Index: include/llvm/CodeGen/TargetLowering.h
===================================================================
--- include/llvm/CodeGen/TargetLowering.h
+++ include/llvm/CodeGen/TargetLowering.h
@@ -509,6 +509,16 @@
     return hasAndNotCompare(X);
   }
 
+  /// There are two ways to clear extreme bits (either low or high):
+  /// Mask:    x &  (-1 << y)  (the instcombine canonical form)
+  /// Shifts:  x >> y << y
+  /// Different targets may have different preferences.
+  /// Returns true if the shift variant is preferred.
+  virtual bool preferShiftsToClearExtremeBits(SDValue X) const {
+    // By default, let's assume that everyone prefers masking.
+    return false;
+  }
+
   /// Return true if the target wants to use the optimization that
   /// turns ext(promotableInst1(...(promotableInstN(load)))) into
   /// promotedInst1(...(promotedInstN(ext(load)))).
Index: lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -409,6 +409,7 @@
     SDValue foldLogicOfSetCCs(bool IsAnd, SDValue N0, SDValue N1,
                               const SDLoc &DL);
     SDValue unfoldMaskedMerge(SDNode *N);
+    SDValue unfoldExtremeBitClearingToShifts(SDNode *N);
     SDValue SimplifySetCC(EVT VT, SDValue N0, SDValue N1, ISD::CondCode Cond,
                           const SDLoc &DL, bool foldBooleans);
     SDValue rebuildSetCC(SDValue N);
@@ -4171,6 +4172,63 @@
   return false;
 }
 
+// Unfold
+//    x &  (-1 'logical shift' y)
+// To
+//    (x 'opposite logical shift' y) 'logical shift' y
+// if it is better for performance.
+SDValue DAGCombiner::unfoldExtremeBitClearingToShifts(SDNode *N) {
+  assert(N->getOpcode() == ISD::AND);
+
+  SDValue N0 = N->getOperand(0);
+  SDValue N1 = N->getOperand(1);
+
+  // Do we actually prefer shifts over mask?
+  if (!TLI.preferShiftsToClearExtremeBits(N0))
+    return SDValue();
+
+  // Try to match  (-1 '[outer] logical shift' y)
+  unsigned OuterShift;
+  unsigned InnerShift; // The opposite direction to the OuterShift.
+  SDValue Y;           // Shift amount.
+  auto matchMask = [&OuterShift, &InnerShift, &Y](SDValue M) -> bool {
+    if (!M.hasOneUse())
+      return false;
+    switch (OuterShift = M->getOpcode()) {
+    case ISD::SHL:
+      InnerShift = ISD::SRL;
+      break;
+    case ISD::SRL:
+      InnerShift = ISD::SHL;
+      break;
+    default:
+      return false;
+    }
+    if (!isAllOnesConstant(M->getOperand(0)))
+      return false;
+    Y = M->getOperand(1);
+    return true;
+  };
+
+  SDValue X;
+  if (matchMask(N1))
+    X = N0;
+  else if (matchMask(N0))
+    X = N1;
+  else
+    return SDValue();
+
+  SDLoc DL(N);
+  EVT VT = N->getValueType(0);
+
+  //     tmp = x   'opposite logical shift' y
+  SDValue T0 = DAG.getNode(InnerShift, DL, VT, X, Y);
+  //     ret = tmp 'logical shift' y
+  SDValue T1 = DAG.getNode(OuterShift, DL, VT, T0, Y);
+
+  return T1;
+}
+
 SDValue DAGCombiner::visitAND(SDNode *N) {
   SDValue N0 = N->getOperand(0);
   SDValue N1 = N->getOperand(1);
@@ -4468,6 +4526,9 @@
       return BSwap;
   }
 
+  if (SDValue Shifts = unfoldExtremeBitClearingToShifts(N))
+    return Shifts;
+
   return SDValue();
 }
 
Index: lib/Target/X86/X86ISelLowering.h
===================================================================
--- lib/Target/X86/X86ISelLowering.h
+++ lib/Target/X86/X86ISelLowering.h
@@ -831,6 +831,8 @@
 
     bool hasAndNot(SDValue Y) const override;
 
+    bool preferShiftsToClearExtremeBits(SDValue Y) const override;
+
     bool convertSetCCLogicToBitwiseLogic(EVT VT) const override {
       return VT.isScalarInteger();
     }
Index: lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- lib/Target/X86/X86ISelLowering.cpp
+++ lib/Target/X86/X86ISelLowering.cpp
@@ -4785,6 +4785,22 @@
   return Subtarget.hasSSE2();
 }
 
+bool X86TargetLowering::preferShiftsToClearExtremeBits(SDValue Y) const {
+  EVT VT = Y.getValueType();
+
+  // For vectors, we don't have a preference, but we probably want a mask.
+  if (VT.isVector())
+    return false;
+
+  // We want BMI2's SHLX/SHRX Shifts Without Affecting Flags.
+  if (!Subtarget.hasBMI2())
+    return false;
+
+  // There are only 32-bit and 64-bit forms for SHLX/SHRX.
+  // And 64-bit form is only preferred on 64-bit targets.
