llvm-project/libclc
Vedran Miletic 79b7f4c125 configure.py: Add gfx900 (Vega, Raven)
Sort amdgcn-- and amdgcn--amdhsa in a consistent way.

llvm-svn: 319017
2017-11-27 11:14:06 +00:00
..
amdgcn/lib amdgcn: Add missing datalayout info to .ll files 2017-10-20 21:10:18 +00:00
amdgcn-amdhsa/lib Fix amdgcn-amdhsa on llvm-3.9 2017-09-29 19:06:52 +00:00
amdgpu/lib amdgpu: Add workaround for unimplemented llvm.exp intrinsic 2017-11-10 22:16:25 +00:00
build configure.py: Make python3 friendly 2017-08-02 15:00:59 +00:00
generic math: Implement minmag 2017-11-15 04:10:39 +00:00
ptx/lib ptx: Use __clc_nextafter to implement nextafter 2017-10-08 19:34:00 +00:00
ptx-nvidiacl/lib Implement mem_fence on ptx 2017-10-09 19:43:04 +00:00
r600/lib r600: Add missing datalayout to .ll files 2017-10-20 21:00:31 +00:00
test
utils Restore support for llvm-3.9 2017-09-29 19:06:41 +00:00
www
.gitignore .gitignore: Ignore amdgcn-mesa object directory 2017-02-24 20:32:18 +00:00
.travis.yml travis: enable checks of nvptx libraries 2017-10-10 18:10:25 +00:00
CREDITS.TXT
LICENSE.TXT
README.TXT
check_external_calls.sh check_external_calls.sh: Print number of calls in tested file. 2017-10-08 20:07:56 +00:00
compile-test.sh
configure.py configure.py: Add gfx900 (Vega, Raven) 2017-11-27 11:14:06 +00:00

README.TXT

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

libclc
------

libclc is an open source, BSD licensed implementation of the library
requirements of the OpenCL C programming language, as specified by the
OpenCL 1.1 Specification. The following sections of the specification
impose library requirements:

  * 6.1: Supported Data Types
  * 6.2.3: Explicit Conversions
  * 6.2.4.2: Reinterpreting Types Using as_type() and as_typen()
  * 6.9: Preprocessor Directives and Macros
  * 6.11: Built-in Functions
  * 9.3: Double Precision Floating-Point
  * 9.4: 64-bit Atomics
  * 9.5: Writing to 3D image memory objects
  * 9.6: Half Precision Floating-Point

libclc is intended to be used with the Clang compiler's OpenCL frontend.

libclc is designed to be portable and extensible. To this end, it provides
generic implementations of most library requirements, allowing the target
to override the generic implementation at the granularity of individual
functions.

libclc currently only supports the PTX target, but support for more
targets is welcome.

Compiling and installing with Make
----------------------------------

$ ./configure.py --with-llvm-config=/path/to/llvm-config && make
$ make install

Note you can use the DESTDIR Makefile variable to do staged installs.

$ make install DESTDIR=/path/for/staged/install

Compiling and installing with Ninja
-----------------------------------

$ ./configure.py -g ninja --with-llvm-config=/path/to/llvm-config && ninja
$ ninja install

Note you can use the DESTDIR environment variable to do staged installs.

$ DESTDIR=/path/for/staged/install ninja install

Website
-------

http://www.pcc.me.uk/~peter/libclc/