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
llvm-svn: 312337
diff --git a/llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp b/llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
index b601cfe..400c4aa 100644
--- a/llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
+++ b/llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
@@ -218,12 +218,17 @@
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();
}