Index: llvm/lib/Transforms/InstCombine/InstCombineAddSub.cpp
===================================================================
--- llvm/lib/Transforms/InstCombine/InstCombineAddSub.cpp
+++ llvm/lib/Transforms/InstCombine/InstCombineAddSub.cpp
@@ -1267,6 +1267,50 @@
   return NewShl;
 }
 
+/// Reduce a sequence of masked half-width multiplies to a single multiply.
+/// ((XLow * YHigh) + (YLow * XHigh)) << HalfBits) + (XLow * YLow) --> X * Y
+static Instruction *foldBoxMultiply(BinaryOperator &I) {
+  if (!I.getType()->isIntegerTy())
+    return nullptr;
+
+  unsigned BitWidth = I.getType()->getScalarSizeInBits();
+  // Skip the odd bitwidth types and large bitwidth types
+  // TODO: Relax the constraint of wide/vectors types.
+  if ((BitWidth & 0x1) || (BitWidth > 128))
+    return nullptr;
+
+  unsigned HalfBits = BitWidth >> 1;
+  APInt HalfMask = APInt::getMaxValue(HalfBits);
+
+  // ResLo = (CrossSum << HalfBits) + (YLo * XLo)
+  Value *XLo, *YLo;
+  Value *CrossSum;
+  if (!match(&I, m_c_Add(m_Shl(m_Value(CrossSum), m_SpecificInt(HalfBits)),
+                         m_Mul(m_Value(YLo), m_Value(XLo)))))
+    return nullptr;
+
+  // XLo = X & HalfMask
+  // YLo = Y & HalfMask
+  // TODO: Refactor with SimplifyDemandedBits or KnownBits known leading zeros
+  // to enhance robustness
+  Value *X, *Y;
+  if (!match(XLo, m_And(m_Value(X), m_SpecificInt(HalfMask))) ||
+      !match(YLo, m_And(m_Value(Y), m_SpecificInt(HalfMask))))
+    return nullptr;
+
+  // CrossSum = (X' * (Y >> Halfbits)) + (Y' * (X >> HalfBits))
+  // X' can be either X or XLo in the pattern (and the same for Y')
+  if (match(CrossSum,
+            m_c_Add(m_c_Mul(m_LShr(m_Specific(Y), m_SpecificInt(HalfBits)),
+                            m_CombineOr(m_Specific(X), m_Specific(XLo))),
+
+                    m_c_Mul(m_LShr(m_Specific(X), m_SpecificInt(HalfBits)),
+                            m_CombineOr(m_Specific(Y), m_Specific(YLo))))))
+    return BinaryOperator::CreateMul(X, Y);
+
+  return nullptr;
+}
+
 Instruction *InstCombinerImpl::visitAdd(BinaryOperator &I) {
   if (Value *V = simplifyAddInst(I.getOperand(0), I.getOperand(1),
                                  I.hasNoSignedWrap(), I.hasNoUnsignedWrap(),
@@ -1286,6 +1330,9 @@
   if (Value *V = SimplifyUsingDistributiveLaws(I))
     return replaceInstUsesWith(I, V);
 
+  if (Instruction *R = foldBoxMultiply(I))
+    return R;
+
   if (Instruction *R = factorizeMathWithShlOps(I, Builder))
     return R;
 
Index: llvm/test/Transforms/InstCombine/mul_fold.ll