+  return (VT == MVT::i32 || (VT == MVT::i64 && Subtarget.is64Bit()));
+}
+
 MVT X86TargetLowering::hasFastEqualityCompare(unsigned NumBits) const {
   MVT VT = MVT::getIntegerVT(NumBits);
   if (isTypeLegal(VT))
Index: test/CodeGen/X86/clear-highbits.ll
===================================================================
--- test/CodeGen/X86/clear-highbits.ll
+++ test/CodeGen/X86/clear-highbits.ll
@@ -33,9 +33,8 @@
 ; X86-TRANSFORM-LABEL: clear_highbits32_c0:
 ; X86-TRANSFORM:       # %bb.0:
 ; X86-TRANSFORM-NEXT:    movb {{[0-9]+}}(%esp), %al
-; X86-TRANSFORM-NEXT:    movl $-1, %ecx
+; X86-TRANSFORM-NEXT:    shlxl %eax, {{[0-9]+}}(%esp), %ecx
 ; X86-TRANSFORM-NEXT:    shrxl %eax, %ecx, %eax
-; X86-TRANSFORM-NEXT:    andl {{[0-9]+}}(%esp), %eax
 ; X86-TRANSFORM-NEXT:    retl
 ;
 ; X64-NOTRANSFORM-LABEL: clear_highbits32_c0:
@@ -48,9 +47,8 @@
 ;
 ; X64-TRANSFORM-LABEL: clear_highbits32_c0:
 ; X64-TRANSFORM:       # %bb.0:
-; X64-TRANSFORM-NEXT:    movl $-1, %eax
+; X64-TRANSFORM-NEXT:    shlxl %esi, %edi, %eax
 ; X64-TRANSFORM-NEXT:    shrxl %esi, %eax, %eax
-; X64-TRANSFORM-NEXT:    andl %edi, %eax
 ; X64-TRANSFORM-NEXT:    retq
   %mask = lshr i32 -1, %numhighbits
   %masked = and i32 %mask, %val
@@ -69,9 +67,8 @@
 ; X86-TRANSFORM-LABEL: clear_highbits32_c1_indexzext:
 ; X86-TRANSFORM:       # %bb.0:
 ; X86-TRANSFORM-NEXT:    movb {{[0-9]+}}(%esp), %al
-; X86-TRANSFORM-NEXT:    movl $-1, %ecx
+; X86-TRANSFORM-NEXT:    shlxl %eax, {{[0-9]+}}(%esp), %ecx
 ; X86-TRANSFORM-NEXT:    shrxl %eax, %ecx, %eax
-; X86-TRANSFORM-NEXT:    andl {{[0-9]+}}(%esp), %eax
 ; X86-TRANSFORM-NEXT:    retl
 ;
 ; X64-NOTRANSFORM-LABEL: clear_highbits32_c1_indexzext:
@@ -84,9 +81,8 @@
 ;
 ; X64-TRANSFORM-LABEL: clear_highbits32_c1_indexzext:
 ; X64-TRANSFORM:       # %bb.0:
-; X64-TRANSFORM-NEXT:    movl $-1, %eax
+; X64-TRANSFORM-NEXT:    shlxl %esi, %edi, %eax
 ; X64-TRANSFORM-NEXT:    shrxl %esi, %eax, %eax
-; X64-TRANSFORM-NEXT:    andl %edi, %eax
 ; X64-TRANSFORM-NEXT:    retq
   %sh_prom = zext i8 %numhighbits to i32
   %mask = lshr i32 -1, %sh_prom
@@ -106,11 +102,10 @@
 ;
 ; X86-TRANSFORM-LABEL: clear_highbits32_c2_load:
 ; X86-TRANSFORM:       # %bb.0:
-; X86-TRANSFORM-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; X86-TRANSFORM-NEXT:    movb {{[0-9]+}}(%esp), %al
-; X86-TRANSFORM-NEXT:    movl $-1, %edx
-; X86-TRANSFORM-NEXT:    shrxl %eax, %edx, %eax
-; X86-TRANSFORM-NEXT:    andl (%ecx), %eax
+; X86-TRANSFORM-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-TRANSFORM-NEXT:    movb {{[0-9]+}}(%esp), %cl
+; X86-TRANSFORM-NEXT:    shlxl %ecx, (%eax), %eax
+; X86-TRANSFORM-NEXT:    shrxl %ecx, %eax, %eax
 ; X86-TRANSFORM-NEXT:    retl
 ;
 ; X64-NOTRANSFORM-LABEL: clear_highbits32_c2_load:
@@ -123,9 +118,8 @@
 ;
 ; X64-TRANSFORM-LABEL: clear_highbits32_c2_load:
 ; X64-TRANSFORM:       # %bb.0:
-; X64-TRANSFORM-NEXT:    movl $-1, %eax
+; X64-TRANSFORM-NEXT:    shlxl %esi, (%rdi), %eax
 ; X64-TRANSFORM-NEXT:    shrxl %esi, %eax, %eax
-; X64-TRANSFORM-NEXT:    andl (%rdi), %eax
