. This would be advantagous because the aomp12 branch that was in use for fixing this codebase has just been joined with the amd internal rocm dev process. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D85742
2020-08-16 06:52:19 +08:00
return()
endif()
[libomptarget][amdgpu] Update plugin CMake to work with latest rocr library
2020-08-27 03:01:42 +08:00
if(NOT LIBOMPTARGET_DEP_LIBELF_FOUND)
libomptarget_say("Not building AMDGPU plugin: LIBELF not found")
[libomptarget] Implement host plugin for amdgpu [libomptarget] Implement host plugin for amdgpu Replacement for D71384. Primary difference is inlining the dependency on atmi followed by extensive simplification and bugfixes. This is the latest version from https://github.com/ROCm-Developer-Tools/amd-llvm-project/tree/aomp12 with minor patches and a rename from hsa to amdgpu, on the basis that this can't be used by other implementations of hsa without additional work. This will not build unless the ROCM_DIR variable is passed so won't break other builds. That variable is used to locate two amdgpu specific libraries that ship as part of rocm: libhsakmt at https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface libhsa-runtime64 at https://github.com/RadeonOpenCompute/ROCR-Runtime These libraries build from source. The build scripts in those repos are for shared libraries, but can be adapted to statically link both into this plugin. There are caveats. - This works well enough to run various tests and benchmarks, and will be used to support the current clang bring up - It is adequately thread safe for the above but there will be races remaining - It is not stylistically correct for llvm, though has had clang-format run - It has suboptimal memory management and locking strategies - The debug printing / error handling is inconsistent I would like to contribute this pretty much as-is and then improve it in-tree. This would be advantagous because the aomp12 branch that was in use for fixing this codebase has just been joined with the amd internal rocm dev process. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D85742
2020-08-16 06:52:19 +08:00
return()
endif()
if(NOT CMAKE_SYSTEM_PROCESSOR MATCHES "(x86_64)|(ppc64le)|(aarch64)$" AND CMAKE_SYSTEM_NAME MATCHES "Linux")
[openmp][libomptarget] Include header from LLVM source tree [openmp][libomptarget] Include header from LLVM source tree The change is to the amdgpu plugin so is unlikely to break anything. The point of contention is whether libomptarget can depend on LLVM. A community discussion was cautiously not opposed yesterday. This introduces a compile time dependency on the LLVM source tree, in this case expressed as skipping the building of the plugin if LLVM_MAIN_INCLUDE_DIR is not set. One the source files will #include llvm/Frontend/OpenMP/OMPGridValues.h, instead of copy&pasting the numbers across. For users that download the monorepo, the llvm tree is already on disk. This will inconvenience users who download only the openmp source as a tar, as they would now also have to download (at least a file or two) from the llvm source, if they want to build the parts of the openmp project that (post this patch) depend on llvm. There was interest expressed in going further - using llvm tools as part of building libomp, or linking against llvm libraries. That seems less clear cut an improvement and worthy of further discussion. This patch seeks only to change policy to support openmp depending on the llvm source tree. Including in the other direction, or using libraries / tools etc, are purposefully out of scope. Reviewers are a best guess at interested parties, please feel free to add others Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D87841
2020-10-15 22:43:39 +08:00
libomptarget_say("Not building AMDGPU plugin: only support AMDGPU in Linux x86_64, ppc64le, or aarch64 hosts.")
