llvm-project/polly
Tobias Grosser 4eaedde530 GPGPU: Use a tile size of 32 by default
The tile size was previously uninitialized. As a result, it was often zero (aka.
no tiling), which is not what we want in general. More importantly, there was
the risk for arbitrary tile sizes to be choosen, which we did not observe, but
which still is highly problematic.

llvm-svn: 275418
2016-07-14 14:14:02 +00:00
..
cmake Respect LLVM_INSTALL_TOOLCHAIN_ONLY. 2016-06-21 18:14:01 +00:00
docs docs: Remove reference to PoCC 2016-05-17 19:44:16 +00:00
include/polly [NFC] Add full title/author information to "Apply the BLIS matmul optimization pattern" 2016-07-14 10:40:15 +00:00
lib GPGPU: Use a tile size of 32 by default 2016-07-14 14:14:02 +00:00
test GPGPU: Use a tile size of 32 by default 2016-07-14 14:14:02 +00:00
tools GPURuntime: Only print status in debug mode 2016-07-06 03:04:53 +00:00
utils Revise polly-{update|check}-format targets 2015-09-14 16:59:50 +00:00
www [WWW] Mark task as done and me as owner of some task 2016-05-02 11:21:30 +00:00
.arcconfig Upgrade all the .arcconfigs to https. 2016-07-14 13:15:37 +00:00
.arclint Adjusted arc linter config for modern version of arcanist 2015-08-12 09:01:16 +00:00
.gitattributes gitattributes: .png and .txt are no text files 2013-07-28 09:05:20 +00:00
.gitignore Add git patch files to .gitignore 2015-06-23 20:55:01 +00:00
CMakeLists.txt GPGPU: create default initialized PPCG scop and gpu program 2016-07-14 10:22:19 +00:00
CREDITS.txt Add myself to the credits 2014-08-10 03:37:29 +00:00
LICENSE.txt Update copyright year to 2016. 2016-03-30 22:41:38 +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.