llvm/test/Transforms/LoopVectorize/AArch64/widen-gep-all-indices-invariant.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
; RUN: opt -passes=loop-vectorize -mtriple=arm64-apple-macosx -S %s | FileCheck %s

; Test case for https://github.com/llvm/llvm-project/issues/169668.
define i32 @gep_with_all_invariant_operands(ptr %src.0, ptr %src.1, i64 %n, i1 %cond) #0 {
; CHECK-LABEL: define i32 @gep_with_all_invariant_operands(
; CHECK-SAME: ptr [[SRC_0:%.*]], ptr [[SRC_1:%.*]], i64 [[N:%.*]], i1 [[COND:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[N]], 1
; CHECK-NEXT:    br label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    [[TMP1:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP2:%.*]] = mul nuw i64 [[TMP1]], 4
; CHECK-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP4:%.*]] = shl nuw i64 [[TMP3]], 2
; CHECK-NEXT:    [[TMP5:%.*]] = sub i64 [[TMP0]], [[TMP4]]
; CHECK-NEXT:    [[TMP6:%.*]] = icmp ugt i64 [[TMP0]], [[TMP4]]
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP6]], i64 [[TMP5]], i64 0
; CHECK-NEXT:    [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[TMP0]])
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr i32, ptr [[SRC_0]], i64 [[N]]
; CHECK-NEXT:    [[TMP9:%.*]] = select i1 [[COND]], ptr [[SRC_1]], ptr [[TMP8]]
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x ptr> poison, ptr [[TMP9]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x ptr> [[BROADCAST_SPLATINSERT]], <vscale x 4 x ptr> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
; CHECK:       [[VECTOR_BODY]]:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], %[[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> align 4 [[BROADCAST_SPLAT]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP2]]
; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX]], i64 [[TMP7]])
; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], i32 0
; CHECK-NEXT:    [[TMP11:%.*]] = xor i1 [[TMP10]], true
; CHECK-NEXT:    br i1 [[TMP11]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    [[TMP12:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], splat (i1 true)
; CHECK-NEXT:    [[FIRST_INACTIVE_LANE:%.*]] = call i64 @llvm.experimental.cttz.elts.i64.nxv4i1(<vscale x 4 x i1> [[TMP12]], i1 false)
; CHECK-NEXT:    [[LAST_ACTIVE_LANE:%.*]] = sub i64 [[FIRST_INACTIVE_LANE]], 1
; CHECK-NEXT:    [[TMP13:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP14:%.*]] = mul nuw i64 [[TMP13]], 4
; CHECK-NEXT:    [[TMP15:%.*]] = mul i64 [[TMP14]], 0
; CHECK-NEXT:    [[TMP16:%.*]] = extractelement <vscale x 4 x i32> [[WIDE_MASKED_GATHER]], i64 [[LAST_ACTIVE_LANE]]
; CHECK-NEXT:    br label %[[EXIT:.*]]
; CHECK:       [[EXIT]]:
; CHECK-NEXT:    ret i32 [[TMP16]]
;
entry:
  br label %loop

loop:
  %iv = phi i64 [ %iv.next, %loop ], [ 0, %entry ]
  %gep = getelementptr i32, ptr %src.0, i64 %n
  %ptr = select i1 %cond, ptr %src.1, ptr %gep
  %val = load i32, ptr %ptr, align 4
  %iv.next = add i64 %iv, 1
  %cmp = icmp ult i64 %iv, %n
  br i1 %cmp, label %loop, label %exit, !llvm.loop !0

exit:
  ret i32 %val
}

attributes #0 = { "target-cpu"="neoverse-v2" }

!0 = distinct !{!0, !1, !2}
!1 = !{!"llvm.loop.vectorize.enable", i1 true}
!2 = !{!"llvm.loop.vectorize.predicate.enable", i1 true}
;.
; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
;.