Remove UnsafeFPMath uses in ARM

paperchalice · paperchalice · commit cf69f3afc89c · 2025-07-31T16:24:19.000+08:00
diff --git a/llvm/lib/Target/ARM/ARMAsmPrinter.cpp b/llvm/lib/Target/ARM/ARMAsmPrinter.cpp
@@ -629,6 +629,21 @@ static bool checkDenormalAttributeConsistency(const Module &M,
   });
 }
 
+// Returns true if all functions have different denormal modes.
+static bool checkDenormalAttributeInconsistency(const Module &M) {
+  if (M.functions().empty())
+    return false;
+  DenormalMode Value =
+      parseDenormalFPAttribute(M.functions()
+                                   .begin()
+                                   ->getFnAttribute("denormal-fp-math")
+                                   .getValueAsString());
+  return any_of(M, [&](const Function &F) {
+    StringRef AttrVal = F.getFnAttribute("denormal-fp-math").getValueAsString();
+    return parseDenormalFPAttribute(AttrVal) != Value;
+  });
+}
+
 void ARMAsmPrinter::emitAttributes() {
   MCTargetStreamer &TS = *OutStreamer->getTargetStreamer();
   ARMTargetStreamer &ATS = static_cast<ARMTargetStreamer &>(TS);
@@ -695,7 +710,9 @@ void ARMAsmPrinter::emitAttributes() {
                                              DenormalMode::getPositiveZero()))
     ATS.emitAttribute(ARMBuildAttrs::ABI_FP_denormal,
                       ARMBuildAttrs::PositiveZero);
-  else if (!TM.Options.UnsafeFPMath)
+  else if (checkDenormalAttributeInconsistency(*MMI->getModule()) ||
+           checkDenormalAttributeConsistency(
+               *MMI->getModule(), "denormal-fp-math", DenormalMode::getIEEE()))
     ATS.emitAttribute(ARMBuildAttrs::ABI_FP_denormal,
                       ARMBuildAttrs::IEEEDenormals);
   else {
@@ -730,7 +747,7 @@ void ARMAsmPrinter::emitAttributes() {
       TM.Options.NoTrappingFPMath)
     ATS.emitAttribute(ARMBuildAttrs::ABI_FP_exceptions,
                       ARMBuildAttrs::Not_Allowed);
-  else if (!TM.Options.UnsafeFPMath) {
+  else {
     ATS.emitAttribute(ARMBuildAttrs::ABI_FP_exceptions, ARMBuildAttrs::Allowed);
 
     // If the user has permitted this code to choose the IEEE 754
diff --git a/llvm/lib/Target/ARM/ARMISelLowering.cpp b/llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -5736,7 +5736,7 @@ static void expandf64Toi32(SDValue Op, SelectionDAG &DAG,
   llvm_unreachable("Unknown VFP cmp argument!");
 }
 
-/// OptimizeVFPBrcond - With -enable-unsafe-fp-math, it's legal to optimize some
+/// OptimizeVFPBrcond - With nnan, it's legal to optimize some
 /// f32 and even f64 comparisons to integer ones.
 SDValue
 ARMTargetLowering::OptimizeVFPBrcond(SDValue Op, SelectionDAG &DAG) const {
@@ -5878,9 +5878,9 @@ SDValue ARMTargetLowering::LowerBR_CC(SDValue Op, SelectionDAG &DAG) const {
     return DAG.getNode(ARMISD::BRCOND, dl, MVT::Other, Chain, Dest, ARMcc, Cmp);
   }
 
