[InstCombine] canonicalize more unsigned saturated add with 'not'

Yet another pattern variation suggested by:
https://bugs.llvm.org/show_bug.cgi?id=14613

There are 8 more potential commuted patterns here on top of the
8 that were already handled (rL354221, rL354276, rL354393).
We have the obvious commute of the 'add' + commute of the cmp
predicate/operands (ugt/ult) + commute of the select operands:

Name: base
%notx = xor i32 %x, -1
%a = add i32 %notx, %y
%c = icmp ult i32 %x, %y
%r = select i1 %c, i32 -1, i32 %a
=>
%c2 = icmp ult i32 %a, %y
%r = select i1 %c2, i32 -1, i32 %a

Name: ugt
%notx = xor i32 %x, -1
%a = add i32 %notx, %y
%c = icmp ugt i32 %y, %x
%r = select i1 %c, i32 -1, i32 %a
=>
%c2 = icmp ult i32 %a, %y
%r = select i1 %c2, i32 -1, i32 %a

Name: commute select
%notx = xor i32 %x, -1
%a = add i32 %notx, %y
%c = icmp ult i32 %y, %x
%r = select i1 %c, i32 %a, i32 -1
=>
%c2 = icmp ult i32 %a, %y
%r = select i1 %c2, i32 -1, i32 %a

Name: ugt + commute select
%notx = xor i32 %x, -1
%a = add i32 %notx, %y
%c = icmp ugt i32 %x, %y
%r = select i1 %c, i32 %a, i32 -1
=>
%c2 = icmp ult i32 %a, %y
%r = select i1 %c2, i32 -1, i32 %a

https://rise4fun.com/Alive/den

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@354887 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/InstCombine/InstCombineSelect.cpp b/lib/Transforms/InstCombine/InstCombineSelect.cpp
index d153c848d38282b87ddea9a7c95ca13e6ab0dbfa..79835ef9316019f11545df4fe436765896a419a4 100644 (file)
--- a/lib/Transforms/InstCombine/InstCombineSelect.cpp
+++ b/lib/Transforms/InstCombine/InstCombineSelect.cpp
@@ -725,6 +725,17 @@ static Value *canonicalizeSaturatedAdd(ICmpInst *Cmp, Value *TVal, Value *FVal,
     Value *NewCmp = Builder.CreateICmp(ICmpInst::ICMP_ULT, FVal, Y);
     return Builder.CreateSelect(NewCmp, TVal, FVal);
   }
+  // The 'not' op may be included in the sum but not the compare.
+  X = Cmp0;
+  Y = Cmp1;
+  if (match(FVal, m_c_Add(m_Not(m_Specific(X)), m_Specific(Y)))) {
+    // Change the comparison to use the sum (false value of the select). That is
+    // a canonical pattern match form for uadd.with.overflow:
+    // (X u< Y) ? -1 : (~X + Y) --> ((~X + Y) u< Y) ? -1 : (~X + Y)
+    // (X u< Y) ? -1 : (Y + ~X) --> ((Y + ~X) u< Y) ? -1 : (Y + ~X)
+    Value *NewCmp = Builder.CreateICmp(ICmpInst::ICMP_ULT, FVal, Y);
+    return Builder.CreateSelect(NewCmp, TVal, FVal);
+  }
 
