aboutsummaryrefslogtreecommitdiff
path: root/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp')
-rw-r--r--llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp72
1 files changed, 43 insertions, 29 deletions
diff --git a/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp b/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
index f0d1117..fcf91e0 100644
--- a/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
+++ b/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
@@ -233,10 +233,11 @@ private:
void copyToDestRegs(CombineInfo &CI, CombineInfo &Paired,
MachineBasicBlock::iterator InsertBefore,
- AMDGPU::OpName OpName, Register DestReg) const;
+ const DebugLoc &DL, AMDGPU::OpName OpName,
+ Register DestReg) const;
Register copyFromSrcRegs(CombineInfo &CI, CombineInfo &Paired,
MachineBasicBlock::iterator InsertBefore,
- AMDGPU::OpName OpName) const;
+ const DebugLoc &DL, AMDGPU::OpName OpName) const;
unsigned read2Opcode(unsigned EltSize) const;
unsigned read2ST64Opcode(unsigned EltSize) const;
@@ -1336,11 +1337,9 @@ SILoadStoreOptimizer::checkAndPrepareMerge(CombineInfo &CI,
int Data1Idx = AMDGPU::getNamedOperandIdx(Write2Opc.getOpcode(),
AMDGPU::OpName::data1);
- const TargetRegisterClass *DataRC0 =
- TII->getRegClass(Write2Opc, Data0Idx, TRI);
+ const TargetRegisterClass *DataRC0 = TII->getRegClass(Write2Opc, Data0Idx);
- const TargetRegisterClass *DataRC1 =
- TII->getRegClass(Write2Opc, Data1Idx, TRI);
+ const TargetRegisterClass *DataRC1 = TII->getRegClass(Write2Opc, Data1Idx);
if (unsigned SubReg = Data0->getSubReg()) {
DataRC0 = TRI->getMatchingSuperRegClass(MRI->getRegClass(Data0->getReg()),
@@ -1367,10 +1366,9 @@ SILoadStoreOptimizer::checkAndPrepareMerge(CombineInfo &CI,
// Paired.
void SILoadStoreOptimizer::copyToDestRegs(
CombineInfo &CI, CombineInfo &Paired,
- MachineBasicBlock::iterator InsertBefore, AMDGPU::OpName OpName,
- Register DestReg) const {
+ MachineBasicBlock::iterator InsertBefore, const DebugLoc &DL,
+ AMDGPU::OpName OpName, Register DestReg) const {
MachineBasicBlock *MBB = CI.I->getParent();
- DebugLoc DL = CI.I->getDebugLoc();
auto [SubRegIdx0, SubRegIdx1] = getSubRegIdxs(CI, Paired);
@@ -1398,9 +1396,9 @@ void SILoadStoreOptimizer::copyToDestRegs(
Register
SILoadStoreOptimizer::copyFromSrcRegs(CombineInfo &CI, CombineInfo &Paired,
MachineBasicBlock::iterator InsertBefore,
+ const DebugLoc &DL,
AMDGPU::OpName OpName) const {
MachineBasicBlock *MBB = CI.I->getParent();
- DebugLoc DL = CI.I->getDebugLoc();
auto [SubRegIdx0, SubRegIdx1] = getSubRegIdxs(CI, Paired);
@@ -1456,7 +1454,8 @@ SILoadStoreOptimizer::mergeRead2Pair(CombineInfo &CI, CombineInfo &Paired,
const TargetRegisterClass *SuperRC = getTargetRegisterClass(CI, Paired);
Register DestReg = MRI->createVirtualRegister(SuperRC);
- DebugLoc DL = CI.I->getDebugLoc();
+ DebugLoc DL =
+ DebugLoc::getMergedLocation(CI.I->getDebugLoc(), Paired.I->getDebugLoc());
Register BaseReg = AddrReg->getReg();
unsigned BaseSubReg = AddrReg->getSubReg();
@@ -1484,7 +1483,7 @@ SILoadStoreOptimizer::mergeRead2Pair(CombineInfo &CI, CombineInfo &Paired,
.addImm(0) // gds
.cloneMergedMemRefs({&*CI.I, &*Paired.I});
- copyToDestRegs(CI, Paired, InsertBefore, AMDGPU::OpName::vdst, DestReg);
+ copyToDestRegs(CI, Paired, InsertBefore, DL, AMDGPU::OpName::vdst, DestReg);
