global_store_dword GPU Native ISA AMD Vector
GLOBAL STORE DWORD Vector/Global Memory
global_store_dword VADDR, VDATA, SADDR, offset
Store one 32-bit dword per lane to the global address space using a 64-bit per-lane address.
Encoding
Verified bit-level encoding data is not yet available for this instruction.
The instruction-format classification below (GLOBAL)
is well-documented and stable; exact per-target opcode/field bit positions have not
yet been imported from a verified source.
Operands
-
VADDR
Per-lane 64-bit address (VGPR pair) -
VDATA
Per-lane value to store (VGPR) -
SADDR
Optional uniform base (SGPR pair) -
offset
Immediate offset
GFX Target Compatibility
| Target | Support |
|---|---|
| gfx942 | ✅ Supported |
| gfx1100 | ✅ Supported |
Related PTX Concepts
Reference
AMDGPU / GFX ISA
Semantics
*(VADDR[lane] + SADDR + offset) = VDATA[lane] for each active lane.
Sources
- ROCm Documentation ↗ — Advanced Micro Devices, Inc.
- User Guide for AMDGPU Backend ↗ — LLVM Project