diff --git a/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp b/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
--- a/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
@@ -1703,11 +1703,37 @@
                                        InstCombinerImpl &IC) {
   Value *Op0 = I.getOperand(0), *Op1 = I.getOperand(1), *X;
   const APInt *Y, *Z;
-  if (!(match(Op0, m_Mul(m_Value(X), m_APInt(Y))) &&
-        match(Op1, m_c_Mul(m_Specific(X), m_APInt(Z)))) &&
-      !(match(Op0, m_Mul(m_APInt(Y), m_Value(X))) &&
-        match(Op1, m_c_Mul(m_Specific(X), m_APInt(Z)))))
+  bool ShiftX = false, ShiftY = false, ShiftZ = false;
+  if ((match(Op0, m_Mul(m_Value(X), m_APInt(Y))) &&
+       match(Op1, m_c_Mul(m_Specific(X), m_APInt(Z)))) ||
+      (match(Op0, m_Mul(m_APInt(Y), m_Value(X))) &&
+       match(Op1, m_c_Mul(m_Specific(X), m_APInt(Z))))) {
+    // Pass
+  } else if (match(Op0, m_Shl(m_Value(X), m_APInt(Y))) &&
+             match(Op1, m_c_Mul(m_Specific(X), m_APInt(Z)))) {
+    ShiftY = true;
+  } else if (match(Op1, m_Shl(m_Value(X), m_APInt(Z))) &&
+             match(Op0, m_c_Mul(m_Specific(X), m_APInt(Y)))) {
+    ShiftZ = true;
+  } else if (match(Op0, m_Shl(m_Value(X), m_APInt(Y))) &&
+             match(Op1, m_Shl(m_Specific(X), m_APInt(Z)))) {
+    ShiftZ = true;
+    ShiftY = true;
+  } else if (match(Op0, m_Shl(m_APInt(Y), m_Value(X))) &&
+             match(Op1, m_Shl(m_APInt(Z), m_Specific(X)))) {
+    ShiftX = true;
+  } else {
     return nullptr;
+  }
+
+  APInt AdjustedY = *Y;
+  APInt AdjustedZ = *Z;
+  // Just treat the shifts as mul, we may end up returning a mul by power
+  // of 2 but that will be cleaned up later.
+  if (ShiftY)
+    AdjustedY = APInt(AdjustedY.getBitWidth(), 1) << AdjustedY;
+  if (ShiftZ)
+    AdjustedZ = APInt(AdjustedZ.getBitWidth(), 1) << AdjustedZ;
 
   bool IsSRem = I.getOpcode() == Instruction::SRem;
 
@@ -1718,13 +1744,18 @@
   bool BO0HasNUW = BO0->hasNoUnsignedWrap();
   bool BO0NoWrap = IsSRem ? BO0HasNSW : BO0HasNUW;
 
-  APInt RemYZ = IsSRem ? Y->srem(*Z) : Y->urem(*Z);
+  APInt RemYZ = IsSRem ? AdjustedY.srem(AdjustedZ) : AdjustedY.urem(AdjustedZ);
   // (rem (mul nuw/nsw X, Y), (mul X, Z))
   //      if (rem Y, Z) == 0
   //          -> 0
   if (RemYZ.isZero() && BO0NoWrap)
     return IC.replaceInstUsesWith(I, ConstantInt::getNullValue(I.getType()));
 
+  auto GetBinOpOut = [&](Value *RemSimplification) -> BinaryOperator * {
+    return ShiftX ? BinaryOperator::CreateShl(RemSimplification, X)
+                  : BinaryOperator::CreateMul(X, RemSimplification);
+  };
+
   OverflowingBinaryOperator *BO1 = cast<OverflowingBinaryOperator>(Op1);
   bool BO1HasNSW = BO1->hasNoSignedWrap();
   bool BO1HasNUW = BO1->hasNoUnsignedWrap();
@@ -1732,9 +1763,8 @@
   // (rem (mul X, Y), (mul nuw/nsw X, Z))
   //      if (rem Y, Z) == Y
   //          -> (mul nuw/nsw X, Y)
-  if (RemYZ == *Y && BO1NoWrap) {
-    BinaryOperator *BO =
-        BinaryOperator::CreateMul(X, ConstantInt::get(I.getType(), *Y));
+  if (RemYZ == AdjustedY && BO1NoWrap) {
+    BinaryOperator *BO = GetBinOpOut(ConstantInt::get(I.getType(), AdjustedY));
     // Copy any overflow flags from Op0.
     BO->setHasNoSignedWrap(IsSRem || BO0HasNSW);
     BO->setHasNoUnsignedWrap(!IsSRem || BO0HasNUW);
@@ -1744,9 +1774,9 @@
   // (rem (mul nuw/nsw X, Y), (mul {nsw} X, Z))
   //      if Y >= Z
   //          -> (mul {nuw} nsw X, (rem Y, Z))
-  if (Y->uge(*Z) && (IsSRem ? (BO0HasNSW && BO1HasNSW) : BO0HasNUW)) {
-    BinaryOperator *BO =
-        BinaryOperator::CreateMul(X, ConstantInt::get(I.getType(), RemYZ));
+  if (AdjustedY.uge(AdjustedZ) &&
+      (IsSRem ? (BO0HasNSW && BO1HasNSW) : BO0HasNUW)) {
+    BinaryOperator *BO = GetBinOpOut(ConstantInt::get(I.getType(), RemYZ));
     BO->setHasNoSignedWrap();
     BO->setHasNoUnsignedWrap(BO0HasNUW);
     return BO;
diff --git a/llvm/test/Transforms/InstCombine/rem-mul-shl.ll b/llvm/test/Transforms/InstCombine/rem-mul-shl.ll
--- a/llvm/test/Transforms/InstCombine/rem-mul-shl.ll
+++ b/llvm/test/Transforms/InstCombine/rem-mul-shl.ll
@@ -75,9 +75,7 @@
 
