Efficient fast hartley transform algorithms for hypercube-connected multicomputers
buir.contributor.author | Aykanat, Cevdet | |
dc.citation.epage | 577 | en_US |
dc.citation.issueNumber | 6 | en_US |
dc.citation.spage | 561 | en_US |
dc.citation.volumeNumber | 6 | en_US |
dc.contributor.author | Aykanat, Cevdet | en_US |
dc.contributor.author | Derviş, A. | en_US |
dc.date.accessioned | 2016-02-08T10:52:22Z | |
dc.date.available | 2016-02-08T10:52:22Z | en_US |
dc.date.issued | 1995 | en_US |
dc.department | Department of Computer Engineering | en_US |
dc.description.abstract | Although fast Hartley transform (FHT) provides efficient spectral analysis of real discrete signals, the literature that addresses the parallelization of FHT is extremely rare. FHT is a real transformation and does not necessitate any complex arithmetics. On the other hand, FHT algorithm has an irregular computational structure which makes efficient parallelization harder. In this paper, we propose a efficient restructuring for the sequential FHT algorithm which brings regularity and symmetry to the computational structure of the FHT. Then, we propose an efficient parallel FHT algorithm for medium-to-coarse grain hypercube multicomputers by introducing a dynamic mapping scheme for the restructured FHT. The proposed parallel algorithm achieves perfect load-balance, minimizes both the number and volume of concurrent communications, allows only nearest-neighbor communications and achieves in-place computation and communication. The proposed algorithm is implemented on a 32-node iPSC/21 hypercube multicomputer. High-efficiency values are obtained even for small size FHT problems. © 1995 IEEE | en_US |
dc.description.provenance | Made available in DSpace on 2016-02-08T10:52:22Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 1995 | en_US |
dc.identifier.doi | 10.1109/71.388039 | en_US |
dc.identifier.eissn | 1558-2183 | en_US |
dc.identifier.issn | 1045-9219 | en_US |
dc.identifier.uri | http://hdl.handle.net/11693/25921 | en_US |
dc.language.iso | English | en_US |
dc.publisher | IEEE | en_US |
dc.relation.isversionof | http://dx.doi.org/10.1109/71.388039 | en_US |
dc.source.title | IEEE Transactions on Parallel and Distributed Systems | en_US |
dc.subject | Ance | en_US |
dc.subject | Digital Signal Processing | en_US |
dc.subject | Form | en_US |
dc.subject | Load Bal- | en_US |
dc.subject | Multicomputer | en_US |
dc.subject | Nearest-Neighbor Communication | en_US |
dc.subject | Parallel Computing | en_US |
dc.subject | Computational Load Balance | en_US |
dc.subject | Concurrent Communication | en_US |
dc.subject | Dynamic Mapping Scheme | en_US |
dc.subject | Fast Hartley Transform | en_US |
dc.subject | Hypercube | en_US |
dc.subject | Hypercube connected multicomputer | en_US |
dc.subject | Nearest neighbor communication | en_US |
dc.subject | Real discrete signals | en_US |
dc.subject | Computational complexity | en_US |
dc.subject | Computational methods | en_US |
dc.subject | Concurrency control | en_US |
dc.subject | Digital signal processing | en_US |
dc.subject | Interconnection networks | en_US |
dc.subject | Mathematical transformations | en_US |
dc.subject | Multiprocessing systems | en_US |
dc.subject | Optimization | en_US |
dc.subject | Parallel processing systems | en_US |
dc.subject | Performance | en_US |
dc.subject | Real Time Systems | en_US |
dc.subject | Spectrum Analysis | en_US |
dc.subject | Parallel Algorithms | en_US |
dc.title | Efficient fast hartley transform algorithms for hypercube-connected multicomputers | en_US |
dc.type | Article | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Efficient Fast Hartley Transform Algorithms for Hypercube-Connected Multicomputers.pdf
- Size:
- 1.76 MB
- Format:
- Adobe Portable Document Format
- Description:
- Full Printable Version