-  if (getTargetMachine().Options.UnsafeFPMath &&
-      (CC == ISD::SETEQ || CC == ISD::SETOEQ ||
-       CC == ISD::SETNE || CC == ISD::SETUNE)) {
+  if (SDNodeFlags Flags = Op->getFlags();
+      Flags.hasNoNaNs() && (CC == ISD::SETEQ || CC == ISD::SETOEQ ||
+                            CC == ISD::SETNE || CC == ISD::SETUNE)) {
     if (SDValue Result = OptimizeVFPBrcond(Op, DAG))
       return Result;
   }
diff --git a/llvm/lib/Target/ARM/ARMSubtarget.cpp b/llvm/lib/Target/ARM/ARMSubtarget.cpp
@@ -88,18 +88,16 @@ ARMFrameLowering *ARMSubtarget::initializeFrameLowering(StringRef CPU,
 ARMSubtarget::ARMSubtarget(const Triple &TT, const std::string &CPU,
                            const std::string &FS,
                            const ARMBaseTargetMachine &TM, bool IsLittle,
-                           bool MinSize)
+                           bool MinSize, DenormalMode DM)
     : ARMGenSubtargetInfo(TT, CPU, /*TuneCPU*/ CPU, FS),
       UseMulOps(UseFusedMulOps), CPUString(CPU), OptMinSize(MinSize),
-      IsLittle(IsLittle), TargetTriple(TT), Options(TM.Options), TM(TM),
+      IsLittle(IsLittle), DM(DM), TargetTriple(TT), Options(TM.Options), TM(TM),
       FrameLowering(initializeFrameLowering(CPU, FS)),
       // At this point initializeSubtargetDependencies has been called so
       // we can query directly.
-      InstrInfo(isThumb1Only()
-                    ? (ARMBaseInstrInfo *)new Thumb1InstrInfo(*this)
-                    : !isThumb()
-                          ? (ARMBaseInstrInfo *)new ARMInstrInfo(*this)
-                          : (ARMBaseInstrInfo *)new Thumb2InstrInfo(*this)),
+      InstrInfo(isThumb1Only() ? (ARMBaseInstrInfo *)new Thumb1InstrInfo(*this)
+                : !isThumb()   ? (ARMBaseInstrInfo *)new ARMInstrInfo(*this)
+                             : (ARMBaseInstrInfo *)new Thumb2InstrInfo(*this)),
       TLInfo(TM, *this) {
 
   CallLoweringInfo.reset(new ARMCallLowering(*getTargetLowering()));
@@ -224,7 +222,7 @@ void ARMSubtarget::initSubtargetFeatures(StringRef CPU, StringRef FS) {
   // NEON f32 ops are non-IEEE 754 compliant. Darwin is ok with it by default.
   const FeatureBitset &Bits = getFeatureBits();
   if ((Bits[ARM::ProcA5] || Bits[ARM::ProcA8]) && // Where this matters
-      (Options.UnsafeFPMath || isTargetDarwin()))
+      (isTargetDarwin() || DM == DenormalMode::getPreserveSign()))
     HasNEONForFP = true;
 
   if (isRWPI())
diff --git a/llvm/lib/Target/ARM/ARMSubtarget.h b/llvm/lib/Target/ARM/ARMSubtarget.h
@@ -186,6 +186,9 @@ class ARMSubtarget : public ARMGenSubtargetInfo {
   /// IsLittle - The target is Little Endian
   bool IsLittle;
 
+  /// DM - Denormal mode
+  DenormalMode DM;
+
   /// TargetTriple - What processor and OS we're targeting.
   Triple TargetTriple;
 
@@ -206,7 +209,7 @@ class ARMSubtarget : public ARMGenSubtargetInfo {
   ///
   ARMSubtarget(const Triple &TT, const std::string &CPU, const std::string &FS,
                const ARMBaseTargetMachine &TM, bool IsLittle,
-               bool MinSize = false);
+               bool MinSize = false, DenormalMode DM = DenormalMode::getIEEE());
 
   /// getMaxInlineSizeThreshold - Returns the maximum memset / memcpy size
   /// that still makes it profitable to inline the call.
diff --git a/llvm/lib/Target/ARM/ARMTargetMachine.cpp b/llvm/lib/Target/ARM/ARMTargetMachine.cpp
@@ -285,14 +285,19 @@ ARMBaseTargetMachine::getSubtargetImpl(const Function &F) const {
   if (F.hasMinSize())
     Key += "+minsize";
 
+  DenormalMode DM = parseDenormalFPAttribute(
+      F.getFnAttribute("denormal-fp-math").getValueAsString());
+  if (DM != DenormalMode::getIEEE())
+    Key += "denormal-fp-math=" + DM.str();
+
   auto &I = SubtargetMap[Key];
   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 = std::make_unique<ARMSubtarget>(TargetTriple, CPU, FS, *this, isLittle,
-                                        F.hasMinSize());
+                                       F.hasMinSize(), DM);
 
     if (!I->isThumb() && !I->hasARMOps())
       F.getContext().emitError("Function '" + F.getName() + "' uses ARM "
diff --git a/llvm/test/CodeGen/ARM/fadds.ll b/llvm/test/CodeGen/ARM/fadds.ll
@@ -7,7 +7,7 @@
 ; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 %s -o - \
 ; RUN:  | FileCheck %s -check-prefix=CORTEXA8
 
-; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 --enable-unsafe-fp-math %s -o - \
+; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 --denormal-fp-math=preserve-sign %s -o - \
 ; RUN:  | FileCheck %s -check-prefix=CORTEXA8U
 