 ; X64-TRANSFORM-NEXT:    retq
   %val = load i32, i32* %w
   %mask = lshr i32 -1, %numhighbits
@@ -145,11 +139,10 @@
 ;
 ; X86-TRANSFORM-LABEL: clear_highbits32_c3_load_indexzext:
 ; X86-TRANSFORM:       # %bb.0:
-; X86-TRANSFORM-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; X86-TRANSFORM-NEXT:    movb {{[0-9]+}}(%esp), %al
-; X86-TRANSFORM-NEXT:    movl $-1, %edx
-; X86-TRANSFORM-NEXT:    shrxl %eax, %edx, %eax
-; X86-TRANSFORM-NEXT:    andl (%ecx), %eax
+; X86-TRANSFORM-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-TRANSFORM-NEXT:    movb {{[0-9]+}}(%esp), %cl
+; X86-TRANSFORM-NEXT:    shlxl %ecx, (%eax), %eax
+; X86-TRANSFORM-NEXT:    shrxl %ecx, %eax, %eax
 ; X86-TRANSFORM-NEXT:    retl
 ;
 ; X64-NOTRANSFORM-LABEL: clear_highbits32_c3_load_indexzext:
@@ -162,9 +155,8 @@
 ;
 ; X64-TRANSFORM-LABEL: clear_highbits32_c3_load_indexzext:
 ; X64-TRANSFORM:       # %bb.0:
-; X64-TRANSFORM-NEXT:    movl $-1, %eax
+; X64-TRANSFORM-NEXT:    shlxl %esi, (%rdi), %eax
 ; X64-TRANSFORM-NEXT:    shrxl %esi, %eax, %eax
-; X64-TRANSFORM-NEXT:    andl (%rdi), %eax
 ; X64-TRANSFORM-NEXT:    retq
   %val = load i32, i32* %w
   %sh_prom = zext i8 %numhighbits to i32
@@ -185,9 +177,8 @@
 ; X86-TRANSFORM-LABEL: clear_highbits32_c4_commutative:
 ; X86-TRANSFORM:       # %bb.0:
 ; X86-TRANSFORM-NEXT:    movb {{[0-9]+}}(%esp), %al
-; X86-TRANSFORM-NEXT:    movl $-1, %ecx
+; X86-TRANSFORM-NEXT:    shlxl %eax, {{[0-9]+}}(%esp), %ecx
 ; X86-TRANSFORM-NEXT:    shrxl %eax, %ecx, %eax
-; X86-TRANSFORM-NEXT:    andl {{[0-9]+}}(%esp), %eax
 ; X86-TRANSFORM-NEXT:    retl
 ;
 ; X64-NOTRANSFORM-LABEL: clear_highbits32_c4_commutative:
@@ -200,9 +191,8 @@
 ;
 ; X64-TRANSFORM-LABEL: clear_highbits32_c4_commutative:
 ; X64-TRANSFORM:       # %bb.0:
-; X64-TRANSFORM-NEXT:    movl $-1, %eax
+; X64-TRANSFORM-NEXT:    shlxl %esi, %edi, %eax
 ; X64-TRANSFORM-NEXT:    shrxl %esi, %eax, %eax
-; X64-TRANSFORM-NEXT:    andl %edi, %eax
 ; X64-TRANSFORM-NEXT:    retq
   %mask = lshr i32 -1, %numhighbits
   %masked = and i32 %val, %mask ; swapped order
@@ -255,9 +245,8 @@
 ;
 ; X64-TRANSFORM-LABEL: clear_highbits64_c0:
 ; X64-TRANSFORM:       # %bb.0:
-; X64-TRANSFORM-NEXT:    movq $-1, %rax
+; X64-TRANSFORM-NEXT:    shlxq %rsi, %rdi, %rax
 ; X64-TRANSFORM-NEXT:    shrxq %rsi, %rax, %rax
-; X64-TRANSFORM-NEXT:    andq %rdi, %rax
 ; X64-TRANSFORM-NEXT:    retq
   %mask = lshr i64 -1, %numhighbits
   %masked = and i64 %mask, %val
@@ -309,9 +298,8 @@
 ; X64-TRANSFORM-LABEL: clear_highbits64_c1_indexzext:
 ; X64-TRANSFORM:       # %bb.0:
 ; X64-TRANSFORM-NEXT:    # kill: def $esi killed $esi def $rsi
-; X64-TRANSFORM-NEXT:    movq $-1, %rax
+; X64-TRANSFORM-NEXT:    shlxq %rsi, %rdi, %rax
 ; X64-TRANSFORM-NEXT:    shrxq %rsi, %rax, %rax
-; X64-TRANSFORM-NEXT:    andq %rdi, %rax
 ; X64-TRANSFORM-NEXT:    retq
   %sh_prom = zext i8 %numhighbits to i64
   %mask = lshr i64 -1, %sh_prom
@@ -369,9 +357,8 @@
 ;
 ; X64-TRANSFORM-LABEL: clear_highbits64_c2_load:
 ; X64-TRANSFORM:       # %bb.0:
-; X64-TRANSFORM-NEXT:    movq $-1, %rax