CI.I->eraseFromParent();
Paired.I->eraseFromParent();
@@ -1541,7 +1540,8 @@ MachineBasicBlock::iterator SILoadStoreOptimizer::mergeWrite2Pair(
(NewOffset0 != NewOffset1) && "Computed offset doesn't fit");
const MCInstrDesc &Write2Desc = TII->get(Opc);
- DebugLoc DL = CI.I->getDebugLoc();
+ DebugLoc DL =
+ DebugLoc::getMergedLocation(CI.I->getDebugLoc(), Paired.I->getDebugLoc());
Register BaseReg = AddrReg->getReg();
unsigned BaseSubReg = AddrReg->getSubReg();
@@ -1582,7 +1582,9 @@ MachineBasicBlock::iterator
SILoadStoreOptimizer::mergeImagePair(CombineInfo &CI, CombineInfo &Paired,
MachineBasicBlock::iterator InsertBefore) {
MachineBasicBlock *MBB = CI.I->getParent();
- DebugLoc DL = CI.I->getDebugLoc();
+ DebugLoc DL =
+ DebugLoc::getMergedLocation(CI.I->getDebugLoc(), Paired.I->getDebugLoc());
+
const unsigned Opcode = getNewOpcode(CI, Paired);
const TargetRegisterClass *SuperRC = getTargetRegisterClass(CI, Paired);
@@ -1607,7 +1609,7 @@ SILoadStoreOptimizer::mergeImagePair(CombineInfo &CI, CombineInfo &Paired,
MachineInstr *New = MIB.addMemOperand(combineKnownAdjacentMMOs(CI, Paired));
- copyToDestRegs(CI, Paired, InsertBefore, AMDGPU::OpName::vdata, DestReg);
+ copyToDestRegs(CI, Paired, InsertBefore, DL, AMDGPU::OpName::vdata, DestReg);
CI.I->eraseFromParent();
Paired.I->eraseFromParent();
@@ -1618,7 +1620,9 @@ MachineBasicBlock::iterator SILoadStoreOptimizer::mergeSMemLoadImmPair(
CombineInfo &CI, CombineInfo &Paired,
MachineBasicBlock::iterator InsertBefore) {
MachineBasicBlock *MBB = CI.I->getParent();
- DebugLoc DL = CI.I->getDebugLoc();
+ DebugLoc DL =
+ DebugLoc::getMergedLocation(CI.I->getDebugLoc(), Paired.I->getDebugLoc());
+
const unsigned Opcode = getNewOpcode(CI, Paired);
const TargetRegisterClass *SuperRC = getTargetRegisterClass(CI, Paired);
@@ -1639,7 +1643,7 @@ MachineBasicBlock::iterator SILoadStoreOptimizer::mergeSMemLoadImmPair(
New.addImm(MergedOffset);
New.addImm(CI.CPol).addMemOperand(combineKnownAdjacentMMOs(CI, Paired));
- copyToDestRegs(CI, Paired, InsertBefore, AMDGPU::OpName::sdst, DestReg);
+ copyToDestRegs(CI, Paired, InsertBefore, DL, AMDGPU::OpName::sdst, DestReg);
CI.I->eraseFromParent();
Paired.I->eraseFromParent();
@@ -1650,7 +1654,9 @@ MachineBasicBlock::iterator SILoadStoreOptimizer::mergeBufferLoadPair(
CombineInfo &CI, CombineInfo &Paired,
MachineBasicBlock::iterator InsertBefore) {
MachineBasicBlock *MBB = CI.I->getParent();
- DebugLoc DL = CI.I->getDebugLoc();
+
+ DebugLoc DL =
+ DebugLoc::getMergedLocation(CI.I->getDebugLoc(), Paired.I->getDebugLoc());
const unsigned Opcode = getNewOpcode(CI, Paired);
@@ -1680,7 +1686,7 @@ MachineBasicBlock::iterator SILoadStoreOptimizer::mergeBufferLoadPair(
.addImm(0) // swz
.addMemOperand(combineKnownAdjacentMMOs(CI, Paired));
- copyToDestRegs(CI, Paired, InsertBefore, AMDGPU::OpName::vdata, DestReg);
+ copyToDestRegs(CI, Paired, InsertBefore, DL, AMDGPU::OpName::vdata, DestReg);
CI.I->eraseFromParent();
Paired.I->eraseFromParent();
@@ -1691,7 +1697,9 @@ MachineBasicBlock::iterator SILoadStoreOptimizer::mergeTBufferLoadPair(
CombineInfo &CI, CombineInfo &Paired,
MachineBasicBlock::iterator InsertBefore) {
MachineBasicBlock *MBB = CI.I->getParent();
- DebugLoc DL = CI.I->getDebugLoc();
+
+ DebugLoc DL =
