A bridging model for parallel computation
Communications of the ACM
Proceedings of the eighth annual ACM symposium on Parallel algorithms and architectures
Communication-efficient parallel sorting (preliminary version)
STOC '96 Proceedings of the twenty-eighth annual ACM symposium on Theory of computing
LogP: a practical model of parallel computation
Communications of the ACM
Emulations between QSM, BSP and LogP: a framework for general-purpose parallel algorithm design
Journal of Parallel and Distributed Computing
| Hi-index | 0.00 |
We investigate the issue of stalling in the LogP model. In particular, we introduce a novel quantitative characterization of stalling, referred to as @d-stalling, which intuitively captures the realistic assumption that once the network's capacity constraint is violated, it takes some time (at most @d) for this information to propagate to the processors involved. We prove a lower bound that shows that LogP under @d-stalling is strictly more powerful than the stall-free version of the model where only strictly stall-free computations are permitted. On the other hand, we show that @d-stalling LogP with @d=L can be simulated with at most logarithmic slowdown by a BSP machine with similar bandwidth and latency values, thus extending the equivalence (up to logarithmic factors) between stall-free LogP and BSP argued in Bilardi et al. (Algorithmica 24 (1999) 405) and Ramachandran et al. (J. Parallel Distributed Comput. 63 (2003) 1175) to the more powerful L-stalling LogP.