[libomptarget] Implement host plugin for amdgpu [libomptarget] Implement host plugin for amdgpu Replacement for D71384. Primary difference is inlining the dependency on atmi followed by extensive simplification and bugfixes. This is the latest version from https://github.com/ROCm-Developer-Tools/amd-llvm-project/tree/aomp12 with minor patches and a rename from hsa to amdgpu, on the basis that this can't be used by other implementations of hsa without additional work. This will not build unless the ROCM_DIR variable is passed so won't break other builds. That variable is used to locate two amdgpu specific libraries that ship as part of rocm: libhsakmt at https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface libhsa-runtime64 at https://github.com/RadeonOpenCompute/ROCR-Runtime These libraries build from source. The build scripts in those repos are for shared libraries, but can be adapted to statically link both into this plugin. There are caveats. - This works well enough to run various tests and benchmarks, and will be used to support the current clang bring up - It is adequately thread safe for the above but there will be races remaining - It is not stylistically correct for llvm, though has had clang-format run - It has suboptimal memory management and locking strategies - The debug printing / error handling is inconsistent I would like to contribute this pretty much as-is and then improve it in-tree. This would be advantagous because the aomp12 branch that was in use for fixing this codebase has just been joined with the amd internal rocm dev process. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D85742
2020-08-16 06:52:19 +08:00
return()
endif()
[openmp][libomptarget] Include header from LLVM source tree [openmp][libomptarget] Include header from LLVM source tree The change is to the amdgpu plugin so is unlikely to break anything. The point of contention is whether libomptarget can depend on LLVM. A community discussion was cautiously not opposed yesterday. This introduces a compile time dependency on the LLVM source tree, in this case expressed as skipping the building of the plugin if LLVM_MAIN_INCLUDE_DIR is not set. One the source files will #include llvm/Frontend/OpenMP/OMPGridValues.h, instead of copy&pasting the numbers across. For users that download the monorepo, the llvm tree is already on disk. This will inconvenience users who download only the openmp source as a tar, as they would now also have to download (at least a file or two) from the llvm source, if they want to build the parts of the openmp project that (post this patch) depend on llvm. There was interest expressed in going further - using llvm tools as part of building libomp, or linking against llvm libraries. That seems less clear cut an improvement and worthy of further discussion. This patch seeks only to change policy to support openmp depending on the llvm source tree. Including in the other direction, or using libraries / tools etc, are purposefully out of scope. Reviewers are a best guess at interested parties, please feel free to add others Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D87841
2020-10-15 22:43:39 +08:00
[OpenMP] Fixed include directories for OpenMP when building OpenMP with LLVM_ENABLE_RUNTIMES Some LLVM headers are generated by CMake. Before the installation, LLVM's headers are distributed everywhere, some of which are in `${LLVM_SRC_ROOT}/llvm/include/llvm`, and some are in `${LLVM_BINARY_ROOT}/include/llvm`. After intallation, they're all in `${LLVM_INSTALLATION_ROOT}/include/llvm`. OpenMP now depends on LLVM headers. Some headers depend on headers generated by CMake. When building OpenMP along with LLVM, a.k.a via `LLVM_ENABLE_RUNTIMES`, we need to tell OpenMP where it can find those headers, especially those still have not been copied/installed. Reviewed By: jdoerfert, jhuber6 Differential Revision: https://reviews.llvm.org/D94534
2021-01-13 03:32:27 +08:00
if (NOT LIBOMPTARGET_LLVM_INCLUDE_DIRS)
libomptarget_say("Not building AMDGPU plugin: Missing definition for LIBOMPTARGET_LLVM_INCLUDE_DIRS")
[openmp][libomptarget] Include header from LLVM source tree [openmp][libomptarget] Include header from LLVM source tree The change is to the amdgpu plugin so is unlikely to break anything. The point of contention is whether libomptarget can depend on LLVM. A community discussion was cautiously not opposed yesterday. This introduces a compile time dependency on the LLVM source tree, in this case expressed as skipping the building of the plugin if LLVM_MAIN_INCLUDE_DIR is not set. One the source files will #include llvm/Frontend/OpenMP/OMPGridValues.h, instead of copy&pasting the numbers across. For users that download the monorepo, the llvm tree is already on disk. This will inconvenience users who download only the openmp source as a tar, as they would now also have to download (at least a file or two) from the llvm source, if they want to build the parts of the openmp project that (post this patch) depend on llvm. There was interest expressed in going further - using llvm tools as part of building libomp, or linking against llvm libraries. That seems less clear cut an improvement and worthy of further discussion. This patch seeks only to change policy to support openmp depending on the llvm source tree. Including in the other direction, or using libraries / tools etc, are purposefully out of scope. Reviewers are a best guess at interested parties, please feel free to add others Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D87841
2020-10-15 22:43:39 +08:00
return()
endif()
[libomptarget][amdgpu] Support building with static rocm libraries
2020-08-19 22:44:30 +08:00
libomptarget_say("Building amdgpu offloading plugin")
[libomptarget] Implement host plugin for amdgpu [libomptarget] Implement host plugin for amdgpu Replacement for D71384. Primary difference is inlining the dependency on atmi followed by extensive simplification and bugfixes. This is the latest version from https://github.com/ROCm-Developer-Tools/amd-llvm-project/tree/aomp12 with minor patches and a rename from hsa to amdgpu, on the basis that this can't be used by other implementations of hsa without additional work. This will not build unless the ROCM_DIR variable is passed so won't break other builds. That variable is used to locate two amdgpu specific libraries that ship as part of rocm: libhsakmt at https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface libhsa-runtime64 at https://github.com/RadeonOpenCompute/ROCR-Runtime These libraries build from source. The build scripts in those repos are for shared libraries, but can be adapted to statically link both into this plugin. There are caveats. - This works well enough to run various tests and benchmarks, and will be used to support the current clang bring up - It is adequately thread safe for the above but there will be races remaining - It is not stylistically correct for llvm, though has had clang-format run - It has suboptimal memory management and locking strategies - The debug printing / error handling is inconsistent I would like to contribute this pretty much as-is and then improve it in-tree. This would be advantagous because the aomp12 branch that was in use for fixing this codebase has just been joined with the amd internal rocm dev process. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D85742
