[SLP]Fix PR66795: Check correct deps for vectorized inst with multiple

vectorized node uses.

If the instruction is vectorized in many different vector nodes, it may
break the dependency analysis for gathered nodes with matched scalars.
Need to properly check the dependency between such gather nodes to avoid
cycle dependency.

Author: alexey-bataev

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

@@ -8939,6 +8939,12 @@ BoUpSLP::isGatherShuffledEntry(const TreeEntry *TE, ArrayRef<Value *> VL,
             TE->UserTreeIndices.front().EdgeIdx <
                 TEPtr->UserTreeIndices.front().EdgeIdx)
           continue;
+        // If the user instruction is used for some reason in different
+        // vectorized nodes - make it depend on index.
+        if (TE->UserTreeIndices.front().UserTE !=
+                TEPtr->UserTreeIndices.front().UserTE &&
+            TE->Idx > TEPtr->Idx)
+          continue;
       }
       // Check if the user node of the TE comes after user node of EntryPtr,
       // otherwise EntryPtr depends on TE.

llvm/test/Transforms/SLPVectorizer/X86/multi-node-vectorized-insts.ll

@@ -0,0 +1,33 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 3
+; RUN: opt -passes=slp-vectorizer -S -mtriple=x86_64-unknown-linux-gnu < %s | FileCheck %s
+
+define void @test(double %0) {
+; CHECK-LABEL: define void @test(
+; CHECK-SAME: double [[TMP0:%.*]]) {
+; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <2 x double> poison, double [[TMP0]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <2 x double> [[TMP2]], <2 x double> poison, <2 x i32> zeroinitializer
+; CHECK-NEXT:    br label [[TMP4:%.*]]
+; CHECK:       4:
+; CHECK-NEXT:    [[TMP5:%.*]] = fsub <2 x double> zeroinitializer, [[TMP3]]
+; CHECK-NEXT:    [[TMP6:%.*]] = fsub <2 x double> zeroinitializer, [[TMP3]]
+; CHECK-NEXT:    br label [[DOTBACKEDGE:%.*]]
+; CHECK:       .backedge:
+; CHECK-NEXT:    [[TMP7:%.*]] = fmul <2 x double> [[TMP5]], [[TMP6]]
+; CHECK-NEXT:    [[TMP8:%.*]] = fcmp olt <2 x double> [[TMP7]], zeroinitializer
+; CHECK-NEXT:    br label [[TMP4]]
+;
+  br label %2
+
+2:
+  %3 = fsub double 0.000000e+00, %0
+  %4 = fsub double 0.000000e+00, %0
+  %5 = fsub double 0.000000e+00, %0
+  br label %.backedge
+
+.backedge:
+  %6 = fmul double %4, %5
+  %7 = fcmp olt double %6, 0.000000e+00
+  %8 = fmul double %5, %3
+  %9 = fcmp olt double %8, 0.000000e+00
+  br label %2
+}