[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