2020-08-16 06:52:19 +08:00
################################################################################
# Define the suffix for the runtime messaging dumps.
add_definitions(-DTARGET_NAME=AMDGPU)
if(CMAKE_SYSTEM_PROCESSOR MATCHES "(ppc64le)|(aarch64)$")
add_definitions(-DLITTLEENDIAN_CPU=1)
endif()
if(CMAKE_BUILD_TYPE MATCHES Debug)
add_definitions(-DDEBUG)
endif()
include_directories(
${CMAKE_CURRENT_SOURCE_DIR}/impl
[OpenMP] Fixed include directories for OpenMP when building OpenMP with LLVM_ENABLE_RUNTIMES Some LLVM headers are generated by CMake. Before the installation, LLVM's headers are distributed everywhere, some of which are in `${LLVM_SRC_ROOT}/llvm/include/llvm`, and some are in `${LLVM_BINARY_ROOT}/include/llvm`. After intallation, they're all in `${LLVM_INSTALLATION_ROOT}/include/llvm`. OpenMP now depends on LLVM headers. Some headers depend on headers generated by CMake. When building OpenMP along with LLVM, a.k.a via `LLVM_ENABLE_RUNTIMES`, we need to tell OpenMP where it can find those headers, especially those still have not been copied/installed. Reviewed By: jdoerfert, jhuber6 Differential Revision: https://reviews.llvm.org/D94534
2021-01-13 03:32:27 +08:00
${LIBOMPTARGET_LLVM_INCLUDE_DIRS}
[libomptarget] Implement host plugin for amdgpu [libomptarget] Implement host plugin for amdgpu Replacement for D71384. Primary difference is inlining the dependency on atmi followed by extensive simplification and bugfixes. This is the latest version from https://github.com/ROCm-Developer-Tools/amd-llvm-project/tree/aomp12 with minor patches and a rename from hsa to amdgpu, on the basis that this can't be used by other implementations of hsa without additional work. This will not build unless the ROCM_DIR variable is passed so won't break other builds. That variable is used to locate two amdgpu specific libraries that ship as part of rocm: libhsakmt at https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface libhsa-runtime64 at https://github.com/RadeonOpenCompute/ROCR-Runtime These libraries build from source. The build scripts in those repos are for shared libraries, but can be adapted to statically link both into this plugin. There are caveats. - This works well enough to run various tests and benchmarks, and will be used to support the current clang bring up - It is adequately thread safe for the above but there will be races remaining - It is not stylistically correct for llvm, though has had clang-format run - It has suboptimal memory management and locking strategies - The debug printing / error handling is inconsistent I would like to contribute this pretty much as-is and then improve it in-tree. This would be advantagous because the aomp12 branch that was in use for fixing this codebase has just been joined with the amd internal rocm dev process. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D85742
2020-08-16 06:52:19 +08:00
)
add_library(omptarget.rtl.amdgpu SHARED
impl/atmi.cpp
impl/atmi_interop_hsa.cpp
impl/data.cpp
[libomptarget][amdgpu] Improve diagnostics on arch mismatch
2020-12-10 02:55:21 +08:00
impl/get_elf_mach_gfx_name.cpp
[libomptarget] Implement host plugin for amdgpu [libomptarget] Implement host plugin for amdgpu Replacement for D71384. Primary difference is inlining the dependency on atmi followed by extensive simplification and bugfixes. This is the latest version from https://github.com/ROCm-Developer-Tools/amd-llvm-project/tree/aomp12 with minor patches and a rename from hsa to amdgpu, on the basis that this can't be used by other implementations of hsa without additional work. This will not build unless the ROCM_DIR variable is passed so won't break other builds. That variable is used to locate two amdgpu specific libraries that ship as part of rocm: libhsakmt at https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface libhsa-runtime64 at https://github.com/RadeonOpenCompute/ROCR-Runtime These libraries build from source. The build scripts in those repos are for shared libraries, but can