===================================================================
--- llvm/test/Transforms/InstCombine/mul_fold.ll
+++ llvm/test/Transforms/InstCombine/mul_fold.ll
@@ -23,11 +23,9 @@
 ; CHECK-NEXT:    call void @use8(i8 [[M10]])
 ; CHECK-NEXT:    [[M01:%.*]] = mul nuw i8 [[IN1LO]], [[IN0HI]]
 ; CHECK-NEXT:    call void @use8(i8 [[M01]])
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i8 [[IN1LO]], [[IN0LO]]
 ; CHECK-NEXT:    [[ADDC:%.*]] = add i8 [[M10]], [[M01]]
 ; CHECK-NEXT:    call void @use8(i8 [[ADDC]])
-; CHECK-NEXT:    [[SHL:%.*]] = shl i8 [[ADDC]], 4
-; CHECK-NEXT:    [[RETLO:%.*]] = add i8 [[SHL]], [[M00]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i8 [[IN0]], [[IN1]]
 ; CHECK-NEXT:    ret i8 [[RETLO]]
 ;
   %In0Lo = and i8 %in0, 15
@@ -56,11 +54,9 @@
 ; CHECK-NEXT:    call void @use8(i8 [[M10]])
 ; CHECK-NEXT:    [[M01:%.*]] = mul nuw i8 [[IN1LO]], [[IN0HI]]
 ; CHECK-NEXT:    call void @use8(i8 [[M01]])
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i8 [[IN1LO]], [[IN0LO]]
 ; CHECK-NEXT:    [[ADDC:%.*]] = add i8 [[M10]], [[M01]]
 ; CHECK-NEXT:    call void @use8(i8 [[ADDC]])
-; CHECK-NEXT:    [[SHL:%.*]] = shl i8 [[ADDC]], 4
-; CHECK-NEXT:    [[RETLO:%.*]] = add i8 [[M00]], [[SHL]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i8 [[IN0]], [[IN1]]
 ; CHECK-NEXT:    ret i8 [[RETLO]]
 ;
   %In0Lo = and i8 %in0, 15
@@ -89,11 +85,9 @@
 ; CHECK-NEXT:    call void @use8(i8 [[M10]])
 ; CHECK-NEXT:    [[M01:%.*]] = mul nuw i8 [[IN1LO]], [[IN0HI]]
 ; CHECK-NEXT:    call void @use8(i8 [[M01]])
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i8 [[IN1LO]], [[IN0LO]]
 ; CHECK-NEXT:    [[ADDC:%.*]] = add i8 [[M01]], [[M10]]
 ; CHECK-NEXT:    call void @use8(i8 [[ADDC]])
-; CHECK-NEXT:    [[SHL:%.*]] = shl i8 [[ADDC]], 4
-; CHECK-NEXT:    [[RETLO:%.*]] = add i8 [[SHL]], [[M00]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i8 [[IN0]], [[IN1]]
 ; CHECK-NEXT:    ret i8 [[RETLO]]
 ;
   %In0Lo = and i8 %in0, 15
@@ -122,11 +116,9 @@
 ; CHECK-NEXT:    call void @use8(i8 [[M10]])
 ; CHECK-NEXT:    [[M01:%.*]] = mul nuw i8 [[IN1LO]], [[IN0HI]]
 ; CHECK-NEXT:    call void @use8(i8 [[M01]])
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i8 [[IN1LO]], [[IN0LO]]
 ; CHECK-NEXT:    [[ADDC:%.*]] = add i8 [[M01]], [[M10]]
 ; CHECK-NEXT:    call void @use8(i8 [[ADDC]])
-; CHECK-NEXT:    [[SHL:%.*]] = shl i8 [[ADDC]], 4
-; CHECK-NEXT:    [[RETLO:%.*]] = add i8 [[M00]], [[SHL]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i8 [[IN0]], [[IN1]]
