[AMDGPU] Ask subtarget if waitcnt instruction is needed before barrier instruction
Differential Revision: https://reviews.llvm.org/D24985
llvm-svn: 282875
diff --git a/llvm/lib/Target/AMDGPU/SIInsertWaits.cpp b/llvm/lib/Target/AMDGPU/SIInsertWaits.cpp
index d24588d..b9551be 100644
--- a/llvm/lib/Target/AMDGPU/SIInsertWaits.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInsertWaits.cpp
@@ -590,8 +590,9 @@
// S_SENDMSG implicitly waits for all outstanding LGKM transfers to finish,
// but we also want to wait for any other outstanding transfers before
// signalling other hardware blocks
- if (I->getOpcode() == AMDGPU::S_BARRIER ||
- I->getOpcode() == AMDGPU::S_SENDMSG)
+ if ((I->getOpcode() == AMDGPU::S_BARRIER &&
+ ST->needWaitcntBeforeBarrier()) ||
+ I->getOpcode() == AMDGPU::S_SENDMSG)
Required = LastIssued;
else
Required = handleOperands(*I);