R600: Proper insert S_WAITCNT instructions

Some instructions like memory reads/writes are executed
asynchronously, so we need to insert S_WAITCNT instructions
to block before accessing their results. Previously we have
just inserted S_WAITCNT instructions after each async
instruction, this patch fixes this and adds a prober
insertion pass.

Patch by: Christian König

Tested-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Signed-off-by: Christian König <deathsimple@vodafone.de>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@172846 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 5 insertions, 0 deletions

diff --git a/lib/Target/R600/AMDGPUTargetMachine.cpp b/lib/Target/R600/AMDGPUTargetMachine.cpp
index d09dc2efff..26ac928347 100644
--- a/lib/Target/R600/AMDGPUTargetMachine.cpp
+++ b/lib/Target/R600/AMDGPUTargetMachine.cpp
@@ -116,6 +116,11 @@ bool AMDGPUPassConfig::addPreRegAlloc() {
 }
 
 bool AMDGPUPassConfig::addPostRegAlloc() {
+  const AMDGPUSubtarget &ST = TM->getSubtarget<AMDGPUSubtarget>();
+
+  if (ST.device()->getGeneration() > AMDGPUDeviceInfo::HD6XXX) {
+    addPass(createSIInsertWaits(*TM));
+  }
   return false;
 }