+ DebugLoc::getMergedLocation(CI.I->getDebugLoc(), Paired.I->getDebugLoc());
const unsigned Opcode = getNewOpcode(CI, Paired);
@@ -1731,7 +1739,7 @@ MachineBasicBlock::iterator SILoadStoreOptimizer::mergeTBufferLoadPair(
.addImm(0) // swz
.addMemOperand(combineKnownAdjacentMMOs(CI, Paired));
- copyToDestRegs(CI, Paired, InsertBefore, AMDGPU::OpName::vdata, DestReg);
+ copyToDestRegs(CI, Paired, InsertBefore, DL, AMDGPU::OpName::vdata, DestReg);
CI.I->eraseFromParent();
Paired.I->eraseFromParent();
@@ -1742,12 +1750,13 @@ MachineBasicBlock::iterator SILoadStoreOptimizer::mergeTBufferStorePair(
CombineInfo &CI, CombineInfo &Paired,
MachineBasicBlock::iterator InsertBefore) {
MachineBasicBlock *MBB = CI.I->getParent();
- DebugLoc DL = CI.I->getDebugLoc();
+ DebugLoc DL =
+ DebugLoc::getMergedLocation(CI.I->getDebugLoc(), Paired.I->getDebugLoc());
const unsigned Opcode = getNewOpcode(CI, Paired);
Register SrcReg =
- copyFromSrcRegs(CI, Paired, InsertBefore, AMDGPU::OpName::vdata);
+ copyFromSrcRegs(CI, Paired, InsertBefore, DL, AMDGPU::OpName::vdata);
auto MIB = BuildMI(*MBB, InsertBefore, DL, TII->get(Opcode))
.addReg(SrcReg, RegState::Kill);
@@ -1789,7 +1798,9 @@ MachineBasicBlock::iterator SILoadStoreOptimizer::mergeFlatLoadPair(
CombineInfo &CI, CombineInfo &Paired,
MachineBasicBlock::iterator InsertBefore) {
MachineBasicBlock *MBB = CI.I->getParent();
- DebugLoc DL = CI.I->getDebugLoc();
+
+ DebugLoc DL =
+ DebugLoc::getMergedLocation(CI.I->getDebugLoc(), Paired.I->getDebugLoc());
const unsigned Opcode = getNewOpcode(CI, Paired);
@@ -1807,7 +1818,7 @@ MachineBasicBlock::iterator SILoadStoreOptimizer::mergeFlatLoadPair(
.addImm(CI.CPol)
.addMemOperand(combineKnownAdjacentMMOs(CI, Paired));
- copyToDestRegs(CI, Paired, InsertBefore, AMDGPU::OpName::vdst, DestReg);
+ copyToDestRegs(CI, Paired, InsertBefore, DL, AMDGPU::OpName::vdst, DestReg);
CI.I->eraseFromParent();
Paired.I->eraseFromParent();
@@ -1818,12 +1829,14 @@ MachineBasicBlock::iterator SILoadStoreOptimizer::mergeFlatStorePair(
CombineInfo &CI, CombineInfo &Paired,
MachineBasicBlock::iterator InsertBefore) {
MachineBasicBlock *MBB = CI.I->getParent();
- DebugLoc DL = CI.I->getDebugLoc();
+
+ DebugLoc DL =
+ DebugLoc::getMergedLocation(CI.I->getDebugLoc(), Paired.I->getDebugLoc());
const unsigned Opcode = getNewOpcode(CI, Paired);
Register SrcReg =
- copyFromSrcRegs(CI, Paired, InsertBefore, AMDGPU::OpName::vdata);
+ copyFromSrcRegs(CI, Paired, InsertBefore, DL, AMDGPU::OpName::vdata);
auto MIB = BuildMI(*MBB, InsertBefore, DL, TII->get(Opcode))
.add(*TII->getNamedOperand(*CI.I, AMDGPU::OpName::vaddr))
@@ -2094,12 +2107,13 @@ MachineBasicBlock::iterator SILoadStoreOptimizer::mergeBufferStorePair(
CombineInfo &CI, CombineInfo &Paired,
MachineBasicBlock::iterator InsertBefore) {
MachineBasicBlock *MBB = CI.I->getParent();
- DebugLoc DL = CI.I->getDebugLoc();
+ DebugLoc DL =
+ DebugLoc::getMergedLocation(CI.I->getDebugLoc(), Paired.I->getDebugLoc());
const unsigned Opcode = getNewOpcode(CI, Paired);
Register SrcReg =
- copyFromSrcRegs(CI, Paired, InsertBefore, AMDGPU::OpName::vdata);
+ copyFromSrcRegs(CI, Paired, InsertBefore, DL, AMDGPU::OpName::vdata);
auto MIB = BuildMI(*MBB, InsertBefore, DL, TII->get(Opcode))
.addReg(SrcReg, RegState::Kill);
generated by cgit v1.1 at 2025-11-11 11:11:20 +0000