diff --git a/llvm/lib/Target/AMDGPU/VOP2Instructions.td b/llvm/lib/Target/AMDGPU/VOP2Instructions.td --- a/llvm/lib/Target/AMDGPU/VOP2Instructions.td +++ b/llvm/lib/Target/AMDGPU/VOP2Instructions.td @@ -1477,19 +1477,19 @@ defm V_FMAAK_F16_t16 : VOP2Only_Real_MADK_gfx11_with_name<0x038, "v_fmaak_f16">; // VOP3 only. -defm V_CNDMASK_B16 : VOP3Only_Realtriple_gfx11<0x25d>; -defm V_LDEXP_F32 : VOP3Only_Realtriple_gfx11<0x31c>; -defm V_BFM_B32 : VOP3Only_Realtriple_gfx11<0x31d>; -defm V_BCNT_U32_B32 : VOP3Only_Realtriple_gfx11<0x31e>; -defm V_MBCNT_LO_U32_B32 : VOP3Only_Realtriple_gfx11<0x31f>; -defm V_MBCNT_HI_U32_B32 : VOP3Only_Realtriple_gfx11<0x320>; -defm V_CVT_PKNORM_I16_F32 : VOP3Only_Realtriple_gfx11<0x321>; -defm V_CVT_PKNORM_U16_F32 : VOP3Only_Realtriple_gfx11<0x322>; -defm V_CVT_PK_U16_U32 : VOP3Only_Realtriple_gfx11<0x323>; -defm V_CVT_PK_I16_I32 : VOP3Only_Realtriple_gfx11<0x324>; -defm V_ADD_CO_U32 : VOP3beOnly_Realtriple_gfx11<0x300>; -defm V_SUB_CO_U32 : VOP3beOnly_Realtriple_gfx11<0x301>; -defm V_SUBREV_CO_U32 : VOP3beOnly_Realtriple_gfx11<0x302>; +defm V_CNDMASK_B16 : VOP3Only_Realtriple_gfx11<0x25d>; +defm V_LDEXP_F32 : VOP3Only_Realtriple_gfx11<0x31c>; +defm V_BFM_B32 : VOP3Only_Realtriple_gfx11<0x31d>; +defm V_BCNT_U32_B32 : VOP3Only_Realtriple_gfx11<0x31e>; +defm V_MBCNT_LO_U32_B32 : VOP3Only_Realtriple_gfx11<0x31f>; +defm V_MBCNT_HI_U32_B32 : VOP3Only_Realtriple_gfx11<0x320>; +defm V_CVT_PK_NORM_I16_F32 : VOP3Only_Realtriple_with_name_gfx11<0x321, "V_CVT_PKNORM_I16_F32", "v_cvt_pk_norm_i16_f32">; +defm V_CVT_PK_NORM_U16_F32 : VOP3Only_Realtriple_with_name_gfx11<0x322, "V_CVT_PKNORM_U16_F32", "v_cvt_pk_norm_u16_f32">; +defm V_CVT_PK_U16_U32 : VOP3Only_Realtriple_gfx11<0x323>; +defm V_CVT_PK_I16_I32 : VOP3Only_Realtriple_gfx11<0x324>; +defm V_ADD_CO_U32 : VOP3beOnly_Realtriple_gfx11<0x300>; +defm V_SUB_CO_U32 : VOP3beOnly_Realtriple_gfx11<0x301>; +defm V_SUBREV_CO_U32 : VOP3beOnly_Realtriple_gfx11<0x302>; let SubtargetPredicate = isGFX11Plus in { defm : VOP2eInstAliases; diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s --- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s +++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s @@ -1450,184 +1450,184 @@ v_cvt_pk_u8_f32 v255, -|0xaf123456|, vcc_hi, null // GFX11: encoding: [0xff,0x01,0x26,0xd6,0xff,0xd6,0xf0,0x21,0x56,0x34,0x12,0xaf] -v_cvt_pknorm_i16_f16 v5, v1, v2 +v_cvt_pk_norm_i16_f16 v5, v1, v2 // GFX11: encoding: [0x05,0x00,0x12,0xd7,0x01,0x05,0x02,0x00] -v_cvt_pknorm_i16_f16 v5, v255, v255 +v_cvt_pk_norm_i16_f16 v5, v255, v255 // GFX11: encoding: [0x05,0x00,0x12,0xd7,0xff,0xff,0x03,0x00] -v_cvt_pknorm_i16_f16 v5, s1, s2 +v_cvt_pk_norm_i16_f16 v5, s1, s2 // GFX11: encoding: [0x05,0x00,0x12,0xd7,0x01,0x04,0x00,0x00] -v_cvt_pknorm_i16_f16 v5, s105, s105 +v_cvt_pk_norm_i16_f16 v5, s105, s105 // GFX11: encoding: [0x05,0x00,0x12,0xd7,0x69,0xd2,0x00,0x00] -v_cvt_pknorm_i16_f16 v5, vcc_lo, ttmp15 +v_cvt_pk_norm_i16_f16 v5, vcc_lo, ttmp15 // GFX11: encoding: [0x05,0x00,0x12,0xd7,0x6a,0xf6,0x00,0x00] -v_cvt_pknorm_i16_f16 v5, vcc_hi, 0xfe0b +v_cvt_pk_norm_i16_f16 v5, vcc_hi, 0xfe0b // GFX11: encoding: [0x05,0x00,0x12,0xd7,0x6b,0xfe,0x01,0x00,0x0b,0xfe,0x00,0x00] -v_cvt_pknorm_i16_f16 v5, ttmp15, src_scc +v_cvt_pk_norm_i16_f16 v5, ttmp15, src_scc // GFX11: encoding: [0x05,0x00,0x12,0xd7,0x7b,0xfa,0x01,0x00] -v_cvt_pknorm_i16_f16 v5, m0, 0.5 +v_cvt_pk_norm_i16_f16 v5, m0, 0.5 // GFX11: encoding: [0x05,0x00,0x12,0xd7,0x7d,0xe0,0x01,0x00] -v_cvt_pknorm_i16_f16 v5, exec_lo, -1 +v_cvt_pk_norm_i16_f16 v5, exec_lo, -1 // GFX11: encoding: [0x05,0x00,0x12,0xd7,0x7e,0x82,0x01,0x00] -v_cvt_pknorm_i16_f16 v5, |exec_hi|, null +v_cvt_pk_norm_i16_f16 v5, |exec_hi|, null // GFX11: encoding: [0x05,0x01,0x12,0xd7,0x7f,0xf8,0x00,0x00] -v_cvt_pknorm_i16_f16 v5, null, exec_lo +v_cvt_pk_norm_i16_f16 v5, null, exec_lo // GFX11: encoding: [0x05,0x00,0x12,0xd7,0x7c,0xfc,0x00,0x00] -v_cvt_pknorm_i16_f16 v5, -1, exec_hi +v_cvt_pk_norm_i16_f16 v5, -1, exec_hi // GFX11: encoding: [0x05,0x00,0x12,0xd7,0xc1,0xfe,0x00,0x00] -v_cvt_pknorm_i16_f16 v5, 0.5, -m0 op_sel:[0,0,0] +v_cvt_pk_norm_i16_f16 v5, 0.5, -m0 op_sel:[0,0,0] // GFX11: encoding: [0x05,0x00,0x12,0xd7,0xf0,0xfa,0x00,0x40] -v_cvt_pknorm_i16_f16 v5, -src_scc, |vcc_lo| op_sel:[1,0,0] +v_cvt_pk_norm_i16_f16 v5, -src_scc, |vcc_lo| op_sel:[1,0,0] // GFX11: encoding: [0x05,0x0a,0x12,0xd7,0xfd,0xd4,0x00,0x20] -v_cvt_pknorm_i16_f16 v255, -|0xfe0b|, -|vcc_hi| op_sel:[0,1,0] +v_cvt_pk_norm_i16_f16 v255, -|0xfe0b|, -|vcc_hi| op_sel:[0,1,0] // GFX11: encoding: [0xff,0x13,0x12,0xd7,0xff,0xd6,0x00,0x60,0x0b,0xfe,0x00,0x00] -v_cvt_pknorm_i16_f32 v5, v1, v2 +v_cvt_pk_norm_i16_f32 v5, v1, v2 // GFX11: encoding: [0x05,0x00,0x21,0xd7,0x01,0x05,0x02,0x00] -v_cvt_pknorm_i16_f32 v5, v255, v255 +v_cvt_pk_norm_i16_f32 v5, v255, v255 // GFX11: encoding: [0x05,0x00,0x21,0xd7,0xff,0xff,0x03,0x00] -v_cvt_pknorm_i16_f32 v5, s1, s2 +v_cvt_pk_norm_i16_f32 v5, s1, s2 // GFX11: encoding: [0x05,0x00,0x21,0xd7,0x01,0x04,0x00,0x00] -v_cvt_pknorm_i16_f32 v5, s105, s105 +v_cvt_pk_norm_i16_f32 v5, s105, s105 // GFX11: encoding: [0x05,0x00,0x21,0xd7,0x69,0xd2,0x00,0x00] -v_cvt_pknorm_i16_f32 v5, vcc_lo, ttmp15 +v_cvt_pk_norm_i16_f32 v5, vcc_lo, ttmp15 // GFX11: encoding: [0x05,0x00,0x21,0xd7,0x6a,0xf6,0x00,0x00] -v_cvt_pknorm_i16_f32 v5, vcc_hi, 0xaf123456 +v_cvt_pk_norm_i16_f32 v5, vcc_hi, 0xaf123456 // GFX11: encoding: [0x05,0x00,0x21,0xd7,0x6b,0xfe,0x01,0x00,0x56,0x34,0x12,0xaf] -v_cvt_pknorm_i16_f32 v5, ttmp15, src_scc +v_cvt_pk_norm_i16_f32 v5, ttmp15, src_scc // GFX11: encoding: [0x05,0x00,0x21,0xd7,0x7b,0xfa,0x01,0x00] -v_cvt_pknorm_i16_f32 v5, m0, 0.5 +v_cvt_pk_norm_i16_f32 v5, m0, 0.5 // GFX11: encoding: [0x05,0x00,0x21,0xd7,0x7d,0xe0,0x01,0x00] -v_cvt_pknorm_i16_f32 v5, exec_lo, -1 +v_cvt_pk_norm_i16_f32 v5, exec_lo, -1 // GFX11: encoding: [0x05,0x00,0x21,0xd7,0x7e,0x82,0x01,0x00] -v_cvt_pknorm_i16_f32 v5, |exec_hi|, null +v_cvt_pk_norm_i16_f32 v5, |exec_hi|, null // GFX11: encoding: [0x05,0x01,0x21,0xd7,0x7f,0xf8,0x00,0x00] -v_cvt_pknorm_i16_f32 