   return nullptr;
 }

diff --git a/test/Transforms/InstCombine/saturating-add-sub.ll b/test/Transforms/InstCombine/saturating-add-sub.ll
index 8e171485514e930666793ab408fd3073209302f4..5c88ef3974632d584f0fc62e341b603755e13fd0 100644 (file)
--- a/test/Transforms/InstCombine/saturating-add-sub.ll
+++ b/test/Transforms/InstCombine/saturating-add-sub.ll
@@ -803,9 +803,9 @@ define i32 @uadd_sat_not(i32 %x, i32 %y) {
 ; CHECK-LABEL: @uadd_sat_not(
 ; CHECK-NEXT:    [[NOTX:%.*]] = xor i32 [[X:%.*]], -1
 ; CHECK-NEXT:    [[A:%.*]] = add i32 [[NOTX]], [[Y:%.*]]
-; CHECK-NEXT:    [[C:%.*]] = icmp ult i32 [[X]], [[Y]]
-; CHECK-NEXT:    [[R:%.*]] = select i1 [[C]], i32 -1, i32 [[A]]
-; CHECK-NEXT:    ret i32 [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ult i32 [[A]], [[Y]]
+; CHECK-NEXT:    [[TMP2:%.*]] = select i1 [[TMP1]], i32 -1, i32 [[A]]
+; CHECK-NEXT:    ret i32 [[TMP2]]
 ;
   %notx = xor i32 %x, -1
   %a = add i32 %notx, %y
@@ -820,9 +820,9 @@ define i32 @uadd_sat_not_commute_add(i32 %xp, i32 %yp) {
 ; CHECK-NEXT:    [[Y:%.*]] = urem i32 42, [[YP:%.*]]
 ; CHECK-NEXT:    [[NOTX:%.*]] = xor i32 [[X]], -1
 ; CHECK-NEXT:    [[A:%.*]] = add nsw i32 [[Y]], [[NOTX]]
-; CHECK-NEXT:    [[C:%.*]] = icmp ult i32 [[X]], [[Y]]
-; CHECK-NEXT:    [[R:%.*]] = select i1 [[C]], i32 -1, i32 [[A]]
-; CHECK-NEXT:    ret i32 [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ult i32 [[A]], [[Y]]
+; CHECK-NEXT:    [[TMP2:%.*]] = select i1 [[TMP1]], i32 -1, i32 [[A]]
+; CHECK-NEXT:    ret i32 [[TMP2]]
 ;
   %x = srem i32 42, %xp ; thwart complexity-based-canonicalization
   %y = urem i32 42, %yp ; thwart complexity-based-canonicalization
@@ -837,9 +837,9 @@ define i32 @uadd_sat_not_ugt(i32 %x, i32 %y) {
 ; CHECK-LABEL: @uadd_sat_not_ugt(
 ; CHECK-NEXT:    [[NOTX:%.*]] = xor i32 [[X:%.*]], -1
 ; CHECK-NEXT:    [[A:%.*]] = add i32 [[NOTX]], [[Y:%.*]]
-; CHECK-NEXT:    [[C:%.*]] = icmp ugt i32 [[Y]], [[X]]
-; CHECK-NEXT:    [[R:%.*]] = select i1 [[C]], i32 -1, i32 [[A]]
-; CHECK-NEXT:    ret i32 [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ult i32 [[A]], [[Y]]
+; CHECK-NEXT:    [[TMP2:%.*]] = select i1 [[TMP1]], i32 -1, i32 [[A]]
+; CHECK-NEXT:    ret i32 [[TMP2]]
 ;
   %notx = xor i32 %x, -1
   %a = add i32 %notx, %y
@@ -853,9 +853,9 @@ define <2 x i32> @uadd_sat_not_ugt_commute_add(<2 x i32> %x, <2 x i32> %yp) {
 ; CHECK-NEXT:    [[Y:%.*]] = sdiv <2 x i32> [[YP:%.*]], <i32 2442, i32 4242>
 ; CHECK-NEXT:    [[NOTX:%.*]] = xor <2 x i32> [[X:%.*]], <i32 -1, i32 -1>
 ; CHECK-NEXT:    [[A:%.*]] = add <2 x i32> [[Y]], [[NOTX]]
-; CHECK-NEXT:    [[C:%.*]] = icmp ugt <2 x i32> [[Y]], [[X]]
-; CHECK-NEXT:    [[R:%.*]] = select <2 x i1> [[C]], <2 x i32> <i32 -1, i32 -1>, <2 x i32> [[A]]
-; CHECK-NEXT:    ret <2 x i32> [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ult <2 x i32> [[A]], [[Y]]
+; CHECK-NEXT:    [[TMP2:%.*]] = select <2 x i1> [[TMP1]], <2 x i32> <i32 -1, i32 -1>, <2 x i32> [[A]]
+; CHECK-NEXT:    ret <2 x i32> [[TMP2]]
 ;
