david-arm updated this revision to Diff 375169.
david-arm retitled this revision from "[AArch64][Clang] Always add -tune-cpu
argument to -cc1 driver" to "[AArch64] Always add -tune-cpu argument to -cc1
driver".
david-arm edited the summary of this revision.
david-arm added a comment.
Herald added subscribers: llvm-commits, hiraditya.
Herald added a project: LLVM.
- Updated the patch to use mtune properly and set the scheduling model
accordingly
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D110258/new/
https://reviews.llvm.org/D110258
Files:
clang/lib/Driver/ToolChains/Clang.cpp
clang/test/Driver/aarch64-mtune.c
llvm/lib/Target/AArch64/AArch64Subtarget.cpp
llvm/lib/Target/AArch64/AArch64Subtarget.h
llvm/lib/Target/AArch64/AArch64TargetMachine.cpp
llvm/unittests/Target/AArch64/InstSizes.cpp
llvm/unittests/Target/AArch64/MatrixRegisterAliasing.cpp
Index: llvm/unittests/Target/AArch64/MatrixRegisterAliasing.cpp
===================================================================
--- llvm/unittests/Target/AArch64/MatrixRegisterAliasing.cpp
+++ llvm/unittests/Target/AArch64/MatrixRegisterAliasing.cpp
@@ -26,6 +26,7 @@
std::unique_ptr<AArch64InstrInfo> createInstrInfo(TargetMachine *TM) {
AArch64Subtarget ST(TM->getTargetTriple(), std::string(TM->getTargetCPU()),
+ std::string(TM->getTargetCPU()),
std::string(TM->getTargetFeatureString()), *TM,
/* isLittle */ false);
return std::make_unique<AArch64InstrInfo>(ST);
Index: llvm/unittests/Target/AArch64/InstSizes.cpp
===================================================================
--- llvm/unittests/Target/AArch64/InstSizes.cpp
+++ llvm/unittests/Target/AArch64/InstSizes.cpp
@@ -29,6 +29,7 @@
std::unique_ptr<AArch64InstrInfo> createInstrInfo(TargetMachine *TM) {
AArch64Subtarget ST(TM->getTargetTriple(), std::string(TM->getTargetCPU()),
+ std::string(TM->getTargetCPU()),
std::string(TM->getTargetFeatureString()), *TM,
/* isLittle */ false);
return std::make_unique<AArch64InstrInfo>(ST);
Index: llvm/lib/Target/AArch64/AArch64TargetMachine.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64TargetMachine.cpp
+++ llvm/lib/Target/AArch64/AArch64TargetMachine.cpp
@@ -354,10 +354,13 @@
const AArch64Subtarget *
AArch64TargetMachine::getSubtargetImpl(const Function &F) const {
Attribute CPUAttr = F.getFnAttribute("target-cpu");
+ Attribute TuneAttr = F.getFnAttribute("tune-cpu");
Attribute FSAttr = F.getFnAttribute("target-features");
std::string CPU =
CPUAttr.isValid() ? CPUAttr.getValueAsString().str() : TargetCPU;
+ std::string TuneCPU =
+ TuneAttr.isValid() ? TuneAttr.getValueAsString().str() : CPU;
std::string FS =
FSAttr.isValid() ? FSAttr.getValueAsString().str() : TargetFS;
@@ -398,6 +401,7 @@
Key += "SVEMax";
Key += std::to_string(MaxSVEVectorSize);
Key += CPU;
+ Key += TuneCPU;
Key += FS;
auto &I = SubtargetMap[Key];
@@ -406,7 +410,7 @@
// creation will depend on the TM and the code generation flags on the
// function that reside in TargetOptions.
resetTargetOptions(F);
- I = std::make_unique<AArch64Subtarget>(TargetTriple, CPU, FS, *this,
+ I = std::make_unique<AArch64Subtarget>(TargetTriple, CPU, TuneCPU, FS, *this,
isLittle, MinSVEVectorSize,
MaxSVEVectorSize);
}
Index: llvm/lib/Target/AArch64/AArch64Subtarget.h
===================================================================
--- llvm/lib/Target/AArch64/AArch64Subtarget.h
+++ llvm/lib/Target/AArch64/AArch64Subtarget.h
@@ -293,7 +293,8 @@
/// passed in feature string so that we can use initializer lists for
/// subtarget initialization.
AArch64Subtarget &initializeSubtargetDependencies(StringRef FS,
- StringRef CPUString);
+ StringRef CPUString,
+ StringRef TuneCPUString);
/// Initialize properties based on the selected processor family.
void initializeProperties();
@@ -301,7 +302,7 @@
public:
/// This constructor initializes the data members to match that
/// of the specified triple.
