[SCEV] Use getConstantMultiple in to get divisibility info from guards. (llvm#162617)

Simplify and generalize the code to get a common constant multiple for
expressions when collecting guards, replacing the manual implementation.

Split off from llvm#160012.

PR: llvm#162617
(cherry picked from commit 6d905e4)

Author: fhahn

llvm/lib/Analysis/ScalarEvolution.cpp

@@ -15683,51 +15683,11 @@ void ScalarEvolution::LoopGuards::collectFromBlock(
       return RewriteMap.lookup_or(S, S);
     };
 
-    // Check for the SCEV expression (A /u B) * B while B is a constant, inside
-    // \p Expr. The check is done recuresively on \p Expr, which is assumed to
-    // be a composition of Min/Max SCEVs. Return whether the SCEV expression (A
-    // /u B) * B was found, and return the divisor B in \p DividesBy. For
-    // example, if Expr = umin (umax ((A /u 8) * 8, 16), 64), return true since
-    // (A /u 8) * 8 matched the pattern, and return the constant SCEV 8 in \p
-    // DividesBy.
-    std::function<bool(const SCEV *, const SCEV *&)> HasDivisibiltyInfo =
-        [&](const SCEV *Expr, const SCEV *&DividesBy) {
-          if (auto *Mul = dyn_cast<SCEVMulExpr>(Expr)) {
-            if (Mul->getNumOperands() != 2)
-              return false;
-            auto *MulLHS = Mul->getOperand(0);
-            auto *MulRHS = Mul->getOperand(1);
-            if (isa<SCEVConstant>(MulLHS))
-              std::swap(MulLHS, MulRHS);
-            if (auto *Div = dyn_cast<SCEVUDivExpr>(MulLHS))
-              if (Div->getOperand(1) == MulRHS) {
-                DividesBy = MulRHS;
-                return true;
-              }
-          }
-          if (auto *MinMax = dyn_cast<SCEVMinMaxExpr>(Expr))
-            return HasDivisibiltyInfo(MinMax->getOperand(0), DividesBy) ||
-                   HasDivisibiltyInfo(MinMax->getOperand(1), DividesBy);
-          return false;
-        };
-
-    // Return true if Expr known to divide by \p DividesBy.
-    std::function<bool(const SCEV *, const SCEV *&)> IsKnownToDivideBy =
-        [&](const SCEV *Expr, const SCEV *DividesBy) {
-          if (SE.getURemExpr(Expr, DividesBy)->isZero())
-            return true;
-          if (auto *MinMax = dyn_cast<SCEVMinMaxExpr>(Expr))
-            return IsKnownToDivideBy(MinMax->getOperand(0), DividesBy) &&
-                   IsKnownToDivideBy(MinMax->getOperand(1), DividesBy);
-          return false;
-        };
-
     const SCEV *RewrittenLHS = GetMaybeRewritten(LHS);
     const SCEV *DividesBy = nullptr;
-    if (HasDivisibiltyInfo(RewrittenLHS, DividesBy))
-      // Check that the whole expression is divided by DividesBy
-      DividesBy =
-          IsKnownToDivideBy(RewrittenLHS, DividesBy) ? DividesBy : nullptr;
+    const APInt &Multiple = SE.getConstantMultiple(RewrittenLHS);
+    if (!Multiple.isOne())
+      DividesBy = SE.getConstant(Multiple);
 
     // Collect rewrites for LHS and its transitive operands based on the
     // condition.