 ; CHECK-NEXT:    ret i8 [[RETLO]]
 ;
   %In0Lo = and i8 %in0, 15
@@ -155,11 +147,9 @@
 ; CHECK-NEXT:    call void @use16(i16 [[M10]])
 ; CHECK-NEXT:    [[M01:%.*]] = mul nuw i16 [[IN1LO]], [[IN0HI]]
 ; CHECK-NEXT:    call void @use16(i16 [[M01]])
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i16 [[IN1LO]], [[IN0LO]]
 ; CHECK-NEXT:    [[ADDC:%.*]] = add i16 [[M10]], [[M01]]
 ; CHECK-NEXT:    call void @use16(i16 [[ADDC]])
-; CHECK-NEXT:    [[SHL:%.*]] = shl i16 [[ADDC]], 8
-; CHECK-NEXT:    [[RETLO:%.*]] = add i16 [[SHL]], [[M00]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i16 [[IN0]], [[IN1]]
 ; CHECK-NEXT:    ret i16 [[RETLO]]
 ;
   %In0Lo = and i16 %in0, 255
@@ -188,11 +178,9 @@
 ; CHECK-NEXT:    call void @use16(i16 [[M10]])
 ; CHECK-NEXT:    [[M01:%.*]] = mul nuw i16 [[IN1LO]], [[IN0HI]]
 ; CHECK-NEXT:    call void @use16(i16 [[M01]])
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i16 [[IN1LO]], [[IN0LO]]
 ; CHECK-NEXT:    [[ADDC:%.*]] = add i16 [[M10]], [[M01]]
 ; CHECK-NEXT:    call void @use16(i16 [[ADDC]])
-; CHECK-NEXT:    [[SHL:%.*]] = shl i16 [[ADDC]], 8
-; CHECK-NEXT:    [[RETLO:%.*]] = add i16 [[M00]], [[SHL]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i16 [[IN0]], [[IN1]]
 ; CHECK-NEXT:    ret i16 [[RETLO]]
 ;
   %In0Lo = and i16 %in0, 255
@@ -221,11 +209,9 @@
 ; CHECK-NEXT:    call void @use16(i16 [[M10]])
 ; CHECK-NEXT:    [[M01:%.*]] = mul nuw i16 [[IN1LO]], [[IN0HI]]
 ; CHECK-NEXT:    call void @use16(i16 [[M01]])
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i16 [[IN1LO]], [[IN0LO]]
 ; CHECK-NEXT:    [[ADDC:%.*]] = add i16 [[M01]], [[M10]]
 ; CHECK-NEXT:    call void @use16(i16 [[ADDC]])
-; CHECK-NEXT:    [[SHL:%.*]] = shl i16 [[ADDC]], 8
-; CHECK-NEXT:    [[RETLO:%.*]] = add i16 [[SHL]], [[M00]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i16 [[IN0]], [[IN1]]
 ; CHECK-NEXT:    ret i16 [[RETLO]]
 ;
   %In0Lo = and i16 %in0, 255
@@ -254,11 +240,9 @@
 ; CHECK-NEXT:    call void @use16(i16 [[M10]])
 ; CHECK-NEXT:    [[M01:%.*]] = mul nuw i16 [[IN1LO]], [[IN0HI]]
 ; CHECK-NEXT:    call void @use16(i16 [[M01]])
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i16 [[IN1LO]], [[IN0LO]]
 ; CHECK-NEXT:    [[ADDC:%.*]] = add i16 [[M01]], [[M10]]
 ; CHECK-NEXT:    call void @use16(i16 [[ADDC]])
-; CHECK-NEXT:    [[SHL:%.*]] = shl i16 [[ADDC]], 8
-; CHECK-NEXT:    [[RETLO:%.*]] = add i16 [[M00]], [[SHL]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i16 [[IN0]], [[IN1]]
 ; CHECK-NEXT:    ret i16 [[RETLO]]
 ;
   %In0Lo = and i16 %in0, 255
