Cohesion
John H. Kelm, Daniel R. Johnson, William Tuohy et al. · Proceedings - International Symposium on Computer Architecture/Proceedings · 2010
Two broad classes of memory models are available today: models with hardware cache coherence, used in conventional chip multiprocessors, and models that rely upon software to manage coherence, found in compute accelerators. In some systems, both types of models are supported using disjoint address spaces and/or physical memories. In this paper we present Cohesion, a hybrid memory model that enables fine-grained temporal reassignment of data between hardware-managed and software-managed coherence domains, allowing a system to support both. Cohesion can be used to dynamically adapt to the sharing needs of both applications and runtimes. Cohesion requires neither copy operations nor multiple address spaces.
Cited by 57 works. doi:10.1145/1815961.1816019
Authors
References
- A Bridging Model for Parallel Computation
- A New Solution to Coherence Problems in Multicache Systems
- The PARSEC benchmark suite
- Using cache memory to reduce processor-memory traffic
- Using cache memory to reduce processor-memory traffic
- Piranha
- NVIDIA Tesla: A Unified Graphics and Computing Architecture
- Parallel programming in Split-C
- Niagara: A 32-Way Multithreaded Sparc Processor
- The Stanford FLASH multiprocessor