s_load_dwordx2  s[4:5], s[0:1], 0x10
s_load_dwordx4  s[0:3], s[0:1], 0x00
v_lshlrev_b32  v0, 2, v0
s_waitcnt     lgkmcnt(0)
v_add_u32     v1, vcc, s2, v0
v_mov_b32     v2, s3
v_addc_u32    v2, vcc, v2, 0, vcc
v_add_u32     v3, vcc, s0, v0
v_mov_b32     v4, s1
v_addc_u32    v4, vcc, v4, 0, vcc
buffer_load_dword v4, v2, s[8:11], 0 offen