#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/CodeGen/BasicTTIImpl.h"
+#include "llvm/IR/Module.h"
#include "llvm/Support/Debug.h"
#include "llvm/Target/CostTable.h"
#include "llvm/Target/TargetLowering.h"
void AMDGPUTTIImpl::getUnrollingPreferences(Loop *L,
TTI::UnrollingPreferences &UP) {
UP.Threshold = 300; // Twice the default.
- UP.Count = UINT_MAX;
+ UP.MaxCount = UINT_MAX;
UP.Partial = true;
// TODO: Do we want runtime unrolling?
for (const BasicBlock *BB : L->getBlocks()) {
+ const DataLayout &DL = BB->getModule()->getDataLayout();
for (const Instruction &I : *BB) {
const GetElementPtrInst *GEP = dyn_cast<GetElementPtrInst>(&I);
if (!GEP || GEP->getAddressSpace() != AMDGPUAS::PRIVATE_ADDRESS)
continue;
const Value *Ptr = GEP->getPointerOperand();
- const AllocaInst *Alloca = dyn_cast<AllocaInst>(GetUnderlyingObject(Ptr));
+ const AllocaInst *Alloca =
+ dyn_cast<AllocaInst>(GetUnderlyingObject(Ptr, DL));
if (Alloca) {
// We want to do whatever we can to limit the number of alloca
// instructions that make it through to the code generator. allocas
unsigned AMDGPUTTIImpl::getRegisterBitWidth(bool) { return 32; }
-unsigned AMDGPUTTIImpl::getMaxInterleaveFactor() {
+unsigned AMDGPUTTIImpl::getMaxInterleaveFactor(unsigned VF) {
// Semi-arbitrary large amount.
return 64;
}