國立虎尾科技大學 |

Enabling Reliable Processing-in-Memory Augmented Storage for Spintronic Domain Wall Memory through Transverse Read.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Enabling Reliable Processing-in-Memory Augmented Storage for Spintronic Domain Wall Memory through Transverse Read./
Author:	Ollivier, Sebastien Sylvain JeanLuc.
Description:	1 online resource (149 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 84-04, Section: B.
Contained By:	Dissertations Abstracts International84-04B.
Subject:	Nanowires. -
Online resource:	click for full text (PQDT)
ISBN:	9798352602744

Enabling Reliable Processing-in-Memory Augmented Storage for Spintronic Domain Wall Memory through Transverse Read.
Ollivier, Sebastien Sylvain JeanLuc.

Enabling Reliable Processing-in-Memory Augmented Storage for Spintronic Domain Wall Memory through Transverse Read. - 1 online resource (149 pages)

Source: Dissertations Abstracts International, Volume: 84-04, Section: B.

Thesis (Ph.D.)--University of Pittsburgh, 2022.

Includes bibliographical references

In recent years, more and more proposals have been explored to replace conventional SRAM, DRAM, and Flash with novel memories. Moreover, the performance gap between data access latency over a memory bus and high-speed processing continues to grow. Domain Wall Memory (DWM)-aka Racetrack Memory-is a spintronic memory that stores multiple data bits in a ferromagnetic nanowire and shifts this data into alignment with one or few access ports to read/write the data. DWM is non-volatile, highly dense (1-4F2 per cell), extremely energy efficient (circa 0.1pJ per write), low latency (circa 1ns per access), and does not suffer from endurance limitations. Domain Wall Memory can serve as an ideal conventional memory/storage replacement throughout the memory hierarchy from cache replacement to main memory.DWM's main drawback is the latency, energy, and potential reliability concern from shifting data to align with access points. However, this structure also permits a novel recently proposed access mode called a Transverse Read (TR), which determines the number of '1's between two access points without pin-pointing their location. This dissertation leverages TR to first propose two new reliability schemes that address misalignment and data loss in DWM due to pinning while shifting. Second, a TR-based Processing-In-Memory (PIM) architecture is proposed that boasts multi-operand bulk-bitwise operations, logical shifting and rotation, multi-operand addition, two operand multiplication, and dense accumulators. The arithmetic operations are shown for Integer/fixed-point and floating-point fidelities. Third, targeting DWM in size, weight, and power (SWaP) constrained architectures such as edge systems multiple applications of DWM PIM are explored including machine learning inference and training for hyperdimensional computing, convolutional neural networks.The proposed reliability improvements offer 10's of years of fault free operation with energy savings and protection over new fault modes compared to prior work. The proposed PIM provides multiple factors over improvements in performance and energy compared to prior PIM work dedicated accelerators and often dedicated application specific integrated circuits (ASICs).

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798352602744Subjects--Topical Terms:

568223
Nanowires.
Index Terms--Genre/Form:

554714
Electronic books.

Enabling Reliable Processing-in-Memory Augmented Storage for Spintronic Domain Wall Memory through Transverse Read.
LDR:03537ntm a22003377 4500 001 1148141
005 20240916070010.5
006 m o d
007 cr bn ---uuuuu
008 250605s2022 xx obm 000 0 eng d
020 $a 9798352602744
035 $a (MiAaPQ)AAI29335748
035 $a (MiAaPQ)Pittsburgh42434
035 $a AAI29335748
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Ollivier, Sebastien Sylvain JeanLuc. $3 1474050
245 1 0 $a Enabling Reliable Processing-in-Memory Augmented Storage for Spintronic Domain Wall Memory through Transverse Read.
264 0 $c 2022
300 $a 1 online resource (149 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 84-04, Section: B.
500 $a Advisor: Jones, Alex K. ;Bhanja, Sanjukta;Hu, Jingtong.
502 $a Thesis (Ph.D.)--University of Pittsburgh, 2022.
504 $a Includes bibliographical references
520 $a In recent years, more and more proposals have been explored to replace conventional SRAM, DRAM, and Flash with novel memories. Moreover, the performance gap between data access latency over a memory bus and high-speed processing continues to grow. Domain Wall Memory (DWM)-aka Racetrack Memory-is a spintronic memory that stores multiple data bits in a ferromagnetic nanowire and shifts this data into alignment with one or few access ports to read/write the data. DWM is non-volatile, highly dense (1-4F2 per cell), extremely energy efficient (circa 0.1pJ per write), low latency (circa 1ns per access), and does not suffer from endurance limitations. Domain Wall Memory can serve as an ideal conventional memory/storage replacement throughout the memory hierarchy from cache replacement to main memory.DWM's main drawback is the latency, energy, and potential reliability concern from shifting data to align with access points. However, this structure also permits a novel recently proposed access mode called a Transverse Read (TR), which determines the number of '1's between two access points without pin-pointing their location. This dissertation leverages TR to first propose two new reliability schemes that address misalignment and data loss in DWM due to pinning while shifting. Second, a TR-based Processing-In-Memory (PIM) architecture is proposed that boasts multi-operand bulk-bitwise operations, logical shifting and rotation, multi-operand addition, two operand multiplication, and dense accumulators. The arithmetic operations are shown for Integer/fixed-point and floating-point fidelities. Third, targeting DWM in size, weight, and power (SWaP) constrained architectures such as edge systems multiple applications of DWM PIM are explored including machine learning inference and training for hyperdimensional computing, convolutional neural networks.The proposed reliability improvements offer 10's of years of fault free operation with energy savings and protection over new fault modes compared to prior work. The proposed PIM provides multiple factors over improvements in performance and energy compared to prior PIM work dedicated accelerators and often dedicated application specific integrated circuits (ASICs).
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Nanowires. $3 568223
650 4 $a Energy consumption. $3 571871
650 4 $a Energy. $3 784773
650 4 $a Nanotechnology. $3 557660
655 7 $a Electronic books. $2 local $3 554714
690 $a 0791
690 $a 0652
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Pittsburgh. $3 1178873
773 0 $t Dissertations Abstracts International $g 84-04B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29335748 $z click for full text (PQDT)