Design and Performance Analysis of Hardware Accelerator for Deep Neural Network in Heterogeneous Platform

Simple item page
dc.contributor.advisorAslan, Semih
dc.contributor.advisorQasem, Apan
dc.contributor.authorSefat, Md Syadus
dc.contributor.committeeMemberAsiabanpour, Bahram
dc.contributor.committeeMemberValles, Damian
dc.date.accessioned2022-01-14T15:48:31Z
dc.date.available2022-01-14T15:48:31Z
dc.date.issued2018-08
dc.description.abstractThis thesis describes a new flexible approach to implementing energy-efficient DNN accelerator on FPGAs. Our design leverages the Coherent Accelerator Processor Interface (CAPI) which provides a cache-coherent view of system memory to attached accelerators. Computational kernels are accelerated on a CAPI-supported Kintex FPGA board. Our implementation bypasses the need for device driver code and significantly reduces the communication and I/O transfer overhead. To improve the performance of the entire application, we propose a collaborative model of execution in which the control of the data flow within the accelerator is kept independent, freeing-up CPU cores to work on other parts of the application. For further performance enhancements, we propose a technique to exploit data locality in the cache, situated in the CAPI Power Service Layer (PSL). Finally, we develop a resource-conscious implementation for more efficient utilization of resources and improved scalability. Compared with the previous work, our architecture achieves both improved performance and better power efficiency.
dc.description.departmentEngineering
dc.formatText
dc.format.extent111 pages
dc.format.medium1 file (.pdf)
dc.identifier.citationSefat, M. D. S. (2018). <i>Design and performance analysis of hardware accelerator for deep neural network in heterogeneous platform</i> (Unpublished thesis). Texas State University, San Marcos, Texas.
dc.identifier.urihttps://hdl.handle.net/10877/15152
dc.language.isoen
dc.subjectHardware
dc.subjectAccelerator
dc.subjectDNN
dc.subjectFPGA
dc.titleDesign and Performance Analysis of Hardware Accelerator for Deep Neural Network in Heterogeneous Platform
dc.typeThesis
thesis.degree.departmentEngineering
thesis.degree.disciplineEngineering
thesis.degree.grantorTexas State University
thesis.degree.levelMasters
thesis.degree.nameMaster of Science

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
SEFAT-THESIS-2018.pdf
Size:
2.83 MB
Format:
Adobe Portable Document Format
Download

License bundle

Now showing 1 - 2 of 2
No Thumbnail Available
Name:
LICENSE.txt
Size:
2.13 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
4.53 KB
Format:
Plain Text
Description:
Download

Collections

Graduate Theses and Dissertations