Show simple item record

dc.contributor.authorChen, Xiaowei
dc.description.abstractMemory wall is becoming a more and more serious bottleneck of the processing speed of microprocessors. The mismatch between CPUs and memories has been increasing since three decades ago. SRAM was introduced as the bridge between the main memory and the CPU. SRAM is designed to be on the same die with CPU and stores temporary data and instructions that are to be processed by the CPU. Thus, the performance of SRAMs has a direct impact on the performance of CPUs. With the application of mass amount data to be processed nowadays, there is a great need for high-performance CPUs. Three dimensional CPUs and CPUs that are specifically designed for machine learning are gaining popularity. The objective of this work is to design high-performance SRAM for these two emerging applications. Firstly, a novel delay cell based on dummy TSV is proposed to replace traditional delay cells for better timing control. Secondly, a unique SRAM with novel architecture is custom designed for a high-performance machine learning processor. Post-layout simulation shows that the SRAM works well with the processing core and its design is optimized to work well with machine learning processors based on convolutional neural networks. A prototype of the SRAM is also tapped out to further verify our design.en_US
dc.publisherNorth Dakota State Universityen_US
dc.rightsNDSU policy 190.6.2en_US
dc.titleHigh Performance Static Random Access Memory Design for Emerging Applicationsen_US
dc.typeDissertationen_US
dc.date.accessioned2021-01-22T21:35:59Z
dc.date.available2021-01-22T21:35:59Z
dc.date.issued2018
dc.identifier.urihttps://hdl.handle.net/10365/31743
dc.subjectconvolutional neural networken_US
dc.subjectdelay cellen_US
dc.subjectimage recognitionen_US
dc.subjectmachine learningen_US
dc.subjectstatic random access memoryen_US
dc.subjectthrough silicon viaen_US
dc.identifier.orcid0000-0002-2408-1488
dc.rights.urihttps://www.ndsu.edu/fileadmin/policy/190.pdfen_US
ndsu.degreeDoctor of Philosophy (PhD)en_US
ndsu.collegeEngineeringen_US
ndsu.departmentElectrical and Computer Engineeringen_US
ndsu.programElectrical and Computer Engineeringen_US
ndsu.advisorChen, Xiaowei


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record