+; X64-TRANSFORM-NEXT:    shlxq %rsi, (%rdi), %rax
 ; X64-TRANSFORM-NEXT:    shrxq %rsi, %rax, %rax
-; X64-TRANSFORM-NEXT:    andq (%rdi), %rax
 ; X64-TRANSFORM-NEXT:    retq
   %val = load i64, i64* %w
   %mask = lshr i64 -1, %numhighbits
@@ -430,9 +417,8 @@
 ; X64-TRANSFORM-LABEL: clear_highbits64_c3_load_indexzext:
 ; X64-TRANSFORM:       # %bb.0:
 ; X64-TRANSFORM-NEXT:    # kill: def $esi killed $esi def $rsi
-; X64-TRANSFORM-NEXT:    movq $-1, %rax
+; X64-TRANSFORM-NEXT:    shlxq %rsi, (%rdi), %rax
 ; X64-TRANSFORM-NEXT:    shrxq %rsi, %rax, %rax
-; X64-TRANSFORM-NEXT:    andq (%rdi), %rax
 ; X64-TRANSFORM-NEXT:    retq
   %val = load i64, i64* %w
   %sh_prom = zext i8 %numhighbits to i64
@@ -485,9 +471,8 @@
 ;
 ; X64-TRANSFORM-LABEL: clear_highbits64_c4_commutative:
 ; X64-TRANSFORM:       # %bb.0:
-; X64-TRANSFORM-NEXT:    movq $-1, %rax
+; X64-TRANSFORM-NEXT:    shlxq %rsi, %rdi, %rax
 ; X64-TRANSFORM-NEXT:    shrxq %rsi, %rax, %rax
-; X64-TRANSFORM-NEXT:    andq %rdi, %rax
 ; X64-TRANSFORM-NEXT:    retq
   %mask = lshr i64 -1, %numhighbits
   %masked = and i64 %val, %mask ; swapped order
Index: test/CodeGen/X86/clear-lowbits.ll
===================================================================
--- test/CodeGen/X86/clear-lowbits.ll
+++ test/CodeGen/X86/clear-lowbits.ll
@@ -33,9 +33,8 @@
 ; X86-TRANSFORM-LABEL: clear_lowbits32_c0:
 ; X86-TRANSFORM:       # %bb.0:
 ; X86-TRANSFORM-NEXT:    movb {{[0-9]+}}(%esp), %al
-; X86-TRANSFORM-NEXT:    movl $-1, %ecx
+; X86-TRANSFORM-NEXT:    shrxl %eax, {{[0-9]+}}(%esp), %ecx
 ; X86-TRANSFORM-NEXT:    shlxl %eax, %ecx, %eax
-; X86-TRANSFORM-NEXT:    andl {{[0-9]+}}(%esp), %eax
 ; X86-TRANSFORM-NEXT:    retl
 ;
 ; X64-NOTRANSFORM-LABEL: clear_lowbits32_c0:
@@ -48,9 +47,8 @@
 ;
 ; X64-TRANSFORM-LABEL: clear_lowbits32_c0:
 ; X64-TRANSFORM:       # %bb.0:
-; X64-TRANSFORM-NEXT:    movl $-1, %eax
+; X64-TRANSFORM-NEXT:    shrxl %esi, %edi, %eax
 ; X64-TRANSFORM-NEXT:    shlxl %esi, %eax, %eax
-; X64-TRANSFORM-NEXT:    andl %edi, %eax
 ; X64-TRANSFORM-NEXT:    retq
   %mask = shl i32 -1, %numlowbits
   %masked = and i32 %mask, %val
@@ -69,9 +67,8 @@
 ; X86-TRANSFORM-LABEL: clear_lowbits32_c1_indexzext:
 ; X86-TRANSFORM:       # %bb.0:
 ; X86-TRANSFORM-NEXT:    movb {{[0-9]+}}(%esp), %al
-; X86-TRANSFORM-NEXT:    movl $-1, %ecx
+; X86-TRANSFORM-NEXT:    shrxl %eax, {{[0-9]+}}(%esp), %ecx
 ; X86-TRANSFORM-NEXT:    shlxl %eax, %ecx, %eax
-; X86-TRANSFORM-NEXT:    andl {{[0-9]+}}(%esp), %eax
 ; X86-TRANSFORM-NEXT:    retl
 ;
 ; X64-NOTRANSFORM-LABEL: clear_lowbits32_c1_indexzext:
@@ -84,9 +81,8 @@
 ;
 ; X64-TRANSFORM-LABEL: clear_lowbits32_c1_indexzext:
 ; X64-TRANSFORM:       # %bb.0:
-; X64-TRANSFORM-NEXT:    movl $-1, %eax
+; X64-TRANSFORM-NEXT:    shrxl %esi, %edi, %eax
 ; X64-TRANSFORM-NEXT:    shlxl %esi, %eax, %eax
-; X64-TRANSFORM-NEXT:    andl %edi, %eax
 ; X64-TRANSFORM-NEXT:    retq
   %sh_prom = zext i8 %numlowbits to i32
   %mask = shl i32 -1, %sh_prom
@@ -106,11 +102,10 @@
 ;
 ; X86-TRANSFORM-LABEL: clear_lowbits32_c2_load:
