RPCS3/llvm
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm.git synced 2024-12-13 14:47:00 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

[AMDGPU] Fix shouldClusterMemOps to process flat loads

Browse Source 
Flat loads do not have vdata operand but have vdst instead.

Differential Revision: https://reviews.llvm.org/D37502

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@312640 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Stanislav Mekhanoshin 2017-09-06 15:31:30 +00:00
parent adf1cb63f2
commit 651c4efd77
2 changed files with 24 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
lib/Target/AMDGPU/SIInstrInfo.cpp
View File

@ -366,7 +366,11 @@ bool SIInstrInfo::shouldClusterMemOps(MachineInstr &FirstLdSt,
(isMTBUF(FirstLdSt) && isMTBUF(SecondLdSt)) ||
(isFLAT(FirstLdSt) && isFLAT(SecondLdSt))) {
FirstDst = getNamedOperand(FirstLdSt, AMDGPU::OpName::vdata);
if (!FirstDst)
FirstDst = getNamedOperand(FirstLdSt, AMDGPU::OpName::vdst);
SecondDst = getNamedOperand(SecondLdSt, AMDGPU::OpName::vdata);
if (!SecondDst)
SecondDst = getNamedOperand(SecondLdSt, AMDGPU::OpName::vdst);
} else if (isSMRD(FirstLdSt) && isSMRD(SecondLdSt)) {
FirstDst = getNamedOperand(FirstLdSt, AMDGPU::OpName::sdst);
SecondDst = getNamedOperand(SecondLdSt, AMDGPU::OpName::sdst);

20
test/CodeGen/AMDGPU/cluster-flat-loads.mir Normal file
View File

@ -0,0 +1,20 @@
# RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass machine-scheduler %s -o - | FileCheck -check-prefix=GCN %s
# GCN-LABEL: name: cluster_flat_loads
# GCN: FLAT_LOAD_DWORD %0, 0
# GCN-NEXT: FLAT_LOAD_DWORD %0, 4
# GCN-NEXT: V_ADD_F32_e64
name: cluster_flat_loads
tracksRegLiveness: true
registers:
- { id: 0, class: vreg_64 }
- { id: 1, class: vgpr_32 }
- { id: 2, class: vgpr_32 }
- { id: 3, class: vgpr_32 }
body: |
bb.0:
%0 = IMPLICIT_DEF
%1 = FLAT_LOAD_DWORD %0, 0, 0, 0, implicit %exec, implicit %flat_scr :: (load 4)
%2 = V_ADD_F32_e64 0, killed %1, 0, 1, 0, 0, implicit %exec
%3 = FLAT_LOAD_DWORD %0, 4, 0, 0, implicit %exec, implicit %flat_scr :: (load 4)
...