東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

A Programmable Processing-In-Memory Architecture for Memory Intensive Applications.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	A Programmable Processing-In-Memory Architecture for Memory Intensive Applications./
作者:	Connolly, Mark.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	53 p.
附註:	Source: Masters Abstracts International, Volume: 82-11.
Contained By:	Masters Abstracts International82-11.
標題:	Computer engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28494713
ISBN:	9798738624346

A Programmable Processing-In-Memory Architecture for Memory Intensive Applications.
Connolly, Mark.

A Programmable Processing-In-Memory Architecture for Memory Intensive Applications. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 53 p.

Source: Masters Abstracts International, Volume: 82-11.

Thesis (M.S.)--Rochester Institute of Technology, 2021.

This item must not be sold to any third party vendors.

While both processing and memory architectures are rapidly improving in performance, memory architecture is lagging behind. As performance of processing architecture continues to eclipse that of memory, the memory architecture continues to become an increasingly unavoidable bottleneck in computer architecture. There are two drawbacks that are commonly associated with memory accesses: i) large delays causing the processor to remain idle waiting on data to become available and ii) the power consumption required to transfer the data. These performance issues are especially notable in research and enterprise computing applications such as deep learning models. Even when data for an application such as this is transferred to a cache before processing to avoid the delay, the large power cost of the transfer is still incurred. Processing-in-memory (PIM) architectures offer a solution to the issues in modern memory architecture. The inclusion of processing elements within the memory architecture reduces data transfers between the host processor and memory, thus reducing penalties incurred by memory accesses. The programmable-PIM (pPIM) architecture is a novel PIM architecture that delivers the performance enhancements of PIM while delivering a high degree of reprogrammability through the use of look-up tables (LUTs). A novel instruction set architecture (ISA) for the pPIM architecture facilitates the architecture's reprogrammability without large impacts on performance. The ISA takes a microcoded approach to handling the control signals of the pPIM control signals. This approach allows variable-stage instructions at a low additional cost to the overall power and area of the architecture. The versatility of the pPIM architecture enables MAC operations and several common activation functions to be modeled for execution on the architecture. As a measure of performance, post-synthesis models of both the pPIM architecture and the ISA are generated for CNN inference. As a proof-of-concept an FPGA model of the pPIM architecture is developed for representations of a single layer neural network (NN) model for classification of MNIST images.

ISBN: 9798738624346Subjects--Topical Terms:

621879
Computer engineering.
Subjects--Index Terms:

Convolutional Neural Network

A Programmable Processing-In-Memory Architecture for Memory Intensive Applications.
LDR:03435nmm a2200409 4500 001 2349538
005 20230509091107.5
006 m o d
007 cr#unu||||||||
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798738624346
035 $a (MiAaPQ)AAI28494713
035 $a AAI28494713
040 $a MiAaPQ $c MiAaPQ
100 1 $a Connolly, Mark. $3 3688948
245 1 0 $a A Programmable Processing-In-Memory Architecture for Memory Intensive Applications.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 53 p.
500 $a Source: Masters Abstracts International, Volume: 82-11.
500 $a Advisor: Ganguly, Amlan.
502 $a Thesis (M.S.)--Rochester Institute of Technology, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a While both processing and memory architectures are rapidly improving in performance, memory architecture is lagging behind. As performance of processing architecture continues to eclipse that of memory, the memory architecture continues to become an increasingly unavoidable bottleneck in computer architecture. There are two drawbacks that are commonly associated with memory accesses: i) large delays causing the processor to remain idle waiting on data to become available and ii) the power consumption required to transfer the data. These performance issues are especially notable in research and enterprise computing applications such as deep learning models. Even when data for an application such as this is transferred to a cache before processing to avoid the delay, the large power cost of the transfer is still incurred. Processing-in-memory (PIM) architectures offer a solution to the issues in modern memory architecture. The inclusion of processing elements within the memory architecture reduces data transfers between the host processor and memory, thus reducing penalties incurred by memory accesses. The programmable-PIM (pPIM) architecture is a novel PIM architecture that delivers the performance enhancements of PIM while delivering a high degree of reprogrammability through the use of look-up tables (LUTs). A novel instruction set architecture (ISA) for the pPIM architecture facilitates the architecture's reprogrammability without large impacts on performance. The ISA takes a microcoded approach to handling the control signals of the pPIM control signals. This approach allows variable-stage instructions at a low additional cost to the overall power and area of the architecture. The versatility of the pPIM architecture enables MAC operations and several common activation functions to be modeled for execution on the architecture. As a measure of performance, post-synthesis models of both the pPIM architecture and the ISA are generated for CNN inference. As a proof-of-concept an FPGA model of the pPIM architecture is developed for representations of a single layer neural network (NN) model for classification of MNIST images.
590 $a School code: 0465.
650 4 $a Computer engineering. $3 621879
650 4 $a Mechanical engineering. $3 649730
650 4 $a Artificial intelligence. $3 516317
653 $a Convolutional Neural Network
653 $a Deep Learning
653 $a Dynamic random-access memory
653 $a Look up table
653 $a Machine Learning
653 $a Processing-In-Memory
690 $a 0464
690 $a 0548
690 $a 0800
710 2 $a Rochester Institute of Technology. $b Computer Engineering. $3 1018788
773 0 $t Masters Abstracts International $g 82-11.
790 $a 0465
791 $a M.S.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28494713