[APInt] Add APInt::insertBits() method to insert an APInt into a larg…

…er APInt

We currently have to insert bits via a temporary variable of the same size as the target with various shift/mask stages, resulting in further temporary variables, all of which require the allocation of memory for large APInts (MaskSizeInBits > 64).

This is another of the compile time issues identified in PR32037 (see also D30265).

This patch adds the APInt::insertBits() helper method which avoids the temporary memory allocation and masks/inserts the raw bits directly into the target.

Differential Revision: https://reviews.llvm.org/D30780

llvm-svn: 297458

llvm/include/llvm/ADT/APInt.h

@@ -1243,6 +1243,9 @@ class LLVM_NODISCARD APInt {
   /// as "bitPosition".
   void flipBit(unsigned bitPosition);
 
+  /// Insert the bits from a smaller APInt starting at bitPosition.
+  void insertBits(const APInt &SubBits, unsigned bitPosition);
+
   /// Return an APInt with the extracted bits [bitPosition,bitPosition+numBits).
   APInt extractBits(unsigned numBits, unsigned bitPosition) const;
 

llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp

@@ -7523,11 +7523,11 @@ bool BuildVectorSDNode::isConstantSplat(APInt &SplatValue,
     if (OpVal.isUndef())
       SplatUndef.setBits(BitPos, BitPos + EltBitSize);
     else if (ConstantSDNode *CN = dyn_cast<ConstantSDNode>(OpVal))
-      SplatValue |= CN->getAPIntValue().zextOrTrunc(EltBitSize).
-                    zextOrTrunc(sz) << BitPos;
+      SplatValue.insertBits(CN->getAPIntValue().zextOrTrunc(EltBitSize),
+                            BitPos);
     else if (ConstantFPSDNode *CN = dyn_cast<ConstantFPSDNode>(OpVal))
-      SplatValue |= CN->getValueAPF().bitcastToAPInt().zextOrTrunc(sz) <<BitPos;
-     else
+      SplatValue.insertBits(CN->getValueAPF().bitcastToAPInt(), BitPos);
+    else
       return false;
   }
 

llvm/lib/Support/APInt.cpp

@@ -588,6 +588,65 @@ void APInt::flipBit(unsigned bitPosition) {
   else setBit(bitPosition);
 }
 
+void APInt::insertBits(const APInt &subBits, unsigned bitPosition) {
+  unsigned subBitWidth = subBits.getBitWidth();
+  assert(0 < subBitWidth && (subBitWidth + bitPosition) <= BitWidth &&
+         "Illegal bit insertion");
+
+  // Insertion is a direct copy.
+  if (subBitWidth == BitWidth) {
+    *this = subBits;
+    return;
+  }
+
+  // Single word result can be done as a direct bitmask.
+  if (isSingleWord()) {
+    uint64_t mask = UINT64_MAX >> (APINT_BITS_PER_WORD - subBitWidth);
+    VAL &= ~(mask << bitPosition);
+    VAL |= (subBits.VAL << bitPosition);
+    return;
+  }
+
+  unsigned loBit = whichBit(bitPosition);
+  unsigned loWord = whichWord(bitPosition);
+  unsigned hi1Word = whichWord(bitPosition + subBitWidth - 1);
+
+  // Insertion within a single word can be done as a direct bitmask.
+  if (loWord == hi1Word) {
+    uint64_t mask = UINT64_MAX >> (APINT_BITS_PER_WORD - subBitWidth);
+    pVal[loWord] &= ~(mask << loBit);
+    pVal[loWord] |= (subBits.VAL << loBit);
+    return;
+  }
+
+  // Insert on word boundaries.
+  if (loBit == 0) {
+    // Direct copy whole words.
+    unsigned numWholeSubWords = subBitWidth / APINT_BITS_PER_WORD;
+    memcpy(pVal + loWord, subBits.getRawData(),
+           numWholeSubWords * APINT_WORD_SIZE);
+
+    // Mask+insert remaining bits.
+    unsigned remainingBits = subBitWidth % APINT_BITS_PER_WORD;
+    if (remainingBits != 0) {
+      uint64_t mask = UINT64_MAX >> (APINT_BITS_PER_WORD - remainingBits);
+      pVal[hi1Word] &= ~mask;
+      pVal[hi1Word] |= subBits.getWord(subBitWidth - 1);
+    }
+    return;
+  }
+
+  // General case - set/clear individual bits in dst based on src.
+  // TODO - there is scope for optimization here, but at the moment this code
+  // path is barely used so prefer readability over performance.
+  for (unsigned i = 0; i != subBitWidth; ++i) {
+    if (subBits[i])
+      setBit(bitPosition + i);
+    else
+      clearBit(bitPosition + i);
+  }
+}
+
 APInt APInt::extractBits(unsigned numBits, unsigned bitPosition) const {
   assert(numBits > 0 && "Can't extract zero bits");
   assert(bitPosition < BitWidth && (numBits + bitPosition) <= BitWidth &&

