Skip to content

[AMDGPU] Remove unused amdgpu-disable-structurizer flag #105800

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 23, 2024
Merged

[AMDGPU] Remove unused amdgpu-disable-structurizer flag #105800

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
57 changes: 21 additions & 36 deletions llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -263,13 +263,6 @@ static cl::opt<bool> EnableAMDGPUAliasAnalysis("enable-amdgpu-aa", cl::Hidden,
cl::desc("Enable AMDGPU Alias Analysis"),
cl::init(true));

// Disable structurizer-based control-flow lowering in order to test convergence
// control tokens. This should eventually be replaced by the wave-transform.
static cl::opt<bool, true> DisableStructurizer(
"amdgpu-disable-structurizer",
cl::desc("Disable structurizer for experiments; produces unusable code"),
cl::location(AMDGPUTargetMachine::DisableStructurizer), cl::ReallyHidden);

// Enable lib calls simplifications
static cl::opt<bool> EnableLibCallSimplify(
"amdgpu-simplify-libcall",
Expand Down Expand Up @@ -622,7 +615,6 @@ AMDGPUTargetMachine::AMDGPUTargetMachine(const Target &T, const Triple &TT,

bool AMDGPUTargetMachine::EnableFunctionCalls = false;
bool AMDGPUTargetMachine::EnableLowerModuleLDS = true;
bool AMDGPUTargetMachine::DisableStructurizer = false;
bool AMDGPUTargetMachine::EnableStructurizerWorkarounds = true;

AMDGPUTargetMachine::~AMDGPUTargetMachine() = default;
Expand Down Expand Up @@ -1239,21 +1231,19 @@ bool GCNPassConfig::addPreISel() {
// Merge divergent exit nodes. StructurizeCFG won't recognize the multi-exit
// regions formed by them.
addPass(&AMDGPUUnifyDivergentExitNodesID);
if (!DisableStructurizer) {
if (EnableStructurizerWorkarounds) {
addPass(createFixIrreduciblePass());
addPass(createUnifyLoopExitsPass());
}
addPass(createStructurizeCFGPass(false)); // true -> SkipUniformRegions
if (EnableStructurizerWorkarounds) {
addPass(createFixIrreduciblePass());
addPass(createUnifyLoopExitsPass());
}
addPass(createStructurizeCFGPass(false)); // true -> SkipUniformRegions

addPass(createAMDGPUAnnotateUniformValuesLegacy());
if (!DisableStructurizer) {
addPass(createSIAnnotateControlFlowLegacyPass());
// TODO: Move this right after structurizeCFG to avoid extra divergence
// analysis. This depends on stopping SIAnnotateControlFlow from making
// control flow modifications.
addPass(createAMDGPURewriteUndefForPHILegacyPass());
}
addPass(createSIAnnotateControlFlowLegacyPass());
// TODO: Move this right after structurizeCFG to avoid extra divergence
// analysis. This depends on stopping SIAnnotateControlFlow from making
// control flow modifications.
addPass(createAMDGPURewriteUndefForPHILegacyPass());

addPass(createLCSSAPass());

if (TM->getOptLevel() > CodeGenOptLevel::Less)
Expand Down Expand Up @@ -1863,7 +1853,6 @@ void AMDGPUCodeGenPassBuilder::addCodeGenPrepare(AddIRPass &addPass) const {
}

void AMDGPUCodeGenPassBuilder::addPreISel(AddIRPass &addPass) const {
const bool DisableStructurizer = AMDGPUTargetMachine::DisableStructurizer;
const bool EnableStructurizerWorkarounds =
AMDGPUTargetMachine::EnableStructurizerWorkarounds;

Expand All @@ -1880,25 +1869,21 @@ void AMDGPUCodeGenPassBuilder::addPreISel(AddIRPass &addPass) const {

addPass(AMDGPUUnifyDivergentExitNodesPass());

if (!DisableStructurizer) {
if (EnableStructurizerWorkarounds) {
addPass(FixIrreduciblePass());
addPass(UnifyLoopExitsPass());
}

addPass(StructurizeCFGPass(/*SkipUniformRegions=*/false));
if (EnableStructurizerWorkarounds) {
addPass(FixIrreduciblePass());
addPass(UnifyLoopExitsPass());
}

addPass(StructurizeCFGPass(/*SkipUniformRegions=*/false));

addPass(AMDGPUAnnotateUniformValuesPass());

if (!DisableStructurizer) {
addPass(SIAnnotateControlFlowPass(TM));
addPass(SIAnnotateControlFlowPass(TM));

// TODO: Move this right after structurizeCFG to avoid extra divergence
// analysis. This depends on stopping SIAnnotateControlFlow from making
// control flow modifications.
addPass(AMDGPURewriteUndefForPHIPass());
}
// TODO: Move this right after structurizeCFG to avoid extra divergence
// analysis. This depends on stopping SIAnnotateControlFlow from making
// control flow modifications.
addPass(AMDGPURewriteUndefForPHIPass());

addPass(LCSSAPass());

Expand Down
1 change: 0 additions & 1 deletion llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,6 @@ class AMDGPUTargetMachine : public LLVMTargetMachine {
public:
static bool EnableFunctionCalls;
static bool EnableLowerModuleLDS;
static bool DisableStructurizer;
static bool EnableStructurizerWorkarounds;

AMDGPUTargetMachine(const Target &T, const Triple &TT, StringRef CPU,
Expand Down
Loading