AMD GPU Memory Model
The memory model underlying AMD's GCN, CDNA and RDNA GPUs, built on the HSA heterogeneous, scoped, release-consistency framework. Memory operations carry explicit scope qualifiers (work-group, agent/device, system) and cache-control hints; ordering between threads holds only within a shared scope.
Properties
Property vector author-extrapolated — set only where the model’s definition pins the cell down (unknown cells are omitted); cells citing a specific source are marked.
- Reordering sound
- yes Store→Load
- yes Store→Store
- yes Load→Load
- yes Load→Store
- Reasoning guarantees
- yes Coherence
- yes No undefined behaviour
- no In-order execution
- yes No out-of-thin-air
Ordering relationships
- Compilation target of
- OpenCL 2.0 Memory Model — OpenCL kernels compile to AMD's GPU ISA via the HSA-based model.
- Vulkan Memory Model — Vulkan/SPIR-V compute shaders compile to AMD's GPU ISA.
- Incomparable with
- NVIDIA PTX Memory Model — Both are scoped release-consistency ISA models, but expose different scope sets (CTA/GPU/system vs HSA work-group/agent/system) and cache-control qualifiers; neither subsumes the other.
References
- Benedict R. Gaster, Derek Hower, Lee Howes. HRF-Relaxed: Adapting HRF to the Complexities of Industrial Heterogeneous Memory Models. ACM TACO, 2015. doi:10.1145/2701618
- Derek R. Hower, Blake A. Hechtman, Bradford M. Beckmann, Benedict R. Gaster, Mark D. Hill, Steven K. Reinhardt, David A. Wood. Heterogeneous-Race-Free Memory Models. ASPLOS 2014, 2014. doi:10.1145/2541940.2541981