Index: llvm/trunk/lib/Transforms/InstCombine/InstCombineAddSub.cpp
===================================================================
--- llvm/trunk/lib/Transforms/InstCombine/InstCombineAddSub.cpp
+++ llvm/trunk/lib/Transforms/InstCombine/InstCombineAddSub.cpp
@@ -1202,7 +1202,10 @@
 
   // (A + 1) + ~B --> A - B
   // ~B + (A + 1) --> A - B
-  if (match(&I, m_c_BinOp(m_Add(m_Value(A), m_One()), m_Not(m_Value(B)))))
+  // (~B + A) + 1 --> A - B
+  // (A + ~B) + 1 --> A - B
+  if (match(&I, m_c_BinOp(m_Add(m_Value(A), m_One()), m_Not(m_Value(B)))) ||
+      match(&I, m_BinOp(m_c_Add(m_Not(m_Value(B)), m_Value(A)), m_One())))
     return BinaryOperator::CreateSub(A, B);
 
   // X % C0 + (( X / C0 ) % C1) * C0 => X % (C0 * C1)
Index: llvm/trunk/test/Transforms/InstCombine/add.ll
===================================================================
--- llvm/trunk/test/Transforms/InstCombine/add.ll
+++ llvm/trunk/test/Transforms/InstCombine/add.ll
@@ -951,9 +951,7 @@
 define i32 @add_to_sub(i32 %M, i32 %B) {
 ; CHECK-LABEL: @add_to_sub(
 ; CHECK-NEXT:    [[A:%.*]] = mul i32 [[M:%.*]], 42
-; CHECK-NEXT:    [[C:%.*]] = xor i32 [[B:%.*]], -1
-; CHECK-NEXT:    [[D:%.*]] = add i32 [[A]], [[C]]
-; CHECK-NEXT:    [[E:%.*]] = add i32 [[D]], 1
+; CHECK-NEXT:    [[E:%.*]] = sub i32 [[A]], [[B:%.*]]
 ; CHECK-NEXT:    ret i32 [[E]]
 ;
   %A = mul i32 %M, 42          ; thwart complexity-based ordering
@@ -966,10 +964,8 @@
 ; E = (~B + A) + 1 = A - B
 define i32 @add_to_sub2(i32 %A, i32 %M) {
 ; CHECK-LABEL: @add_to_sub2(
-; CHECK-NEXT:    [[B:%.*]] = mul i32 [[M:%.*]], 42
-; CHECK-NEXT:    [[C:%.*]] = xor i32 [[B]], -1
-; CHECK-NEXT:    [[D:%.*]] = add i32 [[C]], [[A:%.*]]
-; CHECK-NEXT:    [[E:%.*]] = add i32 [[D]], 1
+; CHECK-NEXT:    [[TMP1:%.*]] = mul i32 [[M:%.*]], -42
+; CHECK-NEXT:    [[E:%.*]] = add i32 [[TMP1]], [[A:%.*]]
 ; CHECK-NEXT:    ret i32 [[E]]
 ;
   %B = mul i32 %M, 42          ; thwart complexity-based ordering
Index: llvm/trunk/test/Transforms/InstCombine/fold-inc-of-add-of-not-x-and-y-to-sub-x-from-y.ll
===================================================================
--- llvm/trunk/test/Transforms/InstCombine/fold-inc-of-add-of-not-x-and-y-to-sub-x-from-y.ll
+++ llvm/trunk/test/Transforms/InstCombine/fold-inc-of-add-of-not-x-and-y-to-sub-x-from-y.ll
@@ -12,9 +12,7 @@
 
 define i32 @t0(i32 %x, i32 %y) {
 ; CHECK-LABEL: @t0(
-; CHECK-NEXT:    [[T0:%.*]] = xor i32 [[X:%.*]], -1
-; CHECK-NEXT:    [[T1:%.*]] = add i32 [[T0]], [[Y:%.*]]
-; CHECK-NEXT:    [[T2:%.*]] = add i32 [[T1]], 1
+; CHECK-NEXT:    [[T2:%.*]] = sub i32 [[Y:%.*]], [[X:%.*]]
 ; CHECK-NEXT:    ret i32 [[T2]]
 ;
   %t0 = xor i32 %x, -1
@@ -29,9 +27,7 @@
 
 define <4 x i32> @t1_vec_splat(<4 x i32> %x, <4 x i32> %y) {
 ; CHECK-LABEL: @t1_vec_splat(
-; CHECK-NEXT:    [[T0:%.*]] = xor <4 x i32> [[X:%.*]], <i32 -1, i32 -1, i32 -1, i32 -1>
-; CHECK-NEXT:    [[T1:%.*]] = add <4 x i32> [[T0]], [[Y:%.*]]
-; CHECK-NEXT:    [[T2:%.*]] = add <4 x i32> [[T1]], <i32 1, i32 1, i32 1, i32 1>
+; CHECK-NEXT:    [[T2:%.*]] = sub <4 x i32> [[Y:%.*]], [[X:%.*]]
 ; CHECK-NEXT:    ret <4 x i32> [[T2]]
 ;
   %t0 = xor <4 x i32> %x, <i32 -1, i32 -1, i32 -1, i32 -1>
@@ -42,9 +38,7 @@
 
