[SECV] Try to push the op into ZExt: A + zext (-A + B) -> zext (B) (llvm#151227)

Try to push the constant operand into a ZExt:
A + zext (-A + B) -> zext (B), if trunc (A) + -A + B does not
unsigned-wrap.

The actual code supports ZExts with arbitrary number of arguments, hence
the getAddExpr in the return.

This helps SCEV reasoning in some cases, commonly when adding an offset
to a zero-extended SCEV that subtracts the same offset.

Note that this is restricted to cases where we can fold away an operand
of the inner Add. This is needed to avoid bad interactions with patterns
when forming ZExts, which try to push to ZExt to add operands.

https://alive2.llvm.org/ce/z/q7d303

PR: llvm#151227

Author: fhahn

llvm/lib/Analysis/ScalarEvolution.cpp

@@ -2682,6 +2682,21 @@ const SCEV *ScalarEvolution::getAddExpr(SmallVectorImpl<const SCEV *> &Ops,
         return getAddExpr(NewOps, PreservedFlags);
       }
     }
+
+    // Try to push the constant operand into a ZExt: A + zext (-A + B) -> zext
+    // (B), if trunc (A) + -A + B  does not unsigned-wrap.
+    if (auto *ZExt = dyn_cast<SCEVZeroExtendExpr>(Ops[1])) {
+      const SCEV *B = ZExt->getOperand(0);
+      const SCEV *NarrowA = getTruncateExpr(A, B->getType());
+      if (isa<SCEVAddExpr>(B) &&
+          NarrowA == getNegativeSCEV(cast<SCEVAddExpr>(B)->getOperand(0)) &&
+          getZeroExtendExpr(NarrowA, ZExt->getType()) == A &&
+          hasFlags(StrengthenNoWrapFlags(this, scAddExpr, {NarrowA, B},
+                                         SCEV::FlagAnyWrap),
+                   SCEV::FlagNUW)) {
+        return getZeroExtendExpr(getAddExpr(NarrowA, B), ZExt->getType());
+      }
+    }
   }
 
   // Canonicalize (-1 * urem X, Y) + X --> (Y * X/Y)

llvm/test/Analysis/ScalarEvolution/zext-add.ll

@@ -17,7 +17,7 @@ define void @test_push_constant_into_zext(ptr %dst, ptr %src, i32 %n, i64 %offse
 ; CHECK-NEXT:    %l = load i8, ptr %outer.ptr, align 1
 ; CHECK-NEXT:    --> %l U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %inner.loop: Variant, %outer.loop: Variant }
 ; CHECK-NEXT:    %ptr.iv.next = getelementptr i8, ptr %ptr.iv, i64 %offset
-; CHECK-NEXT:    --> {(%offset + %src),+,%offset}<%inner.loop> U: full-set S: full-set Exits: (((1 + (zext i32 (-1 + (1 smax %n))<nsw> to i64))<nuw><nsw> * %offset) + %src) LoopDispositions: { %inner.loop: Computable, %outer.loop: Variant }
+; CHECK-NEXT:    --> {(%offset + %src),+,%offset}<%inner.loop> U: full-set S: full-set Exits: (((zext i32 (1 smax %n) to i64) * %offset) + %src) LoopDispositions: { %inner.loop: Computable, %outer.loop: Variant }
 ; CHECK-NEXT:    %iv.next = add i32 %iv, 1
 ; CHECK-NEXT:    --> {1,+,1}<nuw><nsw><%inner.loop> U: [1,-2147483648) S: [1,-2147483648) Exits: (1 smax %n) LoopDispositions: { %inner.loop: Computable, %outer.loop: Variant }
 ; CHECK-NEXT:  Determining loop execution counts for: @test_push_constant_into_zext

