A Distributed Controller for Managing Speculative Functional Units in High Level Synthesis

Barrio, Alberto A. Del; Memik, Seda Öǧrenci; Molina, M.C.; Mendias, J.M.; Hermida, R.

doi:10.1109/tcad.2010.2089565

Cited by 23 publications

(14 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Among the variety of works, we highlight approaches that restructure the controller in a hierarchical way [3], [4], even using State Charts descriptions [5]. Some solutions, like [6], employ a pseudo-distributed approach that enables supporting Speculative Functional Units. The final architecture still relies on a static schedule, but a local controller dynamically checks results of SFUs without stalling the whole datapath.…”

Section: Related Workmentioning

confidence: 99%

High level synthesis of RDF queries for graph analytics

Castellana

Minutoli

Morari

et al. 2015

2015 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)

View full text Add to dashboard Cite

Abstract-In this paper we present a set of techniques that enable the synthesis of efficient custom accelerators for memory intensive, irregular applications. To address the challenges of irregular applications (large memory footprint, unpredictable finegrained data accesses, and high synchronization intensity), and exploit their opportunities (thread level parallelism, memory level parallelism), we propose a novel accelerator design that employs an adaptive and Distributed Controller (DC) architecture, and a Memory Interface Controller (MIC) that supports concurrent and atomic memory operations on a multi-ported/multi-banked shared memory. Among the multitude of algorithms that may benefit from our solution, we focus on the acceleration of graph analytics applications and, in particular, on the synthesis of SPARQL queries on Resource Description Framework (RDF) databases. We achieve this objective by incorporating the synthesis techniques into Bambu, an Open Source high-level synthesis tools, and interfacing it with GEMS, the Graph database Engine for Multithreaded Systems. The GEMS' front-end generates optimized C implementations of the input queries, modeled as graph pattern matching algorithms, which are then automatically synthesized by Bambu. We validate our approach by synthesizing several SPARQL queries from the Lehigh University Benchmark (LUBM).

show abstract

Section: Related Workmentioning

confidence: 99%

High level synthesis of RDF queries for graph analytics

Castellana

Minutoli

Morari

et al. 2015

2015 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)

View full text Add to dashboard Cite

show abstract

“…On the other hand, when many VLFUs are working at the same time, the probability of a misprediction in at least one of them quickly raises, which under a centralized controller will penalize the overall performance. Hence, the development of efficient controllers is as critical as the design of fast VLFUs [18].…”

Section: Related Workmentioning

confidence: 99%

“…Although in this paper a centralized controller, similar to those proposed in [14,[16][17][18], will be adopted in order to take advantage of its simple structure, we will overcome its performance limitations by reducing the number of operations that can cause mispredictions thanks to the management of the multispeculative additive structures that is proposed.…”

Section: Related Workmentioning

confidence: 99%

“…Obviously, the performance of the datapath will be higher if the VLFUs work in the short latency mode most of the time. Although the literature offers several strategies for handling these units [14,[16][17][18]22], all of them are subject to the possibility of the worst-case timing, i.e. VLFUs working in long latency mode.…”

Section: Introductionmentioning

confidence: 99%

“…These units are based on various forms of speculation over a single carry value [12,18] or multiple carries at the same time [21,29]. We shall refer to them as Speculative FUs (SFUs) and Multispeculative FUs (MSFUs), respectively, although we will use MSFUs as the generic term.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improving circuit performance with multispeculative additive trees in high-level synthesis

Barrio¹,

Hermida²,

Memik³

et al. 2014

Microelectronics Journal

Self Cite

View full text Add to dashboard Cite

Abstract-The recent introduction of Variable Latency Functional Units (VLFUs) has broadened the design space of High-LevelSynthesis (HLS). Nevertheless their use is restricted to only few operators in the datapaths because the number of cases to control grows exponentially. In this work an instance of VLFUs is described, and based on its structure, the average latency of tree structures is improved. Multispeculative Functional Units (MSFUs) are arithmetic Functional Units that operate using several predictors for the carry signal. In spite of utilizing more than a predictor, none or only one additional very short cycle is enough for producing the correct result in the majority of the cases. In this paper our proposal takes advantage of multispeculation in order to increase the performance of tree structures with a negligible area penalty. By judiciously introducing these structures into computation trees, it will only be necessary to predict the carry signals in certain selected nodes, thus minimizing the total number of predictions and the number of operations that can potentially mispredict. Hence, the average latency will be diminished and thus performance will be increased. Our experiments show that it is possible to improve 26% execution time. Furthermore, our flow outperforms previous approaches with Speculative FUs.

show abstract