[NFC][AMDGPU] Replace more direct arch comparison with isAMDGCN() #131379
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This is an extension of #131357. Hopefully this would be the last one.
llvmbot
added
clang
|
@llvm/pr-subscribers-clang-driver @llvm/pr-subscribers-flang-driver Author: Shilei Tian (shiltian) ChangesThis is an extension of #131357. Hopefully this would be the last one. Full diff: https://github.com/llvm/llvm-project/pull/131379.diff 10 Files Affected:
diff --git a/clang/include/clang/Driver/ToolChain.h b/clang/include/clang/Driver/ToolChain.h
index 7d1d8feebf35e..90004c64a694a 100644
--- a/clang/include/clang/Driver/ToolChain.h
+++ b/clang/include/clang/Driver/ToolChain.h
@@ -821,7 +821,7 @@ class ToolChain {
return llvm::Triple("nvptx-nvidia-cuda");
if (TT.getArch() == llvm::Triple::nvptx64)
return llvm::Triple("nvptx64-nvidia-cuda");
- if (TT.getArch() == llvm::Triple::amdgcn)
+ if (TT.isAMDGCN())
return llvm::Triple("amdgcn-amd-amdhsa");
}
return TT;
diff --git a/clang/lib/Basic/Targets/AMDGPU.h b/clang/lib/Basic/Targets/AMDGPU.h
index 3d6778fb5a76f..9bee541cfdd5f 100644
--- a/clang/lib/Basic/Targets/AMDGPU.h
+++ b/clang/lib/Basic/Targets/AMDGPU.h
@@ -52,7 +52,7 @@ class LLVM_LIBRARY_VISIBILITY AMDGPUTargetInfo final : public TargetInfo {
std::string TargetID;
bool hasFP64() const {
- return getTriple().getArch() == llvm::Triple::amdgcn ||
+ return getTriple().isAMDGCN() ||
!!(GPUFeatures & llvm::AMDGPU::FEATURE_FP64);
}
@@ -63,11 +63,11 @@ class LLVM_LIBRARY_VISIBILITY AMDGPUTargetInfo final : public TargetInfo {
/// Has fast fma f64
bool hasFastFMA() const {
- return getTriple().getArch() == llvm::Triple::amdgcn;
+ return getTriple().isAMDGCN();
}
bool hasFMAF() const {
- return getTriple().getArch() == llvm::Triple::amdgcn ||
+ return getTriple().isAMDGCN() ||
!!(GPUFeatures & llvm::AMDGPU::FEATURE_FMA);
}
@@ -76,13 +76,11 @@ class LLVM_LIBRARY_VISIBILITY AMDGPUTargetInfo final : public TargetInfo {
}
bool hasLDEXPF() const {
- return getTriple().getArch() == llvm::Triple::amdgcn ||
+ return getTriple().isAMDGCN() ||
!!(GPUFeatures & llvm::AMDGPU::FEATURE_LDEXP);
}
- static bool isAMDGCN(const llvm::Triple &TT) {
- return TT.getArch() == llvm::Triple::amdgcn;
- }
+ static bool isAMDGCN(const llvm::Triple &TT) { return TT.isAMDGCN(); }
static bool isR600(const llvm::Triple &TT) {
return TT.getArch() == llvm::Triple::r600;
@@ -125,7 +123,7 @@ class LLVM_LIBRARY_VISIBILITY AMDGPUTargetInfo final : public TargetInfo {
}
uint64_t getMaxPointerWidth() const override {
- return getTriple().getArch() == llvm::Triple::amdgcn ? 64 : 32;
+ return getTriple().isAMDGCN() ? 64 : 32;
}
bool hasBFloat16Type() const override { return isAMDGCN(getTriple()); }
@@ -269,7 +267,7 @@ class LLVM_LIBRARY_VISIBILITY AMDGPUTargetInfo final : public TargetInfo {
}
bool isValidCPUName(StringRef Name) const override {
- if (getTriple().getArch() == llvm::Triple::amdgcn)
+ if (getTriple().isAMDGCN())
return llvm::AMDGPU::parseArchAMDGCN(Name) != llvm::AMDGPU::GK_NONE;
return llvm::AMDGPU::parseArchR600(Name) != llvm::AMDGPU::GK_NONE;
}
@@ -277,7 +275,7 @@ class LLVM_LIBRARY_VISIBILITY AMDGPUTargetInfo final : public TargetInfo {
void fillValidCPUList(SmallVectorImpl<StringRef> &Values) const override;
bool setCPU(const std::string &Name) override {
- if (getTriple().getArch() == llvm::Triple::amdgcn) {
+ if (getTriple().isAMDGCN()) {
GPUKind = llvm::AMDGPU::parseArchAMDGCN(Name);
GPUFeatures = llvm::AMDGPU::getArchAttrAMDGCN(GPUKind);
} else {
