[globalisel][tablegen] Compute available feature bits correctly.
Summary:
Predicate<> now has a field to indicate how often it must be recomputed.
Currently, there are two frequencies, per-module (RecomputePerFunction==0)
and per-function (RecomputePerFunction==1). Per-function predicates are
currently recomputed more frequently than necessary since the only predicate
in this category is cheap to test. Per-module predicates are now computed in
getSubtargetImpl() while per-function predicates are computed in selectImpl().
Tablegen now manages the PredicateBitset internally. It should only be
necessary to add the required includes.
Also fixed a problem revealed by the test case where
constrainSelectedInstRegOperands() would attempt to tie operands that
BuildMI had already tied.
Reviewers: ab, qcolombet, t.p.northover, rovka, aditya_nandakumar
Reviewed By: rovka
Subscribers: kristof.beyls, igorb, llvm-commits
Differential Revision: https://reviews.llvm.org/D32491
llvm-svn: 301750
diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.td b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
index 82e9c5a..ce40120 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
@@ -314,8 +314,8 @@
// AArch64 Instruction Predicate Definitions.
def IsDarwin : Predicate<"Subtarget->isTargetDarwin()">;
def IsNotDarwin: Predicate<"!Subtarget->isTargetDarwin()">;
-def ForCodeSize : Predicate<"ForCodeSize">;
-def NotForCodeSize : Predicate<"!ForCodeSize">;
+def ForCodeSize : Predicate<"Subtarget->getForCodeSize()">;
+def NotForCodeSize : Predicate<"!Subtarget->getForCodeSize()">;
include "AArch64InstrFormats.td"
diff --git a/llvm/lib/Target/AArch64/AArch64InstructionSelector.cpp b/llvm/lib/Target/AArch64/AArch64InstructionSelector.cpp
index b0e0e3e..9bfd570 100644
--- a/llvm/lib/Target/AArch64/AArch64InstructionSelector.cpp
+++ b/llvm/lib/Target/AArch64/AArch64InstructionSelector.cpp
@@ -51,7 +51,6 @@
const AArch64Subtarget &STI,
const AArch64RegisterBankInfo &RBI);
- void beginFunction(const MachineFunction &MF) override;
bool select(MachineInstr &I) const override;
private:
@@ -74,12 +73,10 @@
const AArch64InstrInfo &TII;
const AArch64RegisterInfo &TRI;
const AArch64RegisterBankInfo &RBI;
- bool ForCodeSize;
- PredicateBitset AvailableFeatures;
- PredicateBitset
- computeAvailableFeatures(const MachineFunction *MF,
- const AArch64Subtarget *Subtarget) const;
+#define GET_GLOBALISEL_PREDICATES_DECL
+#include "AArch64GenGlobalISel.inc"
+#undef GET_GLOBALISEL_PREDICATES_DECL
// We declare the temporaries used by selectImpl() in the class to minimize the
// cost of constructing placeholder values.
@@ -98,7 +95,10 @@
const AArch64TargetMachine &TM, const AArch64Subtarget &STI,
const AArch64RegisterBankInfo &RBI)
: InstructionSelector(), TM(TM), STI(STI), TII(*STI.getInstrInfo()),
- TRI(*STI.getRegisterInfo()), RBI(RBI), ForCodeSize(), AvailableFeatures()
+ TRI(*STI.getRegisterInfo()), RBI(RBI),
+#define GET_GLOBALISEL_PREDICATES_INIT
+#include "AArch64GenGlobalISel.inc"
+#undef GET_GLOBALISEL_PREDICATES_INIT
#define GET_GLOBALISEL_TEMPORARIES_INIT
#include "AArch64GenGlobalISel.inc"
#undef GET_GLOBALISEL_TEMPORARIES_INIT
@@ -577,12 +577,6 @@
return true;
}
-void AArch64InstructionSelector::beginFunction(
- const MachineFunction &MF) {
- ForCodeSize = MF.getFunction()->optForSize();
- AvailableFeatures = computeAvailableFeatures(&MF, &STI);
-}
-
bool AArch64InstructionSelector::select(MachineInstr &I) const {
assert(I.getParent() && "Instruction should be in a basic block!");
assert(I.getParent()->getParent() && "Instruction should be in a function!");
diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
index 042755b..287fbc5 100644
--- a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
+++ b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
@@ -113,11 +113,12 @@
AArch64Subtarget::AArch64Subtarget(const Triple &TT, const std::string &CPU,
const std::string &FS,
- const TargetMachine &TM, bool LittleEndian)
+ const TargetMachine &TM, bool LittleEndian,
+ bool ForCodeSize)
: AArch64GenSubtargetInfo(TT, CPU, FS), ReserveX18(TT.isOSDarwin()),
IsLittle(LittleEndian), TargetTriple(TT), FrameLowering(),
InstrInfo(initializeSubtargetDependencies(FS, CPU)), TSInfo(),
- TLInfo(TM, *this), GISel() {}
+ TLInfo(TM, *this), GISel(), ForCodeSize(ForCodeSize) {}
const CallLowering *AArch64Subtarget::getCallLowering() const {
assert(GISel && "Access to GlobalISel APIs not set");
diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.h b/llvm/lib/Target/AArch64/AArch64Subtarget.h
index 3d66a9e..5b9bee6 100644
--- a/llvm/lib/Target/AArch64/AArch64Subtarget.h
+++ b/llvm/lib/Target/AArch64/AArch64Subtarget.h
@@ -124,6 +124,8 @@
/// an optional library.
