summaryrefslogtreecommitdiffstats
path: root/contrib/llvm/lib/Target/AMDGPU/AMDGPUAnnotateUniformValues.cpp
diff options
context:
space:
mode:
Diffstat (limited to 'contrib/llvm/lib/Target/AMDGPU/AMDGPUAnnotateUniformValues.cpp')
-rw-r--r--contrib/llvm/lib/Target/AMDGPU/AMDGPUAnnotateUniformValues.cpp19
1 files changed, 11 insertions, 8 deletions
diff --git a/contrib/llvm/lib/Target/AMDGPU/AMDGPUAnnotateUniformValues.cpp b/contrib/llvm/lib/Target/AMDGPU/AMDGPUAnnotateUniformValues.cpp
index c011be6..ed53708 100644
--- a/contrib/llvm/lib/Target/AMDGPU/AMDGPUAnnotateUniformValues.cpp
+++ b/contrib/llvm/lib/Target/AMDGPU/AMDGPUAnnotateUniformValues.cpp
@@ -19,8 +19,8 @@
#include "llvm/Analysis/DivergenceAnalysis.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/MemoryDependenceAnalysis.h"
-#include "llvm/IR/InstVisitor.h"
#include "llvm/IR/IRBuilder.h"
+#include "llvm/IR/InstVisitor.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
@@ -37,6 +37,7 @@ class AMDGPUAnnotateUniformValues : public FunctionPass,
LoopInfo *LI;
DenseMap<Value*, GetElementPtrInst*> noClobberClones;
bool isKernelFunc;
+ AMDGPUAS AMDGPUASI;
public:
static char ID;
@@ -106,11 +107,12 @@ bool AMDGPUAnnotateUniformValues::isClobberedInFunction(LoadInst * Load) {
DFS(Start, Checklist);
for (auto &BB : Checklist) {
- BasicBlock::iterator StartIt = (BB == Load->getParent()) ?
- BasicBlock::iterator(Load) : BB->end();
- if (MDR->getPointerDependencyFrom(MemoryLocation(Ptr),
- true, StartIt, BB, Load).isClobber())
- return true;
+ BasicBlock::iterator StartIt = (!L && (BB == Load->getParent())) ?
+ BasicBlock::iterator(Load) : BB->end();
+ auto Q = MDR->getPointerDependencyFrom(MemoryLocation(Ptr), true,
+ StartIt, BB, Load);
+ if (Q.isClobber() || Q.isUnknown())
+ return true;
}
return false;
}
@@ -130,8 +132,8 @@ void AMDGPUAnnotateUniformValues::visitLoadInst(LoadInst &I) {
Value *Ptr = I.getPointerOperand();
if (!DA->isUniform(Ptr))
return;
- auto isGlobalLoad = [](LoadInst &Load)->bool {
- return Load.getPointerAddressSpace() == AMDGPUAS::GLOBAL_ADDRESS;
+ auto isGlobalLoad = [&](LoadInst &Load)->bool {
+ return Load.getPointerAddressSpace() == AMDGPUASI.GLOBAL_ADDRESS;
};
// We're tracking up to the Function boundaries
// We cannot go beyond because of FunctionPass restrictions
@@ -166,6 +168,7 @@ void AMDGPUAnnotateUniformValues::visitLoadInst(LoadInst &I) {
}
bool AMDGPUAnnotateUniformValues::doInitialization(Module &M) {
+ AMDGPUASI = AMDGPU::getAMDGPUAS(M);
return false;
}
OpenPOWER on IntegriCloud