AMDGPU: IMPLICIT_DEFs and DBG_VALUEs do not contribute to wait states

Summary:
This fixes a bug that was exposed on gfx9 in various
GL45-CTS.shaders.loops.*_iterations.select_iteration_count_fragment tests,
e.g. GL45-CTS.shaders.loops.do_while_uniform_iterations.select_iteration_count_fragment

Reviewers: arsenm

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

Differential Revision: https://reviews.llvm.org/D36193

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@312337 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Nicolai Haehnle 2017-09-01 16:56:32 +00:00
parent fc13e66509
commit 96b6414540
2 changed files with 40 additions and 4 deletions

View File

@ -218,12 +218,17 @@ void GCNHazardRecognizer::RecedeCycle() {
int GCNHazardRecognizer::getWaitStatesSince(
function_ref<bool(MachineInstr *)> IsHazard) {
int WaitStates = -1;
int WaitStates = 0;
for (MachineInstr *MI : EmittedInstrs) {
if (MI) {
if (IsHazard(MI))
return WaitStates;
unsigned Opcode = MI->getOpcode();
if (Opcode == AMDGPU::DBG_VALUE || Opcode == AMDGPU::IMPLICIT_DEF)
continue;
}
++WaitStates;
if (!MI || !IsHazard(MI))
continue;
return WaitStates;
}
return std::numeric_limits<int>::max();
}

View File

@ -0,0 +1,31 @@
# RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs -run-pass post-RA-hazard-rec %s -o - | FileCheck -check-prefix=GCN -check-prefix=VI %s
# RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs -run-pass post-RA-hazard-rec %s -o - | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
# GCN: bb.0.entry:
# GCN: %m0 = S_MOV_B32
# GFX9: S_NOP 0
# VI-NOT: S_NOP_0
# GCN: V_INTERP_P1_F32
---
name: hazard_implicit_def
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
registers:
liveins:
- { reg: '%sgpr7', virtual-reg: '' }
- { reg: '%vgpr4', virtual-reg: '' }
body: |
bb.0.entry:
liveins: %sgpr7, %vgpr4
%m0 = S_MOV_B32 killed %sgpr7
%vgpr5 = IMPLICIT_DEF
%vgpr0 = V_INTERP_P1_F32 killed %vgpr4, 0, 0, implicit %m0, implicit %exec
SI_RETURN_TO_EPILOG killed %vgpr5, killed %vgpr0
...