From: Sanjay Patel <spatel@rotateright.com>
Date: Tue, 20 Jun 2017 12:40:55 +0000 (+0000)
Subject: [InstCombine] try to canonicalize xor-of-icmps to and-of-icmps
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=3e4188dc6c50447f583a61e4474778e1faf800b9;p=llvm

[InstCombine] try to canonicalize xor-of-icmps to and-of-icmps

We have a large portfolio of folds for and-of-icmps and or-of-icmps in InstSimplify and InstCombine,
but hardly anything for xor-of-icmps. Rather than trying to rethink and translate all of those folds,
we can use the truth table definition of xor:

X ^ Y --> (X | Y) & !(X & Y)

...to see if we can convert the xor to and/or and then use the existing folds.

http://rise4fun.com/Alive/J9v

Differential Revision: https://reviews.llvm.org/D33342


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@305792 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp b/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp
index 62898b06ede..3407cbeb404 100644
--- a/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp
+++ b/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp
@@ -2351,6 +2351,30 @@ Value *InstCombiner::foldXorOfICmps(ICmpInst *LHS, ICmpInst *RHS) {
     }
   }
 
+  // Instead of trying to imitate the folds for and/or, decompose this 'xor'
+  // into those logic ops. That is, try to turn this into an and-of-icmps
+  // because we have many folds for that pattern.
+  //
+  // This is based on a truth table definition of xor:
+  // X ^ Y --> (X | Y) & !(X & Y)
+  if (Value *OrICmp = SimplifyBinOp(Instruction::Or, LHS, RHS, SQ)) {
+    // TODO: If OrICmp is true, then the definition of xor simplifies to !(X&Y).
+    // TODO: If OrICmp is false, the whole thing is false (InstSimplify?).
+    if (Value *AndICmp = SimplifyBinOp(Instruction::And, LHS, RHS, SQ)) {
+      // TODO: Independently handle cases where the 'and' side is a constant.
+      if (OrICmp == LHS && AndICmp == RHS && RHS->hasOneUse()) {
+        // (LHS | RHS) & !(LHS & RHS) --> LHS & !RHS
+        RHS->setPredicate(RHS->getInversePredicate());
+        return Builder->CreateAnd(LHS, RHS);
+      }
+      if (OrICmp == RHS && AndICmp == LHS && LHS->hasOneUse()) {
+        // !(LHS & RHS) & (LHS | RHS) --> !LHS & !RHS
+        LHS->setPredicate(LHS->getInversePredicate());
+        return Builder->CreateAnd(LHS, RHS);
+      }
+    }
+  }
+
   return nullptr;
 }
 
diff --git a/test/Transforms/InstCombine/set.ll b/test/Transforms/InstCombine/set.ll
index db2b4c3558e..1452015d2ef 100644
--- a/test/Transforms/InstCombine/set.ll
+++ b/test/Transforms/InstCombine/set.ll
@@ -164,10 +164,8 @@ define i1 @bool_eq0(i64 %a) {
 
 define i1 @xor_of_icmps(i64 %a) {
 ; CHECK-LABEL: @xor_of_icmps(
-; CHECK-NEXT:    [[B:%.*]] = icmp sgt i64 %a, 0
-; CHECK-NEXT:    [[C:%.*]] = icmp eq i64 %a, 1
-; CHECK-NEXT:    [[XOR:%.*]] = xor i1 [[C]], [[B]]
-; CHECK-NEXT:    ret i1 [[XOR]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp sgt i64 %a, 1
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %b = icmp sgt i64 %a, 0
   %c = icmp eq i64 %a, 1
@@ -179,10 +177,8 @@ define i1 @xor_of_icmps(i64 %a) {
 
 define i1 @xor_of_icmps_commute(i64 %a) {
 ; CHECK-LABEL: @xor_of_icmps_commute(
-; CHECK-NEXT:    [[B:%.*]] = icmp sgt i64 %a, 0
-; CHECK-NEXT:    [[C:%.*]] = icmp eq i64 %a, 1
-; CHECK-NEXT:    [[XOR:%.*]] = xor i1 [[B]], [[C]]
-; CHECK-NEXT:    ret i1 [[XOR]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp sgt i64 %a, 1
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %b = icmp sgt i64 %a, 0
   %c = icmp eq i64 %a, 1
@@ -209,10 +205,10 @@ define i1 @xor_of_icmps_folds_more(i64 %a) {
 
 define i32 @PR2844(i32 %x) {
 ; CHECK-LABEL: @PR2844(
-; CHECK-NEXT:    [[A:%.*]] = icmp eq i32 %x, 0
+; CHECK-NEXT:    [[A:%.*]] = icmp ne i32 %x, 0
 ; CHECK-NEXT:    [[B:%.*]] = icmp sgt i32 %x, -638208502
-; CHECK-NEXT:    [[NOT_OR:%.*]] = xor i1 [[A]], [[B]]
-; CHECK-NEXT:    [[SEL:%.*]] = zext i1 [[NOT_OR]] to i32
+; CHECK-NEXT:    [[TMP1:%.*]] = and i1 [[A]], [[B]]
+; CHECK-NEXT:    [[SEL:%.*]] = zext i1 [[TMP1]] to i32
 ; CHECK-NEXT:    ret i32 [[SEL]]
 ;
   %A = icmp eq i32 %x, 0