; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=aarch64-unknown-linux-gnu < %s | FileCheck %s

; FIXME: Currently, we avoid narrowing this v4i32 load, in the
; hopes of being able to fold the shift, despite it requiring stack
; storage + loads. Ideally, we should narrow here and load the i32
; directly from the variable offset e.g:
;
; add     x8, x0, x1, lsl #4
; and     x9, x2, #0x3
; ldr     w0, [x8, x9, lsl #2]
;
; The AArch64TargetLowering::shouldReduceLoadWidth heuristic should
; probably be updated to choose load-narrowing instead of folding the
; lsl in larger vector cases.
;
define i32 @narrow_load_v4_i32_single_ele_variable_idx(ptr %ptr, i64 %off, i32 %ele) {
; CHECK-LABEL: narrow_load_v4_i32_single_ele_variable_idx:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    sub sp, sp, #16
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    ldr q0, [x0, x1, lsl #4]
; CHECK-NEXT:    mov x8, sp
; CHECK-NEXT:    // kill: def $w2 killed $w2 def $x2
; CHECK-NEXT:    bfi x8, x2, #2, #2
; CHECK-NEXT:    str q0, [sp]
; CHECK-NEXT:    ldr w0, [x8]
; CHECK-NEXT:    add sp, sp, #16
; CHECK-NEXT:    ret
entry:
  %idx = getelementptr inbounds <4 x i32>, ptr %ptr, i64 %off
  %x = load <4 x i32>, ptr %idx, align 8
  %res = extractelement <4 x i32> %x, i32 %ele
  ret i32 %res
}