summaryrefslogtreecommitdiff
path: root/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
diff options
context:
space:
mode:
Diffstat (limited to 'lib/Target/AMDGPU/AMDGPUTargetMachine.cpp')
-rw-r--r--lib/Target/AMDGPU/AMDGPUTargetMachine.cpp3
1 files changed, 2 insertions, 1 deletions
diff --git a/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp b/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
index 596f02ae4a64..404598ff4738 100644
--- a/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ b/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -116,7 +116,7 @@ static cl::opt<bool> EnableAMDGPUAliasAnalysis("enable-amdgpu-aa", cl::Hidden,
static cl::opt<bool> EnableSIInsertWaitcntsPass(
"enable-si-insert-waitcnts",
cl::desc("Use new waitcnt insertion pass"),
- cl::init(false));
+ cl::init(true));
// Option to run late CFG structurizer
static cl::opt<bool> LateCFGStructurize(
@@ -139,6 +139,7 @@ extern "C" void LLVMInitializeAMDGPUTarget() {
initializeSIShrinkInstructionsPass(*PR);
initializeSIFixControlFlowLiveIntervalsPass(*PR);
initializeSILoadStoreOptimizerPass(*PR);
+ initializeAMDGPUAlwaysInlinePass(*PR);
initializeAMDGPUAnnotateKernelFeaturesPass(*PR);
initializeAMDGPUAnnotateUniformValuesPass(*PR);
initializeAMDGPULowerIntrinsicsPass(*PR);