[SLP][REVEC] Ignore UserTreeIndex if it is empty. (llvm#131993)

Previously, the all_of check did not consider the case where the
TreeEntry is empty (i.e., when it is the first entry).

Author: HanKuanChen

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

@@ -6455,14 +6455,11 @@ void BoUpSLP::reorderTopToBottom() {
             assert(SLPReVec && "Only supported by REVEC.");
             // ShuffleVectorInst does not do reorderOperands (and it should not
             // because ShuffleVectorInst supports only a limited set of
-            // patterns). Only do reorderNodeWithReuses if all of the users are
-            // not ShuffleVectorInst.
-            if (isa<ShuffleVectorInst>(TE->UserTreeIndex.UserTE->getMainOp()))
+            // patterns). Only do reorderNodeWithReuses if the user is not
+            // ShuffleVectorInst.
+            if (TE->UserTreeIndex && TE->UserTreeIndex.UserTE->hasState() &&
+                isa<ShuffleVectorInst>(TE->UserTreeIndex.UserTE->getMainOp()))
               continue;
-            assert((!TE->UserTreeIndex ||
-                    !isa<ShuffleVectorInst>(
-                        TE->UserTreeIndex.UserTE->getMainOp())) &&
-                   "Does not know how to reorder.");
           }
           // Update ordering of the operands with the smaller VF than the given
           // one.

llvm/test/Transforms/SLPVectorizer/X86/revec-reduced-value-replace-extractelement.ll

@@ -0,0 +1,35 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -S --passes=slp-vectorizer -slp-threshold=-99999 < %s -mtriple=x86_64-unknown-linux-gnu -slp-revec | FileCheck %s
+
+define void @test() {
+; CHECK-LABEL: define void @test() {
+; CHECK-NEXT:  [[BB:.*]]:
+; CHECK-NEXT:    [[TRUNC:%.*]] = trunc i64 0 to i32
+; CHECK-NEXT:    br label %[[BB1:.*]]
+; CHECK:       [[BB1]]:
+; CHECK-NEXT:    [[TMP0:%.*]] = phi <2 x i32> [ zeroinitializer, %[[BB]] ], [ [[TMP4:%.*]], %[[BB1]] ]
+; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x i32> [[TMP0]], i32 1
+; CHECK-NEXT:    [[TMP2:%.*]] = call i8 @llvm.vector.reduce.mul.v4i8(<4 x i8> zeroinitializer)
+; CHECK-NEXT:    [[TMP3:%.*]] = zext i8 [[TMP2]] to i32
+; CHECK-NEXT:    [[OP_RDX:%.*]] = mul i32 [[TMP3]], [[TMP1]]
+; CHECK-NEXT:    [[OP_RDX1:%.*]] = mul i32 [[OP_RDX]], [[TRUNC]]
+; CHECK-NEXT:    [[TMP4]] = insertelement <2 x i32> <i32 0, i32 poison>, i32 [[OP_RDX1]], i32 1
+; CHECK-NEXT:    br label %[[BB1]]
+;
+bb:
+  br label %bb1
+
+bb1:
+  %phi = phi i32 [ 0, %bb ], [ %mul9, %bb1 ]
+  %phi2 = phi i32 [ 0, %bb ], [ 0, %bb1 ]
+  %trunc = trunc i64 0 to i32
+  %mul = mul i32 0, %trunc
+  %mul3 = mul i32 %trunc, %phi
+  %mul4 = mul i32 %mul3, %mul
+  %mul5 = mul i32 %mul4, %mul
+  %trunc6 = trunc i64 0 to i32
+  %mul7 = mul i32 0, %trunc6
+  %mul8 = mul i32 %mul5, %mul7
+  %mul9 = mul i32 %mul8, %mul7
+  br label %bb1
+}