[llvm] [InstCombine] Convert or concat to fshl if opposite or concat exists (PR #68502)

[via llvm-commits]

================
@@ -2727,105 +2727,161 @@ Instruction *InstCombinerImpl::matchBSwapOrBitReverse(Instruction &I,
 }
 
 /// Match UB-safe variants of the funnel shift intrinsic.
-static Instruction *matchFunnelShift(Instruction &Or, InstCombinerImpl &IC) {
+static Instruction *matchFunnelShift(Instruction &Or, InstCombinerImpl &IC,
+                                     const DominatorTree &DT) {
   // TODO: Can we reduce the code duplication between this and the related
   // rotate matching code under visitSelect and visitTrunc?
   unsigned Width = Or.getType()->getScalarSizeInBits();
 
-  // First, find an or'd pair of opposite shifts:
-  // or (lshr ShVal0, ShAmt0), (shl ShVal1, ShAmt1)
-  BinaryOperator *Or0, *Or1;
-  if (!match(Or.getOperand(0), m_BinOp(Or0)) ||
-      !match(Or.getOperand(1), m_BinOp(Or1)))
+  Instruction *Or0, *Or1;
+  if (!match(Or.getOperand(0), m_Instruction(Or0)) ||
+      !match(Or.getOperand(1), m_Instruction(Or1)))
     return nullptr;
 
-  Value *ShVal0, *ShVal1, *ShAmt0, *ShAmt1;
-  if (!match(Or0, m_OneUse(m_LogicalShift(m_Value(ShVal0), m_Value(ShAmt0)))) ||
-      !match(Or1, m_OneUse(m_LogicalShift(m_Value(ShVal1), m_Value(ShAmt1)))) ||
-      Or0->getOpcode() == Or1->getOpcode())
-    return nullptr;
+  bool IsFshl = true; // Sub on LSHR.
+  SmallVector<Value *, 3> FShiftArgs;
 
-  // Canonicalize to or(shl(ShVal0, ShAmt0), lshr(ShVal1, ShAmt1)).
-  if (Or0->getOpcode() == BinaryOperator::LShr) {
-    std::swap(Or0, Or1);
-    std::swap(ShVal0, ShVal1);
-    std::swap(ShAmt0, ShAmt1);
-  }
-  assert(Or0->getOpcode() == BinaryOperator::Shl &&
-         Or1->getOpcode() == BinaryOperator::LShr &&
-         "Illegal or(shift,shift) pair");
-
-  // Match the shift amount operands for a funnel shift pattern. This always
-  // matches a subtraction on the R operand.
-  auto matchShiftAmount = [&](Value *L, Value *R, unsigned Width) -> Value * {
-    // Check for constant shift amounts that sum to the bitwidth.
-    const APInt *LI, *RI;
-    if (match(L, m_APIntAllowUndef(LI)) && match(R, m_APIntAllowUndef(RI)))
-      if (LI->ult(Width) && RI->ult(Width) && (*LI + *RI) == Width)
-        return ConstantInt::get(L->getType(), *LI);
-
-    Constant *LC, *RC;
-    if (match(L, m_Constant(LC)) && match(R, m_Constant(RC)) &&
-        match(L, m_SpecificInt_ICMP(ICmpInst::ICMP_ULT, APInt(Width, Width))) &&
-        match(R, m_SpecificInt_ICMP(ICmpInst::ICMP_ULT, APInt(Width, Width))) &&
-        match(ConstantExpr::getAdd(LC, RC), m_SpecificIntAllowUndef(Width)))
-      return ConstantExpr::mergeUndefsWith(LC, RC);
-
-    // (shl ShVal, X) | (lshr ShVal, (Width - x)) iff X < Width.
-    // We limit this to X < Width in case the backend re-expands the intrinsic,
-    // and has to reintroduce a shift modulo operation (InstCombine might remove
-    // it after this fold). This still doesn't guarantee that the final codegen
-    // will match this original pattern.
-    if (match(R, m_OneUse(m_Sub(m_SpecificInt(Width), m_Specific(L))))) {
-      KnownBits KnownL = IC.computeKnownBits(L, /*Depth*/ 0, &Or);
-      return KnownL.getMaxValue().ult(Width) ? L : nullptr;
+  // First, find an or'd pair of opposite shifts:
+  // or (lshr ShVal0, ShAmt0), (shl ShVal1, ShAmt1)
+  if (isa<BinaryOperator>(Or0) && isa<BinaryOperator>(Or1)) {
+    Value *ShVal0, *ShVal1, *ShAmt0, *ShAmt1;
+    if (!match(Or0,
+               m_OneUse(m_LogicalShift(m_Value(ShVal0), m_Value(ShAmt0)))) ||
+        !match(Or1,
+               m_OneUse(m_LogicalShift(m_Value(ShVal1), m_Value(ShAmt1)))) ||
+        Or0->getOpcode() == Or1->getOpcode())
+      return nullptr;
+
+    // Canonicalize to or(shl(ShVal0, ShAmt0), lshr(ShVal1, ShAmt1)).
+    if (Or0->getOpcode() == BinaryOperator::LShr) {
+      std::swap(Or0, Or1);
+      std::swap(ShVal0, ShVal1);
+      std::swap(ShAmt0, ShAmt1);
     }
+    assert(Or0->getOpcode() == BinaryOperator::Shl &&
+           Or1->getOpcode() == BinaryOperator::LShr &&
+           "Illegal or(shift,shift) pair");
+
+    // Match the shift amount operands for a funnel shift pattern. This always
+    // matches a subtraction on the R operand.
+    auto matchShiftAmount = [&](Value *L, Value *R, unsigned Width) -> Value * {
+      // Check for constant shift amounts that sum to the bitwidth.
+      const APInt *LI, *RI;
+      if (match(L, m_APIntAllowUndef(LI)) && match(R, m_APIntAllowUndef(RI)))
+        if (LI->ult(Width) && RI->ult(Width) && (*LI + *RI) == Width)
+          return ConstantInt::get(L->getType(), *LI);
+
+      Constant *LC, *RC;
+      if (match(L, m_Constant(LC)) && match(R, m_Constant(RC)) &&
+          match(L,
+                m_SpecificInt_ICMP(ICmpInst::ICMP_ULT, APInt(Width, Width))) &&
+          match(R,
+                m_SpecificInt_ICMP(ICmpInst::ICMP_ULT, APInt(Width, Width))) &&
+          match(ConstantExpr::getAdd(LC, RC), m_SpecificIntAllowUndef(Width)))
+        return ConstantExpr::mergeUndefsWith(LC, RC);
+
+      // (shl ShVal, X) | (lshr ShVal, (Width - x)) iff X < Width.
+      // We limit this to X < Width in case the backend re-expands the
+      // intrinsic, and has to reintroduce a shift modulo operation (InstCombine
+      // might remove it after this fold). This still doesn't guarantee that the
+      // final codegen will match this original pattern.
+      if (match(R, m_OneUse(m_Sub(m_SpecificInt(Width), m_Specific(L))))) {
+        KnownBits KnownL = IC.computeKnownBits(L, /*Depth*/ 0, &Or);
+        return KnownL.getMaxValue().ult(Width) ? L : nullptr;
+      }
----------------
goldsteinn wrote:

Actually, this check seems gratuitous: https://alive2.llvm.org/ce/z/zD6SKk you can just match and subtract `A - B` where `A & (Width - 1) == 0`.

https://github.com/llvm/llvm-project/pull/68502