 ; X86-TRANSFORM:       # %bb.0:
-; X86-TRANSFORM-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; X86-TRANSFORM-NEXT:    movb {{[0-9]+}}(%esp), %al
-; X86-TRANSFORM-NEXT:    movl $-1, %edx
-; X86-TRANSFORM-NEXT:    shlxl %eax, %edx, %eax
-; X86-TRANSFORM-NEXT:    andl (%ecx), %eax
+; X86-TRANSFORM-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-TRANSFORM-NEXT:    movb {{[0-9]+}}(%esp), %cl
+; X86-TRANSFORM-NEXT:    shrxl %ecx, (%eax), %eax
+; X86-TRANSFORM-NEXT:    shlxl %ecx, %eax, %eax
 ; X86-TRANSFORM-NEXT:    retl
 ;
 ; X64-NOTRANSFORM-LABEL: clear_lowbits32_c2_load:
@@ -123,9 +118,8 @@
 ;
 ; X64-TRANSFORM-LABEL: clear_lowbits32_c2_load:
 ; X64-TRANSFORM:       # %bb.0:
-; X64-TRANSFORM-NEXT:    movl $-1, %eax
+; X64-TRANSFORM-NEXT:    shrxl %esi, (%rdi), %eax
 ; X64-TRANSFORM-NEXT:    shlxl %esi, %eax, %eax
-; X64-TRANSFORM-NEXT:    andl (%rdi), %eax
 ; X64-TRANSFORM-NEXT:    retq
   %val = load i32, i32* %w
   %mask = shl i32 -1, %numlowbits
@@ -145,11 +139,10 @@
 ;
 ; X86-TRANSFORM-LABEL: clear_lowbits32_c3_load_indexzext:
 ; X86-TRANSFORM:       # %bb.0:
-; X86-TRANSFORM-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; X86-TRANSFORM-NEXT:    movb {{[0-9]+}}(%esp), %al
-; X86-TRANSFORM-NEXT:    movl $-1, %edx
-; X86-TRANSFORM-NEXT:    shlxl %eax, %edx, %eax
-; X86-TRANSFORM-NEXT:    andl (%ecx), %eax
+; X86-TRANSFORM-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-TRANSFORM-NEXT:    movb {{[0-9]+}}(%esp), %cl
+; X86-TRANSFORM-NEXT:    shrxl %ecx, (%eax), %eax
+; X86-TRANSFORM-NEXT:    shlxl %ecx, %eax, %eax
 ; X86-TRANSFORM-NEXT:    retl
 ;
 ; X64-NOTRANSFORM-LABEL: clear_lowbits32_c3_load_indexzext:
@@ -162,9 +155,8 @@
 ;
 ; X64-TRANSFORM-LABEL: clear_lowbits32_c3_load_indexzext:
 ; X64-TRANSFORM:       # %bb.0:
-; X64-TRANSFORM-NEXT:    movl $-1, %eax
+; X64-TRANSFORM-NEXT:    shrxl %esi, (%rdi), %eax
 ; X64-TRANSFORM-NEXT:    shlxl %esi, %eax, %eax
-; X64-TRANSFORM-NEXT:    andl (%rdi), %eax
 ; X64-TRANSFORM-NEXT:    retq
   %val = load i32, i32* %w
   %sh_prom = zext i8 %numlowbits to i32
@@ -185,9 +177,8 @@
 ; X86-TRANSFORM-LABEL: clear_lowbits32_c4_commutative:
 ; X86-TRANSFORM:       # %bb.0:
 ; X86-TRANSFORM-NEXT:    movb {{[0-9]+}}(%esp), %al
-; X86-TRANSFORM-NEXT:    movl $-1, %ecx
+; X86-TRANSFORM-NEXT:    shrxl %eax, {{[0-9]+}}(%esp), %ecx
 ; X86-TRANSFORM-NEXT:    shlxl %eax, %ecx, %eax
-; X86-TRANSFORM-NEXT:    andl {{[0-9]+}}(%esp), %eax
 ; X86-TRANSFORM-NEXT:    retl
 ;
 ; X64-NOTRANSFORM-LABEL: clear_lowbits32_c4_commutative:
@@ -200,9 +191,8 @@
 ;
 ; X64-TRANSFORM-LABEL: clear_lowbits32_c4_commutative:
 ; X64-TRANSFORM:       # %bb.0:
-; X64-TRANSFORM-NEXT:    movl $-1, %eax
+; X64-TRANSFORM-NEXT:    shrxl %esi, %edi, %eax
 ; X64-TRANSFORM-NEXT:    shlxl %esi, %eax, %eax
-; X64-TRANSFORM-NEXT:    andl %edi, %eax
 ; X64-TRANSFORM-NEXT:    retq
   %mask = shl i32 -1, %numlowbits
   %masked = and i32 %val, %mask ; swapped order
@@ -255,9 +245,8 @@
 ;
 ; X64-TRANSFORM-LABEL: clear_lowbits64_c0:
 ; X64-TRANSFORM:       # %bb.0:
