Using SDRAM Memories for High-Performance Accesses to Two-Dimensional Matrices Without Transpose.
Saved in:
| Title: | Using SDRAM Memories for High-Performance Accesses to Two-Dimensional Matrices Without Transpose. |
|---|---|
| Authors: | Langemeyer, Stefan1 stefan.langemeyer@ims.uni-hannover.de, Pirsch, Peter1 pirsch@ims.uni-hannover.de, Blume, Holger1 blume@ims.uni-hannover.de |
| Source: | International Journal of Parallel Programming. Apr2013, Vol. 41 Issue 2, p331-354. 24p. 16 Diagrams, 6 Charts, 8 Graphs. |
| Subjects: | Digital filters (Mathematics), Matrices software, Dynamic random access memory, Data mapping, Fourier transforms, Synthetic aperture radar |
| Abstract: | The data throughput of SDRAMs is significantly reduced by the control overhead required for access or transposition of large two-dimensional data matrices stored in SDRAM memories. In this paper, a new address mapping scheme is introduced, taking advantage of multiple banks and burst capabilities of modern SDRAMs. In this way, the data throughput is maximized when reading or writing rows or columns of a two-dimensional data matrix. Other address mapping strategies minimize the total number of SDRAM page-opens while traversing the two-dimensional index-space in row or column direction. In order to achieve a higher data throughput, the new approach uses an alternative bank interleaving method to hide additional wait cycles. In this way, the number of data bus wait cycles do not depend on the overall number of page-opens directly any more. It is shown, that the data bus utilization can be increased significantly. In particular, the new mapping strategy is optimized for access of parallel samples, distributed among a number of SDRAM chips. Therefore, double buffering can be omitted. As a special operation, 2D-FFT processing for radar applications is considered. Depending on SDRAM parameters and dimensions, a continuous bandwidth utilization of 96-98 % is achieved for accesses in both matrix dimensions, including all page-opens and refresh operations. [ABSTRACT FROM AUTHOR] |
| Copyright of International Journal of Parallel Programming is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 85012644 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Using SDRAM Memories for High-Performance Accesses to Two-Dimensional Matrices Without Transpose. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Langemeyer%2C+Stefan%22">Langemeyer, Stefan</searchLink><relatesTo>1</relatesTo><i> stefan.langemeyer@ims.uni-hannover.de</i><br /><searchLink fieldCode="AR" term="%22Pirsch%2C+Peter%22">Pirsch, Peter</searchLink><relatesTo>1</relatesTo><i> pirsch@ims.uni-hannover.de</i><br /><searchLink fieldCode="AR" term="%22Blume%2C+Holger%22">Blume, Holger</searchLink><relatesTo>1</relatesTo><i> blume@ims.uni-hannover.de</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Parallel+Programming%22">International Journal of Parallel Programming</searchLink>. Apr2013, Vol. 41 Issue 2, p331-354. 24p. 16 Diagrams, 6 Charts, 8 Graphs. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Digital+filters+%28Mathematics%29%22">Digital filters (Mathematics)</searchLink><br /><searchLink fieldCode="DE" term="%22Matrices+software%22">Matrices software</searchLink><br /><searchLink fieldCode="DE" term="%22Dynamic+random+access+memory%22">Dynamic random access memory</searchLink><br /><searchLink fieldCode="DE" term="%22Data+mapping%22">Data mapping</searchLink><br /><searchLink fieldCode="DE" term="%22Fourier+transforms%22">Fourier transforms</searchLink><br /><searchLink fieldCode="DE" term="%22Synthetic+aperture+radar%22">Synthetic aperture radar</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: The data throughput of SDRAMs is significantly reduced by the control overhead required for access or transposition of large two-dimensional data matrices stored in SDRAM memories. In this paper, a new address mapping scheme is introduced, taking advantage of multiple banks and burst capabilities of modern SDRAMs. In this way, the data throughput is maximized when reading or writing rows or columns of a two-dimensional data matrix. Other address mapping strategies minimize the total number of SDRAM page-opens while traversing the two-dimensional index-space in row or column direction. In order to achieve a higher data throughput, the new approach uses an alternative bank interleaving method to hide additional wait cycles. In this way, the number of data bus wait cycles do not depend on the overall number of page-opens directly any more. It is shown, that the data bus utilization can be increased significantly. In particular, the new mapping strategy is optimized for access of parallel samples, distributed among a number of SDRAM chips. Therefore, double buffering can be omitted. As a special operation, 2D-FFT processing for radar applications is considered. Depending on SDRAM parameters and dimensions, a continuous bandwidth utilization of 96-98 % is achieved for accesses in both matrix dimensions, including all page-opens and refresh operations. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of International Journal of Parallel Programming is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=85012644 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s10766-012-0225-6 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 24 StartPage: 331 Subjects: – SubjectFull: Digital filters (Mathematics) Type: general – SubjectFull: Matrices software Type: general – SubjectFull: Dynamic random access memory Type: general – SubjectFull: Data mapping Type: general – SubjectFull: Fourier transforms Type: general – SubjectFull: Synthetic aperture radar Type: general Titles: – TitleFull: Using SDRAM Memories for High-Performance Accesses to Two-Dimensional Matrices Without Transpose. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Langemeyer, Stefan – PersonEntity: Name: NameFull: Pirsch, Peter – PersonEntity: Name: NameFull: Blume, Holger IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 04 Text: Apr2013 Type: published Y: 2013 Identifiers: – Type: issn-print Value: 08857458 Numbering: – Type: volume Value: 41 – Type: issue Value: 2 Titles: – TitleFull: International Journal of Parallel Programming Type: main |
| ResultId | 1 |
