[CodeGen] Fix incorrect insertion point selection for reduction nodes in ComplexDeinterleavingPass

When replacing ComplexDeinterleavingPass::ReductionOperation, we can do it
either from the Real or Imaginary part. The correct way is to take whichever
is later in the BasicBlock, but before the patch, we just always took the
Real part.

Fixes llvm#65044

Differential Revision: https://reviews.llvm.org/D159209

Author: igogo-x86

llvm/lib/CodeGen/ComplexDeinterleavingPass.cpp

@@ -1424,7 +1424,17 @@ bool ComplexDeinterleavingGraph::identifyNodes(Instruction *RootI) {
   // CompositeNode we should choose only one either Real or Imag instruction to
   // use as an anchor for generating complex instruction.
   auto It = RootToNode.find(RootI);
-  if (It != RootToNode.end() && It->second->Real == RootI) {
+  if (It != RootToNode.end()) {
+    auto RootNode = It->second;
+    assert(RootNode->Operation ==
+           ComplexDeinterleavingOperation::ReductionOperation);
+    // Find out which part, Real or Imag, comes later, and only if we come to
+    // the latest part, add it to OrderedRoots.
+    auto *R = cast<Instruction>(RootNode->Real);
+    auto *I = cast<Instruction>(RootNode->Imag);
+    auto *ReplacementAnchor = R->comesBefore(I) ? I : R;
+    if (ReplacementAnchor != RootI)
+      return false;
     OrderedRoots.push_back(RootI);
     return true;
   }

llvm/test/CodeGen/AArch64/complex-deinterleaving-crash.ll

@@ -1,11 +1,15 @@
-; XFAIL: *
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
 ; RUN: llc %s --mattr=+complxnum -o - | FileCheck %s
 
 target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128-ni:1-p2:32:8:8:32-ni:2"
 target triple = "aarch64-none-linux-gnu"
 
 ; Check that deinterleaving pass doesn't generate broken IR
 define void @check_deinterleave_crash() #0 {
+; CHECK-LABEL: check_deinterleave_crash:
+; CHECK:       // %bb.0: // %bb
+; CHECK-NEXT:    mov x8, xzr
+; CHECK-NEXT:    str wzr, [x8]
 bb:
   br label %bb173