llvm/test/Transforms/LoopVectorize/RISCV/reverse-load-scatter.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 6
; RUN: opt -mtriple=riscv64-linux-gnu -mattr=+v,+f -passes=loop-vectorize -force-vector-width=2 -scalable-vectorization=on -S < %s | FileCheck %s

define void @reverse_load_scatter(ptr noalias %src, ptr noalias %dst, i64 %n) {
; CHECK-LABEL: define void @reverse_load_scatter(
; CHECK-SAME: ptr noalias [[SRC:%.*]], ptr noalias [[DST:%.*]], i64 [[N:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    br label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
; CHECK:       [[VECTOR_BODY]]:
; CHECK-NEXT:    [[CURRENT_ITERATION_IV:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[CURRENT_ITERATION_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[AVL:%.*]] = phi i64 [ [[N]], %[[VECTOR_PH]] ], [ [[AVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = sub i64 [[N]], [[CURRENT_ITERATION_IV]]
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i64, ptr [[SRC]], i64 [[OFFSET_IDX]]
; CHECK-NEXT:    [[TMP2:%.*]] = zext i32 [[TMP0]] to i64
; CHECK-NEXT:    [[TMP3:%.*]] = sub nuw nsw i64 [[TMP2]], 1
; CHECK-NEXT:    [[TMP4:%.*]] = sub i64 0, [[TMP3]]
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr i64, ptr [[TMP1]], i64 [[TMP4]]
; CHECK-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP5]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP0]])
; CHECK-NEXT:    [[TMP6:%.*]] = call <vscale x 2 x i64> @llvm.experimental.vp.reverse.nxv2i64(<vscale x 2 x i64> [[VP_OP_LOAD]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP0]])
; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i64, ptr [[DST]], <vscale x 2 x i64> [[TMP6]]
; CHECK-NEXT:    call void @llvm.vp.scatter.nxv2i64.nxv2p0(<vscale x 2 x i64> [[TMP6]], <vscale x 2 x ptr> align 8 [[TMP7]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP0]])
; CHECK-NEXT:    [[CURRENT_ITERATION_NEXT]] = add i64 [[TMP2]], [[CURRENT_ITERATION_IV]]
; CHECK-NEXT:    [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP2]]
; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq i64 [[AVL_NEXT]], 0
; CHECK-NEXT:    br i1 [[TMP8]], 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.dec = phi i64 [ %n, %entry ], [ %iv.dec.next, %loop ]
  %src.ptr = getelementptr inbounds i64, ptr %src, i64 %iv.dec
  %val = load i64, ptr %src.ptr, align 8
  %dst.ptr = getelementptr inbounds i64, ptr %dst, i64 %val
  store i64 %val, ptr %dst.ptr, align 8
  %iv.dec.next = add i64 %iv.dec, -1
  %done = icmp eq i64 %iv.dec.next, 0
  br i1 %done, label %exit, label %loop

exit:
  ret void
}