v5, null, exec_lo +v_cvt_pk_norm_i16_f32 v5, null, exec_lo // GFX11: encoding: [0x05,0x00,0x21,0xd7,0x7c,0xfc,0x00,0x00] -v_cvt_pknorm_i16_f32 v5, -1, exec_hi +v_cvt_pk_norm_i16_f32 v5, -1, exec_hi // GFX11: encoding: [0x05,0x00,0x21,0xd7,0xc1,0xfe,0x00,0x00] -v_cvt_pknorm_i16_f32 v5, 0.5, -m0 +v_cvt_pk_norm_i16_f32 v5, 0.5, -m0 // GFX11: encoding: [0x05,0x00,0x21,0xd7,0xf0,0xfa,0x00,0x40] -v_cvt_pknorm_i16_f32 v5, -src_scc, |vcc_lo| +v_cvt_pk_norm_i16_f32 v5, -src_scc, |vcc_lo| // GFX11: encoding: [0x05,0x02,0x21,0xd7,0xfd,0xd4,0x00,0x20] -v_cvt_pknorm_i16_f32 v255, -|0xaf123456|, -|vcc_hi| +v_cvt_pk_norm_i16_f32 v255, -|0xaf123456|, -|vcc_hi| // GFX11: encoding: [0xff,0x03,0x21,0xd7,0xff,0xd6,0x00,0x60,0x56,0x34,0x12,0xaf] -v_cvt_pknorm_u16_f16 v5, v1, v2 +v_cvt_pk_norm_u16_f16 v5, v1, v2 // GFX11: encoding: [0x05,0x00,0x13,0xd7,0x01,0x05,0x02,0x00] -v_cvt_pknorm_u16_f16 v5, v255, v255 +v_cvt_pk_norm_u16_f16 v5, v255, v255 // GFX11: encoding: [0x05,0x00,0x13,0xd7,0xff,0xff,0x03,0x00] -v_cvt_pknorm_u16_f16 v5, s1, s2 +v_cvt_pk_norm_u16_f16 v5, s1, s2 // GFX11: encoding: [0x05,0x00,0x13,0xd7,0x01,0x04,0x00,0x00] -v_cvt_pknorm_u16_f16 v5, s105, s105 +v_cvt_pk_norm_u16_f16 v5, s105, s105 // GFX11: encoding: [0x05,0x00,0x13,0xd7,0x69,0xd2,0x00,0x00] -v_cvt_pknorm_u16_f16 v5, vcc_lo, ttmp15 +v_cvt_pk_norm_u16_f16 v5, vcc_lo, ttmp15 // GFX11: encoding: [0x05,0x00,0x13,0xd7,0x6a,0xf6,0x00,0x00] -v_cvt_pknorm_u16_f16 v5, vcc_hi, 0xfe0b +v_cvt_pk_norm_u16_f16 v5, vcc_hi, 0xfe0b // GFX11: encoding: [0x05,0x00,0x13,0xd7,0x6b,0xfe,0x01,0x00,0x0b,0xfe,0x00,0x00] -v_cvt_pknorm_u16_f16 v5, ttmp15, src_scc +v_cvt_pk_norm_u16_f16 v5, ttmp15, src_scc // GFX11: encoding: [0x05,0x00,0x13,0xd7,0x7b,0xfa,0x01,0x00] -v_cvt_pknorm_u16_f16 v5, m0, 0.5 +v_cvt_pk_norm_u16_f16 v5, m0, 0.5 // GFX11: encoding: [0x05,0x00,0x13,0xd7,0x7d,0xe0,0x01,0x00] -v_cvt_pknorm_u16_f16 v5, exec_lo, -1 +v_cvt_pk_norm_u16_f16 v5, exec_lo, -1 // GFX11: encoding: [0x05,0x00,0x13,0xd7,0x7e,0x82,0x01,0x00] -v_cvt_pknorm_u16_f16 v5, |exec_hi|, null +v_cvt_pk_norm_u16_f16 v5, |exec_hi|, null // GFX11: encoding: [0x05,0x01,0x13,0xd7,0x7f,0xf8,0x00,0x00] -v_cvt_pknorm_u16_f16 v5, null, exec_lo +v_cvt_pk_norm_u16_f16 v5, null, exec_lo // GFX11: encoding: [0x05,0x00,0x13,0xd7,0x7c,0xfc,0x00,0x00] -v_cvt_pknorm_u16_f16 v5, -1, exec_hi +v_cvt_pk_norm_u16_f16 v5, -1, exec_hi // GFX11: encoding: [0x05,0x00,0x13,0xd7,0xc1,0xfe,0x00,0x00] -v_cvt_pknorm_u16_f16 v5, 0.5, -m0 op_sel:[0,0,0] +v_cvt_pk_norm_u16_f16 v5, 0.5, -m0 op_sel:[0,0,0] // GFX11: encoding: [0x05,0x00,0x13,0xd7,0xf0,0xfa,0x00,0x40] -v_cvt_pknorm_u16_f16 v5, -src_scc, |vcc_lo| op_sel:[1,0,0] +v_cvt_pk_norm_u16_f16 v5, -src_scc, |vcc_lo| op_sel:[1,0,0] // GFX11: encoding: [0x05,0x0a,0x13,0xd7,0xfd,0xd4,0x00,0x20] -v_cvt_pknorm_u16_f16 v255, -|0xfe0b|, -|vcc_hi| op_sel:[0,1,0] +v_cvt_pk_norm_u16_f16 v255, -|0xfe0b|, -|vcc_hi| op_sel:[0,1,0] // GFX11: encoding: [0xff,0x13,0x13,0xd7,0xff,0xd6,0x00,0x60,0x0b,0xfe,0x00,0x00] -v_cvt_pknorm_u16_f32 v5, v1, v2 +v_cvt_pk_norm_u16_f32 v5, v1, v2 // GFX11: encoding: [0x05,0x00,0x22,0xd7,0x01,0x05,0x02,0x00] -v_cvt_pknorm_u16_f32 v5, v255, v255 +v_cvt_pk_norm_u16_f32 v5, v255, v255 // GFX11: encoding: [0x05,0x00,0x22,0xd7,0xff,0xff,0x03,0x00] -v_cvt_pknorm_u16_f32 v5, s1, s2 +v_cvt_pk_norm_u16_f32 v5, s1, s2 // GFX11: encoding: [0x05,0x00,0x22,0xd7,0x01,0x04,0x00,0x00] -v_cvt_pknorm_u16_f32 v5, s105, s105 +v_cvt_pk_norm_u16_f32 v5, s105, s105 // GFX11: encoding: [0x05,0x00,0x22,0xd7,0x69,0xd2,0x00,0x00] -v_cvt_pknorm_u16_f32 v5, vcc_lo, ttmp15 +v_cvt_pk_norm_u16_f32 v5, vcc_lo, ttmp15 // GFX11: encoding: [0x05,0x00,0x22,0xd7,0x6a,0xf6,0x00,0x00] -v_cvt_pknorm_u16_f32 v5, vcc_hi, 0xaf123456 +v_cvt_pk_norm_u16_f32 v5, vcc_hi, 0xaf123456 // GFX11: encoding: [0x05,0x00,0x22,0xd7,0x6b,0xfe,0x01,0x00,0x56,0x34,0x12,0xaf] -v_cvt_pknorm_u16_f32 v5, ttmp15, src_scc +v_cvt_pk_norm_u16_f32 v5, ttmp15, src_scc // GFX11: encoding: [0x05,0x00,0x22,0xd7,0x7b,0xfa,0x01,0x00] -v_cvt_pknorm_u16_f32 v5, m0, 0.5 +v_cvt_pk_norm_u16_f32 v5, m0, 0.5 // GFX11: encoding: [0x05,0x00,0x22,0xd7,0x7d,0xe0,0x01,0x00] -v_cvt_pknorm_u16_f32 v5, exec_lo, -1 +v_cvt_pk_norm_u16_f32 v5, exec_lo, -1 // GFX11: encoding: [0x05,0x00,0x22,0xd7,0x7e,0x82,0x01,0x00] -v_cvt_pknorm_u16_f32 v5, |exec_hi|, null +v_cvt_pk_norm_u16_f32 v5, |exec_hi|, null // GFX11: encoding: [0x05,0x01,0x22,0xd7,0x7f,0xf8,0x00,0x00] -v_cvt_pknorm_u16_f32 v5, null, exec_lo +v_cvt_pk_norm_u16_f32 v5, null, exec_lo // GFX11: encoding: [0x05,0x00,0x22,0xd7,0x7c,0xfc,0x00,0x00] -v_cvt_pknorm_u16_f32 v5, -1, exec_hi +v_cvt_pk_norm_u16_f32 v5, -1, exec_hi // GFX11: encoding: [0x05,0x00,0x22,0xd7,0xc1,0xfe,0x00,0x00] -v_cvt_pknorm_u16_f32 v5, 0.5, -m0 +v_cvt_pk_norm_u16_f32 v5, 0.5, -m0 // GFX11: encoding: [0x05,0x00,0x22,0xd7,0xf0,0xfa,0x00,0x40] -v_cvt_pknorm_u16_f32 v5, -src_scc, |vcc_lo| +v_cvt_pk_norm_u16_f32 v5, -src_scc, |vcc_lo| // GFX11: encoding: [0x05,0x02,0x22,0xd7,0xfd,0xd4,0x00,0x20] -v_cvt_pknorm_u16_f32 v255, -|0xaf123456|, -|vcc_hi| +v_cvt_pk_norm_u16_f32 v255, -|0xaf123456|, -|vcc_hi| // GFX11: encoding: [0xff,0x03,0x22,0xd7,0xff,0xd6,0x00,0x60,0x56,0x34,0x12,0xaf] v_div_fixup_f16 v5, v1, v2, s3 diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_alias.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_alias.s new file mode 100644 --- /dev/null +++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_alias.s @@ -0,0 +1,8 @@ +// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32,-wavefrontsize64 -show-encoding %s | FileCheck -check-prefix=GFX11 %s +// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1100 -mattr=-wavefrontsize32,+wavefrontsize64 -show-encoding %s | FileCheck -check-prefix=GFX11 %s + +v_cvt_pknorm_i16_f16 v5, v1, v2 +// GFX11: v_cvt_pk_norm_i16_f16 {{.*}} encoding: [0x05,0x00,0x12,0xd7,0x01,0x05,0x02,0x00] + +v_cvt_pknorm_u16_f16 v5, v1, v2 +// GFX11: v_cvt_pk_norm_u16_f16 {{.