-; X64-TRANSFORM-NEXT:    movq $-1, %rax
+; X64-TRANSFORM-NEXT:    shrxq %rsi, %rdi, %rax
 ; X64-TRANSFORM-NEXT:    shlxq %rsi, %rax, %rax
-; X64-TRANSFORM-NEXT:    andq %rdi, %rax
 ; X64-TRANSFORM-NEXT:    retq
   %mask = shl i64 -1, %numlowbits
   %masked = and i64 %mask, %val
@@ -309,9 +298,8 @@
 ; X64-TRANSFORM-LABEL: clear_lowbits64_c1_indexzext:
 ; X64-TRANSFORM:       # %bb.0:
 ; X64-TRANSFORM-NEXT:    # kill: def $esi killed $esi def $rsi
-; X64-TRANSFORM-NEXT:    movq $-1, %rax
+; X64-TRANSFORM-NEXT:    shrxq %rsi, %rdi, %rax
 ; X64-TRANSFORM-NEXT:    shlxq %rsi, %rax, %rax
-; X64-TRANSFORM-NEXT:    andq %rdi, %rax
 ; X64-TRANSFORM-NEXT:    retq
   %sh_prom = zext i8 %numlowbits to i64
   %mask = shl i64 -1, %sh_prom
@@ -369,9 +357,8 @@
 ;
 ; X64-TRANSFORM-LABEL: clear_lowbits64_c2_load:
 ; X64-TRANSFORM:       # %bb.0:
-; X64-TRANSFORM-NEXT:    movq $-1, %rax
+; X64-TRANSFORM-NEXT:    shrxq %rsi, (%rdi), %rax
 ; X64-TRANSFORM-NEXT:    shlxq %rsi, %rax, %rax
-; X64-TRANSFORM-NEXT:    andq (%rdi), %rax
 ; X64-TRANSFORM-NEXT:    retq
   %val = load i64, i64* %w
   %mask = shl i64 -1, %numlowbits
@@ -430,9 +417,8 @@
 ; X64-TRANSFORM-LABEL: clear_lowbits64_c3_load_indexzext:
 ; X64-TRANSFORM:       # %bb.0:
 ; X64-TRANSFORM-NEXT:    # kill: def $esi killed $esi def $rsi
-; X64-TRANSFORM-NEXT:    movq $-1, %rax
+; X64-TRANSFORM-NEXT:    shrxq %rsi, (%rdi), %rax
 ; X64-TRANSFORM-NEXT:    shlxq %rsi, %rax, %rax
-; X64-TRANSFORM-NEXT:    andq (%rdi), %rax
 ; X64-TRANSFORM-NEXT:    retq
   %val = load i64, i64* %w
   %sh_prom = zext i8 %numlowbits to i64
@@ -485,9 +471,8 @@
 ;
 ; X64-TRANSFORM-LABEL: clear_lowbits64_c4_commutative:
 ; X64-TRANSFORM:       # %bb.0:
-; X64-TRANSFORM-NEXT:    movq $-1, %rax
+; X64-TRANSFORM-NEXT:    shrxq %rsi, %rdi, %rax
 ; X64-TRANSFORM-NEXT:    shlxq %rsi, %rax, %rax
-; X64-TRANSFORM-NEXT:    andq %rdi, %rax
 ; X64-TRANSFORM-NEXT:    retq
   %mask = shl i64 -1, %numlowbits
   %masked = and i64 %val, %mask ; swapped order
@@ -513,9 +498,8 @@
 ; X86-TRANSFORM:       # %bb.0:
 ; X86-TRANSFORM-NEXT:    movl $32, %eax
 ; X86-TRANSFORM-NEXT:    subl {{[0-9]+}}(%esp), %eax
-; X86-TRANSFORM-NEXT:    movl $-1, %ecx
+; X86-TRANSFORM-NEXT:    shrxl %eax, {{[0-9]+}}(%esp), %ecx
 ; X86-TRANSFORM-NEXT:    shlxl %eax, %ecx, %eax
-; X86-TRANSFORM-NEXT:    andl {{[0-9]+}}(%esp), %eax
 ; X86-TRANSFORM-NEXT:    retl
 ;
 ; X64-NOTRANSFORM-LABEL: clear_lowbits32_ic0:
@@ -532,9 +516,8 @@
 ; X64-TRANSFORM:       # %bb.0:
 ; X64-TRANSFORM-NEXT:    movl $32, %eax
 ; X64-TRANSFORM-NEXT:    subl %esi, %eax
-; X64-TRANSFORM-NEXT:    movl $-1, %ecx
+; X64-TRANSFORM-NEXT:    shrxl %eax, %edi, %ecx
 ; X64-TRANSFORM-NEXT:    shlxl %eax, %ecx, %eax
-; X64-TRANSFORM-NEXT:    andl %edi, %eax
 ; X64-TRANSFORM-NEXT:    retq
   %numhighbits = sub i32 32, %numlowbits
   %mask = shl i32 -1, %numhighbits
@@ -556,9 +539,8 @@
 ; X86-TRANSFORM:       # %bb.0:
 ; X86-TRANSFORM-NEXT:    movb $32, %al
 ; X86-TRANSFORM-NEXT:    subb {{[0-9]+}}(%esp), %al