std::unique_ptr<GISelAccessor> GISel;
+ bool ForCodeSize;
+
private:
/// initializeSubtargetDependencies - Initializes using CPUString and the
/// passed in feature string so that we can use initializer lists for
@@ -139,7 +141,7 @@
/// of the specified triple.
AArch64Subtarget(const Triple &TT, const std::string &CPU,
const std::string &FS, const TargetMachine &TM,
- bool LittleEndian);
+ bool LittleEndian, bool ForCodeSize);
/// This object will take onwership of \p GISelAccessor.
void setGISelAccessor(GISelAccessor &GISel) {
@@ -262,6 +264,8 @@
}
}
+ bool getForCodeSize() const { return ForCodeSize; }
+
/// ParseSubtargetFeatures - Parses features string setting specified
/// subtarget options. Definition of function is auto generated by tblgen.
void ParseSubtargetFeatures(StringRef CPU, StringRef FS);
diff --git a/llvm/lib/Target/AArch64/AArch64TargetMachine.cpp b/llvm/lib/Target/AArch64/AArch64TargetMachine.cpp
index dcc51bf..79d7162 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetMachine.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetMachine.cpp
@@ -255,6 +255,7 @@
AArch64TargetMachine::getSubtargetImpl(const Function &F) const {
Attribute CPUAttr = F.getFnAttribute("target-cpu");
Attribute FSAttr = F.getFnAttribute("target-features");
+ bool ForCodeSize = F.optForSize();
std::string CPU = !CPUAttr.hasAttribute(Attribute::None)
? CPUAttr.getValueAsString().str()
@@ -262,15 +263,17 @@
std::string FS = !FSAttr.hasAttribute(Attribute::None)
? FSAttr.getValueAsString().str()
: TargetFS;
+ std::string ForCodeSizeStr =
+ std::string(ForCodeSize ? "+" : "-") + "forcodesize";
- auto &I = SubtargetMap[CPU + FS];
+ auto &I = SubtargetMap[CPU + FS + ForCodeSizeStr];
if (!I) {
// This needs to be done before we create a new subtarget since any
// creation will depend on the TM and the code generation flags on the
// function that reside in TargetOptions.
