llvm-project/polly
Tobias Grosser fe6d9849a1 Add new website for Polly
Use the content of the Polly wiki page[1] to create a new website. I do not yet
plan to officially promote this website, but it is already a solid base that we
can improve and peer review.

[1] http://wiki.llvm.org/Polly

llvm-svn: 130689
2011-05-02 07:48:29 +00:00
..
autoconf Add initial version of Polly 2011-04-29 06:27:02 +00:00
cmake Add initial version of Polly 2011-04-29 06:27:02 +00:00
docs Add initial version of Polly 2011-04-29 06:27:02 +00:00
include ScopInfo: Rememeber the induction variable and its parent loop at the same thime. 2011-04-30 03:26:51 +00:00
lib ScopInfo: Rememeber the induction variable and its parent loop at the same thime. 2011-04-30 03:26:51 +00:00
test Partial support test polly for out of tree build. 2011-04-29 07:34:54 +00:00
tools Add initial version of Polly 2011-04-29 06:27:02 +00:00
utils Add a converter from jscop to iscc input 2011-04-29 06:29:20 +00:00
www Add new website for Polly 2011-05-02 07:48:29 +00:00
CMakeLists.txt Add initial version of Polly 2011-04-29 06:27:02 +00:00
CREDITS.txt Add e-mail to credits file. 2011-04-29 07:54:20 +00:00
LICENSE.txt Add initial version of Polly 2011-04-29 06:27:02 +00:00
Makefile Add initial version of Polly 2011-04-29 06:27:02 +00:00
Makefile.common.in Add initial version of Polly 2011-04-29 06:27:02 +00:00
Makefile.config.in Add initial version of Polly 2011-04-29 06:27:02 +00:00
README Add initial version of Polly 2011-04-29 06:27:02 +00:00
configure Add initial version of Polly 2011-04-29 06:27:02 +00:00

README

Polly - Polyhedral optimizations for LLVM

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.