diff --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp
index 848b27012976d..0ae61fdd0d328 100644
--- a/clang/lib/Driver/Driver.cpp
+++ b/clang/lib/Driver/Driver.cpp
@@ -158,8 +158,7 @@ getHIPOffloadTargetTriple(const Driver &D, const ArgList &Args) {
auto TT = getOffloadTargetTriple(D, Args);
if (!TT)
return std::nullopt;
- if (TT->getArch() == llvm::Triple::amdgcn &&
- TT->getVendor() == llvm::Triple::AMD &&
+ if (TT->isAMDGCN() && TT->getVendor() == llvm::Triple::AMD &&
TT->getOS() == llvm::Triple::AMDHSA)
return TT;
if (TT->getArch() == llvm::Triple::spirv64)
@@ -3410,7 +3409,7 @@ class OffloadingActionBuilder final {
const ToolChain *HostTC = C.getSingleOffloadToolChain<Action::OFK_Host>();
assert(HostTC && "No toolchain for host compilation.");
if (HostTC->getTriple().isNVPTX() ||
- HostTC->getTriple().getArch() == llvm::Triple::amdgcn) {
+ HostTC->getTriple().isAMDGCN()) {
// We do not support targeting NVPTX/AMDGCN for host compilation. Throw
// an error and abort pipeline construction early so we don't trip
// asserts that assume device-side compilation.
diff --git a/clang/lib/Driver/ToolChains/HIPAMD.cpp b/clang/lib/Driver/ToolChains/HIPAMD.cpp
index 271626ed54aed..55a8f2ca87de0 100644
--- a/clang/lib/Driver/ToolChains/HIPAMD.cpp
+++ b/clang/lib/Driver/ToolChains/HIPAMD.cpp
@@ -296,7 +296,7 @@ HIPAMDToolChain::TranslateArgs(const llvm::opt::DerivedArgList &Args,
}
Tool *HIPAMDToolChain::buildLinker() const {
- assert(getTriple().getArch() == llvm::Triple::amdgcn ||
+ assert(getTriple().isAMDGCN() ||
getTriple().getArch() == llvm::Triple::spirv64);
return new tools::AMDGCN::Linker(*this);
}
diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
index 4eb743acf327f..8c38acad0c20a 100644
--- a/clang/lib/Frontend/CompilerInvocation.cpp
+++ b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -4323,7 +4323,7 @@ bool CompilerInvocation::ParseLangArgs(LangOptions &Opts, ArgList &Args,
TT.getArch() == llvm::Triple::loongarch64 ||
TT.getArch() == llvm::Triple::nvptx ||
TT.getArch() == llvm::Triple::nvptx64 ||
- TT.getArch() == llvm::Triple::amdgcn ||
+ TT.isAMDGCN() ||
TT.getArch() == llvm::Triple::x86 ||
TT.getArch() == llvm::Triple::x86_64))
Diags.Report(diag::err_drv_invalid_omp_target) << A->getValue(i);
diff --git a/flang/lib/Frontend/CompilerInvocation.cpp b/flang/lib/Frontend/CompilerInvocation.cpp
index edf738785fb97..de8a3bfb8b48c 100644
--- a/flang/lib/Frontend/CompilerInvocation.cpp
+++ b/flang/lib/Frontend/CompilerInvocation.cpp
@@ -1175,7 +1175,7 @@ static bool parseOpenMPArgs(CompilerInvocation &res, llvm::opt::ArgList &args,
tt.getArch() == llvm::Triple::systemz ||
tt.getArch() == llvm::Triple::nvptx ||
tt.getArch() == llvm::Triple::nvptx64 ||
- tt.getArch() == llvm::Triple::amdgcn ||
+ tt.isAMDGCN() ||
tt.getArch() == llvm::Triple::x86 ||
tt.getArch() == llvm::Triple::x86_64))
diags.Report(clang::diag::err_drv_invalid_omp_target)
diff --git a/llvm/include/llvm/TargetParser/Triple.h b/llvm/include/llvm/TargetParser/Triple.h
index 390ed7fbab8c0..da5b05632f2ec 100644
--- a/llvm/include/llvm/TargetParser/Triple.h
+++ b/llvm/include/llvm/TargetParser/Triple.h
@@ -888,9 +888,7 @@ class Triple {
/// Tests whether the target is AMDGCN
bool isAMDGCN() const { return getArch() == Triple::amdgcn; }
- bool isAMDGPU() const {
- return getArch() == Triple::r600 || getArch() == Triple::amdgcn;
- }
+ bool isAMDGPU() const { return getArch() == Triple::r600 || isAMDGCN(); }
/// Tests whether the target is Thumb (little and big endian).
