Bound-oriented parallel pruning approaches for efficient resource constrained scheduling of high-level synthesis

Chen, Mingsong; Zhou, Lei; Pu, Geguang; He, Jifeng

doi:10.1109/codes-isss.2013.6659001

Cited by 3 publications

(10 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Parallelism is widely studied in HLS [25], [28]. Chen et al [28] proposed a bound-oriented parallel B&B approach for HLS.…”

Section: Related Workmentioning

confidence: 99%

“…In this case, the B&B style searching performance can be degraded. Besides the long-distance backtrack, stuck-at-localsearch problem [28] also needs to be avoided in the B&B style search. Therefore, the dispatching order of the enumerated operations is very important.…”

Section: Derivation Of Parallel Search Tasksmentioning

confidence: 99%

“…Chen et al [28] proposed a bound-oriented parallel B&B approach for HLS. Based on the best upper-and lower-bound information shared among parallel sub-search tasks, [28] can efficiently locate an optimal result by combining both bound speculation and search space partitioning techniques. However, it heavily relies on the analysis of bound information, and does not utilize other features for pruning.…”

Section: Related Workmentioning

confidence: 99%

“…Based on the observation in [28], if the upper bound of best schedule searched so far can be shared among parallel tasks, the search space can be compacted onthe-fly. Therefore the overall RCS time can be significantly Due to different operation ordering, parallel tasks may keep different best schedules searched so far during the search.…”

Section: Collaboration Among Parallel Tasksmentioning

confidence: 99%

“…To effectively share bound and fence information, we developed a cooperation framework as shown in Figure 7 that supports the multi-level bound pruning as well as minimum ω synchronization [28] among parallel search tasks. In this framework, we partitioned the parallel search tasks into clusters according to their task IDs.…”

Section: Collaboration Among Parallel Tasksmentioning

confidence: 99%

See 4 more Smart Citations

Efficient Resource Constrained Scheduling Using Parallel Structure-Aware Pruning Techniques

Chen

Zhang

et al. 2016

IEEE Trans. Comput.

Self Cite

View full text Add to dashboard Cite

Branch-and-bound approaches are promising in pruning fruitless search space during the resource constrained scheduling. However, such approaches only compare the estimated upper and lower bounds of an incomplete schedule to the length of the best feasible schedule at that iteration, which does not fully exploit the potential of the pruning during the search. Aiming to improve the performance of resource constrained scheduling, this paper proposes a parallel structure-aware pruning approach that can traverse the search space significantly faster than state-of-the-art branch-and-bound techniques. This paper makes three major contributions: i) it proposes an efficient pruning technique using the structural scheduling information of the obtained best feasible schedules; ii) it investigates how to perform parallel search to enable efficient multi-directional search and generation of effective fences by tuning the operation enumeration order; and iii) it presents a framework that supports the sharing of minimum upper-bound and fence information among different search tasks to enable efficient parallel structure-aware pruning. The experimental results demonstrate that our parallel pruning approach can drastically reduce the overall resource constrained scheduling time under a wide variety of resource constraints.

show abstract

“…Parallelism is widely studied in HLS [25], [28]. Chen et al [28] proposed a bound-oriented parallel B&B approach for HLS.…”

Section: Related Workmentioning

confidence: 99%

Section: Derivation Of Parallel Search Tasksmentioning

confidence: 99%