*}} encoding: [0x05,0x00,0x13,0xd7,0x01,0x05,0x02,0x00] diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s --- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s +++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s @@ -1309,172 +1309,172 @@ v_cvt_pk_u8_f32_e64_dpp v255, -|v255|, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1 // GFX11: [0xff,0x01,0x26,0xd6,0xfa,0xfe,0xf7,0x23,0xff,0x6f,0x0d,0x30] -v_cvt_pknorm_i16_f16_e64_dpp v5, v1, v2 quad_perm:[3,2,1,0] +v_cvt_pk_norm_i16_f16_e64_dpp v5, v1, v2 quad_perm:[3,2,1,0] // GFX11: [0x05,0x00,0x12,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff] -v_cvt_pknorm_i16_f16_e64_dpp v5, v1, v2 quad_perm:[0,1,2,3] +v_cvt_pk_norm_i16_f16_e64_dpp v5, v1, v2 quad_perm:[0,1,2,3] // GFX11: [0x05,0x00,0x12,0xd7,0xfa,0x04,0x02,0x00,0x01,0xe4,0x00,0xff] -v_cvt_pknorm_i16_f16_e64_dpp v5, v1, v2 row_mirror +v_cvt_pk_norm_i16_f16_e64_dpp v5, v1, v2 row_mirror // GFX11: [0x05,0x00,0x12,0xd7,0xfa,0x04,0x02,0x00,0x01,0x40,0x01,0xff] -v_cvt_pknorm_i16_f16_e64_dpp v5, v1, v2 row_half_mirror +v_cvt_pk_norm_i16_f16_e64_dpp v5, v1, v2 row_half_mirror // GFX11: [0x05,0x00,0x12,0xd7,0xfa,0x04,0x02,0x00,0x01,0x41,0x01,0xff] -v_cvt_pknorm_i16_f16_e64_dpp v5, v1, v2 row_shl:1 +v_cvt_pk_norm_i16_f16_e64_dpp v5, v1, v2 row_shl:1 // GFX11: [0x05,0x00,0x12,0xd7,0xfa,0x04,0x02,0x00,0x01,0x01,0x01,0xff] -v_cvt_pknorm_i16_f16_e64_dpp v5, v1, v2 row_shl:15 +v_cvt_pk_norm_i16_f16_e64_dpp v5, v1, v2 row_shl:15 // GFX11: [0x05,0x00,0x12,0xd7,0xfa,0x04,0x02,0x00,0x01,0x0f,0x01,0xff] -v_cvt_pknorm_i16_f16_e64_dpp v5, v1, v2 row_shr:1 +v_cvt_pk_norm_i16_f16_e64_dpp v5, v1, v2 row_shr:1 // GFX11: [0x05,0x00,0x12,0xd7,0xfa,0x04,0x02,0x00,0x01,0x11,0x01,0xff] -v_cvt_pknorm_i16_f16_e64_dpp v5, v1, v2 row_shr:15 +v_cvt_pk_norm_i16_f16_e64_dpp v5, v1, v2 row_shr:15 // GFX11: [0x05,0x00,0x12,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1f,0x01,0xff] -v_cvt_pknorm_i16_f16_e64_dpp v5, v1, v2 row_ror:1 +v_cvt_pk_norm_i16_f16_e64_dpp v5, v1, v2 row_ror:1 // GFX11: [0x05,0x00,0x12,0xd7,0xfa,0x04,0x02,0x00,0x01,0x21,0x01,0xff] -v_cvt_pknorm_i16_f16_e64_dpp v5, v1, v2 row_ror:15 +v_cvt_pk_norm_i16_f16_e64_dpp v5, v1, v2 row_ror:15 // GFX11: [0x05,0x00,0x12,0xd7,0xfa,0x04,0x02,0x00,0x01,0x2f,0x01,0xff] -v_cvt_pknorm_i16_f16_e64_dpp v5, v1, v2 row_share:0 row_mask:0xf bank_mask:0xf +v_cvt_pk_norm_i16_f16_e64_dpp v5, v1, v2 row_share:0 row_mask:0xf bank_mask:0xf // GFX11: [0x05,0x00,0x12,0xd7,0xfa,0x04,0x02,0x00,0x01,0x50,0x01,0xff] -v_cvt_pknorm_i16_f16_e64_dpp v5, |v1|, -v2 row_share:15 row_mask:0x0 bank_mask:0x1 +v_cvt_pk_norm_i16_f16_e64_dpp v5, |v1|, -v2 row_share:15 row_mask:0x0 bank_mask:0x1 // GFX11: [0x05,0x01,0x12,0xd7,0xfa,0x04,0x02,0x40,0x01,0x5f,0x01,0x01] -v_cvt_pknorm_i16_f16_e64_dpp v5, -v1, |v2| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0 +v_cvt_pk_norm_i16_f16_e64_dpp v5, -v1, |v2| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0 // GFX11: [0x05,0x02,0x12,0xd7,0xfa,0x04,0x02,0x20,0x01,0x60,0x09,0x13] -v_cvt_pknorm_i16_f16_e64_dpp v255, -|v255|, -|v255| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1 +v_cvt_pk_norm_i16_f16_e64_dpp v255, -|v255|, -|v255| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1 // GFX11: [0xff,0x03,0x12,0xd7,0xfa,0xfe,0x03,0x60,0xff,0x6f,0x0d,0x30] -v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 quad_perm:[3,2,1,0] +v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 quad_perm:[3,2,1,0] // GFX11: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff] -v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 quad_perm:[0,1,2,3] +v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 quad_perm:[0,1,2,3] // GFX11: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0xe4,0x00,0xff] -v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 row_mirror +v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 row_mirror // GFX11: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x40,0x01,0xff] -v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 row_half_mirror +v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 row_half_mirror // GFX11: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x41,0x01,0xff] -v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 row_shl:1 +v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 row_shl:1 // GFX11: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x01,0x01,0xff] -v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 row_shl:15 +v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 row_shl:15 // GFX11: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x0f,0x01,0xff] -v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 row_shr:1 +v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 row_shr:1 // GFX11: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x11,0x01,0xff] -v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 row_shr:15 +v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 row_shr:15 // GFX11: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1f,0x01,0xff] -v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 row_ror:1 +v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 row_ror:1 // GFX11: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x21,0x01,0xff] -v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 row_ror:15 +v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 row_ror:15 // GFX11: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x2f,0x01,0xff] -v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 row_share:0 row_mask:0xf bank_mask:0xf +v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 row_share:0 row_mask:0xf bank_mask:0xf // GFX11: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x50,0x01,0xff] -v_cvt_pknorm_i16_f32_e64_dpp v5, |v1|, -v2 row_share:15 row_mask:0x0 bank_mask:0x1 +v_cvt_pk_norm_i16_f32_e64_dpp v5, |v1|, -v2 row_share:15 row_mask:0x0 bank_mask:0x1 // GFX11: [0x05,0x01,0x21,0xd7,0xfa,0x04,0x02,0x40,0x01,0x5f,0x01,0x01] -v_cvt_pknorm_i16_f32_e64_dpp v5, -v1, |v2| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0 +v_cvt_pk_norm_i16_f32_e64_dpp