@@ -285,11 +269,9 @@
 ; CHECK-NEXT:    [[IN1HI:%.*]] = lshr i32 [[IN1]], 16
 ; CHECK-NEXT:    [[M10:%.*]] = mul nuw i32 [[IN1HI]], [[IN0LO]]
 ; CHECK-NEXT:    [[M01:%.*]] = mul nuw i32 [[IN0HI]], [[IN1LO]]
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i32 [[IN1LO]], [[IN0LO]]
 ; CHECK-NEXT:    [[ADDC:%.*]] = add i32 [[M10]], [[M01]]
 ; CHECK-NEXT:    call void @use32(i32 [[ADDC]])
-; CHECK-NEXT:    [[SHL:%.*]] = shl i32 [[ADDC]], 16
-; CHECK-NEXT:    [[RETLO:%.*]] = add i32 [[SHL]], [[M00]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i32 [[IN0]], [[IN1]]
 ; CHECK-NEXT:    ret i32 [[RETLO]]
 ;
   %In0Lo = and i32 %in0, 65535
@@ -314,11 +296,9 @@
 ; CHECK-NEXT:    [[IN1HI:%.*]] = lshr i32 [[IN1]], 16
 ; CHECK-NEXT:    [[M10:%.*]] = mul nuw i32 [[IN1HI]], [[IN0LO]]
 ; CHECK-NEXT:    [[M01:%.*]] = mul nuw i32 [[IN0HI]], [[IN1LO]]
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i32 [[IN1LO]], [[IN0LO]]
 ; CHECK-NEXT:    [[ADDC:%.*]] = add i32 [[M10]], [[M01]]
 ; CHECK-NEXT:    call void @use32(i32 [[ADDC]])
-; CHECK-NEXT:    [[SHL:%.*]] = shl i32 [[ADDC]], 16
-; CHECK-NEXT:    [[RETLO:%.*]] = add i32 [[M00]], [[SHL]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i32 [[IN0]], [[IN1]]
 ; CHECK-NEXT:    ret i32 [[RETLO]]
 ;
   %In0Lo = and i32 %in0, 65535
@@ -343,11 +323,9 @@
 ; CHECK-NEXT:    [[IN1HI:%.*]] = lshr i32 [[IN1]], 16
 ; CHECK-NEXT:    [[M10:%.*]] = mul nuw i32 [[IN1HI]], [[IN0LO]]
 ; CHECK-NEXT:    [[M01:%.*]] = mul nuw i32 [[IN0HI]], [[IN1LO]]
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i32 [[IN1LO]], [[IN0LO]]
 ; CHECK-NEXT:    [[ADDC:%.*]] = add i32 [[M01]], [[M10]]
 ; CHECK-NEXT:    call void @use32(i32 [[ADDC]])
-; CHECK-NEXT:    [[SHL:%.*]] = shl i32 [[ADDC]], 16
-; CHECK-NEXT:    [[RETLO:%.*]] = add i32 [[SHL]], [[M00]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i32 [[IN0]], [[IN1]]
 ; CHECK-NEXT:    ret i32 [[RETLO]]
 ;
   %In0Lo = and i32 %in0, 65535
@@ -372,11 +350,9 @@
 ; CHECK-NEXT:    [[IN1HI:%.*]] = lshr i32 [[IN1]], 16
 ; CHECK-NEXT:    [[M10:%.*]] = mul nuw i32 [[IN1HI]], [[IN0LO]]
 ; CHECK-NEXT:    [[M01:%.*]] = mul nuw i32 [[IN0HI]], [[IN1LO]]
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i32 [[IN1LO]], [[IN0LO]]
 ; CHECK-NEXT:    [[ADDC:%.*]] = add i32 [[M01]], [[M10]]
 ; CHECK-NEXT:    call void @use32(i32 [[ADDC]])
-; CHECK-NEXT:    [[SHL:%.*]] = shl i32 [[ADDC]], 16
-; CHECK-NEXT:    [[RETLO:%.*]] = add i32 [[M00]], [[SHL]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i32 [[IN0]], [[IN1]]
