[SCEV] Fold ((-1 * C1) * D / C1) -> -1 * D. (#157555)

Treat negative constants C as -1 * abs(C1) when folding multiplies and
udivs.

Alive2 Proof: https://alive2.llvm.org/ce/z/bdj9W2

PR: #157555

Author: fhahn

llvm/lib/Analysis/ScalarEvolution.cpp

@@ -3217,15 +3217,19 @@ const SCEV *ScalarEvolution::getMulExpr(SmallVectorImpl<const SCEV *> &Ops,
       }
 
       // Try to fold (C1 * D /u C2) -> C1/C2 * D, if C1 and C2 are powers-of-2,
-      // D is a multiple of C2, and C1 is a multiple of C1.
+      // D is a multiple of C2, and C1 is a multiple of C2.
       const SCEV *D;
+      APInt C1V = LHSC->getAPInt();
+      // (C1 * D /u C2) == -1 * -C1 * D /u C2 when C1 != INT_MIN.
+      if (C1V.isNegative() && !C1V.isMinSignedValue())
+        C1V = C1V.abs();
       const SCEVConstant *C2;
-      const APInt &LHSV = LHSC->getAPInt();
-      if (LHSV.isPowerOf2() &&
+      if (C1V.isPowerOf2() &&
           match(Ops[1], m_scev_UDiv(m_SCEV(D), m_SCEVConstant(C2))) &&
-          C2->getAPInt().isPowerOf2() && LHSV.uge(C2->getAPInt()) &&
-          LHSV.logBase2() <= getMinTrailingZeros(D)) {
-        return getMulExpr(getUDivExpr(LHSC, C2), D);
+          C2->getAPInt().isPowerOf2() && C1V.uge(C2->getAPInt()) &&
+          C1V.logBase2() <= getMinTrailingZeros(D)) {
+        const SCEV *NewMul = getMulExpr(getUDivExpr(getConstant(C1V), C2), D);
+        return C1V == LHSC->getAPInt() ? NewMul : getNegativeSCEV(NewMul);
       }
     }
   }

llvm/test/Analysis/ScalarEvolution/mul-udiv-folds.ll

@@ -23,7 +23,7 @@ define void @udiv4_and_udiv2(i1 %c, ptr %A) {
 ; CHECK-NEXT:    %gep.16 = getelementptr i16, ptr %A, i64 %iv
 ; CHECK-NEXT:    --> {((2 * ((zext i32 %start to i64) /u 4))<nuw><nsw> + %A),+,2}<%loop> U: full-set S: full-set Exits: ((zext i32 %start to i64) + %A) LoopDispositions: { %loop: Computable }
 ; CHECK-NEXT:    %gep.32 = getelementptr i32, ptr %A, i64 %iv
-; CHECK-NEXT:    --> {((zext i32 %start to i64) + %A),+,4}<%loop> U: full-set S: full-set Exits: ((3 * (zext i32 %start to i64))<nuw><nsw> + (-4 * ((zext i32 %start to i64) /u 4))<nsw> + %A) LoopDispositions: { %loop: Computable }
+; CHECK-NEXT:    --> {((zext i32 %start to i64) + %A),+,4}<%loop> U: full-set S: full-set Exits: ((2 * (zext i32 %start to i64))<nuw><nsw> + %A) LoopDispositions: { %loop: Computable }
 ; CHECK-NEXT:    %gep.40 = getelementptr <{ i32, i8 }>, ptr %A, i64 %iv
 ; CHECK-NEXT:    --> {((5 * ((zext i32 %start to i64) /u 4))<nuw><nsw> + %A),+,5}<%loop> U: full-set S: full-set Exits: ((5 * ((zext i32 %start to i64) /u 2))<nuw><nsw> + %A) LoopDispositions: { %loop: Computable }
 ; CHECK-NEXT:    %gep.48 = getelementptr <{ i32, i16 }>, ptr %A, i64 %iv