bool isThumb() const {
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp b/llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
index 746e9e4f65099..5e4ac35224a7b 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
@@ -454,8 +454,7 @@ void AMDGPUDAGToDAGISel::SelectBuildVector(SDNode *N, unsigned RegClassID) {
// 1 = Vector Register Class
SmallVector<SDValue, 32 * 2 + 1> RegSeqArgs(NumVectorElts * 2 + 1);
- bool IsGCN = CurDAG->getSubtarget().getTargetTriple().getArch() ==
- Triple::amdgcn;
+ bool IsGCN = CurDAG->getSubtarget().getTargetTriple().isAMDGCN();
RegSeqArgs[0] = CurDAG->getTargetConstant(RegClassID, DL, MVT::i32);
bool IsRegSeq = true;
unsigned NOps = N->getNumOperands();
diff --git a/llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp b/llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp
index 54ed3789326cb..82e310d73b69a 100644
--- a/llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp
+++ b/llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp
@@ -5463,7 +5463,7 @@ bool AMDGPUAsmParser::ParseAsAbsoluteExpression(uint32_t &Ret) {
}
bool AMDGPUAsmParser::ParseDirectiveAMDGCNTarget() {
- if (getSTI().getTargetTriple().getArch() != Triple::amdgcn)
+ if (!getSTI().getTargetTriple().isAMDGCN())
return TokError("directive only supported for amdgcn architecture");
std::string TargetIDDirective;
@@ -5550,7 +5550,7 @@ bool AMDGPUAsmParser::calculateGPRBlocks(
}
bool AMDGPUAsmParser::ParseDirectiveAMDHSAKernel() {
- if (getSTI().getTargetTriple().getArch() != Triple::amdgcn)
+ if (!getSTI().getTargetTriple().isAMDGCN())
return TokError("directive only supported for amdgcn architecture");
if (!isHsaAbi(getSTI()))
@@ -6142,7 +6142,7 @@ bool AMDGPUAsmParser::ParseDirectiveAMDGPUHsaKernel() {
}
bool AMDGPUAsmParser::ParseDirectiveISAVersion() {
- if (getSTI().getTargetTriple().getArch() != Triple::amdgcn) {
+ if (!getSTI().getTargetTriple().isAMDGCN()) {
return Error(getLoc(),
".amd_amdgpu_isa directive is not available on non-amdgcn "
"architectures");
diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
index ac6b07bad3e35..cf3413d1f8bfb 100644
--- a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
@@ -1004,7 +1004,7 @@ unsigned getEUsPerCU(const MCSubtargetInfo *STI) {
unsigned getMaxWorkGroupsPerCU(const MCSubtargetInfo *STI,
unsigned FlatWorkGroupSize) {
assert(FlatWorkGroupSize != 0);
- if (STI->getTargetTriple().getArch() != Triple::amdgcn)
+ if (!STI->getTargetTriple().isAMDGCN())
return 8;
unsigned MaxWaves = getMaxWavesPerEU(STI) * getEUsPerCU(STI);
unsigned N = getWavesPerWorkGroup(STI, FlatWorkGroupSize);
|
jhuber6
approved these changes
Mar 14, 2025
|
✅ With the latest revision this PR passed the C/C++ code formatter. |
No at the moment, since we still support r600. |
shiltian
deleted the
users/shiltian/use-isamdgcn-to-replace-direct-compare-more
branch
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This is an extension of #131357. Hopefully this would be the last one.