; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt < %s -mtriple=amdgcn-amd-amdhsa -mcpu=gfx942 -passes=slp-vectorizer -S  | FileCheck %s --check-prefix=GFX9

define protected amdgpu_kernel void @myfun(i32 %in, ptr addrspace(1) %aptr1, ptr addrspace(1) %bptr1, ptr addrspace(1) %aptr2, ptr addrspace(1) %bptr2)  {
; GFX9-LABEL: define protected amdgpu_kernel void @myfun(
; GFX9-SAME: i32 [[IN:%.*]], ptr addrspace(1) [[APTR1:%.*]], ptr addrspace(1) [[BPTR1:%.*]], ptr addrspace(1) [[APTR2:%.*]], ptr addrspace(1) [[BPTR2:%.*]]) #[[ATTR0:[0-9]+]] {
; GFX9-NEXT:  [[ENTRY:.*]]:
; GFX9-NEXT:    [[VEC1:%.*]] = load <8 x i16>, ptr addrspace(1) [[APTR1]], align 16
; GFX9-NEXT:    [[BVEC1:%.*]] = load <8 x i16>, ptr addrspace(1) [[BPTR1]], align 16
; GFX9-NEXT:    [[TMP0:%.*]] = shufflevector <8 x i16> [[VEC1]], <8 x i16> poison, <2 x i32> <i32 0, i32 1>
; GFX9-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i16> [[VEC1]], <8 x i16> poison, <2 x i32> <i32 2, i32 3>
; GFX9-NEXT:    [[TMP2:%.*]] = shufflevector <8 x i16> [[VEC1]], <8 x i16> poison, <2 x i32> <i32 4, i32 5>
; GFX9-NEXT:    [[TMP3:%.*]] = shufflevector <8 x i16> [[VEC1]], <8 x i16> poison, <2 x i32> <i32 6, i32 7>
; GFX9-NEXT:    [[TMP4:%.*]] = shufflevector <8 x i16> [[BVEC1]], <8 x i16> poison, <2 x i32> <i32 0, i32 1>
; GFX9-NEXT:    [[TMP5:%.*]] = shufflevector <8 x i16> [[BVEC1]], <8 x i16> poison, <2 x i32> <i32 2, i32 3>
; GFX9-NEXT:    [[TMP6:%.*]] = shufflevector <8 x i16> [[BVEC1]], <8 x i16> poison, <2 x i32> <i32 4, i32 5>
; GFX9-NEXT:    [[TMP7:%.*]] = shufflevector <8 x i16> [[BVEC1]], <8 x i16> poison, <2 x i32> <i32 6, i32 7>
; GFX9-NEXT:    br label %[[DO_BODY:.*]]
; GFX9:       [[DO_BODY]]:
; GFX9-NEXT:    [[ADD:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[NEWADD:%.*]], %[[DO_BODY]] ]
; GFX9-NEXT:    [[TMP8:%.*]] = phi <2 x i16> [ [[TMP0]], %[[ENTRY]] ], [ [[TMP30:%.*]], %[[DO_BODY]] ]
; GFX9-NEXT:    [[TMP9:%.*]] = phi <2 x i16> [ [[TMP1]], %[[ENTRY]] ], [ [[TMP31:%.*]], %[[DO_BODY]] ]
; GFX9-NEXT:    [[TMP10:%.*]] = phi <2 x i16> [ [[TMP2]], %[[ENTRY]] ], [ [[TMP32:%.*]], %[[DO_BODY]] ]
; GFX9-NEXT:    [[TMP11:%.*]] = phi <2 x i16> [ [[TMP3]], %[[ENTRY]] ], [ [[TMP33:%.*]], %[[DO_BODY]] ]
; GFX9-NEXT:    [[TMP12:%.*]] = phi <2 x i16> [ [[TMP4]], %[[ENTRY]] ], [ [[TMP34:%.*]], %[[DO_BODY]] ]
; GFX9-NEXT:    [[TMP13:%.*]] = phi <2 x i16> [ [[TMP5]], %[[ENTRY]] ], [ [[TMP35:%.*]], %[[DO_BODY]] ]
; GFX9-NEXT:    [[TMP14:%.*]] = phi <2 x i16> [ [[TMP6]], %[[ENTRY]] ], [ [[TMP36:%.*]], %[[DO_BODY]] ]
; GFX9-NEXT:    [[TMP15:%.*]] = phi <2 x i16> [ [[TMP7]], %[[ENTRY]] ], [ [[TMP37:%.*]], %[[DO_BODY]] ]
; GFX9-NEXT:    [[TMP16:%.*]] = shufflevector <2 x i16> [[TMP8]], <2 x i16> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; GFX9-NEXT:    [[TMP17:%.*]] = shufflevector <2 x i16> [[TMP9]], <2 x i16> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; GFX9-NEXT:    [[TMP18:%.*]] = shufflevector <2 x i16> [[TMP8]], <2 x i16> [[TMP9]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
; GFX9-NEXT:    [[TMP19:%.*]] = shufflevector <2 x i16> [[TMP10]], <2 x i16> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; GFX9-NEXT:    [[TMP20:%.*]] = shufflevector <8 x i16> [[TMP18]], <8 x i16> [[TMP19]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 poison, i32 poison>
