llvm-project/polly/lib/CodeGen
Tobias Grosser b299d28181 Add preliminary implementation for GPGPU code generation.
Translate the selected parallel loop body into a ptx string and run it
with cuda driver API. We limit this preliminary implementation to
target the following special test cases:
  - Support only 2-dimensional parallel loops with or without only one
    innermost non-parallel loop.
  - Support write memory access to only one array in a SCoP.

Contributed by:  Yabin Hu <yabin.hwu@gmail.com>

llvm-svn: 160164
2012-07-13 07:21:00 +00:00
..
BlockGenerators.cpp Allow polly ask bb-vectorizer to vectorize the loop body. 2012-05-06 10:22:19 +00:00
CMakeLists.txt Add preliminary implementation for GPGPU code generation. 2012-07-13 07:21:00 +00:00
Cloog.cpp CLooG: Do not take into account the context 2012-06-05 19:31:08 +00:00
CodeGeneration.cpp Add preliminary implementation for GPGPU code generation. 2012-07-13 07:21:00 +00:00
IslCodeGeneration.cpp add a check for ISL codegen at configure time 2012-05-07 16:20:07 +00:00
LoopGenerators.cpp Mark the increments of the generated induction variables 'NSW' 2012-05-29 09:11:59 +00:00
Makefile
PTXGenerator.cpp Add preliminary implementation for GPGPU code generation. 2012-07-13 07:21:00 +00:00
Utils.cpp Speculative update to Polly for LLVM r159421 which moved IRBuilder.h. 2012-06-29 12:39:49 +00:00