Development activity of OpenMP support in clang/llvm compiler has moved to www.llvm.org. Please get OpenMP-enabled clang (OpenMP 3.1 is fully supported in clang/llvm 3.7) and contribute to its further development there. This web-site is maintained for archival purposes only.
The OpenMP (Open Multi-Processing) specification is a standard for a set of compiler directives, library routines, and environment variables that can be used to specify shared memory parallelism in Fortran and C/C++ programs.
This project implements OpenMP support in the Clang C language family front-end for the LLVM compiler. The current scope of the project is to support the OpenMP 4.0 specification.
News
November 27, 2015 - Further development of OpenMP support in clang/llvm compiler moved to www.llvm.org.
This site is maintained for archival purposes only. Thank you to everyone who contributed all these years!
September 9, 2014 - Upgrade to clang/LLVM 3.5, updated link to LLVM
OpenMP library.
June 10, 2014 - Initial support of omp teams distribute [simd]
,omp
target teams distribute [simd]
,omp teams distribute
parallel for [simd]
and omp target teams distribute
parallel for [simd]
directives (just parsing and semantic
analysis).
June 9, 2014 - Initial support of omp target data
,omp
target update
and omp target teams
directives
(just parsing and semantic analysis).
May 6, 2014 - Initial support of omp target, teams, distribute,
distribute simd, distribute for, distribute parallel for, distribute
parallel for simd
and omp declare target
directives
(no actual offloading, just parsing and semantic analysis).
April 11, 2014 - Added support of omp cancel
and omp
cancellation point
directives.
March 14, 2014 - Added support of depend
clause in omp
task
directive, support for omp parallel for simd
directive.
February 6, 2014 - Upgrade to clang/llvm 3.4.
December 6, 2013 - Added support of variable length arrays in OpenMP
constructs.
November 25, 2013 - Added support of omp simd
, omp
declare reduction
directives.
September 27, 2013 - Added support of proc_bind
clause.
August 23, 2013 - Initial release.
Try OpenMP/Clang
Getting the source code
$ git clone https://github.com/clang-omp/llvm
$ git clone https://github.com/clang-omp/compiler-rt llvm/projects/compiler-rt
$ git clone -b clang-omp https://github.com/clang-omp/clang llvm/tools/clang
The source code structure follows Clang/LLVM: http://llvm.org/docs/GettingStarted.html.
To run (rather than just compile) code you need to get and build an Intel® OpenMP* Runtime Library.
Also you can try to use trunk-based version of the compiler (supported by Hal Finkel)
$ git clone https://github.com/clang-omp/llvm_trunk llvm
$ git clone https://github.com/clang-omp/compiler-rt_trunk llvm/projects/compiler-rt
$ git clone https://github.com/clang-omp/clang_trunk llvm/tools/clang
Building
To build clang with OpenMP support just follow the clang/LLVM
compiler's standard build procedure (see Getting
Started: Building and Running Clang).
Using
To use the newly installed compiler, add the following to your environment. On Mac OS X, replace LD_LIBRARY_PATH with DYLD_LIBRARY_PATH.
export PATH=/install/prefix/bin:$PATH
export C_INCLUDE_PATH=/install/prefix/include:<OpenMP include path>:$C_INCLUDE_PATH
export CPLUS_INCLUDE_PATH=/install/prefix/include:<OpenMP include path>:$CPLUS_INCLUDE_PATH
export LIBRARY_PATH=/install/prefix/lib:<OpenMP library path>:$LIBRARY_PATH
export LD_LIBRARY_PATH=/install/prefix/lib:<OpenMP library path>:$LD_LIBRARY_PATH
When you build a program that uses OpenMP directives, add the following options to enable OpenMP support and link to the runtime library.
-fopenmp
Using clang-omp with Xcode
Instructions are provided by Sebastian Stenzel.
- Install clang-omp using homebrew:
brew install llvm
. - Add llvm binaries to your path using :
echo 'export PATH="/usr/local/opt/llvm/bin:$PATH"' >> ~/.bash_profile
. - Create a new Xcode project.
- Under Build Settings
- Add a new user-defined setting CC
with the value
/usr/local/bin/clang-omp
- Add
-fopenmp
to Other C Flags - Add
/usr/local/include
to Header Search Paths - Set Enable Modules (C and
Objective-C) to
No
.
- Add a new user-defined setting CC
with the value
- Under Build Phases
- Add
/usr/local/lib/libiomp5.dylib
to Link Binary With Libraries
- Add
#include <libiomp/omp.h>
and start
using #pragma omp ...
in your source code.
A simple example
Confirm that the compiler is working correctly by saving the above code to a file.
$ clang -fopenmp hello.c -o hello
$ ./hello
Compilation should proceed with no errors or warnings.
Execute the output ./hello
. You should see more than
one “Hello” line with different thread numbers. Note that the lines
may be mixed together. If you see only one, try setting the
environment variable OMP_NUM_THREADS
to some number (say 4) and try again.
If you would like to see performance impact, you can try to compile and execute a more complex example Matrices Multiplication.
Contribute
We welcome contributions of all kinds: patches, code reviews, testing and bug reports.
However, as any other open source project, we have to maintain some level of control to prevent complete chaos and keep a single architectural direction. You can send your patches here for review and commit; also, we are very open with granting commit access rights to recognized members of Clang/LLVM community.
We plan eventually to contribute this OpenMP implementation to the Clang trunk, where it will be governed by existing Clang/LLVM community development policies.
Status
Full support for OpenMP 3.1 and most of OpenMP 4.0 features (except for offloading) are implemented. This implementation relies on the Intel OpenMP API, and should be used along with Intel® OpenMP* Runtime Library that supports that API (available from www.openmprtl.org).
The following openly available OpenMP test suites pass:
- OpenMP Validation Suite by OpenUH Research Compiler - passed 119 tests of 123.
Supported platforms
OS: Linux or Mac OS X
Architecture: x86, x86-64, PowerPC, Arm
Important Note
Please note that this is a preliminary version. While everything is carefully tested and works fine, there are known internal design quality issues. We plan to refactor some parts of the code before submitting them to Clang trunk. And yes, any help with this would be appreciated!
Among known design issues are:
- Combined constructs (
#pragma omp parallel for
and#pragma omp parallel sections
). Currently these constructs are represented as a pair of#pragma omp parallel
and#pragma omp for/sections
constructs. This solution leads to ugly representation in AST because of the troubles with the variables capturing. - Calculation of iteration indices for
#pragma omp for
is not quite optimal. AST representation of this construct also is not very good and should be re-designed. - Analysis of atomic constructs and loops should be reworked for better diagnostics and readability.
External Projects
External projects based on OpenMP implementation hosted here. If you want your project to be listed, please let us know.
- Experimental "check" clause for "parallel for" pragma by Luis Felipe Mattos and Juan Salamanca from UNICAMP (Brazil).
License
LLVM, Clang, and Compiler-rt are distributed under LLVM's the University of Illinois/NCSA Open Source License. In addition to the "UIUC" BSD-Style license license, the runtime library component of LLVM (Compiler_rt) is also licensed under the MIT License. For details, including information about third-party components, see LICENSE.txt in the code repositories.
Contact
If you would like to report a bug, or make a feature request, you can submit an issue in Github here.