ds_inc_rtn_u64 GPU Native ISA AMD Vector

LDS / Data Share

ds_inc_rtn_u64

Increment an unsigned 64-bit integer value from a location in a data share with wraparound to 0 if the value exceeds a value in the data register.

Encoding

Binary Layout (AMD CDNA 5)
VDST
63:56
DATA1
55:48
DATA0
47:40
ADDR
39:32
110110
31:26
01100011
25:18
unassigned
17:16
OFFSET1
15:8
OFFSET0
7:0
 

The ENC_VDS layout from AMD's machine-readable ISA specification (AMD CDNA 5). Opcode 99 in OP rebuilds 0x00000000D98C0000, an identifier AMD lists for this encoding. Bits marked unassigned have no field in the specification. Not the same in every generation: AMD CDNA 4 (encoding ENC_DS, field layout), AMD CDNA 3 (encoding ENC_DS, field layout), AMD CDNA 2 (encoding ENC_DS, field layout), AMD CDNA 1 (encoding ENC_DS, field layout), AMD RDNA 3.5 (encoding ENC_DS, field layout), AMD RDNA 3 (encoding ENC_DS, field layout), AMD RDNA 2 (encoding ENC_DS, field layout), AMD RDNA 1 (encoding ENC_DS, field layout). The same in AMD RDNA 4.

Format DS
Width 64 bits
Opcode 99
Identifier 0x00000000D98C0000

Operands

  • VDST
    Written. Operand must be a vector GPR. Uses an 8-bit operand field. Data format: Unsigned 64-bit integral data. (OPR_VGPR, FMT_NUM_U64)
  • ADDR
    Read. Operand must be a vector GPR. Uses an 8-bit operand field. Data format: 32 bits of arbitrary data. (OPR_VGPR, FMT_NUM_B32)
  • DATA0
    Read. Operand must be a vector GPR. Uses an 8-bit operand field. Data format: Unsigned 64-bit integral data. (OPR_VGPR, FMT_NUM_U64)

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

GFX Target Compatibility

TargetSupport
gfx1100✅ Supported

Related

More in LDS / Data Share

Reference

AMDGPU / GFX ISA

Description

Increment an unsigned 64-bit integer value from a location in a data share with wraparound to 0 if the value exceeds a value in the data register. Store the original value from data share into a vector register.

Semantics

addr = CalcDsAddr(ADDR.b32, OFFSET0.b32, OFFSET1.b32); tmp = MEM[addr].u64; src = DATA.u64; MEM[addr].u64 = tmp >= src ? 0ULL : tmp + 1ULL; RETURN_DATA.u64 = tmp

Example

ds_inc_rtn_u64 v[5:6], v1, v[2:3]

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