The Extended Partitioning Problem: Hardware/Software Mapping, Scheduling, and Implementation-bin Selection

Kalavade, Asawaree; LEE, EDWARD A.

doi:10.1016/b978-155860702-6/50027-2

Cited by 24 publications

(27 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, many researchers consider scheduling as part of partitioning (Chatha and Vemuri, 2001;Dick and Jha, 1998;Kalavade and Lee, 1997;Lopez-Vallejo and Lopez, 2003;Mei et al, 2000;Niemann and Marwedel, 1997), whereas others do not (Eles et al, 1996;Grode et al, 1998;Madsen et al, 1997;O'Nils et al, 1995;Vahid and Le, 1997;Vahid, 2002). Some even include the problem of assigning communication events to links between hardware and/or software units (Dick and Jha, 1998;Mei et al, 2000).…”

Section: Work On Hardware/software Partitioningmentioning

confidence: 99%

“…This includes the GCLP algorithm (Kalavade and Lee, 1997;Kalavade and Subrahmanyam, 1998) and the expert system of (LopezVallejo and Lopez, 1998;Lopez-Vallejo and Lopez, 2003), as well as the heuristics in (Gupta and de Micheli, 1993;Wolf, 1997). Hierarchical clustering is another family of well-known heuristics that has been often applied to partitioning problems (Abdelzaher and Shin, 2000;Barros et al, 1993;Vahid, 2002;Vahid and Gajski, 1995).…”

Section: Work On Hardware/software Partitioningmentioning

confidence: 99%

See 1 more Smart Citation

Evaluating the Kernighan-Lin Heuristic for Hardware/Software Partitioning

Mann¹,

Orbán²,

Farkas³

2007

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

In recent years, several heuristics have been proposed for the hardware/software partitioning problem. One of the most promising directions is the adaptation of the Kernighan-Lin algorithm. The Kernighan-Lin heuristic was originally developed for circuit partitioning, but it has been adapted to other domains as well. Moreover, numerous improvements have been suggested so that now several variants of the original algorithm exist. The aim of this paper is to systematically evaluate the possibilities of applying the Kernighan-Lin heuristic to hardware/software partitioning. It is investigated in detail which versions of the heuristic work well in this context. Since hardware/software partitioning also has several formulations, it is also discussed how the problem formulation affects the applicability of this heuristic. Furthermore, possibilities of efficient implementations of the algorithm-by using appropriate data structures-are also presented. These investigations are accompanied by numerous empirical test results.

show abstract

Section: Work On Hardware/software Partitioningmentioning

confidence: 99%

Section: Work On Hardware/software Partitioningmentioning

confidence: 99%

Evaluating the Kernighan-Lin Heuristic for Hardware/Software Partitioning

Mann¹,

Orbán²,

Farkas³

2007

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

show abstract

“…Some researchers used custom heuristics to solve hardware/software partitioning. This includes the GCLP algorithm [24,25] and the expert system of Lopez-Vallejo and Lopez [29,31], as well as the heuristics of Gupta and de Micheli [18] and Wolf [50]. There are also some families of well-known heuristics that are usually applied to partitioning problems.…”

Section: Previous Workmentioning

confidence: 99%

“…In particular, many researchers consider scheduling as part of partitioning [10,12,24,31,34,36], whereas others do not [13,17,32,37,49,47]. Some even include the problem of assigning communication events to links between hardware and/or software units [12,34].…”

Section: Previous Workmentioning

confidence: 99%

Finding optimal hardware/software partitions

Mann

Orbán

Arató

2007

Form Methods Syst Des

View full text Add to dashboard Cite

Most previous approaches to hardware/software partitioning considered heuristic solutions. In contrast, this paper presents an exact algorithm for the problem based on branch-and-bound. Several techniques are investigated to speed up the algorithm, including bounds based on linear programming, a custom inference engine to make the most out of the inferred information, advanced necessary conditions for partial solutions, and different heuristics to obtain high-quality initial solutions. It is demonstrated with empirical measurements that the resulting algorithm can solve highly complex partitioning problems in reasonable time. Moreover, it is about ten times faster than a previous exact algorithm based on integer linear programming. The presented methods can also be useful in other related optimization problems.

show abstract

“…In 1997, Kalavade and Lee extended their early work to handle general architectures. 16 Also at that time, Wolf developed a synthesis method that could handle arbitrary interconnection topologies and arbitrary combinations of CPUs and ASICs. 17 Low-power design became a dominant theme during the 1990s, which prompted research into techniques for low-power cosynthesis.…”

mentioning

confidence: 99%