review.tizen.org Git - platform/upstream/llvm.git/commit

projects / platform / upstream / llvm.git / commit

summary | shortlog | log | commit | commitdiff | tree
(parent: fd52b95) | patch

author	Matt Arsenault <Matthew.Arsenault@amd.com>
	Thu, 4 Dec 2014 20:38:18 +0000 (20:38 +0000)
committer	Matt Arsenault <Matthew.Arsenault@amd.com>
	Thu, 4 Dec 2014 20:38:18 +0000 (20:38 +0000)
commit	43fae6c85512109a16ba14df898fef7a44299afe
tree	b8f2a36b2ff26d68cd3e458410466fdafe33aa5c	tree \| snapshot
parent	fd52b955309788b084cd0e57c1c4a6454734f26a	commit \| diff

Add attributes for AMDGPU register limits.

This is a performance hint that can be applied to kernels
to attempt to limit the number of used registers.

llvm-svn: 223384

clang/include/clang/Basic/Attr.td		diff \| blob \| history
clang/include/clang/Basic/AttrDocs.td		diff \| blob \| history
clang/include/clang/Basic/DiagnosticSemaKinds.td		diff \| blob \| history
clang/include/clang/Sema/AttributeList.h		diff \| blob \| history
clang/lib/CodeGen/TargetInfo.cpp		diff \| blob \| history
clang/lib/Sema/SemaDeclAttr.cpp		diff \| blob \| history
clang/test/CodeGenOpenCL/amdgpu-num-gpr-attr.cl	[new file with mode: 0644]	blob
clang/test/SemaCUDA/amdgpu-num-gpr-attr.cu	[new file with mode: 0644]	blob
clang/test/SemaOpenCL/amdgpu-num-register-attrs.cl	[new file with mode: 0644]	blob

Domain: System / Toolchain;