Syntax of gfx1011 and gfx1012 Instructions

Syntax of gfx1011 and gfx1012 Instructions#

Introduction#

This document describes the syntax of instructions specific to gfx1011 and gfx1012.

For a description of other gfx1011 and gfx1012 instructions see Syntax of GFX10 RDNA1 Instructions.

Notation#

Notation used in this document is explained here.

Overview#

An overview of generic syntax and other features of AMDGPU instructions may be found in this document.

Instructions#

DPP16#

INSTRUCTION            DST      SRC0         SRC1         MODIFIERS
—————————————————————————————————————————————————————————————————————————————————————————————————————
v_dot2c_f32_f16_dpp    vdst,    vsrc0:f16x2, vsrc1:f16x2  dpp16_ctrl row_mask bank_mask bound_ctrl fi
v_dot4c_i32_i8_dpp     vdst,    vsrc0:i8x4,  vsrc1:i8x4   dpp16_ctrl row_mask bank_mask bound_ctrl fi

DPP8#

INSTRUCTION                    DST       SRC0         SRC1             MODIFIERS
——————————————————————————————————————————————————————————————————————————————————
v_dot2c_f32_f16_dpp            vdst,     vsrc0:f16x2, vsrc1:f16x2      dpp8_sel fi
v_dot4c_i32_i8_dpp             vdst,     vsrc0:i8x4,  vsrc1:i8x4       dpp8_sel fi

VOP2#

INSTRUCTION                    DST       SRC0        SRC1
————————————————————————————————————————————————————————————————
v_dot2c_f32_f16                vdst,     src0:f16x2, vsrc1:f16x2
v_dot4c_i32_i8                 vdst,     src0:i8x4,  vsrc1:i8x4

VOP3P#

INSTRUCTION                    DST       SRC0        SRC1        SRC2           MODIFIERS
———————————————————————————————————————————————————————————————————————————————————————————————————
v_dot2_f32_f16                 vdst,     src0:f16x2, src1:f16x2, src2:f32       neg_lo neg_hi clamp
v_dot2_i32_i16                 vdst,     src0:i16x2, src1:i16x2, src2:i32       clamp
v_dot2_u32_u16                 vdst,     src0:u16x2, src1:u16x2, src2:u32       clamp
v_dot4_i32_i8                  vdst,     src0:i8x4,  src1:i8x4,  src2:i32       clamp
v_dot4_u32_u8                  vdst,     src0:u8x4,  src1:u8x4,  src2:u32       clamp
v_dot8_i32_i4                  vdst,     src0:i4x8,  src1:i4x8,  src2:i32       clamp
v_dot8_u32_u4                  vdst,     src0:u4x8,  src1:u4x8,  src2:u32       clamp