1Support, Getting Involved, and FAQ
2==================================
3
4Please do not hesitate to reach out to us via [email protected] or join
5one of our :ref:`regular calls <calls>`. Some common questions are answered in
6the :ref:`faq`.
7
8.. _calls:
9
10Calls
11-----
12
13OpenMP in LLVM Technical Call
14^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
15
16-   Development updates on OpenMP (and OpenACC) in the LLVM Project, including Clang, optimization, and runtime work.
17-   Join `OpenMP in LLVM Technical Call <https://bluejeans.com/544112769//webrtc>`__.
18-   Time: Weekly call on every Wednesday 7:00 AM Pacific time.
19-   Meeting minutes are `here <https://docs.google.com/document/d/1Tz8WFN13n7yJ-SCE0Qjqf9LmjGUw0dWO9Ts1ss4YOdg/edit>`__.
20-   Status tracking `page <https://openmp.llvm.org/docs>`__.
21
22
23OpenMP in Flang Technical Call
24^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
25-   Development updates on OpenMP and OpenACC in the Flang Project.
26-   Join `OpenMP in Flang Technical Call <https://bit.ly/39eQW3o>`_
27-   Time: Weekly call on every Thursdays 8:00 AM Pacific time.
28-   Meeting minutes are `here <https://docs.google.com/document/d/1yA-MeJf6RYY-ZXpdol0t7YoDoqtwAyBhFLr5thu5pFI>`__.
29-   Status tracking `page <https://docs.google.com/spreadsheets/d/1FvHPuSkGbl4mQZRAwCIndvQx9dQboffiD-xD0oqxgU0/edit#gid=0>`__.
30
31
32.. _faq:
33
34FAQ
35---
36
37.. note::
38   The FAQ is a work in progress and most of the expected content is not
39   yet available. While you can expect changes, we always welcome feedback and
40   additions. Please contact, e.g., through ``[email protected]``.
41
42
43Q: How to contribute a patch to the webpage or any other part?
44^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
45
46All patches go through the regular `LLVM review process
47<https://llvm.org/docs/Contributing.html#how-to-submit-a-patch>`_.
48
49
50.. _build_offload_capable_compiler:
51
52Q: How to build an OpenMP GPU offload capable compiler?
53^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
54To build an *effective* OpenMP offload capable compiler, only one extra CMake
55option, `LLVM_ENABLE_RUNTIMES="openmp"`, is needed when building LLVM (Generic
56information about building LLVM is available `here
57<https://llvm.org/docs/GettingStarted.html>`__.).  Make sure all backends that
58are targeted by OpenMP to be enabled. By default, Clang will be built with all
59backends enabled.  When building with `LLVM_ENABLE_RUNTIMES="openmp"` OpenMP
60should not be enabled in `LLVM_ENABLE_PROJECTS` because it is enabled by
61default.
62
63For Nvidia offload, please see :ref:`build_nvidia_offload_capable_compiler`.
64For AMDGPU offload, please see :ref:`build_amdgpu_offload_capable_compiler`.
65
66.. note::
67  The compiler that generates the offload code should be the same (version) as
68  the compiler that builds the OpenMP device runtimes. The OpenMP host runtime
69  can be built by a different compiler.
70
71.. _advanced_builds: https://llvm.org//docs/AdvancedBuilds.html
72
73.. _build_nvidia_offload_capable_compiler:
74
75Q: How to build an OpenMP NVidia offload capable compiler?
76^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
77The Cuda SDK is required on the machine that will execute the openmp application.
78
79If your build machine is not the target machine or automatic detection of the
80available GPUs failed, you should also set:
81
82- `CLANG_OPENMP_NVPTX_DEFAULT_ARCH=sm_XX` where `XX` is the architecture of your GPU, e.g, 80.
83- `LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITIES=YY` where `YY` is the numeric compute capacity of your GPU, e.g., 75.
84
85
86.. _build_amdgpu_offload_capable_compiler:
87
88Q: How to build an OpenMP AMDGPU offload capable compiler?
89^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
90A subset of the `ROCm <https://github.com/radeonopencompute>`_ toolchain is
91required to build the LLVM toolchain and to execute the openmp application.
92Either install ROCm somewhere that cmake's find_package can locate it, or
93build the required subcomponents ROCt and ROCr from source.
94
95The two components used are ROCT-Thunk-Interface, roct, and ROCR-Runtime, rocr.
96Roct is the userspace part of the linux driver. It calls into the driver which
97ships with the linux kernel. It is an implementation detail of Rocr from
98OpenMP's perspective. Rocr is an implementation of `HSA
99<http://www.hsafoundation.com>`_.