llvm/lib/Target/X86/X86ISelLowering.cpp

@@ -5318,12 +5318,11 @@ static bool getTargetConstantBitsFromNode(SDValue Op, unsigned EltSizeInBits,
       return true;
     }
     if (auto *CInt = dyn_cast<ConstantInt>(Cst)) {
-      Mask |= CInt->getValue().zextOrTrunc(SizeInBits).shl(BitOffset);
+      Mask.insertBits(CInt->getValue(), BitOffset);
       return true;
     }
     if (auto *CFP = dyn_cast<ConstantFP>(Cst)) {
-      APInt CstBits = CFP->getValueAPF().bitcastToAPInt();
-      Mask |= CstBits.zextOrTrunc(SizeInBits).shl(BitOffset);
+      Mask.insertBits(CFP->getValueAPF().bitcastToAPInt(), BitOffset);
       return true;
     }
     return false;
@@ -5340,7 +5339,7 @@ static bool getTargetConstantBitsFromNode(SDValue Op, unsigned EltSizeInBits,
       }
       auto *Cst = cast<ConstantSDNode>(Src);
       APInt Bits = Cst->getAPIntValue().zextOrTrunc(SrcEltSizeInBits);
-      MaskBits |= Bits.zext(SizeInBits).shl(BitOffset);
+      MaskBits.insertBits(Bits, BitOffset);
     }
     return SplitBitData();
   }

llvm/lib/Target/X86/X86ShuffleDecodeConstantPool.cpp

@@ -91,8 +91,7 @@ static bool extractConstantMask(const Constant *C, unsigned MaskEltSizeInBits,
       continue;
     }
 
-    auto *Elt = cast<ConstantInt>(COp);
-    MaskBits |= Elt->getValue().zextOrTrunc(CstSizeInBits).shl(BitOffset);
+    MaskBits.insertBits(cast<ConstantInt>(COp)->getValue(), BitOffset);
   }
 
   // Now extract the undef/constant bit data into the raw shuffle masks.

llvm/unittests/ADT/APIntTest.cpp

@@ -1647,6 +1647,59 @@ TEST(APIntTest, reverseBits) {
   }
 }
 
+TEST(APIntTest, insertBits) {
+  APInt iSrc(31, 0x00123456);
+
+  // Direct copy.
+  APInt i31(31, 0x76543210ull);
+  i31.insertBits(iSrc, 0);
+  EXPECT_EQ(static_cast<int64_t>(0x00123456ull), i31.getSExtValue());
+
+  // Single word src/dst insertion.
+  APInt i63(63, 0x01234567FFFFFFFFull);
+  i63.insertBits(iSrc, 4);
+  EXPECT_EQ(static_cast<int64_t>(0x012345600123456Full), i63.getSExtValue());
+
+  // Insert single word src into one word of dst.
+  APInt i120(120, UINT64_MAX, true);
+  i120.insertBits(iSrc, 8);
+  EXPECT_EQ(static_cast<int64_t>(0xFFFFFF80123456FFull), i120.getSExtValue());
+
+  // Insert single word src into two words of dst.
+  APInt i127(127, UINT64_MAX, true);
+  i127.insertBits(iSrc, 48);
+  EXPECT_EQ(i127.extractBits(64, 0).getZExtValue(), 0x3456FFFFFFFFFFFF);
+  EXPECT_EQ(i127.extractBits(63, 64).getZExtValue(), 0x7FFFFFFFFFFF8012);
+
+  // Insert on word boundaries.
+  APInt i128(128, 0);
+  i128.insertBits(APInt(64, UINT64_MAX, true), 0);
+  i128.insertBits(APInt(64, UINT64_MAX, true), 64);
+  EXPECT_EQ(-1, i128.getSExtValue());
+
+  APInt i256(256, UINT64_MAX, true);
+  i256.insertBits(APInt(65, 0), 0);
+  i256.insertBits(APInt(69, 0), 64);
+  i256.insertBits(APInt(128, 0), 128);
+  EXPECT_EQ(0u, i256.getSExtValue());
+
+  APInt i257(257, 0);
+  i257.insertBits(APInt(96, UINT64_MAX, true), 64);
+  EXPECT_EQ(i257.extractBits(64, 0).getZExtValue(), 0x0000000000000000);
+  EXPECT_EQ(i257.extractBits(64, 64).getZExtValue(), 0xFFFFFFFFFFFFFFFF);
+  EXPECT_EQ(i257.extractBits(64, 128).getZExtValue(), 0x00000000FFFFFFFF);
+  EXPECT_EQ(i257.extractBits(65, 192).getZExtValue(), 0x0000000000000000);
+
+  // General insertion.
+  APInt i260(260, UINT64_MAX, true);
+  i260.insertBits(APInt(129, 1ull << 48), 15);
+  EXPECT_EQ(i260.extractBits(64, 0).getZExtValue(), 0x8000000000007FFF);
+  EXPECT_EQ(i260.extractBits(64, 64).getZExtValue(), 0x0000000000000000);
+  EXPECT_EQ(i260.extractBits(64, 128).getZExtValue(), 0xFFFFFFFFFFFF0000);
+  EXPECT_EQ(i260.extractBits(64, 192).getZExtValue(), 0xFFFFFFFFFFFFFFFF);
+  EXPECT_EQ(i260.extractBits(4, 256).getZExtValue(), 0x000000000000000F);
+}
+
 TEST(APIntTest, extractBits) {
   APInt i32(32, 0x1234567);
   EXPECT_EQ(0x3456, i32.extractBits(16, 4));