150
|
1 ..
|
|
2 **************************************************
|
|
3 * *
|
|
4 * Automatically generated file, do not edit! *
|
|
5 * *
|
|
6 **************************************************
|
|
7
|
|
8 ====================================================================================
|
|
9 Syntax of gfx906 Instructions
|
|
10 ====================================================================================
|
|
11
|
|
12 .. contents::
|
|
13 :local:
|
|
14
|
|
15 Introduction
|
|
16 ============
|
|
17
|
|
18 This document describes the syntax of *instructions specific to gfx906*.
|
|
19
|
|
20 For a description of other gfx906 instructions see :doc:`Syntax of Core GFX9 Instructions<AMDGPUAsmGFX9>`.
|
|
21
|
|
22 Notation
|
|
23 ========
|
|
24
|
|
25 Notation used in this document is explained :ref:`here<amdgpu_syn_instruction_notation>`.
|
|
26
|
|
27 Overview
|
|
28 ========
|
|
29
|
|
30 An overview of generic syntax and other features of AMDGPU instructions may be found :ref:`in this document<amdgpu_syn_instructions>`.
|
|
31
|
|
32 Instructions
|
|
33 ============
|
|
34
|
|
35
|
|
36 VOP2
|
|
37 -----------------------
|
|
38
|
|
39 .. parsed-literal::
|
|
40
|
|
41 **INSTRUCTION** **DST** **SRC0** **SRC1** **MODIFIERS**
|
|
42 \ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|
|
|
43 v_fmac_f32 :ref:`vdst<amdgpu_synid906_vdst32_0>`, :ref:`src0<amdgpu_synid906_src32_0>`, :ref:`vsrc1<amdgpu_synid906_vsrc32_0>`
|
|
44 v_fmac_f32_dpp :ref:`vdst<amdgpu_synid906_vdst32_0>`, :ref:`vsrc0<amdgpu_synid906_vsrc32_0>`::ref:`m<amdgpu_synid906_mod_dpp_sdwa_abs_neg>`, :ref:`vsrc1<amdgpu_synid906_vsrc32_0>`::ref:`m<amdgpu_synid906_mod_dpp_sdwa_abs_neg>` :ref:`dpp_ctrl<amdgpu_synid_dpp_ctrl>` :ref:`row_mask<amdgpu_synid_row_mask>` :ref:`bank_mask<amdgpu_synid_bank_mask>` :ref:`bound_ctrl<amdgpu_synid_bound_ctrl>`
|
|
45 v_xnor_b32 :ref:`vdst<amdgpu_synid906_vdst32_0>`, :ref:`src0<amdgpu_synid906_src32_0>`, :ref:`vsrc1<amdgpu_synid906_vsrc32_0>`
|
|
46 v_xnor_b32_dpp :ref:`vdst<amdgpu_synid906_vdst32_0>`, :ref:`vsrc0<amdgpu_synid906_vsrc32_0>`, :ref:`vsrc1<amdgpu_synid906_vsrc32_0>` :ref:`dpp_ctrl<amdgpu_synid_dpp_ctrl>` :ref:`row_mask<amdgpu_synid_row_mask>` :ref:`bank_mask<amdgpu_synid_bank_mask>` :ref:`bound_ctrl<amdgpu_synid_bound_ctrl>`
|
|
47 v_xnor_b32_sdwa :ref:`vdst<amdgpu_synid906_vdst32_0>`, :ref:`src0<amdgpu_synid906_src32_0>`::ref:`m<amdgpu_synid906_mod_sdwa_sext>`, :ref:`vsrc1<amdgpu_synid906_vsrc32_0>`::ref:`m<amdgpu_synid906_mod_sdwa_sext>` :ref:`dst_sel<amdgpu_synid_dst_sel>` :ref:`dst_unused<amdgpu_synid_dst_unused>` :ref:`src0_sel<amdgpu_synid_src0_sel>` :ref:`src1_sel<amdgpu_synid_src1_sel>`