100
101.. code-block:: text
102
103  SOURCE_DIR=same-as-llvm-source # e.g. the checkout of llvm-project, next to openmp
104  BUILD_DIR=somewhere
105  INSTALL_PREFIX=same-as-llvm-install
106
107  cd $SOURCE_DIR
108  git clone [email protected]:RadeonOpenCompute/ROCT-Thunk-Interface.git -b roc-4.2.x \
109    --single-branch
110  git clone [email protected]:RadeonOpenCompute/ROCR-Runtime.git -b rocm-4.2.x \
111    --single-branch
112
113  cd $BUILD_DIR && mkdir roct && cd roct
114  cmake $SOURCE_DIR/ROCT-Thunk-Interface/ -DCMAKE_INSTALL_PREFIX=$INSTALL_PREFIX \
115    -DCMAKE_BUILD_TYPE=Release -DBUILD_SHARED_LIBS=OFF
116  make && make install
117
118  cd $BUILD_DIR && mkdir rocr && cd rocr
119  cmake $SOURCE_DIR/ROCR-Runtime/src -DIMAGE_SUPPORT=OFF \
120    -DCMAKE_INSTALL_PREFIX=$INSTALL_PREFIX -DCMAKE_BUILD_TYPE=Release \
121    -DBUILD_SHARED_LIBS=ON
122  make && make install
123
124``IMAGE_SUPPORT`` requires building rocr with clang and is not used by openmp.
125
126Provided cmake's find_package can find the ROCR-Runtime package, LLVM will
127build a tool ``bin/amdgpu-arch`` which will print a string like ``gfx906`` when
128run if it recognises a GPU on the local system. LLVM will also build a shared
129library, libomptarget.rtl.amdgpu.so, which is linked against rocr.
130
131With those libraries installed, then LLVM build and installed, try:
132
133.. code-block:: shell
134
135    clang -O2 -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa example.c -o example && ./example
136
137Q: What are the known limitations of OpenMP AMDGPU offload?
138^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
139LD_LIBRARY_PATH or rpath/runpath are required to find libomp.so and libomptarget.so
140
141There is no libc. That is, malloc and printf do not exist. Libm is implemented in terms
142of the rocm device library, which will be searched for if linking with '-lm'.
143
144Some versions of the driver for the radeon vii (gfx906) will error unless the
145environment variable 'export HSA_IGNORE_SRAMECC_MISREPORT=1' is set.
146
147It is a recent addition to LLVM and the implementation differs from that which
148has been shipping in ROCm and AOMP for some time. Early adopters will encounter
149bugs.
150
151Q: What are the LLVM components used in offloading and how are they found?
152^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
153The libraries used by an executable compiled for target offloading are:
154- ``libomp.so`` (or similar), the host openmp runtime
155- ``libomptarget.so``, the target-agnostic target offloading openmp runtime
156- plugins loaded by libomptarget.so:
157  - ``libomptarget.rtl.amdgpu.so``
158  - ``libomptarget.rtl.cuda.so``
159  - ``libomptarget.rtl.x86_64.so``
160  - ``libomptarget.rtl.ve.so``
161  - and others
162- dependencies of those plugins, e.g. cuda/rocr for nvptx/amdgpu
163
164The compiled executable is dynamically linked against a host runtime, e.g.
165``libomp.so``, and against the target offloading runtime, ``libomptarget.so``. These
166are found like any other dynamic library, by setting rpath or runpath on the
167executable, by setting ``LD_LIBRARY_PATH``, or by adding them to the system search.
168
169``libomptarget.so`` has rpath or runpath (whichever the system default is) set to
170``$ORIGIN``, and the plugins are located next to it, so it will find the plugins
171without any environment variables set. If ``LD_LIBRARY_PATH`` is set, whether it
172overrides which plugin is found depends on whether your system treats ``-Wl,-rpath``
173as RPATH or RUNPATH.
174
175The plugins will try to find their dependencies in plugin-dependent fashion.
176
177The cuda plugin is dynamically linked against libcuda if cmake found it at
178compiler build time. Otherwise it will attempt to dlopen ``libcuda.so``. It does
179not have rpath set.
180
181The amdgpu plugin is linked against ROCr if cmake found it at compiler build
182time. Otherwise it will attempt to dlopen ``libhsa-runtime64.so``. It has rpath
183set to ``$ORIGIN``, so installing ``libhsa-runtime64.so`` in the same directory is a
184way to locate it without environment variables.
185
186In addition to those, there is a compiler runtime library called deviceRTL.
187This is compiled from mostly common code into an architecture specific
188bitcode library, e.g. ``libomptarget-nvptx-sm_70.bc``.
189
190Clang and the deviceRTL need to match closely as the interface between them
191changes frequently. Using both from the same monorepo checkout is strongly
192recommended.
193
194Unlike the host side which lets environment variables select components, the
195deviceRTL that is located in the clang lib directory is preferred. Only if
196it is absent, the ``LIBRARY_PATH`` environment variable is searched to find a
197bitcode file with the right name. This can be overridden by passing a clang
198flag, ``--libomptarget-nvptx-bc-path`` or ``--libomptarget-amdgcn-bc-path``. That
199can specify a directory or an exact bitcode file to use.
200
201
202Q: Does OpenMP offloading support work in pre-packaged LLVM releases?
203^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
204For now, the answer is most likely *no*. Please see :ref:`build_offload_capable_compiler`.