-; X86-TRANSFORM-NEXT:    movl $-1, %ecx
+; X86-TRANSFORM-NEXT:    shrxl %eax, {{[0-9]+}}(%esp), %ecx
 ; X86-TRANSFORM-NEXT:    shlxl %eax, %ecx, %eax
-; X86-TRANSFORM-NEXT:    andl {{[0-9]+}}(%esp), %eax
 ; X86-TRANSFORM-NEXT:    retl
 ;
 ; X64-NOTRANSFORM-LABEL: clear_lowbits32_ic1_indexzext:
@@ -574,9 +556,8 @@
 ; X64-TRANSFORM:       # %bb.0:
 ; X64-TRANSFORM-NEXT:    movb $32, %al
 ; X64-TRANSFORM-NEXT:    subb %sil, %al
-; X64-TRANSFORM-NEXT:    movl $-1, %ecx
+; X64-TRANSFORM-NEXT:    shrxl %eax, %edi, %ecx
 ; X64-TRANSFORM-NEXT:    shlxl %eax, %ecx, %eax
-; X64-TRANSFORM-NEXT:    andl %edi, %eax
 ; X64-TRANSFORM-NEXT:    retq
   %numhighbits = sub i8 32, %numlowbits
   %sh_prom = zext i8 %numhighbits to i32
@@ -599,12 +580,11 @@
 ;
 ; X86-TRANSFORM-LABEL: clear_lowbits32_ic2_load:
 ; X86-TRANSFORM:       # %bb.0:
-; X86-TRANSFORM-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; X86-TRANSFORM-NEXT:    movl $32, %eax
-; X86-TRANSFORM-NEXT:    subl {{[0-9]+}}(%esp), %eax
-; X86-TRANSFORM-NEXT:    movl $-1, %edx
-; X86-TRANSFORM-NEXT:    shlxl %eax, %edx, %eax
-; X86-TRANSFORM-NEXT:    andl (%ecx), %eax
+; X86-TRANSFORM-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-TRANSFORM-NEXT:    movl $32, %ecx
+; X86-TRANSFORM-NEXT:    subl {{[0-9]+}}(%esp), %ecx
+; X86-TRANSFORM-NEXT:    shrxl %ecx, (%eax), %eax
+; X86-TRANSFORM-NEXT:    shlxl %ecx, %eax, %eax
 ; X86-TRANSFORM-NEXT:    retl
 ;
 ; X64-NOTRANSFORM-LABEL: clear_lowbits32_ic2_load:
@@ -621,9 +601,8 @@
 ; X64-TRANSFORM:       # %bb.0:
 ; X64-TRANSFORM-NEXT:    movl $32, %eax
 ; X64-TRANSFORM-NEXT:    subl %esi, %eax
-; X64-TRANSFORM-NEXT:    movl $-1, %ecx
+; X64-TRANSFORM-NEXT:    shrxl %eax, (%rdi), %ecx
 ; X64-TRANSFORM-NEXT:    shlxl %eax, %ecx, %eax
-; X64-TRANSFORM-NEXT:    andl (%rdi), %eax
 ; X64-TRANSFORM-NEXT:    retq
   %val = load i32, i32* %w
   %numhighbits = sub i32 32, %numlowbits
@@ -645,12 +624,11 @@
 ;
 ; X86-TRANSFORM-LABEL: clear_lowbits32_ic3_load_indexzext:
 ; X86-TRANSFORM:       # %bb.0:
-; X86-TRANSFORM-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; X86-TRANSFORM-NEXT:    movb $32, %al
-; X86-TRANSFORM-NEXT:    subb {{[0-9]+}}(%esp), %al
-; X86-TRANSFORM-NEXT:    movl $-1, %edx
-; X86-TRANSFORM-NEXT:    shlxl %eax, %edx, %eax
-; X86-TRANSFORM-NEXT:    andl (%ecx), %eax
+; X86-TRANSFORM-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-TRANSFORM-NEXT:    movb $32, %cl
+; X86-TRANSFORM-NEXT:    subb {{[0-9]+}}(%esp), %cl
+; X86-TRANSFORM-NEXT:    shrxl %ecx, (%eax), %eax
+; X86-TRANSFORM-NEXT:    shlxl %ecx, %eax, %eax
 ; X86-TRANSFORM-NEXT:    retl
 ;
 ; X64-NOTRANSFORM-LABEL: clear_lowbits32_ic3_load_indexzext:
@@ -666,9 +644,8 @@
 ; X64-TRANSFORM:       # %bb.0:
 ; X64-TRANSFORM-NEXT:    movb $32, %al
 ; X64-TRANSFORM-NEXT:    subb %sil, %al
-; X64-TRANSFORM-NEXT:    movl $-1, %ecx
+; X64-TRANSFORM-NEXT:    shrxl %eax, (%rdi), %ecx
 ; X64-TRANSFORM-NEXT:    shlxl %eax, %ecx, %eax
-; X64-TRANSFORM-NEXT:    andl (%rdi), %eax
 ; X64-TRANSFORM-NEXT:    retq
   %val = load i32, i32* %w