v5, -v1, |v2| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0 // GFX11: [0x05,0x02,0x21,0xd7,0xfa,0x04,0x02,0x20,0x01,0x60,0x09,0x13] -v_cvt_pknorm_i16_f32_e64_dpp v255, -|v255|, -|v255| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1 +v_cvt_pk_norm_i16_f32_e64_dpp v255, -|v255|, -|v255| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1 // GFX11: [0xff,0x03,0x21,0xd7,0xfa,0xfe,0x03,0x60,0xff,0x6f,0x0d,0x30] -v_cvt_pknorm_u16_f16_e64_dpp v5, v1, v2 quad_perm:[3,2,1,0] +v_cvt_pk_norm_u16_f16_e64_dpp v5, v1, v2 quad_perm:[3,2,1,0] // GFX11: [0x05,0x00,0x13,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff] -v_cvt_pknorm_u16_f16_e64_dpp v5, v1, v2 quad_perm:[0,1,2,3] +v_cvt_pk_norm_u16_f16_e64_dpp v5, v1, v2 quad_perm:[0,1,2,3] // GFX11: [0x05,0x00,0x13,0xd7,0xfa,0x04,0x02,0x00,0x01,0xe4,0x00,0xff] -v_cvt_pknorm_u16_f16_e64_dpp v5, v1, v2 row_mirror +v_cvt_pk_norm_u16_f16_e64_dpp v5, v1, v2 row_mirror // GFX11: [0x05,0x00,0x13,0xd7,0xfa,0x04,0x02,0x00,0x01,0x40,0x01,0xff] -v_cvt_pknorm_u16_f16_e64_dpp v5, v1, v2 row_half_mirror +v_cvt_pk_norm_u16_f16_e64_dpp v5, v1, v2 row_half_mirror // GFX11: [0x05,0x00,0x13,0xd7,0xfa,0x04,0x02,0x00,0x01,0x41,0x01,0xff] -v_cvt_pknorm_u16_f16_e64_dpp v5, v1, v2 row_shl:1 +v_cvt_pk_norm_u16_f16_e64_dpp v5, v1, v2 row_shl:1 // GFX11: [0x05,0x00,0x13,0xd7,0xfa,0x04,0x02,0x00,0x01,0x01,0x01,0xff] -v_cvt_pknorm_u16_f16_e64_dpp v5, v1, v2 row_shl:15 +v_cvt_pk_norm_u16_f16_e64_dpp v5, v1, v2 row_shl:15 // GFX11: [0x05,0x00,0x13,0xd7,0xfa,0x04,0x02,0x00,0x01,0x0f,0x01,0xff] -v_cvt_pknorm_u16_f16_e64_dpp v5, v1, v2 row_shr:1 +v_cvt_pk_norm_u16_f16_e64_dpp v5, v1, v2 row_shr:1 // GFX11: [0x05,0x00,0x13,0xd7,0xfa,0x04,0x02,0x00,0x01,0x11,0x01,0xff] -v_cvt_pknorm_u16_f16_e64_dpp v5, v1, v2 row_shr:15 +v_cvt_pk_norm_u16_f16_e64_dpp v5, v1, v2 row_shr:15 // GFX11: [0x05,0x00,0x13,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1f,0x01,0xff] -v_cvt_pknorm_u16_f16_e64_dpp v5, v1, v2 row_ror:1 +v_cvt_pk_norm_u16_f16_e64_dpp v5, v1, v2 row_ror:1 // GFX11: [0x05,0x00,0x13,0xd7,0xfa,0x04,0x02,0x00,0x01,0x21,0x01,0xff] -v_cvt_pknorm_u16_f16_e64_dpp v5, v1, v2 row_ror:15 +v_cvt_pk_norm_u16_f16_e64_dpp v5, v1, v2 row_ror:15 // GFX11: [0x05,0x00,0x13,0xd7,0xfa,0x04,0x02,0x00,0x01,0x2f,0x01,0xff] -v_cvt_pknorm_u16_f16_e64_dpp v5, v1, v2 row_share:0 row_mask:0xf bank_mask:0xf +v_cvt_pk_norm_u16_f16_e64_dpp v5, v1, v2 row_share:0 row_mask:0xf bank_mask:0xf // GFX11: [0x05,0x00,0x13,0xd7,0xfa,0x04,0x02,0x00,0x01,0x50,0x01,0xff] -v_cvt_pknorm_u16_f16_e64_dpp v5, |v1|, -v2 row_share:15 row_mask:0x0 bank_mask:0x1 +v_cvt_pk_norm_u16_f16_e64_dpp v5, |v1|, -v2 row_share:15 row_mask:0x0 bank_mask:0x1 // GFX11: [0x05,0x01,0x13,0xd7,0xfa,0x04,0x02,0x40,0x01,0x5f,0x01,0x01] -v_cvt_pknorm_u16_f16_e64_dpp v5, -v1, |v2| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0 +v_cvt_pk_norm_u16_f16_e64_dpp v5, -v1, |v2| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0 // GFX11: [0x05,0x02,0x13,0xd7,0xfa,0x04,0x02,0x20,0x01,0x60,0x09,0x13] -v_cvt_pknorm_u16_f16_e64_dpp v255, -|v255|, -|v255| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1 +v_cvt_pk_norm_u16_f16_e64_dpp v255, -|v255|, -|v255| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1 // GFX11: [0xff,0x03,0x13,0xd7,0xfa,0xfe,0x03,0x60,0xff,0x6f,0x0d,0x30] -v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 quad_perm:[3,2,1,0] +v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 quad_perm:[3,2,1,0] // GFX11: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff] -v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 quad_perm:[0,1,2,3] +v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 quad_perm:[0,1,2,3] // GFX11: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0xe4,0x00,0xff] -v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 row_mirror +v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 row_mirror // GFX11: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x40,0x01,0xff] -v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 row_half_mirror +v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 row_half_mirror // GFX11: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x41,0x01,0xff] -v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 row_shl:1 +v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 row_shl:1 // GFX11: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x01,0x01,0xff] -v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 row_shl:15 +v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 row_shl:15 // GFX11: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x0f,0x01,0xff] -v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 row_shr:1 +v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 row_shr:1 // GFX11: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x11,0x01,0xff] -v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 row_shr:15 +v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 row_shr:15 // GFX11: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1f,0x01,0xff] -v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 row_ror:1 +v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 row_ror:1 // GFX11: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x21,0x01,0xff] -v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 row_ror:15 +v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 row_ror:15 // GFX11: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x2f,0x01,0xff] -v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 row_share:0 row_mask:0xf bank_mask:0xf +v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 row_share:0 row_mask:0xf bank_mask:0xf // GFX11: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x50,0x01,0xff] -v_cvt_pknorm_u16_f32_e64_dpp v5, |v1|, -v2 row_share:15 row_mask:0x0 bank_mask:0x1 +v_cvt_pk_norm_u16_f32_e64_dpp v5, |v1|, -v2 row_share:15 row_mask:0x0 bank_mask:0x1 // GFX11: [0x05,0x01,0x22,0xd7,0xfa,0x04,0x02,0x40,0x01,0x5f,0x01,0x01] -v_cvt_pknorm_u16_f32_e64_dpp v5, -v1, |v2| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0 +v_cvt_pk_norm_u16_f32_e64_dpp v5, -v1, |v2| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0 // GFX11: [0x05,0x02,0x22,0xd7,0xfa,0x04,0x02,0x20,0x01,0x60,0x09,0x13] -v_cvt_pknorm_u16_f32_e64_dpp v255, -|v255|, -|v255| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1 +v_cvt_pk_norm_u16_f32_e64_dpp v255, -|v255|, -|v255| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1 // GFX11: [0xff,0x03,0x22,0xd7,0xfa,0xfe,0x03,0x60,0xff,0x6f,0x0d,0x30] v_div_fixup_f16_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s --- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s +++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s @@ -672,52 +672,52 @@ v_cvt_pk_u8_f32_e64_dpp v255, -|v255|, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0 // GFX11: [0xff,0x01,0x26,0xd6,0xe9,0xfe,0xf7,0x23,0xff,0x00,0x00,0x00] -v_cvt_pknorm_i16_f16_e64_dpp v5, v1, v2 dpp8:[7,6,5,4,3,2,1,0] +v_cvt_pk_norm_i16_f16_e64_dpp v5, v1, v2 dpp8:[7,6,5,4,3,2,1,0] // GFX11: [0x05,0x00,0x12,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05] -v_cvt_pknorm_i16_f16_e64_dpp v5, |v1|, -v2 dpp8:[7,6,5,4,3,2,1,0] +v_cvt_pk_norm_i16_f16_e64_dpp v5, |v1|, -v2 dpp8:[7,6,5,4,3,2,1,0] // GFX11: [0x05,0x01,0x12,0xd7,0xe9,0x04,0x02,0x40,0x01,0x77,0x39,0x05] -v_cvt_pknorm_i16_f16_e64_dpp v5, -v1, |v2| dpp8:[7,6,5,4,3,2,1,0] fi:1 +v_cvt_pk_norm_i16_f16_e64_dpp v5, -v1, |v2| dpp8:[7,6,5,4,3,2,1,0] fi:1 // GFX11: [0x05,0x02,0x12,0xd7,0xea,0x04,0x02,0x20,0x01,0x77,0x39,0x05] -v_cvt_pknorm_i16_f16_e64_dpp v255, -|v255|, -|v255| dpp8:[0,0,0,0,0,0,0,0] fi:0 +v_cvt_pk_norm_i16_f16_e64_dpp v255, -|v255|, -|v255| dpp8:[0,0,0,0,0,0,0,0] fi:0 // GFX11: [0xff,0x03,0x12,0xd7,0xe9,0xfe,0x03,0x60,0xff,0x00,0x00,0x00] -v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 dpp8:[7,6,5,4,3,2,1,0] +v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 dpp8:[7,6,5,4,3,2,1,0] // GFX11: [0x05,0x00,0x21,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05] -v_cvt_pknorm_i16_f32_e64_dpp v5, |v1|, -v2 dpp8:[7,6,5,4,3,2,1,0] +v_cvt_pk_norm_i16_f32_e64_dpp v5, |v1|, -v2 dpp8:[7,6,5,4,3,2,1,0] // GFX11: [0x05,0x01,0x21,0xd7,0xe9,0x04,0x02,0x40,0x01,0x77,0x39,0x05] -v_cvt_pknorm_i16_f32_e64_dpp v5, -v1, |v2| dpp8:[7,6,5,4,3,2,1,0] fi:1 +v_cvt_pk_norm_i16_f32_e64_dpp v5, -v1, |v2| dpp8:[7,6,5,4,3,2,1,0] fi:1 // GFX11: [0x05,0x02,0x21,0xd7,0xea,0x04,0x02,0x20,0x01,0x77,0x39,0x05] -v_cvt_pknorm_i16_f32_e64_dpp v255, -|v255|, -|v255| dpp8:[0,0,0,0,0,0,0,0] fi:0 +v_cvt_pk_norm_i16_f32_e64_dpp v255, -|v255|, -|v255| dpp8:[0,0,0,0,0,0,0,0] fi:0 // GFX11: [0xff,0x03,0x21,0xd7,0xe9,0xfe,0x03,0x60,0xff,0x00,0x00,0x00] -v_cvt_pknorm_u16_f16_e64_dpp v5, v1, v2 dpp8:[7,6,5,4,3,2,1,0] +v_cvt_pk_norm_u16_f16_e64_dpp v5, v1, v2 dpp8:[7,6,5,4,3,2,1,0] // GFX11: [0x05,0x00,0x13,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05] -v_cvt_pknorm_u16_f16_e64_dpp v5, |v1|, -v2 dpp8:[7,6,5,4,3,2,1,0] +v_cvt_pk_norm_u16_f16_e64_dpp v5, |v1|, -v2 dpp8:[7,6,5,4,3,2,1,0] // GFX11: [0x05,0x01,0x13,0xd7,0xe9,0x04,0x02,0x40,0x01,0x77,0x39,0x05] -v_cvt_pknorm_u16_f16_e64_dpp v5, -v1, |v2| dpp8:[7,6,5,4,3,2,1,0] fi:1 +v_cvt_pk_norm_u16_f16_e64_dpp v5, -v1, |v2| dpp8:[7,6,5,4,3,2,1,0] fi:1 // GFX11: [0x05,0x02,0x13,0xd7,0xea,0x04,0x02,0x20,0x01,0x77,0x39,0x05] -v_cvt_pknorm_u16_f16_e64_dpp v255, -|v255|, -|v255| dpp8:[0,0,0,0,0,0,0,0] fi:0 +v_cvt_pk_norm_u16_f16_e64_dpp v255, -|v255|, -|v255| dpp8:[0,0,0,0,0,0,0,0] fi:0 // GFX11: [0xff,0x03,0x13,0xd7,0xe9,0xfe,0x03,0x60,0xff,0x00,0x00,0x00] -v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 dpp8:[7,6,5,4,3,2,1,0] +v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 dpp8:[7,6,5,4,3,2,1,0] // GFX11: [0x05,0x00,0x22,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05] -v_cvt_pknorm_u16_f32_e64_dpp v5, |v1|, -v2 dpp8:[7,6,5,4,3,2,1,0] +v_cvt_pk_norm_u16_f32_e64_dpp v5, |v1|, -v2 dpp8:[7,6,5,4,3,2,1,0] // GFX11: [0x05,0x01,0x22,0xd7,0xe9,0x04,0x02,0x40,0x01,0x77,0x39,0x05] -v_cvt_pknorm_u16_f32_e64_dpp v5, -v1, |v2| dpp8:[7,6,5,4,3,2,1,0] fi:1 +v_cvt_pk_norm_u16_f32_e64_dpp v5, -v1, |v2| dpp8:[7,6,5,4,3,2,1,0] fi:1 // GFX11: [0x05,0x02,0x22,0xd7,0xea,0x04,0x02,0x20,0x01,0x77,0x39,0x05] -v_cvt_pknorm_u16_f32_e64_dpp v255, -|v255|, -|v255| dpp8:[0,0,0,0,0,0,0,0] fi:0 +v_cvt_pk_norm_u16_f32_e64_dpp v255, -|v255|, -|v255| dpp8:[0,0,0,0,0,0,0,0] fi:0 // GFX11: [0xff,0x03,0x22,0xd7,0xe9,0xfe,0x03,0x60,0xff,0x00,0x00,0x00] v_div_fixup_f16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt --- a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt +++ b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt @@ -1344,94 +1344,94 @@ # GFX11: v_cvt_pk_u8_f32 v255, -|0xaf123456|, vcc_hi, null ; encoding: [0xff,0x01,0x26,0xd6,0xff,0xd6,0xf0,0x21,0x56,0x34,0x12,0xaf] 0xff,0x01,0x26,0xd6,0xff,0xd6,0xf0,0x21,0x56,0x34,0x12,0xaf -# GFX11: v_cvt_pknorm_i16_f32 v5, v1, v2 ; encoding: [0x05,0x00,0x21,0xd7,0x01,0x05,0x02,0x00] +# GFX11: v_cvt_pk_norm_i16_f32 v5, v1, v2 ; encoding: [0x05,0x00,0x21,0xd7,0x01,0x05,0x02,0x00] 0x05,0x00,0x21,0xd7,0x01,0x05,0x02,0x00 -# GFX11: v_cvt_pknorm_i16_f32 v5, v255, v255 ; encoding: [0x05,0x00,0x21,0xd7,0xff,0xff,0x03,0x00] +# GFX11: v_cvt_pk_norm_i16_f32 v5, v255, v255 ; encoding: [0x05,0x00,0x21,0xd7,0xff,0xff,0x03,0x00] 0x05,0x00,0x21,0xd7,0xff,0xff,0x03,0x00 -# GFX11: v_cvt_pknorm_i16_f32 v5, s1, s2 ; encoding: [0x05,0x00,0x21,0xd7,0x01,0x04,0x00,0x00] +# GFX11: v_cvt_pk_norm_i16_f32 v5, s1, s2 ; encoding: [0x05,0x00,0x21,0xd7,0x01,0x04,0x00,0x00] 0x05,0x00,0x21,0xd7,0x01,0x04,0x00,0x00 -# GFX11: v_cvt_pknorm_i16_f32 v5, s105, s105 ; encoding: [0x05,0x00,0x21,0xd7,0x69,0xd2,0x00,0x00] +# GFX11: v_cvt_pk_norm_i16_f32 v5, s105, s105 ; encoding: [0x05,0x00,0x21,0xd7,0x69,0xd2,0x00,0x00] 0x05,0x00,0x21,0xd7,0x69,0xd2,0x00,0x00 -# GFX11: v_cvt_pknorm_i16_f32 v5, vcc_lo, ttmp15 ; encoding: [0x05,0x00,0x21,0xd7,0x6a,0xf6,0x00,0x00] +# GFX11: v_cvt_pk_norm_i16_f32 v5, vcc_lo, ttmp15 ; encoding: [0x05,0x00,0x21,0xd7,0x6a,0xf6,0x00,0x00] 0x05,0x00,0x21,0xd7,0x6a,0xf6,0x00,0x00 -# GFX11: v_cvt_pknorm_i16_f32 v5, vcc_hi, 0xaf123456 ; encoding: [0x05,0x00,0x21,0xd7,0x6b,0xfe,0x01,0x00,0x56,0x34,0x12,0xaf] +# GFX11: v_cvt_pk_norm_i16_f32 v5, vcc_hi, 0xaf123456 ; encoding: [0x05,0x00,0x21,0xd7,0x6b,0xfe,0x01,0x00,0x56,0x34,0x12,0xaf] 0x05,0x00,0x21,0xd7,0x6b,0xfe,0x01,0x00,0x56,0x34,0x12,0xaf -# GFX11: v_cvt_pknorm_i16_f32 v5, ttmp15, src_scc ; encoding: [0x05,0x00,0x21,0xd7,0x7b,0xfa,0x01,0x00] +# GFX11: v_cvt_pk_norm_i16_f32 v5, ttmp15, src_scc ; encoding: [0x05,0x00,0x21,0xd7,0x7b,0xfa,0x01,0x00] 0x05,0x00,0x21,0xd7,0x7b,0xfa,0x01,0x00 -# GFX11: v_cvt_pknorm_i16_f32 v5, m0, 0.5 ; encoding: [0x05,0x00,0x21,0xd7,0x7d,0xe0,0x01,0x00] +# GFX11: v_cvt_pk_norm_i16_f32 v5, m0, 0.5 ; encoding: [0x05,0x00,0x21,0xd7,0x7d,0xe0,0x01,0x00] 0x05,0x00,0x21,0xd7,0x7d,0xe0,0x01,0x00 -# GFX11: v_cvt_pknorm_i16_f32 v5, exec_lo, -1 ; encoding: [0x05,0x00,0x21,0xd7,0x7e,0x82,0x01,0x00] +# GFX11: v_cvt_pk_norm_i16_f32 v5, exec_lo, -1 ; encoding: [0x05,0x00,0x21,0xd7,0x7e,0x82,0x01,0x00] 0x05,0x00,0x21,0xd7,0x7e,0x82,0x01,0x00 -# GFX11: v_cvt_pknorm_i16_f32 v5, |exec_hi|, null ; encoding: [0x05,0x01,0x21,0xd7,0x7f,0xf8,0x00,0x00] +# GFX11: v_cvt_pk_norm_i16_f32 v5, |exec_hi|, null ; encoding: [0x05,0x01,0x21,0xd7,0x7f,0xf8,0x00,0x00] 0x05,0x01,0x21,0xd7,0x7f,0xf8,0x00,0x00 -# GFX11: v_cvt_pknorm_i16_f32 v5, null, exec_lo ; encoding: [0x05,0x00,0x21,0xd7,0x7c,0xfc,0x00,0x00] +# GFX11: v_cvt_pk_norm_i16_f32 v5, null, exec_lo ; encoding: [0x05,0x00,0x21,0xd7,0x7c,0xfc,0x00,0x00] 0x05,0x00,0x21,0xd7,0x7c,0xfc,0x00,0x00 -# GFX11: v_cvt_pknorm_i16_f32 v5, -1, exec_hi ; encoding: [0x05,0x00,0x21,0xd7,0xc1,0xfe,0x00,0x00] +# GFX11: v_cvt_pk_norm_i16_f32 v5, -1, exec_hi ; encoding: [0x05,0x00,0x21,0xd7,0xc1,0xfe,0x00,0x00] 0x05,0x00,0x21,0xd7,0xc1,0xfe,0x00,0x00 -# GFX11: v_cvt_pknorm_i16_f32 v5, 0.5, -m0 ; encoding: [0x05,0x00,0x21,0xd7,0xf0,0xfa,0x00,0x40] +# GFX11: v_cvt_pk_norm_i16_f32 v5, 0.5, -m0 ; encoding: [0x05,0x00,0x21,0xd7,0xf0,0xfa,0x00,0x40] 0x05,0x00,0x21,0xd7,0xf0,0xfa,0x00,0x40 -# GFX11: v_cvt_pknorm_i16_f32 v5, -src_scc, |vcc_lo| ; encoding: [0x05,0x02,0x21,0xd7,0xfd,0xd4,0x00,0x20] +# GFX11: v_cvt_pk_norm_i16_f32 v5, -src_scc, |vcc_lo| ; encoding: [0x05,0x02,0x21,0xd7,0xfd,0xd4,0x00,0x20] 0x05,0x02,0x21,0xd7,0xfd,0xd4,0x00,0x20 -# GFX11: v_cvt_pknorm_i16_f32 v255, -|0xaf123456|, -|vcc_hi| ; encoding: [0xff,0x03,0x21,0xd7,0xff,0xd6,0x00,0x60,0x56,0x34,0x12,0xaf] +# GFX11: v_cvt_pk_norm_i16_f32 v255, -|0xaf123456|, -|vcc_hi| ; encoding: [0xff,0x03,0x21,0xd7,0xff,0xd6,0x00,0x60,0x56,0x34,0x12,0xaf] 0xff,0x03,0x21,0xd7,0xff,0xd6,0x00,0x60,0x56,0x34,0x12,0xaf -# GFX11: v_cvt_pknorm_u16_f32 v5, v1, v2 ; encoding: [0x05,0x00,0x22,0xd7,0x01,0x05,0x02,0x00] +# GFX11: v_cvt_pk_norm_u16_f32 v5, v1, v2 ; encoding: [0x05,0x00,0x22,0xd7,0x01,0x05,0x02,0x00] 0x05,0x00,0x22,0xd7,0x01,0x05,0x02,0x00 -# GFX11: v_cvt_pknorm_u16_f32 v5, v255, v255 ; encoding: [0x05,0x00,0x22,0xd7,0xff,0xff,0x03,0x00] +# GFX11: v_cvt_pk_norm_u16_f32 v5, v255, v255 ; encoding: [0x05,0x00,0x22,0xd7,0xff,0xff,0x03,0x00] 0x05,0x00,0x22,0xd7,0xff,0xff,0x03,0x00 -# GFX11: v_cvt_pknorm_u16_f32 v5, s1, s2 ; encoding: [0x05,0x00,0x22,0xd7,0x01,0x04,0x00,0x00] +# GFX11: v_cvt_pk_norm_u16_f32 v5, s1, s2 ; encoding: [0x05,0x00,0x22,0xd7,0x01,0x04,0x00,0x00] 0x05,0x00,0x22,0xd7,0x01,0x04,0x00,0x00 -# GFX11: v_cvt_pknorm_u16_f32 v5, s105, s105 ; encoding: [0x05,0x00,0x22,0xd7,0x69,0xd2,0x00,0x00] +# GFX11: v_cvt_pk_norm_u16_f32 v5, s105, s105 ; encoding: [0x05,0x00,0x22,0xd7,0x69,0xd2,0x00,0x00] 0x05,0x00,0x22,0xd7,0x69,0xd2,0x00,0x00 -# GFX11: v_cvt_pknorm_u16_f32 v5, vcc_lo, ttmp15 ; encoding: [0x05,0x00,0x22,0xd7,0x6a,0xf6,0x00,0x00] +# GFX11: v_cvt_pk_norm_u16_f32 v5, vcc_lo, ttmp15 ; encoding: [0x05,0x00,0x22,0xd7,0x6a,0xf6,0x00,0x00] 0x05,0x00,0x22,0xd7,0x6a,0xf6,0x00,0x00 -# GFX11: v_cvt_pknorm_u16_f32 v5, vcc_hi, 0xaf123456 ; encoding: [0x05,0x00,0x22,0xd7,0x6b,0xfe,0x01,0x00,0x56,0x34,0x12,0xaf] +# GFX11: v_cvt_pk_norm_u16_f32 v5, vcc_hi, 0xaf123456 ; encoding: [0x05,0x00,0x22,0xd7,0x6b,0xfe,0x01,0x00,0x56,0x34,0x12,0xaf] 0x05,0x00,0x22,0xd7,0x6b,0xfe,0x01,0x00,0x56,0x34,0x12,0xaf -# GFX11: v_cvt_pknorm_u16_f32 v5, ttmp15, src_scc ; encoding: [0x05,0x00,0x22,0xd7,0x7b,0xfa,0x01,0x00] +# GFX11: v_cvt_pk_norm_u16_f32 v5, ttmp15, src_scc ; encoding: [0x05,0x00,0x22,0xd7,0x7b,0xfa,0x01,0x00] 0x05,0x00,0x22,0xd7,0x7b,0xfa,0x01,0x00 -# GFX11: v_cvt_pknorm_u16_f32 v5, m0, 0.5 ; encoding: [0x05,0x00,0x22,0xd7,0x7d,0xe0,0x01,0x00] +# GFX11: v_cvt_pk_norm_u16_f32 v5, m0, 0.5 ; encoding: [0x05,0x00,0x22,0xd7,0x7d,0xe0,0x01,0x00] 0x05,0x00,0x22,0xd7,0x7d,0xe0,0x01,0x00 -# GFX11: v_cvt_pknorm_u16_f32 v5, exec_lo, -1 ; encoding: [0x05,0x00,0x22,0xd7,0x7e,0x82,0x01,0x00] +# GFX11: v_cvt_pk_norm_u16_f32 v5, exec_lo, -1 ; encoding: [0x05,0x00,0x22,0xd7,0x7e,0x82,0x01,0x00] 0x05,0x00,0x22,0xd7,0x7e,0x82,0x01,0x00 -# GFX11: v_cvt_pknorm_u16_f32 v5, |exec_hi|, null ; encoding: [0x05,0x01,0x22,0xd7,0x7f,0xf8,0x00,0x00] +# GFX11: v_cvt_pk_norm_u16_f32 v5, |exec_hi|, null ; encoding: [0x05,0x01,0x22,0xd7,0x7f,0xf8,0x00,0x00] 0x05,0x01,0x22,0xd7,0x7f,0xf8,0x00,0x00 -# GFX11: v_cvt_pknorm_u16_f32 v5, null, exec_lo ; encoding: [0x05,0x00,0x22,0xd7,0x7c,0xfc,0x00,0x00] +# GFX11: v_cvt_pk_norm_u16_f32 v5, null, exec_lo ; encoding: [0x05,0x00,0x22,0xd7,0x7c,0xfc,0x00,0x00] 0x05,0x00,0x22,0xd7,0x7c,0xfc,0x00,0x00 -# GFX11: v_cvt_pknorm_u16_f32 v5, -1, exec_hi ; encoding: [0x05,0x00,0x22,0xd7,0xc1,0xfe,0x00,0x00] +# GFX11: v_cvt_pk_norm_u16_f32 v5, -1, exec_hi ; encoding: [0x05,0x00,0x22,0xd7,0xc1,0xfe,0x00,0x00] 0x05,0x00,0x22,0xd7,0xc1,0xfe,0x00,0x00 -# GFX11: v_cvt_pknorm_u16_f32 v5, 0.5, -m0 ; encoding: [0x05,0x00,0x22,0xd7,0xf0,0xfa,0x00,0x40] +# GFX11: v_cvt_pk_norm_u16_f32 v5, 0.5, -m0 ; encoding: [0x05,0x00,0x22,0xd7,0xf0,0xfa,0x00,0x40] 0x05,0x00,0x22,0xd7,0xf0,0xfa,0x00,0x40 -# GFX11: v_cvt_pknorm_u16_f32 v5, -src_scc, |vcc_lo| ; encoding: [0x05,0x02,0x22,0xd7,0xfd,0xd4,0x00,0x20] +# GFX11: v_cvt_pk_norm_u16_f32 v5, -src_scc, |vcc_lo| ; encoding: [0x05,0x02,0x22,0xd7,0xfd,0xd4,0x00,0x20] 0x05,0x02,0x22,0xd7,0xfd,0xd4,0x00,0x20 -# GFX11: v_cvt_pknorm_u16_f32 v255, -|0xaf123456|, -|vcc_hi| ; encoding: [0xff,0x03,0x22,0xd7,0xff,0xd6,0x00,0x60,0x56,0x34,0x12,0xaf] +# GFX11: v_cvt_pk_norm_u16_f32 v255, -|0xaf123456|, -|vcc_hi| ; encoding: [0xff,0x03,0x22,0xd7,0xff,0xd6,0x00,0x60,0x56,0x34,0x12,0xaf] 0xff,0x03,0x22,0xd7,0xff,0xd6,0x00,0x60,0x56,0x34,0x12,0xaf # GFX11: v_div_fixup_f16 v5, v1, v2, s3 ; encoding: [0x05,0x00,0x54,0xd6,0x01,0x05,0x0e,0x00] diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp16.