projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 0219a27) | patch
AMDPGU/SI: Use AssertZext node to mask high bit for scratch offsets
authorTom Stellard <thomas.stellard@amd.com>
Thu, 16 Jul 2015 19:40:07 +0000 (19:40 +0000)
committerTom Stellard <thomas.stellard@amd.com>
Thu, 16 Jul 2015 19:40:07 +0000 (19:40 +0000)
commitcac05d9b5837f7d5bc73d9d87b555ca9e562d351
treec8ca4c5ad78cc03a3d344688d197c27ab311b4f1tree | snapshot
parent0219a272ec3c1a3784bd85bd0dc2fa457743ffd6commit | diff
AMDPGU/SI: Use AssertZext node to mask high bit for scratch offsets

Summary:
We can safely assume that the high bit of scratch offsets will never
be set, because this would require at least 128 GB of GPU memory.

Reviewers: arsenm

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D11225

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@242433 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/AMDGPU/AMDGPU.td diff | blob | history
lib/Target/AMDGPU/AMDGPUSubtarget.cpp diff | blob | history
lib/Target/AMDGPU/AMDGPUSubtarget.h diff | blob | history
lib/Target/AMDGPU/SIISelLowering.cpp diff | blob | history
C/C++ LLVM-based compilers that forbids OOTA behaviors