llvm/test/Analysis/ScalarEvolution/trip-count-minmax.ll

@@ -61,7 +61,7 @@ define void @umin(i32 noundef %a, i32 noundef %b) {
 ; CHECK-NEXT:  Loop %for.body: backedge-taken count is (-1 + ((2 * %a) umin (4 * %b)))
 ; CHECK-NEXT:  Loop %for.body: constant max backedge-taken count is i32 2147483646
 ; CHECK-NEXT:  Loop %for.body: symbolic max backedge-taken count is (-1 + ((2 * %a) umin (4 * %b)))
-; CHECK-NEXT:  Loop %for.body: Trip multiple is 1
+; CHECK-NEXT:  Loop %for.body: Trip multiple is 2
 ;
 ; void umin(unsigned a, unsigned b) {
 ;   a *= 2;
@@ -157,7 +157,7 @@ define void @smin(i32 noundef %a, i32 noundef %b) {
 ; CHECK-NEXT:  Loop %for.body: backedge-taken count is (-1 + ((2 * %a)<nsw> smin (4 * %b)<nsw>))
 ; CHECK-NEXT:  Loop %for.body: constant max backedge-taken count is i32 2147483646
 ; CHECK-NEXT:  Loop %for.body: symbolic max backedge-taken count is (-1 + ((2 * %a)<nsw> smin (4 * %b)<nsw>))
-; CHECK-NEXT:  Loop %for.body: Trip multiple is 1
+; CHECK-NEXT:  Loop %for.body: Trip multiple is 2
 ;
 ; void smin(signed a, signed b) {
 ;   a *= 2;