llvm/test/Transforms/IndVarSimplify/AArch64/fold-ext-add.ll

@@ -10,21 +10,21 @@ define void @pred_mip_12(ptr %dst, ptr %src, i32 %n, i64 %offset) {
 ; CHECK-SAME: ptr [[DST:%.*]], ptr [[SRC:%.*]], i32 [[N:%.*]], i64 [[OFFSET:%.*]]) {
 ; CHECK-NEXT:  [[ENTRY:.*]]:
 ; CHECK-NEXT:    [[SMAX:%.*]] = call i32 @llvm.smax.i32(i32 [[N]], i32 1)
+; CHECK-NEXT:    [[TMP0:%.*]] = zext nneg i32 [[SMAX]] to i64
+; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[OFFSET]], [[TMP0]]
+; CHECK-NEXT:    [[SCEVGEP:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[TMP1]]
 ; CHECK-NEXT:    br label %[[OUTER_LOOP:.*]]
 ; CHECK:       [[OUTER_LOOP_LOOPEXIT:.*]]:
-; CHECK-NEXT:    [[PTR_IV_NEXT_LCSSA:%.*]] = phi ptr [ [[PTR_IV_NEXT:%.*]], %[[INNER_LOOP:.*]] ]
 ; CHECK-NEXT:    br label %[[OUTER_LOOP]]
 ; CHECK:       [[OUTER_LOOP]]:
-; CHECK-NEXT:    [[OUTER_PTR:%.*]] = phi ptr [ [[SRC]], %[[ENTRY]] ], [ [[PTR_IV_NEXT_LCSSA]], %[[OUTER_LOOP_LOOPEXIT]] ]
+; CHECK-NEXT:    [[OUTER_PTR:%.*]] = phi ptr [ [[SRC]], %[[ENTRY]] ], [ [[SCEVGEP]], %[[OUTER_LOOP_LOOPEXIT]] ]
 ; CHECK-NEXT:    [[C:%.*]] = call i1 @cond()
 ; CHECK-NEXT:    br i1 [[C]], label %[[INNER_LOOP_PREHEADER:.*]], label %[[EXIT:.*]]
 ; CHECK:       [[INNER_LOOP_PREHEADER]]:
-; CHECK-NEXT:    br label %[[INNER_LOOP]]
+; CHECK-NEXT:    br label %[[INNER_LOOP:.*]]
 ; CHECK:       [[INNER_LOOP]]:
 ; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ [[IV_NEXT:%.*]], %[[INNER_LOOP]] ], [ 0, %[[INNER_LOOP_PREHEADER]] ]
-; CHECK-NEXT:    [[PTR_IV:%.*]] = phi ptr [ [[PTR_IV_NEXT]], %[[INNER_LOOP]] ], [ [[SRC]], %[[INNER_LOOP_PREHEADER]] ]
 ; CHECK-NEXT:    [[L:%.*]] = load i8, ptr [[OUTER_PTR]], align 1
-; CHECK-NEXT:    [[PTR_IV_NEXT]] = getelementptr i8, ptr [[PTR_IV]], i64 [[OFFSET]]
 ; CHECK-NEXT:    store i8 [[L]], ptr [[DST]], align 2
 ; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i32 [[IV]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i32 [[IV_NEXT]], [[SMAX]]

llvm/test/Transforms/IndVarSimplify/zext-nuw.ll

@@ -15,11 +15,9 @@ define void @_Z3fn1v() {
 ; CHECK-NEXT:    [[J_SROA_0_0_COPYLOAD:%.*]] = load i8, ptr [[X5]], align 1
 ; CHECK-NEXT:    br label [[DOTPREHEADER4_LR_PH:%.*]]
 ; CHECK:       .preheader4.lr.ph:
-; CHECK-NEXT:    [[TMP1:%.*]] = add nsw i32 [[X4]], -1
-; CHECK-NEXT:    [[TMP2:%.*]] = zext nneg i32 [[TMP1]] to i64
-; CHECK-NEXT:    [[TMP3:%.*]] = add nuw nsw i64 [[TMP2]], 1
 ; CHECK-NEXT:    [[TMP4:%.*]] = sext i8 [[J_SROA_0_0_COPYLOAD]] to i64
-; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP3]], [[TMP4]]
+; CHECK-NEXT:    [[TMP2:%.*]] = zext nneg i32 [[X4]] to i64
+; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], [[TMP2]]
 ; CHECK-NEXT:    br label [[DOTPREHEADER4:%.*]]
 ; CHECK:       .preheader4:
 ; CHECK-NEXT:    [[K_09:%.*]] = phi ptr [ undef, [[DOTPREHEADER4_LR_PH]] ], [ [[X25:%.*]], [[X22:%.*]] ]