 ; CHECK-NEXT:    ret i32 [[RETLO]]
 ;
   %In0Lo = and i32 %in0, 65535
@@ -401,11 +377,9 @@
 ; CHECK-NEXT:    [[IN1HI:%.*]] = lshr i64 [[IN1]], 32
 ; CHECK-NEXT:    [[M10:%.*]] = mul nuw i64 [[IN0LO]], [[IN1HI]]
 ; CHECK-NEXT:    [[M01:%.*]] = mul nuw i64 [[IN0HI]], [[IN1LO]]
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i64 [[IN1LO]], [[IN0LO]]
 ; CHECK-NEXT:    [[ADDC:%.*]] = add i64 [[M10]], [[M01]]
 ; CHECK-NEXT:    call void @use64(i64 [[ADDC]])
-; CHECK-NEXT:    [[SHL:%.*]] = shl i64 [[ADDC]], 32
-; CHECK-NEXT:    [[RETLO:%.*]] = add i64 [[SHL]], [[M00]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i64 [[IN0]], [[IN1]]
 ; CHECK-NEXT:    ret i64 [[RETLO]]
 ;
   %In0Lo = and i64 %in0, 4294967295
@@ -430,11 +404,9 @@
 ; CHECK-NEXT:    [[IN1HI:%.*]] = lshr i64 [[IN1]], 32
 ; CHECK-NEXT:    [[M10:%.*]] = mul nuw i64 [[IN0LO]], [[IN1HI]]
 ; CHECK-NEXT:    [[M01:%.*]] = mul nuw i64 [[IN0HI]], [[IN1LO]]
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i64 [[IN1LO]], [[IN0LO]]
 ; CHECK-NEXT:    [[ADDC:%.*]] = add i64 [[M10]], [[M01]]
 ; CHECK-NEXT:    call void @use64(i64 [[ADDC]])
-; CHECK-NEXT:    [[SHL:%.*]] = shl i64 [[ADDC]], 32
-; CHECK-NEXT:    [[RETLO:%.*]] = add i64 [[M00]], [[SHL]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i64 [[IN0]], [[IN1]]
 ; CHECK-NEXT:    ret i64 [[RETLO]]
 ;
   %In0Lo = and i64 %in0, 4294967295
@@ -459,11 +431,9 @@
 ; CHECK-NEXT:    [[IN1HI:%.*]] = lshr i64 [[IN1]], 32
 ; CHECK-NEXT:    [[M10:%.*]] = mul nuw i64 [[IN0LO]], [[IN1HI]]
 ; CHECK-NEXT:    [[M01:%.*]] = mul nuw i64 [[IN0HI]], [[IN1LO]]
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i64 [[IN1LO]], [[IN0LO]]
 ; CHECK-NEXT:    [[ADDC:%.*]] = add i64 [[M01]], [[M10]]
 ; CHECK-NEXT:    call void @use64(i64 [[ADDC]])
-; CHECK-NEXT:    [[SHL:%.*]] = shl i64 [[ADDC]], 32
-; CHECK-NEXT:    [[RETLO:%.*]] = add i64 [[SHL]], [[M00]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i64 [[IN0]], [[IN1]]
 ; CHECK-NEXT:    ret i64 [[RETLO]]
 ;
   %In0Lo = and i64 %in0, 4294967295
@@ -488,11 +458,9 @@
 ; CHECK-NEXT:    [[IN1HI:%.*]] = lshr i64 [[IN1]], 32
 ; CHECK-NEXT:    [[M10:%.*]] = mul nuw i64 [[IN0LO]], [[IN1HI]]
 ; CHECK-NEXT:    [[M01:%.*]] = mul nuw i64 [[IN0HI]], [[IN1LO]]
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i64 [[IN1LO]], [[IN0LO]]
 ; CHECK-NEXT:    [[ADDC:%.*]] = add i64 [[M01]], [[M10]]
 ; CHECK-NEXT:    call void @use64(i64 [[ADDC]])
-; CHECK-NEXT:    [[SHL:%.*]] = shl i64 [[ADDC]], 32
-; CHECK-NEXT:    [[RETLO:%.*]] = add i64 [[M00]], [[SHL]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i64 [[IN0]], [[IN1]]
