diff options
| author | Marek Olsak <marek.olsak@amd.com> | 2018-08-29 20:03:00 +0000 |
|---|---|---|
| committer | Marek Olsak <marek.olsak@amd.com> | 2018-08-29 20:03:00 +0000 |
| commit | 3fc2079cf4e1640f20b13861c3a73a2044d3f2c9 (patch) | |
| tree | 8844d99ee9607babc29429ec9b379ab03b0ac2f2 /llvm/lib | |
| parent | a965d3515411fceb23e8d1430c154397fb7ae112 (diff) | |
| download | bcm5719-llvm-3fc2079cf4e1640f20b13861c3a73a2044d3f2c9.tar.gz bcm5719-llvm-3fc2079cf4e1640f20b13861c3a73a2044d3f2c9.zip | |
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
Diffstat (limited to 'llvm/lib')
| -rw-r--r-- | llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp b/llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp index 1cae11686bc..e70de24dded 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp +++ b/llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp @@ -1408,7 +1408,11 @@ bool AMDGPUDAGToDAGISel::SelectSMRD(SDValue Addr, SDValue &SBase, SDValue &Offset, bool &Imm) const { SDLoc SL(Addr); - if (CurDAG->isBaseWithConstantOffset(Addr)) { + // A 32-bit (address + offset) should not cause unsigned 32-bit integer + // wraparound, because s_load instructions perform the addition in 64 bits. + if ((Addr.getValueType() != MVT::i32 || + Addr->getFlags().hasNoUnsignedWrap()) && + CurDAG->isBaseWithConstantOffset(Addr)) { SDValue N0 = Addr.getOperand(0); SDValue N1 = Addr.getOperand(1); |