 ; RUN: llc -mtriple=arm-darwin -mcpu=cortex-a8 %s -o - \
diff --git a/llvm/test/CodeGen/ARM/fmuls.ll b/llvm/test/CodeGen/ARM/fmuls.ll
@@ -7,7 +7,7 @@
 ; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 %s -o - \
 ; RUN:  | FileCheck %s -check-prefix=CORTEXA8
 
-; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 --enable-unsafe-fp-math %s -o - \
+; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 --denormal-fp-math=preserve-sign %s -o - \
 ; RUN:  | FileCheck %s -check-prefix=CORTEXA8U
 
 ; RUN: llc -mtriple=arm-darwin -mcpu=cortex-a8 %s -o - \
diff --git a/llvm/test/CodeGen/ARM/fnegs.ll b/llvm/test/CodeGen/ARM/fnegs.ll
@@ -10,7 +10,7 @@
 ; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 %s -o - \
 ; RUN:  | FileCheck %s -check-prefix=CORTEXA8
 
-; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 --enable-unsafe-fp-math %s -o - \
+; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 --denormal-fp-math=preserve-sign %s -o - \
 ; RUN:  | FileCheck %s -check-prefix=CORTEXA8U
 
 ; RUN: llc -mtriple=arm-darwin -mcpu=cortex-a8 %s -o - \
diff --git a/llvm/test/CodeGen/ARM/fnmscs.ll b/llvm/test/CodeGen/ARM/fnmscs.ll
@@ -13,7 +13,7 @@
 ; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 -regalloc=basic %s -o - \
 ; RUN:  | FileCheck %s -check-prefix=A8
 
-; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 --enable-unsafe-fp-math %s -o - \
+; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 --enable-unsafe-fp-math  %s -o - \
 ; RUN:  | FileCheck %s -check-prefix=A8U
 
 ; RUN: llc -mtriple=arm-darwin -mcpu=cortex-a8 %s -o - \
diff --git a/llvm/test/CodeGen/ARM/fp_convert.ll b/llvm/test/CodeGen/ARM/fp_convert.ll
@@ -7,7 +7,7 @@
 ; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 %s -o - \
 ; RUN: | FileCheck %s -check-prefix=VFP2
 
-; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 --enable-unsafe-fp-math %s -o - \
+; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 --denormal-fp-math=preserve-sign %s -o - \
 ; RUN:  | FileCheck %s -check-prefix=NEON
 
 ; RUN: llc -mtriple=arm-darwin -mcpu=cortex-a8 %s -o - \
diff --git a/llvm/test/CodeGen/ARM/fpcmp-opt.ll b/llvm/test/CodeGen/ARM/fpcmp-opt.ll
@@ -1,4 +1,4 @@
-; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 -mattr=+vfp2 -enable-unsafe-fp-math %s -o - \
+; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 -mattr=+vfp2 %s -o - \
 ; RUN:  | FileCheck %s
 
 ; rdar://7461510
@@ -42,7 +42,7 @@ entry:
 ; CHECK-NOT: vmrs
 ; CHECK: bne
   %0 = load double, ptr %a
-  %1 = fcmp oeq double %0, 0.000000e+00
+  %1 = fcmp nnan oeq double %0, 0.000000e+00
   br i1 %1, label %bb1, label %bb2
 
 bb1:
@@ -65,7 +65,7 @@ entry:
 ; CHECK-NOT: vmrs
 ; CHECK: bne
   %0 = load float, ptr %a
-  %1 = fcmp oeq float %0, 0.000000e+00
+  %1 = fcmp nnan oeq float %0, 0.000000e+00
   br i1 %1, label %bb1, label %bb2
 
 bb1:
diff --git a/llvm/test/CodeGen/ARM/fsubs.ll b/llvm/test/CodeGen/ARM/fsubs.ll
@@ -4,7 +4,7 @@
 ; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 %s -o - \
 ; RUN:  | FileCheck %s -check-prefix=NFP1
 
-; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 --enable-unsafe-fp-math %s -o - \
+; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a8 --denormal-fp-math=preserve-sign %s -o - \
 ; RUN:  | FileCheck %s -check-prefix=NFP1U
 
 ; RUN: llc -mtriple=arm-darwin -mcpu=cortex-a8 %s -o - \
diff --git a/llvm/test/CodeGen/ARM/neon-spfp.ll b/llvm/test/CodeGen/ARM/neon-spfp.ll
@@ -4,11 +4,11 @@
 ; RUN: llc < %s -mtriple armv7a-none-linux-gnueabihf -mcpu=cortex-a15 | FileCheck %s -check-prefix=CHECK-LINUXA15
 ; RUN: llc < %s -mtriple armv7a-none-linux-gnueabihf -mcpu=swift | FileCheck %s -check-prefix=CHECK-LINUXSWIFT
 
