test/Transforms/LoopVectorize/AArch64/sve-widen-extractvalue.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --filter-out-after "^scalar.ph" --version 5
; RUN: opt -S -passes=loop-vectorize < %s | FileCheck %s

target triple = "aarch64-unknown-linux-gnu"

define void @widen_extractvalue(ptr %dst, {i64, i64} %sv) #0 {
; CHECK-LABEL: define void @widen_extractvalue(
; CHECK-SAME: ptr [[DST:%.*]], { i64, i64 } [[SV:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.vscale.i32()
; CHECK-NEXT:    [[TMP1:%.*]] = shl nuw i32 [[TMP0]], 1
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 1000, [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @llvm.vscale.i32()
; CHECK-NEXT:    [[TMP3:%.*]] = mul nuw i32 [[TMP2]], 2
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i32 1000, [[TMP3]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i32 1000, [[N_MOD_VF]]
; CHECK-NEXT:    [[EXTRACT0:%.*]] = extractvalue { i64, i64 } [[SV]], 0
; CHECK-NEXT:    [[DOTSPLATINSERT1:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[EXTRACT0]], i64 0
; CHECK-NEXT:    [[DOTSPLAT2:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT1]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP10:%.*]] = extractvalue { i64, i64 } [[SV]], 1
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP10]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT1]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP7:%.*]] = add <vscale x 2 x i64> [[DOTSPLAT2]], [[BROADCAST_SPLAT2]]
; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
; CHECK:       [[VECTOR_BODY]]:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr i64, ptr [[DST]], i32 [[INDEX]]
; CHECK-NEXT:    store <vscale x 2 x i64> [[TMP7]], ptr [[TMP8]], align 8
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], [[TMP3]]
; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP9]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 1000, [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], [[EXIT:label %.*]], label %[[SCALAR_PH]]
; CHECK:       [[SCALAR_PH]]:
;
entry:
  br label %loop.body

loop.body:
  %iv = phi i32 [ 0, %entry ], [ %iv.next, %loop.body ]
  %a = extractvalue { i64, i64 } %sv, 0
  %b = extractvalue { i64, i64 } %sv, 1
  %addr = getelementptr i64, ptr %dst, i32 %iv
  %add = add i64 %a, %b
  store i64 %add, ptr %addr
  %iv.next = add nsw i32 %iv, 1
  %cond = icmp ne i32 %iv.next, 1000
  br i1 %cond, label %loop.body, label %exit, !llvm.loop !0

exit:
  ret void
}

attributes #0 = { "target-features"="+sve" }

!0 = distinct !{!0, !1, !2, !3, !4, !5}
!1 = !{!"llvm.loop.mustprogress"}
!2 = !{!"llvm.loop.vectorize.width", i32 2}
!3 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}
!4 = !{!"llvm.loop.interleave.count", i32 1}
!5 = !{!"llvm.loop.vectorize.enable", i1 true}