projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: a965d35) | patch
AMDGPU: Handle 32-bit address wraparounds for SMRD opcodes
authorMarek Olsak <marek.olsak@amd.com>
Wed, 29 Aug 2018 20:03:00 +0000 (20:03 +0000)
committerMarek Olsak <marek.olsak@amd.com>
Wed, 29 Aug 2018 20:03:00 +0000 (20:03 +0000)
commit3fc2079cf4e1640f20b13861c3a73a2044d3f2c9
tree8844d99ee9607babc29429ec9b379ab03b0ac2f2tree | snapshot
parenta965d3515411fceb23e8d1430c154397fb7ae112commit | diff
AMDGPU: Handle 32-bit address wraparounds for SMRD opcodes

Summary: This fixes GPU hangs with OpenGL bindless handle arithmetic.

Reviewers: arsenm, nhaehnle

Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits

Differential Revision: https://reviews.llvm.org/D51203

llvm-svn: 340959
llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp diff | blob | history
llvm/test/CodeGen/AMDGPU/constant-address-space-32bit.ll diff | blob | history
Domain: System / Toolchain;