projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 0b69fa9) | patch
AMDGPU/SI: Fix encoding for FLAT_SCRATCH registers on VI
authorTom Stellard <thomas.stellard@amd.com>
Mon, 21 Dec 2015 18:44:27 +0000 (18:44 +0000)
committerTom Stellard <thomas.stellard@amd.com>
Mon, 21 Dec 2015 18:44:27 +0000 (18:44 +0000)
commit15368636686ba54560244bb08ece60f1c4ad2ab0
tree1942a500376ce88c89a3c749f32fe7086bcb1043tree | snapshot
parent0b69fa94843c911b2faaf48625a50857a42aa542commit | diff
AMDGPU/SI: Fix encoding for FLAT_SCRATCH registers on VI

Summary:
These register has different encodings on CI and VI, so we add pseudo
FLAT_SCRACTH registers to be used before MC, and subtarget specific
registers to be used by the MC layer.

Reviewers: arsenm

Subscribers: arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D15661

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@256178 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/AMDGPU/AMDGPUMCInstLower.cpp diff | blob | history
lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp diff | blob | history
lib/Target/AMDGPU/SIRegisterInfo.td diff | blob | history
lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp diff | blob | history
lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h diff | blob | history
test/MC/AMDGPU/flat-scratch.s diff | blob | history
C/C++ LLVM-based compilers that forbids OOTA behaviors