[DAGCombiner] Disable narrowExtractedVectorLoad for indexed loads. (llvm#135847)

The later code does not expect or preserve the index output.

Fixes llvm#135821

Author: topperc

llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp

@@ -25183,7 +25183,7 @@ static SDValue narrowExtractedVectorLoad(SDNode *Extract, SelectionDAG &DAG) {
     return SDValue();
 
   auto *Ld = dyn_cast<LoadSDNode>(Extract->getOperand(0));
-  if (!Ld || Ld->getExtensionType() || !Ld->isSimple())
+  if (!Ld || !ISD::isNormalLoad(Ld) || !Ld->isSimple())
     return SDValue();
 
   // Allow targets to opt-out.

llvm/test/CodeGen/AArch64/pr135821.ll

@@ -0,0 +1,27 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc < %s -mtriple=aarch64-unknown-linux-gnu  | FileCheck %s
+
+define <4 x float> @f(ptr  %0) {
+; CHECK-LABEL: f:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    sub sp, sp, #32
+; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
+; CHECK-NEXT:    .cfi_offset w30, -16
+; CHECK-NEXT:    ldr q1, [x0, #56]!
+; CHECK-NEXT:    ldr d0, [x0, #16]
+; CHECK-NEXT:    mov v1.d[1], v0.d[0]
+; CHECK-NEXT:    str q1, [sp] // 16-byte Folded Spill
+; CHECK-NEXT:    bl use
+; CHECK-NEXT:    ldr q0, [sp] // 16-byte Folded Reload
+; CHECK-NEXT:    ldr x30, [sp, #16] // 8-byte Folded Reload
+; CHECK-NEXT:    add sp, sp, #32
+; CHECK-NEXT:    ret
+  %2 = getelementptr inbounds nuw i8, ptr %0, i64 56
+  %3 = load <6 x float>, ptr %2, align 4
+  %4 = shufflevector <6 x float> %3, <6 x float> poison, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
+  tail call void @use(ptr %2)
+  ret <4 x float> %4
+}
+
+declare void @use(ptr)