   %y = sdiv <2 x i32> %yp, <i32 2442, i32 4242> ; thwart complexity-based-canonicalization
   %notx = xor <2 x i32> %x, <i32 -1, i32 -1>
@@ -869,9 +869,9 @@ define i32 @uadd_sat_not_commute_select(i32 %x, i32 %y) {
 ; CHECK-LABEL: @uadd_sat_not_commute_select(
 ; CHECK-NEXT:    [[NOTX:%.*]] = xor i32 [[X:%.*]], -1
 ; CHECK-NEXT:    [[A:%.*]] = add i32 [[NOTX]], [[Y:%.*]]
-; CHECK-NEXT:    [[C:%.*]] = icmp ult i32 [[Y]], [[X]]
-; CHECK-NEXT:    [[R:%.*]] = select i1 [[C]], i32 [[A]], i32 -1
-; CHECK-NEXT:    ret i32 [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ult i32 [[A]], [[Y]]
+; CHECK-NEXT:    [[TMP2:%.*]] = select i1 [[TMP1]], i32 -1, i32 [[A]]
+; CHECK-NEXT:    ret i32 [[TMP2]]
 ;
   %notx = xor i32 %x, -1
   %a = add i32 %notx, %y
@@ -885,9 +885,9 @@ define i32 @uadd_sat_not_commute_select_commute_add(i32 %x, i32 %yp) {
 ; CHECK-NEXT:    [[Y:%.*]] = sdiv i32 42, [[YP:%.*]]
 ; CHECK-NEXT:    [[NOTX:%.*]] = xor i32 [[X:%.*]], -1
 ; CHECK-NEXT:    [[A:%.*]] = add i32 [[Y]], [[NOTX]]
-; CHECK-NEXT:    [[C:%.*]] = icmp ult i32 [[Y]], [[X]]
-; CHECK-NEXT:    [[R:%.*]] = select i1 [[C]], i32 [[A]], i32 -1
-; CHECK-NEXT:    ret i32 [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ult i32 [[A]], [[Y]]
+; CHECK-NEXT:    [[TMP2:%.*]] = select i1 [[TMP1]], i32 -1, i32 [[A]]
+; CHECK-NEXT:    ret i32 [[TMP2]]
 ;
   %y = sdiv i32 42, %yp ; thwart complexity-based-canonicalization
   %notx = xor i32 %x, -1
@@ -903,9 +903,9 @@ define <2 x i32> @uadd_sat_not_commute_select_ugt(<2 x i32> %xp, <2 x i32> %yp)
 ; CHECK-NEXT:    [[Y:%.*]] = srem <2 x i32> <i32 12, i32 412>, [[YP:%.*]]
 ; CHECK-NEXT:    [[NOTX:%.*]] = xor <2 x i32> [[X]], <i32 -1, i32 -1>
 ; CHECK-NEXT:    [[A:%.*]] = add <2 x i32> [[Y]], [[NOTX]]
-; CHECK-NEXT:    [[C:%.*]] = icmp ugt <2 x i32> [[X]], [[Y]]
-; CHECK-NEXT:    [[R:%.*]] = select <2 x i1> [[C]], <2 x i32> [[A]], <2 x i32> <i32 -1, i32 -1>
-; CHECK-NEXT:    ret <2 x i32> [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ult <2 x i32> [[A]], [[Y]]
+; CHECK-NEXT:    [[TMP2:%.*]] = select <2 x i1> [[TMP1]], <2 x i32> <i32 -1, i32 -1>, <2 x i32> [[A]]
+; CHECK-NEXT:    ret <2 x i32> [[TMP2]]
 ;
   %x = urem <2 x i32> <i32 42, i32 -42>, %xp ; thwart complexity-based-canonicalization
   %y = srem <2 x i32> <i32 12, i32 412>, %yp ; thwart complexity-based-canonicalization
@@ -920,9 +920,9 @@ define i32 @uadd_sat_not_commute_select_ugt_commute_add(i32 %x, i32 %y) {
 ; CHECK-LABEL: @uadd_sat_not_commute_select_ugt_commute_add(
 ; CHECK-NEXT:    [[NOTX:%.*]] = xor i32 [[X:%.*]], -1
 ; CHECK-NEXT:    [[A:%.*]] = add i32 [[NOTX]], [[Y:%.*]]
-; CHECK-NEXT:    [[C:%.*]] = icmp ugt i32 [[X]], [[Y]]
-; CHECK-NEXT:    [[R:%.*]] = select i1 [[C]], i32 [[A]], i32 -1
-; CHECK-NEXT:    ret i32 [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ult i32 [[A]], [[Y]]
+; CHECK-NEXT:    [[TMP2:%.*]] = select i1 [[TMP1]], i32 -1, i32 [[A]]
+; CHECK-NEXT:    ret i32 [[TMP2]]
 ;
   %notx = xor i32 %x, -1
   %a = add i32 %notx, %y