- AArch64Subtarget(const Triple &TT, const std::string &CPU,
+ AArch64Subtarget(const Triple &TT, const std::string &CPU, const std::string &TuneCPU,
const std::string &FS, const TargetMachine &TM,
bool LittleEndian,
unsigned MinSVEVectorSizeInBitsOverride = 0,
Index: llvm/lib/Target/AArch64/AArch64Subtarget.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64Subtarget.cpp
+++ llvm/lib/Target/AArch64/AArch64Subtarget.cpp
@@ -52,13 +52,17 @@
AArch64Subtarget &
AArch64Subtarget::initializeSubtargetDependencies(StringRef FS,
- StringRef CPUString) {
+ StringRef CPUString,
+ StringRef TuneCPUString) {
// Determine default and user-specified characteristics
if (CPUString.empty())
CPUString = "generic";
- ParseSubtargetFeatures(CPUString, /*TuneCPU*/ CPUString, FS);
+ if (TuneCPUString.empty())
+ TuneCPUString = CPUString;
+
+ ParseSubtargetFeatures(CPUString, TuneCPUString, FS);
initializeProperties();
return *this;
@@ -196,18 +200,18 @@
}
}
-AArch64Subtarget::AArch64Subtarget(const Triple &TT, const std::string &CPU,
+AArch64Subtarget::AArch64Subtarget(const Triple &TT, const std::string &CPU, const std::string &TuneCPU,
const std::string &FS,
const TargetMachine &TM, bool LittleEndian,
unsigned MinSVEVectorSizeInBitsOverride,
unsigned MaxSVEVectorSizeInBitsOverride)
- : AArch64GenSubtargetInfo(TT, CPU, /*TuneCPU*/ CPU, FS),
+ : AArch64GenSubtargetInfo(TT, CPU, TuneCPU, FS),
ReserveXRegister(AArch64::GPR64commonRegClass.getNumRegs()),
CustomCallSavedXRegs(AArch64::GPR64commonRegClass.getNumRegs()),
IsLittle(LittleEndian),
MinSVEVectorSizeInBits(MinSVEVectorSizeInBitsOverride),
MaxSVEVectorSizeInBits(MaxSVEVectorSizeInBitsOverride), TargetTriple(TT),
- FrameLowering(), InstrInfo(initializeSubtargetDependencies(FS, CPU)),
+ FrameLowering(), InstrInfo(initializeSubtargetDependencies(FS, CPU, TuneCPU)),
TSInfo(), TLInfo(TM, *this) {
if (AArch64::isX18ReservedByDefault(TT))
ReserveXRegister.set(18);
Index: clang/test/Driver/aarch64-mtune.c
===================================================================
--- /dev/null
+++ clang/test/Driver/aarch64-mtune.c
@@ -0,0 +1,42 @@
+// Ensure we support the -mtune flag.
+
+// There shouldn't be a default -mtune.
+// RUN: %clang -target aarch64-unknown-unknown -c -### %s 2>&1 \
+// RUN: | FileCheck %s -check-prefix=notune
+// notune-NOT: "-tune-cpu" "generic"
+
+// RUN: %clang -target aarch64-unknown-unknown -c -### %s -mtune=generic 2>&1 \
+// RUN: | FileCheck %s -check-prefix=generic
+// generic: "-tune-cpu" "generic"
+
+// RUN: %clang -target aarch64-unknown-unknown -c -### %s -mtune=neoverse-n1 2>&1 \
+// RUN: | FileCheck %s -check-prefix=neoverse-n1
+// neoverse-n1: "-tune-cpu" "neoverse-n1"
+
+// RUN: %clang -target aarch64-unknown-unknown -c -### %s -mtune=thunderx2t99 2>&1 \
+// RUN: | FileCheck %s -check-prefix=thunderx2t99
+// thunderx2t99: "-tune-cpu" "thunderx2t99"
+
+// Check interaction between march and mtune.
+
+// RUN: %clang -target aarch64-unknown-unknown -c -### %s -march=armv8-a 2>&1 \
+// RUN: | FileCheck %s -check-prefix=marcharmv8a
+// marcharmv8a: "-target-cpu" "generic"
+// marcharmv8a-NOT: "-tune-cpu" "generic"
+
+// RUN: %clang -target aarch64-unknown-unknown -c -### %s -march=armv8-a -mtune=cortex-a75 2>&1 \
+// RUN: | FileCheck %s -check-prefix=marcharmv8a-a75
+// marcharmv8a-a75: "-target-cpu" "generic"
+// marcharmv8a-a75: "-tune-cpu" "cortex-a75"
+
+// Check interaction between mcpu and mtune.
+
+// RUN: %clang -target aarch64-unknown-unknown -c -### %s -mcpu=thunderx 2>&1 \
+// RUN: | FileCheck %s -check-prefix=mcputhunderx
+// mcputhunderx: "-target-cpu" "thunderx"
+// mcputhunderx-NOT: "-tune-cpu"
+
+// RUN: %clang -target aarch64-unknown-unknown -c -### %s -mcpu=cortex-a75 -mtune=cortex-a57 2>&1 \
+// RUN: | FileCheck %s -check-prefix=mcpua75-mtunea57
+// mcpua75-mtunea57: "-target-cpu" "cortex-a75"
+// mcpua75-mtunea57: "-tune-cpu" "cortex-a57"
Index: clang/lib/Driver/ToolChains/Clang.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -1837,6 +1837,21 @@
}
AddAAPCSVolatileBitfieldArgs(Args, CmdArgs);
+
+ if (const Arg *A = Args.getLastArg(clang::driver::options::OPT_mtune_EQ)) {
+ StringRef Name = A->getValue();
+
+ std::string TuneCPU;
+ if (Name == "native")
+ TuneCPU = std::string(llvm::sys::getHostCPUName());
+ else
+ TuneCPU = std::string(Name);
+
+ if (!TuneCPU.empty()) {
+ CmdArgs.push_back("-tune-cpu");
+ CmdArgs.push_back(Args.MakeArgString(TuneCPU));
+ }
+ }
}
void Clang::AddMIPSTargetArgs(const ArgList &Args,
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
