Magic-Mirror/llvm-capstone
1
0
Fork 0
mirror of https://github.com/capstone-engine/llvm-capstone.git synced 2024-11-23 22:00:10 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[libomptarget] Initial documentation on amdgpu offload

Browse Source 
[libomptarget] Initial documentation on amdgpu offload

Reviewed By: jdoerfert

Differential Revision: https://reviews.llvm.org/D101927
This commit is contained in:
Jon Chesterfield 2021-05-05 19:58:51 +01:00
parent 18959a6a09
commit 25fe17d3c1
1 changed files with 72 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

80
openmp/docs/SupportAndFAQ.rst
View File

@ -49,20 +49,16 @@ All patches go through the regular `LLVM review process
.. _build_offload_capable_compiler:
Q: How to build an OpenMP offload capable compiler?
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Q: How to build an OpenMP GPU offload capable compiler?
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
To build an *effective* OpenMP offload capable compiler, only one extra CMake
option, `LLVM_ENABLE_RUNTIMES="openmp"`, is needed when building LLVM (Generic
information about building LLVM is available `here <https://llvm.org/docs/GettingStarted.html>`__.).
Make sure all backends that are targeted by OpenMP to be enabled. By default,
Clang will be built with all backends enabled.
If your build machine is not the target machine or automatic detection of the
available GPUs failed, you should also set:
- `CLANG_OPENMP_NVPTX_DEFAULT_ARCH=sm_XX` where `XX` is the architecture of your GPU, e.g, 80.
- `LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITIES=YY` where `YY` is the numeric compute capacity of your GPU, e.g., 75.
For Nvidia offload, please see :ref:`_build_nvidia_offload_capable_compiler`.
For AMDGPU offload, please see :ref:`_build_amdgpu_offload_capable_compiler`.
.. note::
The compiler that generates the offload code should be the same (version) as
@ -71,7 +67,75 @@ available GPUs failed, you should also set:
.. _advanced_builds: https://llvm.org//docs/AdvancedBuilds.html
.. _build_nvidia_offload_capable_compiler:
Q: How to build an OpenMP NVidia offload capable compiler?
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
The Cuda SDK is required on the machine that will execute the openmp application.
If your build machine is not the target machine or automatic detection of the
available GPUs failed, you should also set:
- `CLANG_OPENMP_NVPTX_DEFAULT_ARCH=sm_XX` where `XX` is the architecture of your GPU, e.g, 80.
- `LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITIES=YY` where `YY` is the numeric compute capacity of your GPU, e.g., 75.
.. _build_amdgpu_offload_capable_compiler:
Q: How to build an OpenMP AMDGPU offload capable compiler?
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
A subset of the `ROCm <https://github.com/radeonopencompute>` toolchain is
required to build the LLVM toolchain and to execute the openmp application.
Either install ROCm somewhere that cmake's find_package can locate it, or
build the required subcomponents ROCt and ROCr from source.
The two components used are ROCT-Thunk-Interface, roct, and ROCR-Runtime,
rocr. Roct is the userspace part of the linux driver. It calls into the
driver which ships with the linux kernel. It is an implementation detail of
Rocr from OpenMP's perspective. Rocr is an implementation of `HSA <http://www.hsafoundation.com>`.
SOURCE_DIR=same-as-llvm-source # e.g. the checkout of llvm-project, next to openmp
BUILD_DIR=somewhere
INSTALL_PREFIX=same-as-llvm-install
cd $SOURCE_DIR
git clone git@github.com:RadeonOpenCompute/ROCT-Thunk-Interface.git -b roc-4.1.x --single-branch
git clone git@github.com:RadeonOpenCompute/ROCR-Runtime.git -b rocm-4.1.x --single-branch
cd $BUILD_DIR && mkdir roct && cd roct
cmake $SOURCE_DIR/ROCT-Thunk-Interface/ -DCMAKE_INSTALL_PREFIX=$INSTALL_PREFIX -DCMAKE_BUILD_TYPE=Release -DBUILD_SHARED_LIBS=OFF
make && make install
cd $BUILD_DIR && mkdir rocr && cd rocr
cmake $SOURCE_DIR/ROCR-Runtime/src -DIMAGE_SUPPORT=OFF -DCMAKE_INSTALL_PREFIX=$INSTALL_PREFIX -DCMAKE_BUILD_TYPE=Release -DBUILD_SHARED_LIBS=ON
make && make install
IMAGE_SUPPORT requires building rocr with clang and is not used by openmp.
Provided cmake's find_package can find the ROCR-Runtime package, LLVM will
build a tool `bin/amdgpu-arch` which will print a string like 'gfx906' when
run if it recognises a GPU on the local system. LLVM will also build a shared
library, libomptarget.rtl.amdgpu.so, which is linked against rocr.
With those libraries installed, then LLVM build and installed, try:
clang -O2 -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa example.c -o example && ./example
Q: What are the known limitations of OpenMP AMDGPU offload?
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
LD_LIBRARY_PATH is presently required to find the openmp libraries.
There is no libc. That is, malloc and printf do not exist. Also no libm, so
functions like cos(double) will not work from target regions.
Cards from the gfx10 line, 'navi', that use wave32 are not yet implemented.
Some versions of the driver for the radeon vii (gfx906) will error unless the
environment variable 'export HSA_IGNORE_SRAMECC_MISREPORT=1' is set.
It is a recent addition to LLVM and the implementation differs from that which
has been shipping in ROCm and AOMP for some time. Early adopters will encounter
bugs.
Q: Does OpenMP offloading support work in pre-packaged LLVM releases?
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^