 define <4 x i32> @t2_vec_undef0(<4 x i32> %x, <4 x i32> %y) {
 ; CHECK-LABEL: @t2_vec_undef0(
-; CHECK-NEXT:    [[T0:%.*]] = xor <4 x i32> [[X:%.*]], <i32 -1, i32 -1, i32 undef, i32 -1>
-; CHECK-NEXT:    [[T1:%.*]] = add <4 x i32> [[T0]], [[Y:%.*]]
-; CHECK-NEXT:    [[T2:%.*]] = add <4 x i32> [[T1]], <i32 1, i32 1, i32 1, i32 1>
+; CHECK-NEXT:    [[T2:%.*]] = sub <4 x i32> [[Y:%.*]], [[X:%.*]]
 ; CHECK-NEXT:    ret <4 x i32> [[T2]]
 ;
   %t0 = xor <4 x i32> %x, <i32 -1, i32 -1, i32 undef, i32 -1>
@@ -55,9 +49,7 @@
 
 define <4 x i32> @t3_vec_undef1(<4 x i32> %x, <4 x i32> %y) {
 ; CHECK-LABEL: @t3_vec_undef1(
-; CHECK-NEXT:    [[T0:%.*]] = xor <4 x i32> [[X:%.*]], <i32 -1, i32 -1, i32 -1, i32 -1>
-; CHECK-NEXT:    [[T1:%.*]] = add <4 x i32> [[T0]], [[Y:%.*]]
-; CHECK-NEXT:    [[T2:%.*]] = add <4 x i32> [[T1]], <i32 1, i32 1, i32 undef, i32 1>
+; CHECK-NEXT:    [[T2:%.*]] = sub <4 x i32> [[Y:%.*]], [[X:%.*]]
 ; CHECK-NEXT:    ret <4 x i32> [[T2]]
 ;
   %t0 = xor <4 x i32> %x, <i32 -1, i32 -1, i32 -1, i32 -1>
@@ -68,9 +60,7 @@
 
 define <4 x i32> @t4_vec_undef2(<4 x i32> %x, <4 x i32> %y) {
 ; CHECK-LABEL: @t4_vec_undef2(
-; CHECK-NEXT:    [[T0:%.*]] = xor <4 x i32> [[X:%.*]], <i32 -1, i32 -1, i32 undef, i32 -1>
-; CHECK-NEXT:    [[T1:%.*]] = add <4 x i32> [[T0]], [[Y:%.*]]
-; CHECK-NEXT:    [[T2:%.*]] = add <4 x i32> [[T1]], <i32 1, i32 1, i32 undef, i32 1>
+; CHECK-NEXT:    [[T2:%.*]] = sub <4 x i32> [[Y:%.*]], [[X:%.*]]
 ; CHECK-NEXT:    ret <4 x i32> [[T2]]
 ;
   %t0 = xor <4 x i32> %x, <i32 -1, i32 -1, i32 undef, i32 -1>
@@ -89,8 +79,7 @@
 ; CHECK-LABEL: @t5(
 ; CHECK-NEXT:    [[T0:%.*]] = xor i32 [[X:%.*]], -1
 ; CHECK-NEXT:    call void @use32(i32 [[T0]])
-; CHECK-NEXT:    [[T1:%.*]] = add i32 [[T0]], [[Y:%.*]]
-; CHECK-NEXT:    [[T2:%.*]] = add i32 [[T1]], 1
+; CHECK-NEXT:    [[T2:%.*]] = sub i32 [[Y:%.*]], [[X]]
 ; CHECK-NEXT:    ret i32 [[T2]]
 ;
   %t0 = xor i32 %x, -1
@@ -105,7 +94,7 @@
 ; CHECK-NEXT:    [[T0:%.*]] = xor i32 [[X:%.*]], -1
 ; CHECK-NEXT:    [[T1:%.*]] = add i32 [[T0]], [[Y:%.*]]
 ; CHECK-NEXT:    call void @use32(i32 [[T1]])
-; CHECK-NEXT:    [[T2:%.*]] = add i32 [[T1]], 1
+; CHECK-NEXT:    [[T2:%.*]] = sub i32 [[Y]], [[X]]
 ; CHECK-NEXT:    ret i32 [[T2]]
 ;
   %t0 = xor i32 %x, -1
@@ -121,7 +110,7 @@
 ; CHECK-NEXT:    call void @use32(i32 [[T0]])
 ; CHECK-NEXT:    [[T1:%.*]] = add i32 [[T0]], [[Y:%.*]]
 ; CHECK-NEXT:    call void @use32(i32 [[T1]])
-; CHECK-NEXT:    [[T2:%.*]] = add i32 [[T1]], 1
+; CHECK-NEXT:    [[T2:%.*]] = sub i32 [[Y]], [[X]]
 ; CHECK-NEXT:    ret i32 [[T2]]
 ;
   %t0 = xor i32 %x, -1
@@ -145,7 +134,7 @@
 ; CHECK-NEXT:    call void @use32(i32 [[T0]])
 ; CHECK-NEXT:    [[T1:%.*]] = add i32 [[Y]], [[T0]]
 ; CHECK-NEXT:    call void @use32(i32 [[T1]])
-; CHECK-NEXT:    [[T2:%.*]] = add i32 [[T1]], 1
+; CHECK-NEXT:    [[T2:%.*]] = sub i32 [[Y]], [[X]]
 ; CHECK-NEXT:    ret i32 [[T2]]
 ;
   %y = call i32 @gen32()