resetTargetOptions(F);
I = llvm::make_unique<AArch64Subtarget>(TargetTriple, CPU, FS, *this,
- isLittle);
+ isLittle, ForCodeSize);
#ifndef LLVM_BUILD_GLOBAL_ISEL
GISelAccessor *GISel = new GISelAccessor();
#else
diff --git a/llvm/lib/Target/X86/X86InstrInfo.td b/llvm/lib/Target/X86/X86InstrInfo.td
index c3def46..ce08764 100644
--- a/llvm/lib/Target/X86/X86InstrInfo.td
+++ b/llvm/lib/Target/X86/X86InstrInfo.td
@@ -877,7 +877,9 @@
def IsWin64 : Predicate<"Subtarget->isTargetWin64()">;
def NotWin64 : Predicate<"!Subtarget->isTargetWin64()">;
def NotWin64WithoutFP : Predicate<"!Subtarget->isTargetWin64() ||"
- "Subtarget->getFrameLowering()->hasFP(*MF)">;
+ "Subtarget->getFrameLowering()->hasFP(*MF)"> {
+ let RecomputePerFunction = 1;
+}
def IsPS4 : Predicate<"Subtarget->isTargetPS4()">;
def NotPS4 : Predicate<"!Subtarget->isTargetPS4()">;
def IsNaCl : Predicate<"Subtarget->isTargetNaCl()">;
@@ -887,9 +889,9 @@
def NearData : Predicate<"TM.getCodeModel() == CodeModel::Small ||"
"TM.getCodeModel() == CodeModel::Kernel">;
def IsNotPIC : Predicate<"!TM.isPositionIndependent()">;
-def OptForSize : Predicate<"OptForSize">;
-def OptForMinSize : Predicate<"OptForMinSize">;
-def OptForSpeed : Predicate<"!OptForSize">;
+def OptForSize : Predicate<"Subtarget->getOptForSize()">;
+def OptForMinSize : Predicate<"Subtarget->getOptForMinSize()">;
+def OptForSpeed : Predicate<"!Subtarget->getOptForSize()">;
def FastBTMem : Predicate<"!Subtarget->isBTMemSlow()">;
def CallImmAddr : Predicate<"Subtarget->isLegalToCallImmediateAddr()">;
def FavorMemIndirectCall : Predicate<"!Subtarget->callRegIndirect()">;
diff --git a/llvm/lib/Target/X86/X86InstructionSelector.cpp b/llvm/lib/Target/X86/X86InstructionSelector.cpp
index f6d17c5..3457d35 100644
--- a/llvm/lib/Target/X86/X86InstructionSelector.cpp
+++ b/llvm/lib/Target/X86/X86InstructionSelector.cpp
@@ -48,7 +48,6 @@
X86InstructionSelector(const X86TargetMachine &TM, const X86Subtarget &STI,
const X86RegisterBankInfo &RBI);
- void beginFunction(const MachineFunction &MF) override;
bool select(MachineInstr &I) const override;
private:
@@ -80,12 +79,10 @@
const X86InstrInfo &TII;
const X86RegisterInfo &TRI;
const X86RegisterBankInfo &RBI;
- bool OptForSize;
- bool OptForMinSize;
- PredicateBitset AvailableFeatures;
- PredicateBitset computeAvailableFeatures(const MachineFunction *MF,
- const X86Subtarget *Subtarget) const;
+#define GET_GLOBALISEL_PREDICATES_DECL
+#include "X86GenGlobalISel.inc"
+#undef GET_GLOBALISEL_PREDICATES_DECL
#define GET_GLOBALISEL_TEMPORARIES_DECL
#include "X86GenGlobalISel.inc"
@@ -102,8 +99,10 @@
const X86Subtarget &STI,
const X86RegisterBankInfo &RBI)
: InstructionSelector(), TM(TM), STI(STI), TII(*STI.getInstrInfo()),
- TRI(*STI.getRegisterInfo()), RBI(RBI), OptForSize(false),
- OptForMinSize(false), AvailableFeatures()
+ TRI(*STI.getRegisterInfo()), RBI(RBI),
+#define GET_GLOBALISEL_PREDICATES_INIT
+#include "X86GenGlobalISel.inc"
+#undef GET_GLOBALISEL_PREDICATES_INIT
#define GET_GLOBALISEL_TEMPORARIES_INIT
#include "X86GenGlobalISel.inc"
#undef GET_GLOBALISEL_TEMPORARIES_INIT
@@ -206,12 +205,6 @@
return true;
}
-void X86InstructionSelector::beginFunction(const MachineFunction &MF) {
- OptForSize = MF.getFunction()->optForSize();
- OptForMinSize = MF.getFunction()->optForMinSize();
- AvailableFeatures = computeAvailableFeatures(&MF, &STI);
-}
-
bool X86InstructionSelector::select(MachineInstr &I) const {
assert(I.getParent() && "Instruction should be in a basic block!");
assert(I.getParent()->getParent() && "Instruction should be in a function!");
diff --git a/llvm/lib/Target/X86/X86Subtarget.cpp b/llvm/lib/Target/X86/X86Subtarget.cpp
index 4154530..b805ddf 100644
--- a/llvm/lib/Target/X86/X86Subtarget.cpp
+++ b/llvm/lib/Target/X86/X86Subtarget.cpp
@@ -326,7 +326,8 @@
X86Subtarget::X86Subtarget(const Triple &TT, StringRef CPU, StringRef FS,
const X86TargetMachine &TM,
- unsigned StackAlignOverride)
+ unsigned StackAlignOverride, bool OptForSize,
+ bool OptForMinSize)
: X86GenSubtargetInfo(TT, CPU, FS), X86ProcFamily(Others),
PICStyle(PICStyles::None), TM(TM), TargetTriple(TT),
StackAlignOverride(StackAlignOverride),
@@ -335,8 +336,9 @@
TargetTriple.getEnvironment() != Triple::CODE16),
In16BitMode(TargetTriple.getArch() == Triple::x86 &&
TargetTriple.getEnvironment() == Triple::CODE16),
- InstrInfo(initializeSubtargetDependencies(CPU, FS)),
- TLInfo(TM, *this), FrameLowering(*this, getStackAlignment()) {
+ InstrInfo(initializeSubtargetDependencies(CPU, FS)), TLInfo(TM, *this),
+ FrameLowering(*this, getStackAlignment()), OptForSize(OptForSize),
+ OptForMinSize(OptForMinSize) {
// Determine the PICStyle based on the target selected.
