[llvm] a3fd060 - [InstCombine] Add transforms for `(icmp {u|s}ge/le (xor X, Y), X)`

[Noah Goldstein via llvm-commits]

Author: Noah Goldstein
Date: 2023-04-17T22:39:06-05:00
New Revision: a3fd060d4223c6a7470554561bc479d4b8e423f4

URL: https://github.com/llvm/llvm-project/commit/a3fd060d4223c6a7470554561bc479d4b8e423f4
DIFF: https://github.com/llvm/llvm-project/commit/a3fd060d4223c6a7470554561bc479d4b8e423f4.diff

LOG: [InstCombine] Add transforms for `(icmp {u|s}ge/le (xor X, Y), X)`

If Y is non-zero we can simplify the ge/le -> gt/lt

`(X ^ Y_NonZero) u>= X` --> `(X ^ Y_NonZero) u> X`
    - https://alive2.llvm.org/ce/z/k482NQ
`(X ^ Y_NonZero) u<= X` --> `(X ^ Y_NonZero) u< X`
    - https://alive2.llvm.org/ce/z/TuUDGy
`(X ^ Y_NonZero) s>= X` --> `(X ^ Y_NonZero) s> X`
    - https://alive2.llvm.org/ce/z/vXQypR
`(X ^ Y_NonZero) s<= X` --> `(X ^ Y_NonZero) s< X    `
    - https://alive2.llvm.org/ce/z/fbUq-z

Reviewed By: spatel

Differential Revision: https://reviews.llvm.org/D144608

Added: 
    

Modified: 
    llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
    llvm/test/Transforms/InstCombine/icmp-of-xor-x.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
index 5c2f65eca28f6..bd3000ada1f38 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
@@ -4153,6 +4153,30 @@ static Instruction *foldICmpXNegX(ICmpInst &I,
   return nullptr;
 }
 
+static Instruction *foldICmpXorXX(ICmpInst &I, const SimplifyQuery &Q,
+                                  InstCombinerImpl &IC) {
+  Value *Op0 = I.getOperand(0), *Op1 = I.getOperand(1), *A;
+  // Normalize xor operand as operand 0.
+  CmpInst::Predicate Pred = I.getPredicate();
+  if (match(Op1, m_c_Xor(m_Specific(Op0), m_Value()))) {
+    std::swap(Op0, Op1);
+    Pred = ICmpInst::getSwappedPredicate(Pred);
+  }
+  if (!match(Op0, m_c_Xor(m_Specific(Op1), m_Value(A))))
+    return nullptr;
+
+  // icmp (X ^ Y_NonZero) u>= X --> icmp (X ^ Y_NonZero) u> X
+  // icmp (X ^ Y_NonZero) u<= X --> icmp (X ^ Y_NonZero) u< X
+  // icmp (X ^ Y_NonZero) s>= X --> icmp (X ^ Y_NonZero) s> X
+  // icmp (X ^ Y_NonZero) s<= X --> icmp (X ^ Y_NonZero) s< X
+  CmpInst::Predicate PredOut = CmpInst::getStrictPredicate(Pred);
+  if (PredOut != Pred &&
+      isKnownNonZero(A, Q.DL, /*Depth=*/0, Q.AC, Q.CxtI, Q.DT))
+    return new ICmpInst(PredOut, Op0, Op1);
+
+  return nullptr;
+}
+
 /// Try to fold icmp (binop), X or icmp X, (binop).
 /// TODO: A large part of this logic is duplicated in InstSimplify's
 /// simplifyICmpWithBinOp(). We should be able to share that and avoid the code
@@ -4449,6 +4473,9 @@ Instruction *InstCombinerImpl::foldICmpBinOp(ICmpInst &I,
                               ConstantExpr::getNeg(RHSC));
   }
 
+  if (Instruction * R = foldICmpXorXX(I, Q, *this))
+    return R;
+
   {
     // Try to remove shared multiplier from comparison:
     // X * Z u{lt/le/gt/ge}/eq/ne Y * Z

diff  --git a/llvm/test/Transforms/InstCombine/icmp-of-xor-x.ll b/llvm/test/Transforms/InstCombine/icmp-of-xor-x.ll
index c6d23504f04e2..9b6572697cf5e 100644
--- a/llvm/test/Transforms/InstCombine/icmp-of-xor-x.ll
+++ b/llvm/test/Transforms/InstCombine/icmp-of-xor-x.ll
@@ -9,7 +9,7 @@ define i1 @xor_uge(i8 %x, i8 %y) {
 ; CHECK-NEXT:    [[YNZ:%.*]] = icmp ne i8 [[Y:%.*]], 0
 ; CHECK-NEXT:    call void @llvm.assume(i1 [[YNZ]])
 ; CHECK-NEXT:    [[XOR:%.*]] = xor i8 [[X:%.*]], [[Y]]
-; CHECK-NEXT:    [[R:%.*]] = icmp uge i8 [[XOR]], [[X]]
+; CHECK-NEXT:    [[R:%.*]] = icmp ugt i8 [[XOR]], [[X]]
 ; CHECK-NEXT:    ret i1 [[R]]
 ;
   %ynz = icmp ne i8 %y, 0
@@ -34,7 +34,7 @@ define <2 x i1> @xor_ule_2(<2 x i8> %x, <2 x i8> %yy) {
 ; CHECK-LABEL: @xor_ule_2(
 ; CHECK-NEXT:    [[Y:%.*]] = or <2 x i8> [[YY:%.*]], <i8 9, i8 8>
 ; CHECK-NEXT:    [[XOR:%.*]] = xor <2 x i8> [[Y]], [[X:%.*]]
-; CHECK-NEXT:    [[R:%.*]] = icmp ule <2 x i8> [[XOR]], [[X]]
+; CHECK-NEXT:    [[R:%.*]] = icmp ult <2 x i8> [[XOR]], [[X]]
 ; CHECK-NEXT:    ret <2 x i1> [[R]]
 ;
   %y = or <2 x i8> %yy, <i8 9, i8 8>
@@ -49,7 +49,7 @@ define i1 @xor_sle_2(i8 %xx, i8 %y, i8 %z) {
 ; CHECK-NEXT:    [[YNZ:%.*]] = icmp ne i8 [[Y:%.*]], 0
 ; CHECK-NEXT:    call void @llvm.assume(i1 [[YNZ]])
 ; CHECK-NEXT:    [[XOR:%.*]] = xor i8 [[X]], [[Y]]
-; CHECK-NEXT:    [[R:%.*]] = icmp sle i8 [[X]], [[XOR]]
+; CHECK-NEXT:    [[R:%.*]] = icmp sgt i8 [[XOR]], [[X]]
 ; CHECK-NEXT:    ret i1 [[R]]
 ;
   %x = add i8 %xx, %z
@@ -65,7 +65,7 @@ define i1 @xor_sge(i8 %xx, i8 %yy) {
 ; CHECK-NEXT:    [[X:%.*]] = mul i8 [[XX:%.*]], [[XX]]
 ; CHECK-NEXT:    [[Y:%.*]] = or i8 [[YY:%.*]], -128
 ; CHECK-NEXT:    [[XOR:%.*]] = xor i8 [[Y]], [[X]]
-; CHECK-NEXT:    [[R:%.*]] = icmp sge i8 [[X]], [[XOR]]
+; CHECK-NEXT:    [[R:%.*]] = icmp slt i8 [[XOR]], [[X]]
 ; CHECK-NEXT:    ret i1 [[R]]
 ;
   %x = mul i8 %xx, %xx