|
|
48
|
|
49 VOP3
|
|
50 -----------------------
|
|
51
|
|
52 .. parsed-literal::
|
|
53
|
|
54 **INSTRUCTION** **DST** **SRC0** **SRC1** **MODIFIERS**
|
|
55 \ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|
|
|
56 v_fmac_f32_e64 :ref:`vdst<amdgpu_synid906_vdst32_0>`, :ref:`src0<amdgpu_synid906_src32_1>`::ref:`m<amdgpu_synid906_mod_vop3_abs_neg>`, :ref:`src1<amdgpu_synid906_src32_2>`::ref:`m<amdgpu_synid906_mod_vop3_abs_neg>` :ref:`clamp<amdgpu_synid_clamp>` :ref:`omod<amdgpu_synid_omod>`
|
|
57 v_xnor_b32_e64 :ref:`vdst<amdgpu_synid906_vdst32_0>`, :ref:`src0<amdgpu_synid906_src32_1>`, :ref:`src1<amdgpu_synid906_src32_2>`
|
|
58
|
|
59 VOP3P
|
|
60 -----------------------
|
|
61
|
|
62 .. parsed-literal::
|
|
63
|
|
64 **INSTRUCTION** **DST** **SRC0** **SRC1** **SRC2** **MODIFIERS**
|
|
65 \ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|\ |---|
|
|
66 v_dot2_f32_f16 :ref:`vdst<amdgpu_synid906_vdst32_0>`, :ref:`src0<amdgpu_synid906_src32_1>`::ref:`f16x2<amdgpu_synid906_type_dev>`, :ref:`src1<amdgpu_synid906_src32_2>`::ref:`f16x2<amdgpu_synid906_type_dev>`, :ref:`src2<amdgpu_synid906_src32_2>`::ref:`f32<amdgpu_synid906_type_dev>` :ref:`neg_lo<amdgpu_synid_neg_lo>` :ref:`neg_hi<amdgpu_synid_neg_hi>` :ref:`clamp<amdgpu_synid_clamp>`
|
207
|
67 v_dot2_i32_i16 :ref:`vdst<amdgpu_synid906_vdst32_0>`, :ref:`src0<amdgpu_synid906_src32_3>`::ref:`i16x2<amdgpu_synid906_type_dev>`, :ref:`src1<amdgpu_synid906_src32_4>`::ref:`i16x2<amdgpu_synid906_type_dev>`, :ref:`src2<amdgpu_synid906_src32_2>`::ref:`i32<amdgpu_synid906_type_dev>` :ref:`clamp<amdgpu_synid_clamp>`
|
|
68 v_dot2_u32_u16 :ref:`vdst<amdgpu_synid906_vdst32_0>`, :ref:`src0<amdgpu_synid906_src32_3>`::ref:`u16x2<amdgpu_synid906_type_dev>`, :ref:`src1<amdgpu_synid906_src32_4>`::ref:`u16x2<amdgpu_synid906_type_dev>`, :ref:`src2<amdgpu_synid906_src32_2>`::ref:`u32<amdgpu_synid906_type_dev>` :ref:`clamp<amdgpu_synid_clamp>`
|
150
|
69 v_dot4_i32_i8 :ref:`vdst<amdgpu_synid906_vdst32_0>`, :ref:`src0<amdgpu_synid906_src32_1>`::ref:`i8x4<amdgpu_synid906_type_dev>`, :ref:`src1<amdgpu_synid906_src32_2>`::ref:`i8x4<amdgpu_synid906_type_dev>`, :ref:`src2<amdgpu_synid906_src32_2>`::ref:`i32<amdgpu_synid906_type_dev>` :ref:`clamp<amdgpu_synid_clamp>`
|
|
70 v_dot4_u32_u8 :ref:`vdst<amdgpu_synid906_vdst32_0>`, :ref:`src0<amdgpu_synid906_src32_1>`::ref:`u8x4<amdgpu_synid906_type_dev>`, :ref:`src1<amdgpu_synid906_src32_2>`::ref:`u8x4<amdgpu_synid906_type_dev>`, :ref:`src2<amdgpu_synid906_src32_2>`::ref:`u32<amdgpu_synid906_type_dev>` :ref:`clamp<amdgpu_synid_clamp>`
|
|