if (!isPositionIndependent())
setPICStyle(PICStyles::None);
diff --git a/llvm/lib/Target/X86/X86Subtarget.h b/llvm/lib/Target/X86/X86Subtarget.h
index fd057f3..8568cf0 100644
--- a/llvm/lib/Target/X86/X86Subtarget.h
+++ b/llvm/lib/Target/X86/X86Subtarget.h
@@ -328,12 +328,16 @@
X86TargetLowering TLInfo;
X86FrameLowering FrameLowering;
+ bool OptForSize;
+ bool OptForMinSize;
+
public:
/// This constructor initializes the data members to match that
/// of the specified triple.
///
X86Subtarget(const Triple &TT, StringRef CPU, StringRef FS,
- const X86TargetMachine &TM, unsigned StackAlignOverride);
+ const X86TargetMachine &TM, unsigned StackAlignOverride,
+ bool OptForSize, bool OptForMinSize);
/// This object will take onwership of \p GISelAccessor.
void setGISelAccessor(GISelAccessor &GISel) { this->GISel.reset(&GISel); }
@@ -499,6 +503,9 @@
bool isSLM() const { return X86ProcFamily == IntelSLM; }
bool useSoftFloat() const { return UseSoftFloat; }
+ bool getOptForSize() const { return OptForSize; }
+ bool getOptForMinSize() const { return OptForMinSize; }
+
/// Use mfence if we have SSE2 or we're on x86-64 (even if we asked for
/// no-sse2). There isn't any reason to disable it if the target processor
/// supports it.
diff --git a/llvm/lib/Target/X86/X86TargetMachine.cpp b/llvm/lib/Target/X86/X86TargetMachine.cpp
index 623cf38..086f55d 100644
--- a/llvm/lib/Target/X86/X86TargetMachine.cpp
+++ b/llvm/lib/Target/X86/X86TargetMachine.cpp
@@ -268,6 +268,12 @@
FS = Key.substr(CPU.size());
+ bool OptForSize = F.optForSize();
+ bool OptForMinSize = F.optForMinSize();
+
+ Key += std::string(OptForSize ? "+" : "-") + "optforsize";
+ Key += std::string(OptForMinSize ? "+" : "-") + "optforminsize";
+
auto &I = SubtargetMap[Key];
if (!I) {
// This needs to be done before we create a new subtarget since any
@@ -275,7 +281,8 @@
// function that reside in TargetOptions.
resetTargetOptions(F);
I = llvm::make_unique<X86Subtarget>(TargetTriple, CPU, FS, *this,
- Options.StackAlignmentOverride);
+ Options.StackAlignmentOverride,
+ OptForSize, OptForMinSize);
#ifndef LLVM_BUILD_GLOBAL_ISEL
GISelAccessor *GISel = new GISelAccessor();
#else
@@ -286,7 +293,8 @@
auto *RBI = new X86RegisterBankInfo(*I->getRegisterInfo());
GISel->RegBankInfo.reset(RBI);
- GISel->InstSelector.reset(createX86InstructionSelector(*this, *I, *RBI));
+ GISel->InstSelector.reset(createX86InstructionSelector(
+ *this, *I, *RBI));
#endif
I->setGISelAccessor(*GISel);
}