s_get_barrier_state GPU Native ISA AMD Scalar
Scalar Arithmetic
AMDGPU SOP1 scalar instruction. (Format and name extracted from LLVM's AMDGPU backend source - semantics not yet curated.)
Encoding
The ENC_SOP1 layout from AMD's machine-readable ISA specification (AMD CDNA 5). Opcode 80 in OP rebuilds 0xBE805000, an identifier AMD lists for this encoding. No other generation in the specification defines this instruction.
Operands
-
SDST
Written. Any scalar GPR operand including VCC and NULL. Data format: 32 bits of arbitrary data. (OPR_SREG, FMT_NUM_B32) -
SSRC0
Read. N/A Data format: 32 bits of arbitrary data. (OPR_SSRC_BARRIER_ID, FMT_NUM_B32)
In AMD's order, as its machine-readable ISA specification lists them for the ENC_SOP1 encoding (AMD CDNA 5).
GFX Target Compatibility
Per-target GFX compatibility has not yet been verified for this instruction.
Related
More in Scalar Arithmetic
Reference
Example
s_get_barrier_state s0, 0A real instruction accepted by the LLVM assembler, taken verbatim from LLVM's own AMDGPU MC test suite (gfx13_asm_sop1.s). Not from an AMD document, and not authored here.
Sources
- User Guide for AMDGPU Backend ↗ - LLVM Project
- AMD Machine-Readable GPU ISA Specification ↗ - Advanced Micro Devices, Inc.
- LLVM MC assembler tests for AMDGPU ↗ - LLVM Project