v_med3_u16 GPU Native ISA AMD Vector

Vector Arithmetic

v_med3_u16

Select the median of three unsigned 16-bit integer values and store the selected value into a vector register.

Encoding

Binary Layout (AMD CDNA 5)
NEG
63:61
OMOD
60:59
SRC2
58:50
SRC1
49:41
SRC0
40:32
110101
31:26
1001010001
25:16
CLAMP
15
OPSEL
14:11
ABS
10:8
VDST
7:0
 

The ENC_VOP3 layout from AMD's machine-readable ISA specification (AMD CDNA 5). Opcode 593 in OP rebuilds 0x00000000D6510000, an identifier AMD lists for this encoding. Not the same in every generation: AMD CDNA 4 (opcode 508, field layout), AMD CDNA 3 (opcode 508, field layout), AMD CDNA 2 (opcode 508, field layout), AMD CDNA 1 (opcode 508, field layout), AMD RDNA 3.5 (field layout), AMD RDNA 3 (field layout), AMD RDNA 2 (opcode 857, field layout), AMD RDNA 1 (opcode 857, field layout). The same in AMD RDNA 4.

Format VOP3
Width 64 bits
Opcode 593
Identifier 0x00000000D6510000

Operands

  • VDST
    Written. Operand must be a vector GPR. Uses an 8-bit operand field. Data format: Unsigned 16-bit integral data. (OPR_VGPR, FMT_NUM_U16)
  • SRC0
    Read. All operands. Covers all operands that are allowed as scalar or vector sources. Data format: Unsigned 16-bit integral data. (OPR_SRC, FMT_NUM_U16)
  • SRC1
    Read. All operands. Covers all operands that are allowed as scalar or vector sources. Data format: Unsigned 16-bit integral data. (OPR_SRC, FMT_NUM_U16)
  • SRC2
    Read. All operands. Covers all operands that are allowed as scalar or vector sources. Data format: Unsigned 16-bit integral data. (OPR_SRC, FMT_NUM_U16)

In AMD's order, as its machine-readable ISA specification lists them for the ENC_VOP3 encoding (AMD CDNA 5).

GFX Target Compatibility

TargetSupport
gfx1100✅ Supported

Related

More in Vector Arithmetic

Reference

AMDGPU / GFX ISA

Semantics

if v_max3_u16(S0.u16, S1.u16, S2.u16) == S0.u16 then D0.u16 = v_max_u16(S1.u16, S2.u16) elsif v_max3_u16(S0.u16, S1.u16, S2.u16) == S1.u16 then D0.u16 = v_max_u16(S0.u16, S2.u16) else D0.u16 = v_max_u16(S0.u16, S1.u16) endif

Example

v_med3_u16 v5, v1, v2, s3

A real instruction accepted by the LLVM assembler, taken verbatim from LLVM's own AMDGPU MC test suite. Not from an AMD document, and not authored here.

Sources