 define <2 x i8> @urem_XY_XZ_with_CY_lt_CZ_with_nsw_out(<2 x i8> %X) {
 ; CHECK-LABEL: @urem_XY_XZ_with_CY_lt_CZ_with_nsw_out(
-; CHECK-NEXT:    [[BO0:%.*]] = shl nsw <2 x i8> [[X:%.*]], <i8 2, i8 2>
-; CHECK-NEXT:    [[BO1:%.*]] = mul nuw <2 x i8> [[X]], <i8 12, i8 12>
-; CHECK-NEXT:    [[R:%.*]] = urem <2 x i8> [[BO0]], [[BO1]]
+; CHECK-NEXT:    [[R:%.*]] = shl nuw nsw <2 x i8> [[X:%.*]], <i8 2, i8 2>
 ; CHECK-NEXT:    ret <2 x i8> [[R]]
 ;
   %BO0 = shl nsw <2 x i8> %X, <i8 2, i8 2>
@@ -88,9 +86,7 @@
 
 define i8 @urem_XY_XZ_with_CY_lt_CZ_no_nsw_out(i8 %X) {
 ; CHECK-LABEL: @urem_XY_XZ_with_CY_lt_CZ_no_nsw_out(
-; CHECK-NEXT:    [[BO0:%.*]] = mul nuw i8 [[X:%.*]], 3
-; CHECK-NEXT:    [[BO1:%.*]] = shl nuw nsw i8 [[X]], 3
-; CHECK-NEXT:    [[R:%.*]] = urem i8 [[BO0]], [[BO1]]
+; CHECK-NEXT:    [[R:%.*]] = mul nuw i8 [[X:%.*]], 3
 ; CHECK-NEXT:    ret i8 [[R]]
 ;
   %BO0 = mul nuw i8 %X, 3
@@ -265,9 +261,7 @@
 
 define <2 x i8> @srem_XY_XZ_with_CY_lt_CZ(<2 x i8> %X) {
 ; CHECK-LABEL: @srem_XY_XZ_with_CY_lt_CZ(
-; CHECK-NEXT:    [[BO0:%.*]] = shl <2 x i8> [[X:%.*]], <i8 3, i8 3>
-; CHECK-NEXT:    [[BO1:%.*]] = mul nsw <2 x i8> [[X]], <i8 15, i8 15>
-; CHECK-NEXT:    [[R:%.*]] = srem <2 x i8> [[BO0]], [[BO1]]
+; CHECK-NEXT:    [[R:%.*]] = shl nsw <2 x i8> [[X:%.*]], <i8 3, i8 3>
 ; CHECK-NEXT:    ret <2 x i8> [[R]]
 ;
   %BO0 = shl <2 x i8> %X, <i8 3, i8 3>
@@ -289,9 +283,7 @@
 
 define i8 @srem_XY_XZ_with_CY_lt_CZ_no_nsw_out(i8 %X) {
 ; CHECK-LABEL: @srem_XY_XZ_with_CY_lt_CZ_no_nsw_out(
-; CHECK-NEXT:    [[BO0:%.*]] = mul nsw i8 [[X:%.*]], 5
-; CHECK-NEXT:    [[BO1:%.*]] = shl nuw nsw i8 [[X]], 4
-; CHECK-NEXT:    [[R:%.*]] = srem i8 [[BO0]], [[BO1]]
+; CHECK-NEXT:    [[R:%.*]] = mul nsw i8 [[X:%.*]], 5
 ; CHECK-NEXT:    ret i8 [[R]]
 ;
   %BO0 = mul nsw i8 %X, 5
@@ -315,9 +307,7 @@
 
 define i8 @srem_XY_XZ_with_CY_gt_CZ(i8 %X) {
 ; CHECK-LABEL: @srem_XY_XZ_with_CY_gt_CZ(
-; CHECK-NEXT:    [[BO0:%.*]] = shl nsw i8 [[X:%.*]], 3
-; CHECK-NEXT:    [[BO1:%.*]] = mul nsw i8 [[X]], 6
-; CHECK-NEXT:    [[R:%.*]] = srem i8 [[BO0]], [[BO1]]
+; CHECK-NEXT:    [[R:%.*]] = shl nsw i8 [[X:%.*]], 1
 ; CHECK-NEXT:    ret i8 [[R]]
 ;
   %BO0 = shl nsw i8 %X, 3
@@ -339,9 +329,7 @@
 
 define <2 x i8> @srem_XY_XZ_with_CY_gt_CZ_no_nuw_out(<2 x i8> %X) {
 ; CHECK-LABEL: @srem_XY_XZ_with_CY_gt_CZ_no_nuw_out(
-; CHECK-NEXT:    [[BO0:%.*]] = mul nsw <2 x i8> [[X:%.*]], <i8 10, i8 10>
-; CHECK-NEXT:    [[BO1:%.*]] = shl nuw nsw <2 x i8> [[X]], <i8 3, i8 3>
-; CHECK-NEXT:    [[R:%.*]] = srem <2 x i8> [[BO0]], [[BO1]]
+; CHECK-NEXT:    [[R:%.*]] = shl nsw <2 x i8> [[X:%.*]], <i8 1, i8 1>
 ; CHECK-NEXT:    ret <2 x i8> [[R]]
 ;
   %BO0 = mul nsw <2 x i8> %X, <i8 10, i8 10>