205
206Q: Does OpenMP offloading support work in packages distributed as part of my OS?
207^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
208For now, the answer is most likely *no*. Please see :ref:`build_offload_capable_compiler`.
209
210
211.. _math_and_complex_in_target_regions:
212
213Q: Does Clang support `<math.h>` and `<complex.h>` operations in OpenMP target on GPUs?
214^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
215
216Yes, LLVM/Clang allows math functions and complex arithmetic inside of OpenMP
217target regions that are compiled for GPUs.
218
219Clang provides a set of wrapper headers that are found first when `math.h` and
220`complex.h`, for C, `cmath` and `complex`, for C++, or similar headers are
221included by the application. These wrappers will eventually include the system
222version of the corresponding header file after setting up a target device
223specific environment. The fact that the system header is included is important
224because they differ based on the architecture and operating system and may
225contain preprocessor, variable, and function definitions that need to be
226available in the target region regardless of the targeted device architecture.
227However, various functions may require specialized device versions, e.g.,
228`sin`, and others are only available on certain devices, e.g., `__umul64hi`. To
229provide "native" support for math and complex on the respective architecture,
230Clang will wrap the "native" math functions, e.g., as provided by the device
231vendor, in an OpenMP begin/end declare variant. These functions will then be
232picked up instead of the host versions while host only variables and function
233definitions are still available. Complex arithmetic and functions are support
234through a similar mechanism. It is worth noting that this support requires
235`extensions to the OpenMP begin/end declare variant context selector
236<https://clang.llvm.org/docs/AttributeReference.html#pragma-omp-declare-variant>`__
237that are exposed through LLVM/Clang to the user as well.
238
239Q: What is a way to debug errors from mapping memory to a target device?
240^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
241
242An experimental way to debug these errors is to use :ref:`remote process
243offloading <remote_offloading_plugin>`.
244By using ``libomptarget.rtl.rpc.so`` and ``openmp-offloading-server``, it is
245possible to explicitly perform memory transfers between processes on the host
246CPU and run sanitizers while doing so in order to catch these errors.
247
248Q: Why does my application say "Named symbol not found" and abort when I run it?
249^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
250
251This is most likely caused by trying to use OpenMP offloading with static
252libraries. Static libraries do not contain any device code, so when the runtime
253attempts to execute the target region it will not be found and you will get an
254an error like this.
255
256.. code-block:: text
257
258   CUDA error: Loading '__omp_offloading_fd02_3231c15__Z3foov_l2' Failed
259   CUDA error: named symbol not found
260   Libomptarget error: Unable to generate entries table for device id 0.
261
262Currently, the only solution is to change how the application is built and avoid
263the use of static libraries.
264
265Q: Can I use dynamically linked libraries with OpenMP offloading?
266^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
267
268Dynamically linked libraries can be only used if there is no device code split
269between the library and application. Anything declared on the device inside the
270shared library will not be visible to the application when it's linked.
271
272Q: How to build an OpenMP offload capable compiler with an outdated host compiler?
273^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
274
275Enabling the OpenMP runtime will perform a two-stage build for you.
276If your host compiler is different from your system-wide compiler, you may need
277to set the CMake variable `GCC_INSTALL_PREFIX` so clang will be able to find the
278correct GCC toolchain in the second stage of the build.
279
280For example, if your system-wide GCC installation is too old to build LLVM and
281you would like to use a newer GCC, set the CMake variable `GCC_INSTALL_PREFIX`
282to inform clang of the GCC installation you would like to use in the second stage.
283
284Q: How can I include OpenMP offloading support in my CMake project?
285^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
286
287Currently, there is an experimental CMake find module for OpenMP target
288offloading provided by LLVM. It will attempt to find OpenMP target offloading
289support for your compiler. The flags necessary for OpenMP target offloading will
290be loaded into the ``OpenMPTarget::OpenMPTarget_<device>`` target or the
291``OpenMPTarget_<device>_FLAGS`` variable if successful. Currently supported
292devices are ``AMDGPU`` and ``NVPTX``.
293
294To use this module, simply add the path to CMake's current module path and call
295``find_package``. The module will be installed with your OpenMP installation by
296default. Including OpenMP offloading support in an application should now only
297require a few additions.
298
299.. code-block:: cmake
300
301  cmake_minimum_required(VERSION 3.13.4)
302  project(offloadTest VERSION 1.0 LANGUAGES CXX)
303
304  list(APPEND CMAKE_MODULE_PATH "${PATH_TO_OPENMP_INSTALL}/lib/cmake/openmp")
305
306  find_package(OpenMPTarget REQUIRED NVPTX)
307
308  add_executable(offload)
309  target_link_libraries(offload PRIVATE OpenMPTarget::OpenMPTarget_NVPTX)
310  target_sources(offload PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/src/Main.cpp)
311
312Using this module requires at least CMake version 3.13.4. Supported languages
313are C and C++ with Fortran support planned in the future. Compiler support is
314best for Clang but this module should work for other compiler vendors such as
315IBM, GNU.
316