 ; CHECK-NEXT:    ret i64 [[RETLO]]
 ;
   %In0Lo = and i64 %in0, 4294967295
@@ -517,11 +485,9 @@
 ; CHECK-NEXT:    [[IN1HI:%.*]] = lshr i32 [[IN1]], 16
 ; CHECK-NEXT:    [[M10:%.*]] = mul nuw i32 [[IN1HI]], [[IN0LO]]
 ; CHECK-NEXT:    [[M01:%.*]] = mul nuw i32 [[IN1LO]], [[IN0HI]]
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i32 [[IN1LO]], [[IN0LO]]
 ; CHECK-NEXT:    [[ADDC:%.*]] = add i32 [[M10]], [[M01]]
 ; CHECK-NEXT:    call void @use32(i32 [[ADDC]])
-; CHECK-NEXT:    [[SHL:%.*]] = shl i32 [[ADDC]], 16
-; CHECK-NEXT:    [[RETLO:%.*]] = add i32 [[SHL]], [[M00]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i32 [[IN0]], [[IN1]]
 ; CHECK-NEXT:    ret i32 [[RETLO]]
 ;
   %In0Lo = and i32 %in0, 65535
@@ -542,16 +508,7 @@
 ; https://alive2.llvm.org/ce/z/2BqKLt
 define i8 @mul8_low(i8 %in0, i8 %in1) {
 ; CHECK-LABEL: @mul8_low(
-; CHECK-NEXT:    [[IN0LO:%.*]] = and i8 [[IN0:%.*]], 15
-; CHECK-NEXT:    [[IN0HI:%.*]] = lshr i8 [[IN0]], 4
-; CHECK-NEXT:    [[IN1LO:%.*]] = and i8 [[IN1:%.*]], 15
-; CHECK-NEXT:    [[IN1HI:%.*]] = lshr i8 [[IN1]], 4
-; CHECK-NEXT:    [[M10:%.*]] = mul i8 [[IN1HI]], [[IN0]]
-; CHECK-NEXT:    [[M01:%.*]] = mul i8 [[IN0HI]], [[IN1]]
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i8 [[IN1LO]], [[IN0LO]]
-; CHECK-NEXT:    [[ADDC:%.*]] = add i8 [[M10]], [[M01]]
-; CHECK-NEXT:    [[SHL:%.*]] = shl i8 [[ADDC]], 4
-; CHECK-NEXT:    [[RETLO:%.*]] = add i8 [[SHL]], [[M00]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i8 [[IN0:%.*]], [[IN1:%.*]]
 ; CHECK-NEXT:    ret i8 [[RETLO]]
 ;
   %In0Lo = and i8 %in0, 15
@@ -569,16 +526,7 @@
 
 define i16 @mul16_low(i16 %in0, i16 %in1) {
 ; CHECK-LABEL: @mul16_low(
-; CHECK-NEXT:    [[IN0LO:%.*]] = and i16 [[IN0:%.*]], 255
-; CHECK-NEXT:    [[IN0HI:%.*]] = lshr i16 [[IN0]], 8
-; CHECK-NEXT:    [[IN1LO:%.*]] = and i16 [[IN1:%.*]], 255
-; CHECK-NEXT:    [[IN1HI:%.*]] = lshr i16 [[IN1]], 8
-; CHECK-NEXT:    [[M10:%.*]] = mul i16 [[IN1HI]], [[IN0]]
-; CHECK-NEXT:    [[M01:%.*]] = mul i16 [[IN0HI]], [[IN1]]
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i16 [[IN1LO]], [[IN0LO]]
-; CHECK-NEXT:    [[ADDC:%.*]] = add i16 [[M10]], [[M01]]
-; CHECK-NEXT:    [[SHL:%.*]] = shl i16 [[ADDC]], 8
-; CHECK-NEXT:    [[RETLO:%.*]] = add i16 [[SHL]], [[M00]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i16 [[IN0:%.*]], [[IN1:%.*]]
 ; CHECK-NEXT:    ret i16 [[RETLO]]
 ;
   %In0Lo = and i16 %in0, 255
@@ -596,16 +544,7 @@
 
 define i32 @mul32_low(i32 %in0, i32 %in1) {