-; RUN: llc < %s -mtriple armv7a-none-linux-gnueabihf -mcpu=cortex-a5 --enable-unsafe-fp-math | FileCheck %s -check-prefix=CHECK-UNSAFEA5
-; RUN: llc < %s -mtriple armv7a-none-linux-gnueabihf -mcpu=cortex-a8 --enable-unsafe-fp-math | FileCheck %s -check-prefix=CHECK-UNSAFEA8
-; RUN: llc < %s -mtriple armv7a-none-linux-gnueabihf -mcpu=cortex-a9 --enable-unsafe-fp-math | FileCheck %s -check-prefix=CHECK-UNSAFEA9
-; RUN: llc < %s -mtriple armv7a-none-linux-gnueabihf -mcpu=cortex-a15 --enable-unsafe-fp-math | FileCheck %s -check-prefix=CHECK-UNSAFEA15
-; RUN: llc < %s -mtriple armv7a-none-linux-gnueabihf -mcpu=swift --enable-unsafe-fp-math | FileCheck %s -check-prefix=CHECK-UNSAFESWIFT
+; RUN: llc < %s -mtriple armv7a-none-linux-gnueabihf -mcpu=cortex-a5 --denormal-fp-math=preserve-sign | FileCheck %s -check-prefix=CHECK-UNSAFEA5
+; RUN: llc < %s -mtriple armv7a-none-linux-gnueabihf -mcpu=cortex-a8 --denormal-fp-math=preserve-sign | FileCheck %s -check-prefix=CHECK-UNSAFEA8
+; RUN: llc < %s -mtriple armv7a-none-linux-gnueabihf -mcpu=cortex-a9 --denormal-fp-math=preserve-sign | FileCheck %s -check-prefix=CHECK-UNSAFEA9
+; RUN: llc < %s -mtriple armv7a-none-linux-gnueabihf -mcpu=cortex-a15 --denormal-fp-math=preserve-sign | FileCheck %s -check-prefix=CHECK-UNSAFEA15
+; RUN: llc < %s -mtriple armv7a-none-linux-gnueabihf -mcpu=swift --denormal-fp-math=preserve-sign | FileCheck %s -check-prefix=CHECK-UNSAFESWIFT
 
 ; RUN: llc < %s -mtriple armv7a-none-darwin -mcpu=cortex-a5 | FileCheck %s -check-prefix=CHECK-DARWINA5
 ; RUN: llc < %s -mtriple armv7a-none-darwin -mcpu=cortex-a8 | FileCheck %s -check-prefix=CHECK-DARWINA8

Original file line number	Diff line number	Diff line change
`@@ -5736,7 +5736,7 @@ static void expandf64Toi32(SDValue Op, SelectionDAG &DAG,`
`5736`	`5736`	`llvm_unreachable("Unknown VFP cmp argument!");`
`5737`	`5737`	`}`
`5738`	`5738`
`5739`		`-/// OptimizeVFPBrcond - With -enable-unsafe-fp-math, it's legal to optimize some`
	`5739`	`+/// OptimizeVFPBrcond - With nnan, it's legal to optimize some`
`5740`	`5740`	`/// f32 and even f64 comparisons to integer ones.`
`5741`	`5741`	`SDValue`
`5742`	`5742`	`ARMTargetLowering::OptimizeVFPBrcond(SDValue Op, SelectionDAG &DAG) const {`
`@@ -5878,9 +5878,9 @@ SDValue ARMTargetLowering::LowerBR_CC(SDValue Op, SelectionDAG &DAG) const {`
`5878`	`5878`	`return DAG.getNode(ARMISD::BRCOND, dl, MVT::Other, Chain, Dest, ARMcc, Cmp);`
`5879`	`5879`	`}`
`5880`	`5880`
`5881`		`- if (getTargetMachine().Options.UnsafeFPMath &&`
`5882`		`- (CC == ISD::SETEQ \|\| CC == ISD::SETOEQ \|\|`
`5883`		`- CC == ISD::SETNE \|\| CC == ISD::SETUNE)) {`
	`5881`	`+ if (SDNodeFlags Flags = Op->getFlags();`
	`5882`	`+ Flags.hasNoNaNs() && (CC == ISD::SETEQ \|\| CC == ISD::SETOEQ \|\|`
	`5883`	`+ CC == ISD::SETNE \|\| CC == ISD::SETUNE)) {`
`5884`	`5884`	`if (SDValue Result = OptimizeVFPBrcond(Op, DAG))`
`5885`	`5885`	`return Result;`
`5886`	`5886`	`}`