   %numhighbits = sub i8 32, %numlowbits
@@ -693,9 +670,8 @@
 ; X86-TRANSFORM:       # %bb.0:
 ; X86-TRANSFORM-NEXT:    movl $32, %eax
 ; X86-TRANSFORM-NEXT:    subl {{[0-9]+}}(%esp), %eax
-; X86-TRANSFORM-NEXT:    movl $-1, %ecx
+; X86-TRANSFORM-NEXT:    shrxl %eax, {{[0-9]+}}(%esp), %ecx
 ; X86-TRANSFORM-NEXT:    shlxl %eax, %ecx, %eax
-; X86-TRANSFORM-NEXT:    andl {{[0-9]+}}(%esp), %eax
 ; X86-TRANSFORM-NEXT:    retl
 ;
 ; X64-NOTRANSFORM-LABEL: clear_lowbits32_ic4_commutative:
@@ -712,9 +688,8 @@
 ; X64-TRANSFORM:       # %bb.0:
 ; X64-TRANSFORM-NEXT:    movl $32, %eax
 ; X64-TRANSFORM-NEXT:    subl %esi, %eax
-; X64-TRANSFORM-NEXT:    movl $-1, %ecx
+; X64-TRANSFORM-NEXT:    shrxl %eax, %edi, %ecx
 ; X64-TRANSFORM-NEXT:    shlxl %eax, %ecx, %eax
-; X64-TRANSFORM-NEXT:    andl %edi, %eax
 ; X64-TRANSFORM-NEXT:    retq
   %numhighbits = sub i32 32, %numlowbits
   %mask = shl i32 -1, %numhighbits
@@ -774,9 +749,8 @@
 ; X64-TRANSFORM:       # %bb.0:
 ; X64-TRANSFORM-NEXT:    movl $64, %eax
 ; X64-TRANSFORM-NEXT:    subl %esi, %eax
-; X64-TRANSFORM-NEXT:    movq $-1, %rcx
+; X64-TRANSFORM-NEXT:    shrxq %rax, %rdi, %rcx
 ; X64-TRANSFORM-NEXT:    shlxq %rax, %rcx, %rax
-; X64-TRANSFORM-NEXT:    andq %rdi, %rax
 ; X64-TRANSFORM-NEXT:    retq
   %numhighbits = sub i64 64, %numlowbits
   %mask = shl i64 -1, %numhighbits
@@ -833,9 +807,8 @@
 ; X64-TRANSFORM:       # %bb.0:
 ; X64-TRANSFORM-NEXT:    movb $64, %al
 ; X64-TRANSFORM-NEXT:    subb %sil, %al
-; X64-TRANSFORM-NEXT:    movq $-1, %rcx
+; X64-TRANSFORM-NEXT:    shrxq %rax, %rdi, %rcx
 ; X64-TRANSFORM-NEXT:    shlxq %rax, %rcx, %rax
-; X64-TRANSFORM-NEXT:    andq %rdi, %rax
 ; X64-TRANSFORM-NEXT:    retq
   %numhighbits = sub i8 64, %numlowbits
   %sh_prom = zext i8 %numhighbits to i64
@@ -900,9 +873,8 @@
 ; X64-TRANSFORM:       # %bb.0:
 ; X64-TRANSFORM-NEXT:    movl $64, %eax
 ; X64-TRANSFORM-NEXT:    subl %esi, %eax
-; X64-TRANSFORM-NEXT:    movq $-1, %rcx
+; X64-TRANSFORM-NEXT:    shrxq %rax, (%rdi), %rcx
 ; X64-TRANSFORM-NEXT:    shlxq %rax, %rcx, %rax
-; X64-TRANSFORM-NEXT:    andq (%rdi), %rax
 ; X64-TRANSFORM-NEXT:    retq
   %val = load i64, i64* %w
   %numhighbits = sub i64 64, %numlowbits
@@ -966,9 +938,8 @@
 ; X64-TRANSFORM:       # %bb.0:
 ; X64-TRANSFORM-NEXT:    movb $64, %al
 ; X64-TRANSFORM-NEXT:    subb %sil, %al
-; X64-TRANSFORM-NEXT:    movq $-1, %rcx
+; X64-TRANSFORM-NEXT:    shrxq %rax, (%rdi), %rcx
 ; X64-TRANSFORM-NEXT:    shlxq %rax, %rcx, %rax
-; X64-TRANSFORM-NEXT:    andq (%rdi), %rax
 ; X64-TRANSFORM-NEXT:    retq
   %val = load i64, i64* %w
   %numhighbits = sub i8 64, %numlowbits
@@ -1028,9 +999,8 @@
 ; X64-TRANSFORM:       # %bb.0:
 ; X64-TRANSFORM-NEXT:    movl $64, %eax
 ; X64-TRANSFORM-NEXT:    subl %esi, %eax
-; X64-TRANSFORM-NEXT:    movq $-1, %rcx
+; X64-TRANSFORM-NEXT:    shrxq %rax, %rdi, %rcx
 ; X64-TRANSFORM-NEXT:    shlxq %rax, %rcx, %rax
-; X64-TRANSFORM-NEXT:    andq %rdi, %rax
 ; X64-TRANSFORM-NEXT:    retq
   %numhighbits = sub i64 64, %numlowbits
   %mask = shl i64 -1, %numhighbits