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp16.txt --- a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp16.txt +++ b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp16.txt @@ -1041,88 +1041,88 @@ # GFX11: v_cvt_pk_u8_f32_e64_dpp v255, -|v255|, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0x01,0x26,0xd6,0xfa,0xfe,0xf7,0x23,0xff,0x6f,0x0d,0x30] 0xff,0x01,0x26,0xd6,0xfa,0xfe,0xf7,0x23,0xff,0x6f,0x0d,0x30 -# GFX11: v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff] +# GFX11: v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff] 0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff -# GFX11: v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0xe4,0x00,0xff] +# GFX11: v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0xe4,0x00,0xff] 0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0xe4,0x00,0xff -# GFX11: v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x40,0x01,0xff] +# GFX11: v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x40,0x01,0xff] 0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x40,0x01,0xff -# GFX11: v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x41,0x01,0xff] +# GFX11: v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x41,0x01,0xff] 0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x41,0x01,0xff -# GFX11: v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x01,0x01,0xff] +# GFX11: v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x01,0x01,0xff] 0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x01,0x01,0xff -# GFX11: v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x0f,0x01,0xff] +# GFX11: v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x0f,0x01,0xff] 0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x0f,0x01,0xff -# GFX11: v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x11,0x01,0xff] +# GFX11: v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x11,0x01,0xff] 0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x11,0x01,0xff -# GFX11: v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1f,0x01,0xff] +# GFX11: v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1f,0x01,0xff] 0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1f,0x01,0xff -# GFX11: v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x21,0x01,0xff] +# GFX11: v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x21,0x01,0xff] 0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x21,0x01,0xff -# GFX11: v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x2f,0x01,0xff] +# GFX11: v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x2f,0x01,0xff] 0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x2f,0x01,0xff -# GFX11: v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x50,0x01,0xff] +# GFX11: v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x50,0x01,0xff] 0x05,0x00,0x21,0xd7,0xfa,0x04,0x02,0x00,0x01,0x50,0x01,0xff -# GFX11: v_cvt_pknorm_i16_f32_e64_dpp v5, |v1|, -v2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x01,0x21,0xd7,0xfa,0x04,0x02,0x40,0x01,0x5f,0x01,0x01] +# GFX11: v_cvt_pk_norm_i16_f32_e64_dpp v5, |v1|, -v2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x01,0x21,0xd7,0xfa,0x04,0x02,0x40,0x01,0x5f,0x01,0x01] 0x05,0x01,0x21,0xd7,0xfa,0x04,0x02,0x40,0x01,0x5f,0x01,0x01 -# GFX11: v_cvt_pknorm_i16_f32_e64_dpp v5, -v1, |v2| row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x02,0x21,0xd7,0xfa,0x04,0x02,0x20,0x01,0x60,0x01,0x13] +# GFX11: v_cvt_pk_norm_i16_f32_e64_dpp v5, -v1, |v2| row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x02,0x21,0xd7,0xfa,0x04,0x02,0x20,0x01,0x60,0x01,0x13] 0x05,0x02,0x21,0xd7,0xfa,0x04,0x02,0x20,0x01,0x60,0x01,0x13 -# GFX11: v_cvt_pknorm_i16_f32_e64_dpp v255, -|v255|, -|v255| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0x03,0x21,0xd7,0xfa,0xfe,0x03,0x60,0xff,0x6f,0x0d,0x30] +# GFX11: v_cvt_pk_norm_i16_f32_e64_dpp v255, -|v255|, -|v255| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0x03,0x21,0xd7,0xfa,0xfe,0x03,0x60,0xff,0x6f,0x0d,0x30] 0xff,0x03,0x21,0xd7,0xfa,0xfe,0x03,0x60,0xff,0x6f,0x0d,0x30 -# GFX11: v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff] +# GFX11: v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff] 0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff -# GFX11: v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0xe4,0x00,0xff] +# GFX11: v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0xe4,0x00,0xff] 0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0xe4,0x00,0xff -# GFX11: v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x40,0x01,0xff] +# GFX11: v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x40,0x01,0xff] 0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x40,0x01,0xff -# GFX11: v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x41,0x01,0xff] +# GFX11: v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x41,0x01,0xff] 0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x41,0x01,0xff -# GFX11: v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x01,0x01,0xff] +# GFX11: v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x01,0x01,0xff] 0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x01,0x01,0xff -# GFX11: v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x0f,0x01,0xff] +# GFX11: v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x0f,0x01,0xff] 0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x0f,0x01,0xff -# GFX11: v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x11,0x01,0xff] +# GFX11: v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x11,0x01,0xff] 0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x11,0x01,0xff -# GFX11: v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1f,0x01,0xff] +# GFX11: v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1f,0x01,0xff] 0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1f,0x01,0xff -# GFX11: v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x21,0x01,0xff] +# GFX11: v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x21,0x01,0xff] 0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x21,0x01,0xff -# GFX11: v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x2f,0x01,0xff] +# GFX11: v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x2f,0x01,0xff] 0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x2f,0x01,0xff -# GFX11: v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x50,0x01,0xff] +# GFX11: v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x50,0x01,0xff] 0x05,0x00,0x22,0xd7,0xfa,0x04,0x02,0x00,0x01,0x50,0x01,0xff -# GFX11: v_cvt_pknorm_u16_f32_e64_dpp v5, |v1|, -v2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x01,0x22,0xd7,0xfa,0x04,0x02,0x40,0x01,0x5f,0x01,0x01] +# GFX11: v_cvt_pk_norm_u16_f32_e64_dpp v5, |v1|, -v2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x01,0x22,0xd7,0xfa,0x04,0x02,0x40,0x01,0x5f,0x01,0x01] 0x05,0x01,0x22,0xd7,0xfa,0x04,0x02,0x40,0x01,0x5f,0x01,0x01 -# GFX11: v_cvt_pknorm_u16_f32_e64_dpp v5, -v1, |v2| row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x02,0x22,0xd7,0xfa,0x04,0x02,0x20,0x01,0x60,0x01,0x13] +# GFX11: v_cvt_pk_norm_u16_f32_e64_dpp v5, -v1, |v2| row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x02,0x22,0xd7,0xfa,0x04,0x02,0x20,0x01,0x60,0x01,0x13] 0x05,0x02,0x22,0xd7,0xfa,0x04,0x02,0x20,0x01,0x60,0x01,0x13 -# GFX11: v_cvt_pknorm_u16_f32_e64_dpp v255, -|v255|, -|v255| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0x03,0x22,0xd7,0xfa,0xfe,0x03,0x60,0xff,0x6f,0x0d,0x30] +# GFX11: v_cvt_pk_norm_u16_f32_e64_dpp v255, -|v255|, -|v255| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0x03,0x22,0xd7,0xfa,0xfe,0x03,0x60,0xff,0x6f,0x0d,0x30] 0xff,0x03,0x22,0xd7,0xfa,0xfe,0x03,0x60,0xff,0x6f,0x0d,0x30 # GFX11: v_fma_f32_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x13,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp8.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp8.txt --- a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp8.txt +++ b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp8.txt @@ -573,28 +573,28 @@ # GFX11: v_cvt_pk_u8_f32_e64_dpp v255, -|v255|, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x01,0x26,0xd6,0xea,0xfe,0xf7,0x23,0xff,0x00,0x00,0x00] 0xff,0x01,0x26,0xd6,0xea,0xfe,0xf7,0x23,0xff,0x00,0x00,0x00 -# GFX11: v_cvt_pknorm_i16_f32_e64_dpp v5, v1, v2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x21,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05] +# GFX11: v_cvt_pk_norm_i16_f32_e64_dpp v5, v1, v2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x21,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05] 0x05,0x00,0x21,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05 -# GFX11: v_cvt_pknorm_i16_f32_e64_dpp v5, |v1|, -v2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x21,0xd7,0xe9,0x04,0x02,0x40,0x01,0x77,0x39,0x05] +# GFX11: v_cvt_pk_norm_i16_f32_e64_dpp v5, |v1|, -v2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x21,0xd7,0xe9,0x04,0x02,0x40,0x01,0x77,0x39,0x05] 0x05,0x01,0x21,0xd7,0xe9,0x04,0x02,0x40,0x01,0x77,0x39,0x05 -# GFX11: v_cvt_pknorm_i16_f32_e64_dpp v5, -v1, |v2| dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x02,0x21,0xd7,0xe9,0x04,0x02,0x20,0x01,0x77,0x39,0x05] +# GFX11: v_cvt_pk_norm_i16_f32_e64_dpp v5, -v1, |v2| dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x02,0x21,0xd7,0xe9,0x04,0x02,0x20,0x01,0x77,0x39,0x05] 0x05,0x02,0x21,0xd7,0xe9,0x04,0x02,0x20,0x01,0x77,0x39,0x05 -# GFX11: v_cvt_pknorm_i16_f32_e64_dpp v255, -|v255|, -|v255| dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x03,0x21,0xd7,0xea,0xfe,0x03,0x60,0xff,0x00,0x00,0x00] +# GFX11: v_cvt_pk_norm_i16_f32_e64_dpp v255, -|v255|, -|v255| dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x03,0x21,0xd7,0xea,0xfe,0x03,0x60,0xff,0x00,0x00,0x00] 0xff,0x03,0x21,0xd7,0xea,0xfe,0x03,0x60,0xff,0x00,0x00,0x00 -# GFX11: v_cvt_pknorm_u16_f32_e64_dpp v5, v1, v2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x22,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05] +# GFX11: v_cvt_pk_norm_u16_f32_e64_dpp v5, v1, v2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x22,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05] 0x05,0x00,0x22,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05 -# GFX11: v_cvt_pknorm_u16_f32_e64_dpp v5, |v1|, -v2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x22,0xd7,0xe9,0x04,0x02,0x40,0x01,0x77,0x39,0x05] +# GFX11: v_cvt_pk_norm_u16_f32_e64_dpp v5, |v1|, -v2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x22,0xd7,0xe9,0x04,0x02,0x40,0x01,0x77,0x39,0x05] 0x05,0x01,0x22,0xd7,0xe9,0x04,0x02,0x40,0x01,0x77,0x39,0x05 -# GFX11: v_cvt_pknorm_u16_f32_e64_dpp v5, -v1, |v2| dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x02,0x22,0xd7,0xe9,0x04,0x02,0x20,0x01,0x77,0x39,0x05] +# GFX11: v_cvt_pk_norm_u16_f32_e64_dpp v5, -v1, |v2| dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x02,0x22,0xd7,0xe9,0x04,0x02,0x20,0x01,0x77,0x39,0x05] 0x05,0x02,0x22,0xd7,0xe9,0x04,0x02,0x20,0x01,0x77,0x39,0x05 -# GFX11: v_cvt_pknorm_u16_f32_e64_dpp v255, -|v255|, -|v255| dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x03,0x22,0xd7,0xea,0xfe,0x03,0x60,0xff,0x00,0x00,0x00] +# GFX11: v_cvt_pk_norm_u16_f32_e64_dpp v255, -|v255|, -|v255| dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x03,0x22,0xd7,0xea,0xfe,0x03,0x60,0xff,0x00,0x00,0x00] 0xff,0x03,0x22,0xd7,0xea,0xfe,0x03,0x60,0xff,0x00,0x00,0x00 # GFX11: v_fma_f32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x13,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05]