llvm/test/Transforms/LoopVectorize/single_early_exit.ll

@@ -594,19 +594,50 @@ define i64 @loop_guards_needed_to_prove_deref_multiple(i32 %x, i1 %c, ptr derefe
 ; CHECK-NEXT:    call void @llvm.assume(i1 [[PRE_2]])
 ; CHECK-NEXT:    [[N:%.*]] = add i32 [[SEL]], -1
 ; CHECK-NEXT:    [[N_EXT:%.*]] = zext i32 [[N]] to i64
+; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[SEL]], -2
+; CHECK-NEXT:    [[TMP1:%.*]] = zext i32 [[TMP0]] to i64
+; CHECK-NEXT:    [[TMP2:%.*]] = add nuw nsw i64 [[TMP1]], 2
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP2]], 4
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK:       vector.ph:
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP2]], 4
+; CHECK-NEXT:    [[IV_NEXT:%.*]] = sub i64 [[TMP2]], [[N_MOD_VF]]
 ; CHECK-NEXT:    br label [[LOOP_HEADER:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[LOOP_HEADER]] ]
+; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[INDEX]]
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i8>, ptr [[TMP3]], align 1
+; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq <4 x i8> [[WIDE_LOAD]], zeroinitializer
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
+; CHECK-NEXT:    [[TMP5:%.*]] = freeze <4 x i1> [[TMP4]]
+; CHECK-NEXT:    [[TMP6:%.*]] = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> [[TMP5]])
+; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[IV_NEXT]]
+; CHECK-NEXT:    [[TMP8:%.*]] = or i1 [[TMP6]], [[TMP7]]
+; CHECK-NEXT:    br i1 [[TMP8]], label [[MIDDLE_SPLIT:%.*]], label [[LOOP_HEADER]], !llvm.loop [[LOOP11:![0-9]+]]
+; CHECK:       middle.split:
+; CHECK-NEXT:    br i1 [[TMP6]], label [[VECTOR_EARLY_EXIT:%.*]], label [[LOOP_LATCH:%.*]]
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP2]], [[IV_NEXT]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT_LOOPEXIT:%.*]], label [[SCALAR_PH]]
+; CHECK:       vector.early.exit:
+; CHECK-NEXT:    [[TMP9:%.*]] = call i64 @llvm.experimental.cttz.elts.i64.v4i1(<4 x i1> [[TMP4]], i1 true)
+; CHECK-NEXT:    [[TMP10:%.*]] = add i64 [[INDEX]], [[TMP9]]
+; CHECK-NEXT:    br label [[EXIT_LOOPEXIT]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[IV_NEXT]], [[LOOP_LATCH]] ], [ 0, [[PH]] ]
+; CHECK-NEXT:    br label [[LOOP_HEADER1:%.*]]
 ; CHECK:       loop.header:
-; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], [[LOOP_LATCH:%.*]] ], [ 0, [[PH]] ]
-; CHECK-NEXT:    [[GEP_SRC_I:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[IV]]
+; CHECK-NEXT:    [[IV1:%.*]] = phi i64 [ [[IV_NEXT1:%.*]], [[LOOP_LATCH1:%.*]] ], [ [[IV]], [[SCALAR_PH]] ]
+; CHECK-NEXT:    [[GEP_SRC_I:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[IV1]]
 ; CHECK-NEXT:    [[L:%.*]] = load i8, ptr [[GEP_SRC_I]], align 1
 ; CHECK-NEXT:    [[C_1:%.*]] = icmp eq i8 [[L]], 0
-; CHECK-NEXT:    br i1 [[C_1]], label [[EXIT_LOOPEXIT:%.*]], label [[LOOP_LATCH]]
+; CHECK-NEXT:    br i1 [[C_1]], label [[EXIT_LOOPEXIT]], label [[LOOP_LATCH1]]
 ; CHECK:       loop.latch:
-; CHECK-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
-; CHECK-NEXT:    [[EC:%.*]] = icmp eq i64 [[IV]], [[N_EXT]]
-; CHECK-NEXT:    br i1 [[EC]], label [[EXIT_LOOPEXIT]], label [[LOOP_HEADER]]
+; CHECK-NEXT:    [[IV_NEXT1]] = add i64 [[IV1]], 1
+; CHECK-NEXT:    [[EC:%.*]] = icmp eq i64 [[IV1]], [[N_EXT]]
+; CHECK-NEXT:    br i1 [[EC]], label [[EXIT_LOOPEXIT]], label [[LOOP_HEADER1]], !llvm.loop [[LOOP12:![0-9]+]]
 ; CHECK:       exit.loopexit:
-; CHECK-NEXT:    [[RES_PH:%.*]] = phi i64 [ [[IV]], [[LOOP_HEADER]] ], [ 0, [[LOOP_LATCH]] ]
+; CHECK-NEXT:    [[RES_PH:%.*]] = phi i64 [ [[IV1]], [[LOOP_HEADER1]] ], [ 0, [[LOOP_LATCH1]] ], [ 0, [[LOOP_LATCH]] ], [ [[TMP10]], [[VECTOR_EARLY_EXIT]] ]
 ; CHECK-NEXT:    br label [[EXIT]]
 ; CHECK:       exit:
 ; CHECK-NEXT:    [[RES:%.*]] = phi i64 [ -1, [[ENTRY:%.*]] ], [ -2, [[THEN]] ], [ [[RES_PH]], [[EXIT_LOOPEXIT]] ]
@@ -653,11 +684,4 @@ exit:
 ; CHECK: [[LOOP4]] = distinct !{[[LOOP4]], [[META1]], [[META2]]}
 ; CHECK: [[LOOP5]] = distinct !{[[LOOP5]], [[META2]], [[META1]]}
 ; CHECK: [[LOOP6]] = distinct !{[[LOOP6]], [[META1]], [[META2]]}
-; CHECK: [[LOOP7]] = distinct !{[[LOOP7]], [[META1]]}
-; CHECK: [[LOOP8]] = distinct !{[[LOOP8]], [[META1]], [[META2]]}
-; CHECK: [[LOOP9]] = distinct !{[[LOOP9]], [[META2]], [[META1]]}
-; CHECK: [[LOOP10]] = distinct !{[[LOOP10]], [[META1]], [[META2]]}
-; CHECK: [[LOOP11]] = distinct !{[[LOOP11]], [[META2]], [[META1]]}
-; CHECK: [[LOOP12]] = distinct !{[[LOOP12]], [[META1]], [[META2]]}
-; CHECK: [[LOOP13]] = distinct !{[[LOOP13]], [[META2]], [[META1]]}
 ;.