llvm-project/polly
Philip Pfaffe 4d24093ac4 Back out of GPU Codegen if NVPTX is not available
Summary:
When enabling GPU codegen in polly, CMake will fail if NVPTX is not a target
supported by the LLVM polly is being built against. In that case, GPU codegen
should be switched off.

Reviewers: Meinersbur, grosser, bollu

Reviewed By: Meinersbur

Subscribers: mgorny, bollu, pollydev, llvm-commits

Differential Revision: https://reviews.llvm.org/D47888

llvm-svn: 334233
2018-06-07 21:10:49 +00:00
..
cmake [CMake] Use only keyword-version of target_link_library. NFC. 2018-01-12 16:09:18 +00:00
docs [doc] Overhaul doc on preparing IR for processing by Polly. 2018-04-06 19:24:18 +00:00
include/polly [OpTree] Introduce shortcut for computing the def->target mapping. NFCI. 2018-06-06 21:37:35 +00:00
lib Run clang-format 2018-06-07 08:32:13 +00:00
test [Acc] Followup for r333105: Fix one additional testcase 2018-05-24 10:18:09 +00:00
tools [GPUJIT] Improved temporary file handling. 2017-09-19 10:41:29 +00:00
unittests Remove the last uses of isl::give and isl::take 2018-04-29 00:28:26 +00:00
utils [arc] Remove unittesting from arcconfig 2018-05-15 13:43:42 +00:00
www [Polly] Information about generalized matrix multiplication 2017-09-24 19:00:25 +00:00
.arcconfig [arc] Remove unittesting from arcconfig 2018-05-15 13:43:42 +00:00
.arclint [External] Move lib/JSON to lib/External/JSON. NFC. 2017-02-05 15:26:56 +00:00
.gitattributes
.gitignore Do not track the isl PDF manual in SVN 2017-01-16 11:48:03 +00:00
CMakeLists.txt Back out of GPU Codegen if NVPTX is not available 2018-06-07 21:10:49 +00:00
CREDITS.txt
LICENSE.txt [External] Move lib/JSON to lib/External/JSON. NFC. 2017-02-05 15:26:56 +00:00
README Test commit 2017-06-28 12:58:44 +00:00

README

Polly - Polyhedral optimizations for LLVM
-----------------------------------------
http://polly.llvm.org/

Polly uses a mathematical representation, the polyhedral model, to represent and
transform loops and other control flow structures. Using an abstract
representation it is possible to reason about transformations in a more general
way and to use highly optimized linear programming libraries to figure out the
optimal loop structure. These transformations can be used to do constant
propagation through arrays, remove dead loop iterations, optimize loops for
cache locality, optimize arrays, apply advanced automatic parallelization, drive
vectorization, or they can be used to do software pipelining.