be adapted to statically link both into this plugin. There are caveats. - This works well enough to run various tests and benchmarks, and will be used to support the current clang bring up - It is adequately thread safe for the above but there will be races remaining - It is not stylistically correct for llvm, though has had clang-format run - It has suboptimal memory management and locking strategies - The debug printing / error handling is inconsistent I would like to contribute this pretty much as-is and then improve it in-tree. This would be advantagous because the aomp12 branch that was in use for fixing this codebase has just been joined with the amd internal rocm dev process. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D85742
2020-08-16 06:52:19 +08:00
impl/machine.cpp
impl/system.cpp
impl/utils.cpp
impl/msgpack.cpp
[openmp][libomptarget] Include header from LLVM source tree [openmp][libomptarget] Include header from LLVM source tree The change is to the amdgpu plugin so is unlikely to break anything. The point of contention is whether libomptarget can depend on LLVM. A community discussion was cautiously not opposed yesterday. This introduces a compile time dependency on the LLVM source tree, in this case expressed as skipping the building of the plugin if LLVM_MAIN_INCLUDE_DIR is not set. One the source files will #include llvm/Frontend/OpenMP/OMPGridValues.h, instead of copy&pasting the numbers across. For users that download the monorepo, the llvm tree is already on disk. This will inconvenience users who download only the openmp source as a tar, as they would now also have to download (at least a file or two) from the llvm source, if they want to build the parts of the openmp project that (post this patch) depend on llvm. There was interest expressed in going further - using llvm tools as part of building libomp, or linking against llvm libraries. That seems less clear cut an improvement and worthy of further discussion. This patch seeks only to change policy to support openmp depending on the llvm source tree. Including in the other direction, or using libraries / tools etc, are purposefully out of scope. Reviewers are a best guess at interested parties, please feel free to add others Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D87841
2020-10-15 22:43:39 +08:00
src/rtl.cpp
[libomptarget] Implement host plugin for amdgpu [libomptarget] Implement host plugin for amdgpu Replacement for D71384. Primary difference is inlining the dependency on atmi followed by extensive simplification and bugfixes. This is the latest version from https://github.com/ROCm-Developer-Tools/amd-llvm-project/tree/aomp12 with minor patches and a rename from hsa to amdgpu, on the basis that this can't be used by other implementations of hsa without additional work. This will not build unless the ROCM_DIR variable is passed so won't break other builds. That variable is used to locate two amdgpu specific libraries that ship as part of rocm: libhsakmt at https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface libhsa-runtime64 at https://github.com/RadeonOpenCompute/ROCR-Runtime These libraries build from source. The build scripts in those repos are for shared libraries, but can be adapted to statically link both into this plugin. There are caveats. - This works well enough to run various tests and benchmarks, and will be used to support the current clang bring up - It is adequately thread safe for the above but there will be races remaining - It is not stylistically correct for llvm, though has had clang-format run - It has suboptimal memory management and locking strategies - The debug printing / error handling is inconsistent I would like to contribute this pretty much as-is and then improve it in-tree. This would be advantagous because the aomp12 branch that was in use for fixing this codebase has just been joined with the amd internal rocm dev process. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D85742
2020-08-16 06:52:19 +08:00
)
