; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 5
; RUN: opt < %s -passes=loop-vectorize -force-vector-width=4 -S | FileCheck %s

; Check that we don't unnecessarily broadcast %pow
define void @powi_only_first_lane_used_of_second_arg(ptr %p, i32 %pow) {
; CHECK-LABEL: define void @powi_only_first_lane_used_of_second_arg(
; CHECK-SAME: ptr [[P:%.*]], i32 [[POW:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    br label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
; CHECK:       [[VECTOR_BODY]]:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr float, ptr [[P]], i32 [[INDEX]]
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x float>, ptr [[TMP0]], align 4
; CHECK-NEXT:    [[TMP2:%.*]] = call <4 x float> @llvm.powi.v4f32.i32(<4 x float> [[WIDE_LOAD]], i32 [[POW]])
; CHECK-NEXT:    store <4 x float> [[TMP2]], ptr [[TMP0]], align 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP3:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1024
; CHECK-NEXT:    br i1 [[TMP3]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    br label %[[EXIT:.*]]
; CHECK:       [[EXIT]]:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i32 [0, %entry], [%iv.next, %loop]
  %p.gep = getelementptr float, ptr %p, i32 %iv
  %x = load float, ptr %p.gep
  %y = call float @llvm.powi(float %x, i32 %pow)
  store float %y, ptr %p.gep
  %iv.next = add i32 %iv, 1
  %done = icmp eq i32 %iv.next, 1024
  br i1 %done, label %exit, label %loop

exit:
  ret void
}