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
@@ -1702,11 +1702,31 @@
 static Instruction *simplifyIRemMulShl(BinaryOperator &I,
                                        InstCombinerImpl &IC) {
   Value *Op0 = I.getOperand(0), *Op1 = I.getOperand(1), *X, *Y, *Z;
-  if (!(match(Op0, m_Mul(m_Value(X), m_Value(Y))) &&
-        match(Op1, m_c_Mul(m_Specific(X), m_Value(Z)))) &&
-      !(match(Op0, m_Mul(m_Value(Y), m_Value(X))) &&
-        match(Op1, m_c_Mul(m_Specific(X), m_Value(Z)))))
+  bool ShiftX = false, ShiftY = false, ShiftZ = false;
+  if ((match(Op0, m_Mul(m_Value(X), m_Value(Y))) &&
+       match(Op1, m_c_Mul(m_Specific(X), m_Value(Z)))) ||
+      (match(Op0, m_Mul(m_Value(Y), m_Value(X))) &&
+       match(Op1, m_c_Mul(m_Specific(X), m_Value(Z))))) {
+    // Pass
+  } else if (match(Op0, m_Shl(m_Value(X), m_Value(Y))) &&
+             match(Op1, m_c_Mul(m_Specific(X), m_Value(Z)))) {
+    ShiftY = true;
+  } else if (match(Op1, m_Shl(m_Value(X), m_Value(Z))) &&
+             match(Op0, m_c_Mul(m_Specific(X), m_Value(Y)))) {
+    ShiftZ = true;
+  } else if (match(Op0, m_Shl(m_Value(X), m_Value(Y))) &&
+             match(Op1, m_Shl(m_Specific(X), m_Value(Z)))) {
+    ShiftZ = true;
+    ShiftY = true;
+  } else if (match(Op0, m_Shl(m_Value(Y), m_Value(X))) &&
+             match(Op1, m_Shl(m_Value(Z), m_Specific(X)))) {
+    ShiftX = true;
+  } else {
     return nullptr;
+  }
+
+  OverflowingBinaryOperator *BO0 = cast<OverflowingBinaryOperator>(Op0);
+  OverflowingBinaryOperator *BO1 = cast<OverflowingBinaryOperator>(Op1);
 
   auto GetOperandAsConstantInt = [](Value *Op) -> ConstantInt * {
     if (Op->getType()->isVectorTy())
@@ -1728,8 +1748,12 @@
   APInt APIntY = ConstY->getValue();
   APInt APIntZ = ConstZ->getValue();
 
-  OverflowingBinaryOperator *BO0 = cast<OverflowingBinaryOperator>(Op0);
-  OverflowingBinaryOperator *BO1 = cast<OverflowingBinaryOperator>(Op1);
+  // 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)
+    APIntY = APInt(APIntY.getBitWidth(), 1) << APIntY;
+  if (ShiftZ)
+    APIntZ = APInt(APIntZ.getBitWidth(), 1) << APIntZ;
 
   bool BO0HasNSW = BO0->hasNoSignedWrap();
   bool BO0HasNUW = BO0->hasNoUnsignedWrap();
@@ -1741,6 +1765,11 @@
   if (RemYZ.isZero() && (IsSRem ? BO0HasNSW : BO0HasNUW))
     return IC.replaceInstUsesWith(I, ConstantInt::getNullValue(I.getType()));
 
+  auto GetBinOpOut = [&](Value *RemSimplification) -> BinaryOperator * {
+    return ShiftX ? BinaryOperator::CreateShl(RemSimplification, X)
+                  : BinaryOperator::CreateMul(X, RemSimplification);
+  };
+
   bool BO1HasNSW = BO1->hasNoSignedWrap();
   bool BO1HasNUW = BO1->hasNoUnsignedWrap();
 
@@ -1748,8 +1777,7 @@
   //      if (rem Y, Z) == Y
   //          -> (mul nuw/nsw X, Y)
   if (RemYZ == APIntY && (IsSRem ? BO1HasNSW : BO1HasNUW)) {
-    BinaryOperator *BO =
-        BinaryOperator::CreateMul(X, ConstantInt::get(I.getType(), APIntY));
+    BinaryOperator *BO = GetBinOpOut(ConstantInt::get(I.getType(), APIntY));
     // Copy any overflow flags from Op0.
     if (IsSRem || BO0HasNSW)
       BO->setHasNoSignedWrap();
@@ -1762,8 +1790,7 @@
   //      if Y >= Z
   //          -> (mul {nuw} nsw X, (rem Y, Z))
   if (APIntY.uge(APIntZ) && (IsSRem ? (BO0HasNSW && BO1HasNSW) : BO0HasNUW)) {
-    BinaryOperator *BO =
-        BinaryOperator::CreateMul(X, ConstantInt::get(I.getType(), RemYZ));
+    BinaryOperator *BO = GetBinOpOut(ConstantInt::get(I.getType(), RemYZ));
     BO->setHasNoSignedWrap();
     if (BO0HasNUW)
       BO->setHasNoUnsignedWrap();
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>