; GFX9-NEXT:    [[TMP21:%.*]] = shufflevector <2 x i16> [[TMP11]], <2 x i16> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; GFX9-NEXT:    [[TMP22:%.*]] = shufflevector <8 x i16> [[TMP20]], <8 x i16> [[TMP21]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; GFX9-NEXT:    [[TMP23:%.*]] = shufflevector <2 x i16> [[TMP12]], <2 x i16> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; GFX9-NEXT:    [[TMP24:%.*]] = shufflevector <2 x i16> [[TMP13]], <2 x i16> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; GFX9-NEXT:    [[TMP25:%.*]] = shufflevector <2 x i16> [[TMP12]], <2 x i16> [[TMP13]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
; GFX9-NEXT:    [[TMP26:%.*]] = shufflevector <2 x i16> [[TMP14]], <2 x i16> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; GFX9-NEXT:    [[TMP27:%.*]] = shufflevector <8 x i16> [[TMP25]], <8 x i16> [[TMP26]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 poison, i32 poison>
; GFX9-NEXT:    [[TMP28:%.*]] = shufflevector <2 x i16> [[TMP15]], <2 x i16> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; GFX9-NEXT:    [[TMP29:%.*]] = shufflevector <8 x i16> [[TMP27]], <8 x i16> [[TMP28]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; GFX9-NEXT:    [[RES:%.*]] = add <8 x i16> [[TMP22]], [[TMP29]]
; GFX9-NEXT:    [[VEC2:%.*]] = load <8 x i16>, ptr addrspace(1) [[APTR2]], align 16
; GFX9-NEXT:    [[BVEC2:%.*]] = load <8 x i16>, ptr addrspace(1) [[BPTR2]], align 16
; GFX9-NEXT:    [[NEWADD]] = add i32 [[ADD]], 1
; GFX9-NEXT:    [[COND:%.*]] = icmp sgt i32 [[NEWADD]], [[IN]]
; GFX9-NEXT:    [[TMP30]] = shufflevector <8 x i16> [[VEC2]], <8 x i16> poison, <2 x i32> <i32 0, i32 1>
; GFX9-NEXT:    [[TMP31]] = shufflevector <8 x i16> [[VEC2]], <8 x i16> poison, <2 x i32> <i32 2, i32 3>
; GFX9-NEXT:    [[TMP32]] = shufflevector <8 x i16> [[VEC2]], <8 x i16> poison, <2 x i32> <i32 4, i32 5>
; GFX9-NEXT:    [[TMP33]] = shufflevector <8 x i16> [[VEC2]], <8 x i16> poison, <2 x i32> <i32 6, i32 7>
; GFX9-NEXT:    [[TMP34]] = shufflevector <8 x i16> [[BVEC2]], <8 x i16> poison, <2 x i32> <i32 0, i32 1>
; GFX9-NEXT:    [[TMP35]] = shufflevector <8 x i16> [[BVEC2]], <8 x i16> poison, <2 x i32> <i32 2, i32 3>
; GFX9-NEXT:    [[TMP36]] = shufflevector <8 x i16> [[BVEC2]], <8 x i16> poison, <2 x i32> <i32 4, i32 5>
; GFX9-NEXT:    [[TMP37]] = shufflevector <8 x i16> [[BVEC2]], <8 x i16> poison, <2 x i32> <i32 6, i32 7>
; GFX9-NEXT:    br i1 [[COND]], label %[[DO_BODY]], label %[[END:.*]]
; GFX9:       [[END]]:
; GFX9-NEXT:    ret void
;
entry:
  %vec1 = load <8 x i16>, ptr addrspace(1) %aptr1
  %el0 = extractelement <8 x i16> %vec1, i64 0
  %el1 = extractelement <8 x i16> %vec1, i64 1
  %el2 = extractelement <8 x i16> %vec1, i64 2
  %el3 = extractelement <8 x i16> %vec1, i64 3
  %el4 = extractelement <8 x i16> %vec1, i64 4
  %el5 = extractelement <8 x i16> %vec1, i64 5
  %el6 = extractelement <8 x i16> %vec1, i64 6
  %el7 = extractelement <8 x i16> %vec1, i64 7
  %bvec1 = load <8 x i16>, ptr addrspace(1) %bptr1
  %bel0 = extractelement <8 x i16> %bvec1, i64 0
  %bel1 = extractelement <8 x i16> %bvec1, i64 1
  %bel2 = extractelement <8 x i16> %bvec1, i64 2
  %bel3 = extractelement <8 x i16> %bvec1, i64 3
  %bel4 = extractelement <8 x i16> %bvec1, i64 4
  %bel5 = extractelement <8 x i16> %bvec1, i64 5
  %bel6 = extractelement <8 x i16> %bvec1, i64 6
  %bel7 = extractelement <8 x i16> %bvec1, i64 7
  br label %do.body

do.body:
  %a_thread_buf1 = phi i16 [%el1, %entry], [%newel1, %do.body]
