[APInt] Add APInt::setBits() method to set all bits in range

The current pattern for setting bits in range is typically:

Mask |= APInt::getBitsSet(MaskSizeInBits, LoPos, HiPos);

Which can be particularly slow for large APInts (MaskSizeInBits > 64) as they require the allocation memory for the temporary variable.

This is one of the key compile time issues identified in PR32037.

This patch adds the APInt::setBits() helper method which avoids the temporary memory allocation completely, this first implementation uses setBit() internally instead but already significantly reduces the regression in PR32037 (~10% drop). Additional optimization may be possible.

I investigated whether there is need for APInt::clearBits() and APInt::flipBits() equivalents but haven't seen these patterns to be particularly common, but reusing the code would be trivial.

Differential Revision: https://reviews.llvm.org/D30265

llvm-svn: 296102

2 files changed, 6 insertions, 9 deletions

diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 720f93a4fbe..6b404a498e3 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -5236,8 +5236,7 @@ static bool getTargetConstantBitsFromNode(SDValue Op, unsigned EltSizeInBits,
       return false;
     unsigned CstSizeInBits = Cst->getType()->getPrimitiveSizeInBits();
     if (isa<UndefValue>(Cst)) {
-      unsigned HiBits = BitOffset + CstSizeInBits;
-      Undefs |= APInt::getBitsSet(SizeInBits, BitOffset, HiBits);
+      Undefs.setBits(BitOffset, BitOffset + CstSizeInBits);
       return true;
     }
     if (auto *CInt = dyn_cast<ConstantInt>(Cst)) {
@@ -5258,8 +5257,7 @@ static bool getTargetConstantBitsFromNode(SDValue Op, unsigned EltSizeInBits,
       const SDValue &Src = Op.getOperand(i);
       unsigned BitOffset = i * SrcEltSizeInBits;
       if (Src.isUndef()) {
-        unsigned HiBits = BitOffset + SrcEltSizeInBits;
-        UndefBits |= APInt::getBitsSet(SizeInBits, BitOffset, HiBits);
+        UndefBits.setBits(BitOffset, BitOffset + SrcEltSizeInBits);
         continue;
       }
       auto *Cst = cast<ConstantSDNode>(Src);
@@ -26353,11 +26351,11 @@ void X86TargetLowering::computeKnownBitsForTargetNode(const SDValue Op,
       break;
     LLVM_FALLTHROUGH;
   case X86ISD::SETCC:
-    KnownZero |= APInt::getHighBitsSet(BitWidth, BitWidth - 1);
+    KnownZero.setBits(1, BitWidth);
     break;
   case X86ISD::MOVMSK: {
     unsigned NumLoBits = Op.getOperand(0).getValueType().getVectorNumElements();
-    KnownZero = APInt::getHighBitsSet(BitWidth, BitWidth - NumLoBits);
+    KnownZero.setBits(NumLoBits, BitWidth);
     break;
   }
   case X86ISD::VZEXT: {
@@ -26374,7 +26372,7 @@ void X86TargetLowering::computeKnownBitsForTargetNode(const SDValue Op,
     DAG.computeKnownBits(N0, KnownZero, KnownOne, DemandedSrcElts, Depth + 1);
     KnownOne = KnownOne.zext(BitWidth);
     KnownZero = KnownZero.zext(BitWidth);
-    KnownZero |= APInt::getHighBitsSet(BitWidth, BitWidth - InBitWidth);
+    KnownZero.setBits(InBitWidth, BitWidth);
     break;
   }
   }
diff --git a/llvm/lib/Target/X86/X86ShuffleDecodeConstantPool.cpp b/llvm/lib/Target/X86/X86ShuffleDecodeConstantPool.cpp
index 4d278d4b05a..41ad0971461 100644
--- a/llvm/lib/Target/X86/X86ShuffleDecodeConstantPool.cpp
+++ b/llvm/lib/Target/X86/X86ShuffleDecodeConstantPool.cpp
@@ -60,8 +60,7 @@ static bool extractConstantMask(const Constant *C, unsigned MaskEltSizeInBits,
     unsigned BitOffset = i * CstEltSizeInBits;
 
     if (isa<UndefValue>(COp)) {
-      unsigned HiBits = BitOffset + CstEltSizeInBits;
-      UndefBits |= APInt::getBitsSet(CstSizeInBits, BitOffset, HiBits);
+      UndefBits.setBits(BitOffset, BitOffset + CstEltSizeInBits);
       continue;
     }