Tobias Grosser bc653f2031 GPGPU: Do not run mostly sequential kernels in GPU ...

In case sequential kernels are found deeper in the loop tree than any parallel
kernel, the overall scop is probably mostly sequential. Hence, run it on the
CPU.

llvm-svn: 281849

2016-09-18 08:31:09 +00:00

..

BlockGenerators.cpp

Perform copying to created arrays according to the packing transformation

2016-09-14 06:26:09 +00:00

CodegenCleanup.cpp

Try to fix polly buildbots.

2016-07-06 02:21:00 +00:00

CodeGeneration.cpp

Drop '@brief' from doxygen comments

2016-09-02 06:33:33 +00:00

IRBuilder.cpp

Perform copying to created arrays according to the packing transformation

2016-09-14 06:26:09 +00:00

IslAst.cpp

Perform copying to created arrays according to the packing transformation

2016-09-14 06:26:09 +00:00

IslExprBuilder.cpp

Drop '@brief' from doxygen comments

2016-09-02 06:33:33 +00:00

IslNodeBuilder.cpp

Perform copying to created arrays according to the packing transformation

2016-09-14 06:26:09 +00:00

LoopGenerators.cpp

clang-tidy: apply modern-use-nullptr fixes

2016-06-22 16:22:00 +00:00

PPCGCodeGeneration.cpp

GPGPU: Do not run mostly sequential kernels in GPU

2016-09-18 08:31:09 +00:00

RuntimeDebugBuilder.cpp

Update for llvm r274769

2016-07-07 18:03:30 +00:00

Utils.cpp

Duplicate part of the Region interface in the Scop class [NFC]

2016-05-23 12:42:38 +00:00