llvm-project/polly
Michael Kruse 1aad76c18f [CodeGen] Add invalidation of the loop SCEVs after merge block generation.
The SCEVs of loops surrounding the escape users of a merge blocks are
forgotten, so that loop trip counts based on old values can be revoked.

This fixes llvm.org//PR32536

Contributed-by: Baranidharan Mohan <mbdharan@gmail.com>

Differential Revision: https://reviews.llvm.org/D33195

llvm-svn: 303561
2017-05-22 15:36:53 +00:00
..
cmake [Polly][CMake] Fix variable name in target exports 2017-05-12 10:39:38 +00:00
docs [Docs] Use ReadTheDocs theme if available. 2017-05-22 13:36:15 +00:00
include/polly [CodeGen] Add invalidation of the loop SCEVs after merge block generation. 2017-05-22 15:36:53 +00:00
lib [CodeGen] Add invalidation of the loop SCEVs after merge block generation. 2017-05-22 15:36:53 +00:00
test [CodeGen] Add invalidation of the loop SCEVs after merge block generation. 2017-05-22 15:36:53 +00:00
tools [GPUJIT] Disabled gcc's -Wpedantic for use of dlsym 2017-05-10 11:51:44 +00:00
unittests Drop nonexisting ScopPassManager directory 2017-05-15 14:12:30 +00:00
utils Revise polly-{update|check}-format targets 2015-09-14 16:59:50 +00:00
www Add two Polly images 2017-04-05 11:50:31 +00:00
.arcconfig Upgrade all the .arcconfigs to https. 2016-07-14 13:15:37 +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 [Polly][CMake] Exclude isl_config from the polly-check-format target. 2017-05-15 13:20:26 +00:00
CREDITS.txt Add myself to the credits 2014-08-10 03:37:29 +00:00
LICENSE.txt [External] Move lib/JSON to lib/External/JSON. NFC. 2017-02-05 15:26:56 +00:00
README

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.