71 v_dot8_i32_i4 :ref:`vdst<amdgpu_synid906_vdst32_0>`, :ref:`src0<amdgpu_synid906_src32_1>`::ref:`i4x8<amdgpu_synid906_type_dev>`, :ref:`src1<amdgpu_synid906_src32_2>`::ref:`i4x8<amdgpu_synid906_type_dev>`, :ref:`src2<amdgpu_synid906_src32_2>`::ref:`i32<amdgpu_synid906_type_dev>` :ref:`clamp<amdgpu_synid_clamp>`
|
|
72 v_dot8_u32_u4 :ref:`vdst<amdgpu_synid906_vdst32_0>`, :ref:`src0<amdgpu_synid906_src32_1>`::ref:`u4x8<amdgpu_synid906_type_dev>`, :ref:`src1<amdgpu_synid906_src32_2>`::ref:`u4x8<amdgpu_synid906_type_dev>`, :ref:`src2<amdgpu_synid906_src32_2>`::ref:`u32<amdgpu_synid906_type_dev>` :ref:`clamp<amdgpu_synid_clamp>`
|
|
73 v_fma_mix_f32 :ref:`vdst<amdgpu_synid906_vdst32_0>`, :ref:`src0<amdgpu_synid906_src32_1>`::ref:`m<amdgpu_synid906_mod_vop3_abs_neg>`::ref:`fx<amdgpu_synid906_mad_type_dev>`, :ref:`src1<amdgpu_synid906_src32_2>`::ref:`m<amdgpu_synid906_mod_vop3_abs_neg>`::ref:`fx<amdgpu_synid906_mad_type_dev>`, :ref:`src2<amdgpu_synid906_src32_2>`::ref:`m<amdgpu_synid906_mod_vop3_abs_neg>`::ref:`fx<amdgpu_synid906_mad_type_dev>` :ref:`m_op_sel<amdgpu_synid_mad_mix_op_sel>` :ref:`m_op_sel_hi<amdgpu_synid_mad_mix_op_sel_hi>` :ref:`clamp<amdgpu_synid_clamp>`
|
|
74 v_fma_mixhi_f16 :ref:`vdst<amdgpu_synid906_vdst32_0>`, :ref:`src0<amdgpu_synid906_src32_1>`::ref:`m<amdgpu_synid906_mod_vop3_abs_neg>`::ref:`fx<amdgpu_synid906_mad_type_dev>`, :ref:`src1<amdgpu_synid906_src32_2>`::ref:`m<amdgpu_synid906_mod_vop3_abs_neg>`::ref:`fx<amdgpu_synid906_mad_type_dev>`, :ref:`src2<amdgpu_synid906_src32_2>`::ref:`m<amdgpu_synid906_mod_vop3_abs_neg>`::ref:`fx<amdgpu_synid906_mad_type_dev>` :ref:`m_op_sel<amdgpu_synid_mad_mix_op_sel>` :ref:`m_op_sel_hi<amdgpu_synid_mad_mix_op_sel_hi>` :ref:`clamp<amdgpu_synid_clamp>`
|
|
75 v_fma_mixlo_f16 :ref:`vdst<amdgpu_synid906_vdst32_0>`, :ref:`src0<amdgpu_synid906_src32_1>`::ref:`m<amdgpu_synid906_mod_vop3_abs_neg>`::ref:`fx<amdgpu_synid906_mad_type_dev>`, :ref:`src1<amdgpu_synid906_src32_2>`::ref:`m<amdgpu_synid906_mod_vop3_abs_neg>`::ref:`fx<amdgpu_synid906_mad_type_dev>`, :ref:`src2<amdgpu_synid906_src32_2>`::ref:`m<amdgpu_synid906_mod_vop3_abs_neg>`::ref:`fx<amdgpu_synid906_mad_type_dev>` :ref:`m_op_sel<amdgpu_synid_mad_mix_op_sel>` :ref:`m_op_sel_hi<amdgpu_synid_mad_mix_op_sel_hi>` :ref:`clamp<amdgpu_synid_clamp>`
|
|
76
|
|
77 .. |---| unicode:: U+02014 .. em dash
|
|
78
|
|
79
|
|
80 .. toctree::
|
|
81 :hidden:
|
|
82
|
|
83 AMDGPUAsmGFX9
|
|
84 gfx906_src32_0
|
|
85 gfx906_src32_1
|
|
86 gfx906_src32_2
|
207
|
87 gfx906_src32_3
|
|
88 gfx906_src32_4
|
150
|
89 gfx906_vdst32_0
|
|
90 gfx906_vsrc32_0
|
|
91 gfx906_mad_type_dev
|
|
92 gfx906_mod_dpp_sdwa_abs_neg
|
|
93 gfx906_mod_sdwa_sext
|
|
94 gfx906_mod_vop3_abs_neg
|
|
95 gfx906_type_dev
|