4 files changed, 81 insertions, 11 deletions
diff --git a/llvm/lib/CodeGen/GlobalISel/GISelValueTracking.cpp b/llvm/lib/CodeGen/GlobalISel/GISelValueTracking.cpp
index 90c60d4..04d9309 100644
--- a/llvm/lib/CodeGen/GlobalISel/GISelValueTracking.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/GISelValueTracking.cpp
@@ -112,7 +112,7 @@ APInt GISelValueTracking::getKnownOnes(Register R) {
   return getKnownBits(R).One;
 }
 
-LLVM_ATTRIBUTE_UNUSED static void
+[[maybe_unused]] static void
 dumpResult(const MachineInstr &MI, const KnownBits &Known, unsigned Depth) {
   dbgs() << "[" << Depth << "] Compute known bits: " << MI << "[" << Depth
          << "] Computed for: " << MI << "[" << Depth << "] Known: 0x"
@@ -1975,6 +1975,81 @@ unsigned GISelValueTracking::computeNumSignBits(Register R,
 
     break;
   }
+  case TargetOpcode::G_SUB: {
+    Register Src2 = MI.getOperand(2).getReg();
+    unsigned Src2NumSignBits =
+        computeNumSignBits(Src2, DemandedElts, Depth + 1);
+    if (Src2NumSignBits == 1)
+      return 1; // Early out.
+
+    // Handle NEG.
+    Register Src1 = MI.getOperand(1).getReg();
+    KnownBits Known1 = getKnownBits(Src1, DemandedElts, Depth);
+    if (Known1.isZero()) {
+      KnownBits Known2 = getKnownBits(Src2, DemandedElts, Depth);
+      // If the input is known to be 0 or 1, the output is 0/-1, which is all
+      // sign bits set.
+      if ((Known2.Zero | 1).isAllOnes())
+        return TyBits;
+
+      // If the input is known to be positive (the sign bit is known clear),
+      // the output of the NEG has, at worst, the same number of sign bits as
+      // the input.
+      if (Known2.isNonNegative()) {
+        FirstAnswer = Src2NumSignBits;
+        break;
+      }
+
+      // Otherwise, we treat this like a SUB.
+    }
+
+    unsigned Src1NumSignBits =
+        computeNumSignBits(Src1, DemandedElts, Depth + 1);
+    if (Src1NumSignBits == 1)
+      return 1; // Early Out.
+
+    // Sub can have at most one carry bit.  Thus we know that the output
+    // is, at worst, one more bit than the inputs.
+    FirstAnswer = std::min(Src1NumSignBits, Src2NumSignBits) - 1;
+    break;
+  }
+  case TargetOpcode::G_ADD: {
+    Register Src2 = MI.getOperand(2).getReg();
+    unsigned Src2NumSignBits =
+        computeNumSignBits(Src2, DemandedElts, Depth + 1);
+    if (Src2NumSignBits <= 2)
+      return 1; // Early out.
+
+    Register Src1 = MI.getOperand(1).getReg();
+    unsigned Src1NumSignBits =
+        computeNumSignBits(Src1, DemandedElts, Depth + 1);
+    if (Src1NumSignBits == 1)
+      return 1; // Early Out.
+
+    // Special case decrementing a value (ADD X, -1):
+    KnownBits Known2 = getKnownBits(Src2, DemandedElts, Depth);
+    if (Known2.isAllOnes()) {
+      KnownBits Known1 = getKnownBits(Src1, DemandedElts, Depth);
+      // If the input is known to be 0 or 1, the output is 0/-1, which is all
+      // sign bits set.
+      if ((Known1.Zero | 1).isAllOnes())
+        return TyBits;
+
+      // If we are subtracting one from a positive number, there is no carry
+      // out of the result.
+      if (Known1.isNonNegative()) {
+        FirstAnswer = Src1NumSignBits;
+        break;
+      }
+
+      // Otherwise, we treat this like an ADD.
+    }
+
+    // Add can have at most one carry bit.  Thus we know that the output
+    // is, at worst, one more bit than the inputs.
+    FirstAnswer = std::min(Src1NumSignBits, Src2NumSignBits) - 1;
+    break;
+  }
   case TargetOpcode::G_FCMP:
   case TargetOpcode::G_ICMP: {
     bool IsFP = Opcode == TargetOpcode::G_FCMP;
diff --git a/llvm/lib/CodeGen/GlobalISel/LegalizeMutations.cpp b/llvm/lib/CodeGen/GlobalISel/LegalizeMutations.cpp
index 25c1db9..ded4df4 100644
--- a/llvm/lib/CodeGen/GlobalISel/LegalizeMutations.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/LegalizeMutations.cpp
@@ -55,12 +55,10 @@ LegalizeMutation LegalizeMutations::changeElementCountTo(unsigned TypeIdx,
 }
 
 LegalizeMutation LegalizeMutations::changeElementCountTo(unsigned TypeIdx,
-                                                         LLT NewEltTy) {
+                                                         ElementCount EC) {
   return [=](const LegalityQuery &Query) {
     const LLT OldTy = Query.Types[TypeIdx];
-    ElementCount NewEltCount = NewEltTy.isVector() ? NewEltTy.getElementCount()
-                                                   : ElementCount::getFixed(1);
-    return std::make_pair(TypeIdx, OldTy.changeElementCount(NewEltCount));
+    return std::make_pair(TypeIdx, OldTy.changeElementCount(EC));
   };
 }
 
diff --git a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
index cffaf7c..38ec83f 100644
--- a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
@@ -3292,8 +3292,7 @@ LegalizerHelper::widenScalar(MachineInstr &MI, unsigned TypeIdx, LLT WideTy) {
     if (TypeIdx != 2)
       return UnableToLegalize;
     Observer.changingInstr(MI);
-    // TODO: Probably should be zext
-    widenScalarSrc(MI, WideTy, 2, TargetOpcode::G_SEXT);
+    widenScalarSrc(MI, WideTy, 2, TargetOpcode::G_ZEXT);
     Observer.changedInstr(MI);
     return Legalized;
   }
@@ -3325,8 +3324,7 @@ LegalizerHelper::widenScalar(MachineInstr &MI, unsigned TypeIdx, LLT WideTy) {
 
     if (TypeIdx == 2) {
       Observer.changingInstr(MI);
-      // TODO: Probably should be zext
-      widenScalarSrc(MI, WideTy, 3, TargetOpcode::G_SEXT);
+      widenScalarSrc(MI, WideTy, 3, TargetOpcode::G_ZEXT);
       Observer.changedInstr(MI);
       return Legalized;
     }
diff --git a/llvm/lib/CodeGen/GlobalISel/Utils.cpp b/llvm/lib/CodeGen/GlobalISel/Utils.cpp
index 055fdc6..ca82857 100644
--- a/llvm/lib/CodeGen/GlobalISel/Utils.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/Utils.cpp
@@ -818,8 +818,7 @@ bool llvm::isKnownNeverNaN(Register Val, const MachineRegisterInfo &MRI,
   if (!DefMI)
     return false;
 
-  const TargetMachine& TM = DefMI->getMF()->getTarget();
-  if (DefMI->getFlag(MachineInstr::FmNoNans) || TM.Options.NoNaNsFPMath)
+  if (DefMI->getFlag(MachineInstr::FmNoNans))
     return true;
 
   // If the value is a constant, we can obviously see if it is a NaN or not.