Performance evaluation of broadcast and global combine operations in all-port wormhole-routed OTIS-Mesh interconnection networks

Mahafzah, Basel A.; Tahboub, Ruby Y.; Tahboub, Omar Y.

doi:10.1007/s10586-009-0117-8

Cited by 18 publications

(7 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, n} with i = j, are intended to model the (longer) optical connections. The resulting OTIS network is denoted by OTIS-G. Of course, an OTIS network is dependent upon its base graph G, and numerous results have been proven for both specific base graphs and classes of base graphs (see, for example, the papers [1,3,7,8,17,18,19,23] and the references therein).…”

Section: Optical Transpose Interconnection Networkmentioning

confidence: 99%

Multiswapped networks and their topological and algorithmic properties

Stewart¹

2013

Journal of Computer and System Sciences

View full text Add to dashboard Cite

Section: Optical Transpose Interconnection Networkmentioning

confidence: 99%

Multiswapped networks and their topological and algorithmic properties

Stewart¹

2013

Journal of Computer and System Sciences

View full text Add to dashboard Cite

“…The experimental results showed that the OTIS-hypercube outperformed the hypercube network. Another research work evaluated the performance of broadcast and global combine communication operations on OTIS-mesh, in terms of number of communication steps, latency, and latency improvement [26]. Moreover, Hashemi-Najafabadi and Sarbazi-Azad [27] introduced and validated a mathematical performance model of adaptive wormhole routing in OTIS-hypercube.…”

Section: Related Workmentioning

confidence: 99%

The OTIS hyper hexa-cell optoelectronic architecture

et al. 2011

Self Cite

View full text Add to dashboard Cite

Optical transpose interconnection system (OTIS) is an optoelectronic architecture that promises to be a great choice for future-generation parallel systems. OTIS combines the advantages of electronic and optical links, where electronic links are used for short distances which require low material cost, and optical links are used for long distances which provide high speed network with low power consumption. Taking into account the advantageous characteristics of OTIS and based on the attractive properties of hyper hexa-cell (HHC) interconnection topology from low diameter and good minimum node degree, this paper introduces a new optoelectronic architecture referred to as OTIS hyper hexa-cell (OHHC). This paper also provides an evaluation and a comparison of the new topology with OTIS-mesh in terms of the following topological properties: size, diameter, maximum and minimum node degree, bisection width, total cost and optical cost. The results of this study proved the excellence of the proposed OHHC over OTIS-mesh in terms of diameter, minimum node degree, bisection width, and optical cost.

show abstract

“…So, one way to improve the runtime of the bucket sort algorithm is to run it on parallel or distributed architecture. Examples of these architectures are Optical Chained-Cubic Tree (OCCT) [15] and Optical Transpose Interconnection System (OTIS) and its variants, such as OTIS-Mesh, OTIS-Hypercube, and OTIS Hyper-Hexa Cell (OHHC) [16][17][18][19][20].…”

Section: Introductionmentioning

confidence: 99%

“…To illustrate the sequential BS algorithm's steps, Fig. 1 shows an example of the BS algorithm's steps to sort 16 elements (i.e., n = 16) using 4 buckets (i.e., b = 4), where the 16 elements' values are generated uniformly over the interval [1,16]. According to Algorithm 1, in the first step, the size and the subintervals of the buckets are determined using Eqs.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Parallel bucket sort algorithm on optical chained-cubic tree interconnection network

Mahafzah

2023

Preprint

Self Cite

View full text Add to dashboard Cite

The performance of sorting algorithms has a great impact on many computationally intensive applications. Researchers worked on parallelizing many sorting algorithms to improve their sequential counterpart performance. Thus, several interconnection networks have been presented for that purpose, such as tree and hypercube as basic interconnection networks and Chained-Cubic Tree (CCT) and Optical CCT (OCCT) as hybrid interconnection networks. The OCCT is constructed from a tree and hypercubes where optical links are added between hypercubes on a certain level of the tree. These optical links are used for long-distance and provide speed and low power consumption. In this paper, a new modified Parallel Bucket Sort (PBS) algorithm is presented and applied to the OCCT interconnection network. This PBS algorithm is evaluated analytically and by simulation in terms of various performance metrics including parallel runtime, computation time, communication time, concatenation time, speedup, and efficiency, for a different number of processors, dataset sizes, and data distributions including random and descending. Simulation results show that the highest obtained speedup is approximately 862 on OCCT using 1020 processors and descending input data distribution of size 40 MB. Also, the highest obtained efficiency is approximately 92% on OCCT using 124 processors and descending input data distribution of size 40 MB, which means the utilization of the OCCT processors reaches 92%.

show abstract

Performance evaluation of broadcast and global combine operations in all-port wormhole-routed OTIS-Mesh interconnection networks

Cited by 18 publications

References 29 publications

Multiswapped networks and their topological and algorithmic properties

Multiswapped networks and their topological and algorithmic properties

The OTIS hyper hexa-cell optoelectronic architecture

Parallel bucket sort algorithm on optical chained-cubic tree interconnection network

Contact Info

Product

Resources

About