https://bugs.llvm.org/show_bug.cgi?id=49644
Bug ID: 49644
Summary: [AMDGPU][MC][GFX10] Many VOP3 only opcodes are decoded
with _e64 suffix
Product: libraries
Version: trunk
Hardware: PC
OS: Windows NT
Status: NEW
Severity: enhancement
Priority: P
Component: Backend: AMDGPU
Assignee: unassignedb...@nondot.org
Reporter: dpreobrazhen...@luxoft.com
CC: llvm-bugs@lists.llvm.org
The following opcodes are VOP3 only but they are printed with _e64 suffix when
decoded:
v_add_co_u32
v_sub_co_u32
v_subrev_co_u32
v_add_nc_u16
v_sub_nc_u16
v_ashrrev_i16
v_lshlrev_b16
v_lshrrev_b16
v_bcnt_u32_b32
v_bfm_b32
v_ldexp_f32
v_mul_lo_u16
v_cvt_pk_i16_i32
v_cvt_pk_u16_u32
v_cvt_pknorm_i16_f32
v_cvt_pknorm_u16_f32
v_mbcnt_hi_u32_b32
v_mbcnt_lo_u32_b32
v_max_i16
v_max_u16
v_min_i16
v_min_u16
Examples:
Test:
0xff,0x00,0x0f,0xd7,0x01,0x05,0x02,0x00
Output:
v_add_co_u32_e64 v255, s0, v1, v2
Test:
0xff,0x00,0x63,0xd7,0x01,0x05,0x02,0x00
Output:
v_bfm_b32_e64 v255, v1, v2
--
You are receiving this mail because:
You are on the CC list for the bug._______________________________________________
llvm-bugs mailing list
llvm-bugs@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-bugs
