]> granicus.if.org Git - llvm/commit
Merging r242673:
authorHans Wennborg <hans@hanshq.net>
Mon, 20 Jul 2015 16:46:01 +0000 (16:46 +0000)
committerHans Wennborg <hans@hanshq.net>
Mon, 20 Jul 2015 16:46:01 +0000 (16:46 +0000)
commitb26a5f5b1ef28279186313caac13d1f27ab9661e
treed39f48af87c09cea79b74dc0d41ce672ff7375d3
parentdffc572cbeaa79e080e5940de971a32ca058f981
Merging r242673:
------------------------------------------------------------------------
r242673 | tstellar | 2015-07-20 07:28:41 -0700 (Mon, 20 Jul 2015) | 11 lines

AMDGPU/SI: Add VI patterns to select FLAT instructions for global memory ops

Summary:
The MUBUF addr64 bit has been removed on VI, so we must use FLAT
instructions when the pointer is stored in VGPRs.

Reviewers: arsenm

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D11067
------------------------------------------------------------------------

git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_37@242685 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
lib/Target/AMDGPU/SIISelLowering.cpp
lib/Target/AMDGPU/SIISelLowering.h
lib/Target/AMDGPU/VIInstructions.td
test/CodeGen/AMDGPU/cgp-addressing-modes.ll
test/CodeGen/AMDGPU/global_atomics.ll