projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 07bdf7f) | patch
R600/SI: Implement getOptimalMemOpType
authorMatt Arsenault <Matthew.Arsenault@amd.com>
Mon, 28 Jul 2014 17:49:26 +0000 (17:49 +0000)
committerMatt Arsenault <Matthew.Arsenault@amd.com>
Mon, 28 Jul 2014 17:49:26 +0000 (17:49 +0000)
commit46645fa102dee90861ea395f592c5758e0eee4f8
treecd175a8ea4f4352f380fd63e225eb9f681f81d02tree | snapshot
parent07bdf7f720effecc77b73a077bfe620390386a32commit | diff
R600/SI: Implement getOptimalMemOpType

The default guess uses i32. This needs an address space argument
to really do the right thing in all cases.

llvm-svn: 214104
llvm/lib/Target/R600/SIISelLowering.cpp diff | blob | history
llvm/lib/Target/R600/SIISelLowering.h diff | blob | history
llvm/test/CodeGen/R600/llvm.memcpy.ll [new file with mode: 0644] blob
Domain: System / Toolchain;