 ; CHECK-LABEL: @mul32_low(
-; CHECK-NEXT:    [[IN0LO:%.*]] = and i32 [[IN0:%.*]], 65535
-; CHECK-NEXT:    [[IN0HI:%.*]] = lshr i32 [[IN0]], 16
-; CHECK-NEXT:    [[IN1LO:%.*]] = and i32 [[IN1:%.*]], 65535
-; CHECK-NEXT:    [[IN1HI:%.*]] = lshr i32 [[IN1]], 16
-; CHECK-NEXT:    [[M10:%.*]] = mul i32 [[IN1HI]], [[IN0]]
-; CHECK-NEXT:    [[M01:%.*]] = mul i32 [[IN0HI]], [[IN1]]
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i32 [[IN1LO]], [[IN0LO]]
-; CHECK-NEXT:    [[ADDC:%.*]] = add i32 [[M10]], [[M01]]
-; CHECK-NEXT:    [[SHL:%.*]] = shl i32 [[ADDC]], 16
-; CHECK-NEXT:    [[RETLO:%.*]] = add i32 [[SHL]], [[M00]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i32 [[IN0:%.*]], [[IN1:%.*]]
 ; CHECK-NEXT:    ret i32 [[RETLO]]
 ;
   %In0Lo = and i32 %in0, 65535
@@ -623,16 +562,7 @@
 
 define i64 @mul64_low(i64 %in0, i64 %in1) {
 ; CHECK-LABEL: @mul64_low(
-; CHECK-NEXT:    [[IN0LO:%.*]] = and i64 [[IN0:%.*]], 4294967295
-; CHECK-NEXT:    [[IN0HI:%.*]] = lshr i64 [[IN0]], 32
-; CHECK-NEXT:    [[IN1LO:%.*]] = and i64 [[IN1:%.*]], 4294967295
-; CHECK-NEXT:    [[IN1HI:%.*]] = lshr i64 [[IN1]], 32
-; CHECK-NEXT:    [[M10:%.*]] = mul i64 [[IN1HI]], [[IN0]]
-; CHECK-NEXT:    [[M01:%.*]] = mul i64 [[IN0HI]], [[IN1]]
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i64 [[IN1LO]], [[IN0LO]]
-; CHECK-NEXT:    [[ADDC:%.*]] = add i64 [[M10]], [[M01]]
-; CHECK-NEXT:    [[SHL:%.*]] = shl i64 [[ADDC]], 32
-; CHECK-NEXT:    [[RETLO:%.*]] = add i64 [[SHL]], [[M00]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i64 [[IN0:%.*]], [[IN1:%.*]]
 ; CHECK-NEXT:    ret i64 [[RETLO]]
 ;
   %In0Lo = and i64 %in0, 4294967295
@@ -650,16 +580,7 @@
 
 define i128 @mul128_low(i128 %in0, i128 %in1) {
 ; CHECK-LABEL: @mul128_low(
-; CHECK-NEXT:    [[IN0LO:%.*]] = and i128 [[IN0:%.*]], 18446744073709551615
-; CHECK-NEXT:    [[IN0HI:%.*]] = lshr i128 [[IN0]], 64
-; CHECK-NEXT:    [[IN1LO:%.*]] = and i128 [[IN1:%.*]], 18446744073709551615
-; CHECK-NEXT:    [[IN1HI:%.*]] = lshr i128 [[IN1]], 64
-; CHECK-NEXT:    [[M10:%.*]] = mul i128 [[IN1HI]], [[IN0]]
-; CHECK-NEXT:    [[M01:%.*]] = mul i128 [[IN0HI]], [[IN1]]
-; CHECK-NEXT:    [[M00:%.*]] = mul nuw i128 [[IN1LO]], [[IN0LO]]
-; CHECK-NEXT:    [[ADDC:%.*]] = add i128 [[M10]], [[M01]]
-; CHECK-NEXT:    [[SHL:%.*]] = shl i128 [[ADDC]], 64
-; CHECK-NEXT:    [[RETLO:%.*]] = add i128 [[SHL]], [[M00]]
+; CHECK-NEXT:    [[RETLO:%.*]] = mul i128 [[IN0:%.*]], [[IN1:%.*]]
 ; CHECK-NEXT:    ret i128 [[RETLO]]
 ;
   %In0Lo = and i128 %in0, 18446744073709551615