# Install plugin under the lib destination folder.
# When we build for debug, OPENMP_LIBDIR_SUFFIX get set to -debug
install(TARGETS omptarget.rtl.amdgpu LIBRARY DESTINATION "lib${OPENMP_LIBDIR_SUFFIX}")
[libomptarget][amdgpu] Update plugin CMake to work with latest rocr library
2020-08-27 03:01:42 +08:00
set_property(TARGET omptarget.rtl.amdgpu PROPERTY INSTALL_RPATH "$ORIGIN")
[libomptarget] Implement host plugin for amdgpu [libomptarget] Implement host plugin for amdgpu Replacement for D71384. Primary difference is inlining the dependency on atmi followed by extensive simplification and bugfixes. This is the latest version from https://github.com/ROCm-Developer-Tools/amd-llvm-project/tree/aomp12 with minor patches and a rename from hsa to amdgpu, on the basis that this can't be used by other implementations of hsa without additional work. This will not build unless the ROCM_DIR variable is passed so won't break other builds. That variable is used to locate two amdgpu specific libraries that ship as part of rocm: libhsakmt at https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface libhsa-runtime64 at https://github.com/RadeonOpenCompute/ROCR-Runtime These libraries build from source. The build scripts in those repos are for shared libraries, but can be adapted to statically link both into this plugin. There are caveats. - This works well enough to run various tests and benchmarks, and will be used to support the current clang bring up - It is adequately thread safe for the above but there will be races remaining - It is not stylistically correct for llvm, though has had clang-format run - It has suboptimal memory management and locking strategies - The debug printing / error handling is inconsistent I would like to contribute this pretty much as-is and then improve it in-tree. This would be advantagous because the aomp12 branch that was in use for fixing this codebase has just been joined with the amd internal rocm dev process. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D85742
2020-08-16 06:52:19 +08:00
target_link_libraries(
omptarget.rtl.amdgpu
[libomptarget][amdgpu] Update plugin CMake to work with latest rocr library
2020-08-27 03:01:42 +08:00
PRIVATE
[OpenMP] Take elf_common.c as a interface library For now `elf_common.c` is taken as a common part included into different plugin implementations directly via `#include "../../common/elf_common.c"`, which is not a best practice. Since it is simple enough such that we don't need to create a real library for it, we just take it as a interface library so that other targets can link it directly. Another advantage of this method is, we don't need to add the folder into header search path which can potentially pollute the search path. VE and AMD platforms have not been tested because I don't have target machines. Reviewed By: JonChesterfield Differential Revision: https://reviews.llvm.org/D94443
2021-01-12 06:34:17 +08:00
elf_common
[libomptarget][amdgpu] Update plugin CMake to work with latest rocr library
2020-08-27 03:01:42 +08:00
hsa-runtime64::hsa-runtime64
pthread dl elf
[libomptarget] Implement host plugin for amdgpu [libomptarget] Implement host plugin for amdgpu Replacement for D71384. Primary difference is inlining the dependency on atmi followed by extensive simplification and bugfixes. This is the latest version from https://github.com/ROCm-Developer-Tools/amd-llvm-project/tree/aomp12 with minor patches and a rename from hsa to amdgpu, on the basis that this can't be used by other implementations of hsa without additional work. This will not build unless the ROCM_DIR variable is passed so won't break other builds. That variable is used to locate two amdgpu specific libraries that ship as part of rocm: libhsakmt at https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface libhsa-runtime64 at https://github.com/RadeonOpenCompute/ROCR-Runtime These libraries build from source. The build scripts in those repos are for shared libraries, but can be adapted to statically link both into this plugin. There are caveats. - This works well enough to run various tests and benchmarks, and will be used to support the current clang bring up - It is adequately thread safe for the above but there will be races remaining - It is not stylistically correct for llvm, though has had clang-format run - It has suboptimal memory management and locking strategies - The debug printing / error handling is inconsistent I would like to contribute this pretty much as-is and then improve it in-tree. This would be advantagous because the aomp12 branch that was in use for fixing this codebase has just been joined with the amd internal rocm dev process. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D85742
2020-08-16 06:52:19 +08:00
"-Wl,--version-script=${CMAKE_CURRENT_SOURCE_DIR}/../exports"
"-Wl,-z,defs"
)
# Report to the parent scope that we are building a plugin for amdgpu
set(LIBOMPTARGET_SYSTEM_TARGETS "${LIBOMPTARGET_SYSTEM_TARGETS} amdgcn-amd-amdhsa" PARENT_SCOPE)