diff --git a/llvm/lib/Transforms/Vectorize/VectorCombine.cpp b/llvm/lib/Transforms/Vectorize/VectorCombine.cpp
--- a/llvm/lib/Transforms/Vectorize/VectorCombine.cpp
+++ b/llvm/lib/Transforms/Vectorize/VectorCombine.cpp
@@ -88,10 +88,10 @@
     NewCost = VectorOpCost + ExtractCost + !Ext0->hasOneUse() * ExtractCost +
               !Ext1->hasOneUse() * ExtractCost;
   }
-  // TODO: The cost comparison should not differ based on opcode. Either we
-  //       want to be uniformly more or less aggressive in deciding if a vector
-  //       operation should replace the scalar operation.
-  return IsBinOp ? OldCost <= NewCost : OldCost < NewCost;
+  // Aggressively form a vector op if the cost is equal because the transform
+  // may enable further optimization.
+  // Codegen can reverse this transform (scalarize) if it was not profitable.
+  return OldCost < NewCost;
 }
 
 /// Try to reduce extract element costs by converting scalar compares to vector
diff --git a/llvm/test/Transforms/VectorCombine/X86/extract-binop.ll b/llvm/test/Transforms/VectorCombine/X86/extract-binop.ll
--- a/llvm/test/Transforms/VectorCombine/X86/extract-binop.ll
+++ b/llvm/test/Transforms/VectorCombine/X86/extract-binop.ll
@@ -74,14 +74,15 @@
   ret i8 %r
 }
 
-; Negative test - extracts are free and vector op has same cost as scalar.
+; Extracts are free and vector op has same cost as scalar, but we
+; speculatively transform to vector to create more optimization
+; opportunities..
 
 define double @ext0_ext0_fadd(<2 x double> %x, <2 x double> %y) {
 ; CHECK-LABEL: @ext0_ext0_fadd(
-; CHECK-NEXT:    [[E0:%.*]] = extractelement <2 x double> [[X:%.*]], i32 0
-; CHECK-NEXT:    [[E1:%.*]] = extractelement <2 x double> [[Y:%.*]], i32 0
-; CHECK-NEXT:    [[R:%.*]] = fadd double [[E0]], [[E1]]
-; CHECK-NEXT:    ret double [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = fadd <2 x double> [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[TMP1]], i32 0
+; CHECK-NEXT:    ret double [[TMP2]]
 ;
   %e0 = extractelement <2 x double> %x, i32 0
   %e1 = extractelement <2 x double> %y, i32 0
@@ -118,14 +119,14 @@
   ret double %r
 }
 
-; Negative test - disguised same vector operand; scalar code is cheaper than general case.
+; Disguised same vector operand; scalar code is not cheaper (with default
+; x86 target), so aggressively form vector binop.
 
 define i32 @ext1_ext1_add_same_vec(<4 x i32> %x) {
 ; CHECK-LABEL: @ext1_ext1_add_same_vec(
-; CHECK-NEXT:    [[E0:%.*]] = extractelement <4 x i32> [[X:%.*]], i32 1
-; CHECK-NEXT:    [[E1:%.*]] = extractelement <4 x i32> [[X]], i32 1
-; CHECK-NEXT:    [[R:%.*]] = add i32 [[E0]], [[E1]]
-; CHECK-NEXT:    ret i32 [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = add <4 x i32> [[X:%.*]], [[X]]
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x i32> [[TMP1]], i32 1
+; CHECK-NEXT:    ret i32 [[TMP2]]
 ;
   %e0 = extractelement <4 x i32> %x, i32 1
   %e1 = extractelement <4 x i32> %x, i32 1
@@ -133,13 +134,13 @@
   ret i32 %r
 }
 
-; Negative test - same vector operand; scalar code is cheaper than general case.
+; Functionally equivalent to above test; should transform as above.
 
 define i32 @ext1_ext1_add_same_vec_cse(<4 x i32> %x) {
 ; CHECK-LABEL: @ext1_ext1_add_same_vec_cse(
-; CHECK-NEXT:    [[E0:%.*]] = extractelement <4 x i32> [[X:%.*]], i32 1
-; CHECK-NEXT:    [[R:%.*]] = add i32 [[E0]], [[E0]]
-; CHECK-NEXT:    ret i32 [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = add <4 x i32> [[X:%.*]], [[X]]
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x i32> [[TMP1]], i32 1
+; CHECK-NEXT:    ret i32 [[TMP2]]
 ;
   %e0 = extractelement <4 x i32> %x, i32 1
   %r = add i32 %e0, %e0
@@ -200,15 +201,15 @@
   ret i8 %r
 }
 
-; Negative test - vector code would not be cheaper.
+; Vector code costs the same as scalar, so aggressively form vector op.
 
 define i8 @ext1_ext1_add_uses1(<16 x i8> %x, <16 x i8> %y) {
 ; CHECK-LABEL: @ext1_ext1_add_uses1(
 ; CHECK-NEXT:    [[E0:%.*]] = extractelement <16 x i8> [[X:%.*]], i32 0
 ; CHECK-NEXT:    call void @use_i8(i8 [[E0]])
-; CHECK-NEXT:    [[E1:%.*]] = extractelement <16 x i8> [[Y:%.*]], i32 0
-; CHECK-NEXT:    [[R:%.*]] = add i8 [[E0]], [[E1]]
-; CHECK-NEXT:    ret i8 [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = add <16 x i8> [[X]], [[Y:%.*]]
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <16 x i8> [[TMP1]], i32 0
+; CHECK-NEXT:    ret i8 [[TMP2]]
 ;
   %e0 = extractelement <16 x i8> %x, i32 0
   call void @use_i8(i8 %e0)
@@ -217,15 +218,15 @@
   ret i8 %r
 }
 
-; Negative test - vector code would not be cheaper.
+; Vector code costs the same as scalar, so aggressively form vector op.
 
 define i8 @ext1_ext1_add_uses2(<16 x i8> %x, <16 x i8> %y) {
 ; CHECK-LABEL: @ext1_ext1_add_uses2(
-; CHECK-NEXT:    [[E0:%.*]] = extractelement <16 x i8> [[X:%.*]], i32 0
 ; CHECK-NEXT:    [[E1:%.*]] = extractelement <16 x i8> [[Y:%.*]], i32 0
 ; CHECK-NEXT:    call void @use_i8(i8 [[E1]])
-; CHECK-NEXT:    [[R:%.*]] = add i8 [[E0]], [[E1]]
-; CHECK-NEXT:    ret i8 [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = add <16 x i8> [[X:%.*]], [[Y]]
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <16 x i8> [[TMP1]], i32 0
+; CHECK-NEXT:    ret i8 [[TMP2]]
 ;
   %e0 = extractelement <16 x i8> %x, i32 0
   %e1 = extractelement <16 x i8> %y, i32 0