llvm/test/CodeGen/AMDGPU/fabs-vector-truncate.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
; RUN: llc -mtriple=amdgpu9.50-amd-amdhsa < %s | FileCheck %s

define amdgpu_kernel void @reduced_fabs_vector_truncate_crash(<2 x float> %0) {
; CHECK-LABEL: reduced_fabs_vector_truncate_crash:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
; CHECK-NEXT:    v_mov_b32_e32 v1, 0
; CHECK-NEXT:    v_mov_b64_e32 v[2:3], 0
; CHECK-NEXT:    s_waitcnt lgkmcnt(0)
; CHECK-NEXT:    s_bitset0_b32 s1, 31
; CHECK-NEXT:    s_bitset0_b32 s0, 31
; CHECK-NEXT:    v_mov_b32_e32 v0, s1
; CHECK-NEXT:    v_cvt_pk_f16_f32 v0, s0, v0
; CHECK-NEXT:    global_store_dwordx2 v[2:3], v[0:1], off
; CHECK-NEXT:    s_endpgm
  %2 = fptrunc <2 x float> %0 to <2 x half>
  %3 = shufflevector <2 x half> %2, <2 x half> zeroinitializer, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %4 = tail call <4 x half> @llvm.fabs.v4f16(<4 x half> %3)
  store <4 x half> %4, ptr addrspace(1) null, align 8
  ret void
}