  %a_thread_buf2 = phi i16 [%el2, %entry], [%newel2, %do.body]
  %a_thread_buf3 = phi i16 [%el3, %entry], [%newel3, %do.body]
  %a_thread_buf4 = phi i16 [%el4, %entry], [%newel4, %do.body]
  %a_thread_buf5 = phi i16 [%el5, %entry], [%newel5, %do.body]
  %a_thread_buf6 = phi i16 [%el6, %entry], [%newel6, %do.body]
  %a_thread_buf7 = phi i16 [%el7, %entry], [%newel7, %do.body]
  %b_thread_buf1 = phi i16 [%bel1, %entry], [%bnewel1, %do.body]
  %b_thread_buf2 = phi i16 [%bel2, %entry], [%bnewel2, %do.body]
  %b_thread_buf3 = phi i16 [%bel3, %entry], [%bnewel3, %do.body]
  %b_thread_buf4 = phi i16 [%bel4, %entry], [%bnewel4, %do.body]
  %b_thread_buf5 = phi i16 [%bel5, %entry], [%bnewel5, %do.body]
  %b_thread_buf6 = phi i16 [%bel6, %entry], [%bnewel6, %do.body]
  %b_thread_buf7 = phi i16 [%bel7, %entry], [%bnewel7, %do.body]
  %add = phi i32 [0, %entry], [%newadd, %do.body]
  %a_thread_buf0 = phi i16 [%el0, %entry], [%newel0, %do.body]
  %b_thread_buf0 = phi i16 [%bel0, %entry], [%bnewel0, %do.body]
  %a_thread_vec0 = insertelement <8 x i16> poison, i16 %a_thread_buf0, i64 0
  %a_thread_vec1 = insertelement <8 x i16> %a_thread_vec0, i16 %a_thread_buf1, i64 1
  %a_thread_vec2 = insertelement <8 x i16> %a_thread_vec1, i16 %a_thread_buf2, i64 2
  %a_thread_vec3 = insertelement <8 x i16> %a_thread_vec2, i16 %a_thread_buf3, i64 3
  %a_thread_vec4 = insertelement <8 x i16> %a_thread_vec3, i16 %a_thread_buf4, i64 4
  %a_thread_vec5 = insertelement <8 x i16> %a_thread_vec4, i16 %a_thread_buf5, i64 5
  %a_thread_vec6 = insertelement <8 x i16> %a_thread_vec5, i16 %a_thread_buf6, i64 6
  %a_thread_vec7 = insertelement <8 x i16> %a_thread_vec6, i16 %a_thread_buf7, i64 7
  %b_thread_vec0 = insertelement <8 x i16> poison, i16 %b_thread_buf0, i64 0
  %b_thread_vec1 = insertelement <8 x i16> %b_thread_vec0, i16 %b_thread_buf1, i64 1
  %b_thread_vec2 = insertelement <8 x i16> %b_thread_vec1, i16 %b_thread_buf2, i64 2
  %b_thread_vec3 = insertelement <8 x i16> %b_thread_vec2, i16 %b_thread_buf3, i64 3
  %b_thread_vec4 = insertelement <8 x i16> %b_thread_vec3, i16 %b_thread_buf4, i64 4
  %b_thread_vec5 = insertelement <8 x i16> %b_thread_vec4, i16 %b_thread_buf5, i64 5
  %b_thread_vec6 = insertelement <8 x i16> %b_thread_vec5, i16 %b_thread_buf6, i64 6
  %b_thread_vec7 = insertelement <8 x i16> %b_thread_vec6, i16 %b_thread_buf7, i64 7
  %res = add <8 x i16> %a_thread_vec7, %b_thread_vec7
  %vec2 = load <8 x i16>, ptr addrspace(1) %aptr2
  %newel0 = extractelement <8 x i16> %vec2, i64 0
  %newel1 = extractelement <8 x i16> %vec2, i64 1
  %newel2 = extractelement <8 x i16> %vec2, i64 2
  %newel3 = extractelement <8 x i16> %vec2, i64 3
  %newel4 = extractelement <8 x i16> %vec2, i64 4
  %newel5 = extractelement <8 x i16> %vec2, i64 5
  %newel6 = extractelement <8 x i16> %vec2, i64 6
  %newel7 = extractelement <8 x i16> %vec2, i64 7
  %bvec2 = load <8 x i16>, ptr addrspace(1) %bptr2
  %bnewel0 = extractelement <8 x i16> %bvec2, i64 0
  %bnewel1 = extractelement <8 x i16> %bvec2, i64 1
  %bnewel2 = extractelement <8 x i16> %bvec2, i64 2
  %bnewel3 = extractelement <8 x i16> %bvec2, i64 3
  %bnewel4 = extractelement <8 x i16> %bvec2, i64 4
  %bnewel5 = extractelement <8 x i16> %bvec2, i64 5
  %bnewel6 = extractelement <8 x i16> %bvec2, i64 6
  %bnewel7 = extractelement <8 x i16> %bvec2, i64 7
  %newadd = add i32 %add, 1
  %cond = icmp sgt i32 %newadd, %in
  br i1 %cond, label %do.body, label %end

end:
  ret void
}