2017 IFIP/IEEE International Conference on Very Large Scale Integration (VLSI-SoC) 2017
DOI: 10.1109/vlsi-soc.2017.8203479
|View full text |Cite
|
Sign up to set email alerts
|

Memristive devices for computing: Beyond CMOS and beyond von Neumann

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
28
0

Year Published

2018
2018
2024
2024

Publication Types

Select...
5
3
1

Relationship

3
6

Authors

Journals

citations
Cited by 46 publications
(28 citation statements)
references
References 53 publications
0
28
0
Order By: Relevance
“…Memristors can also hold their resistance state in the absence of an external active source. The electrical properties of a memristor depend on the physical mechanism or resistance switching, which could be due to metal ions forming a conductive bridge (CBRAM), movement of oxygen ions (RRAM), phase change of the active material (PCM) or self-directed channel (SDC) [16]. PCM memristors usually acquire only two states, one of high resistance (RESET or off-state) and another of low resistance (SET or on-state).…”
Section: Memristorsmentioning
confidence: 99%
“…Memristors can also hold their resistance state in the absence of an external active source. The electrical properties of a memristor depend on the physical mechanism or resistance switching, which could be due to metal ions forming a conductive bridge (CBRAM), movement of oxygen ions (RRAM), phase change of the active material (PCM) or self-directed channel (SDC) [16]. PCM memristors usually acquire only two states, one of high resistance (RESET or off-state) and another of low resistance (SET or on-state).…”
Section: Memristorsmentioning
confidence: 99%
“…• CIM-Periphery (CIM-P): In CIM-P, the computation result is produced within the peripheral circuitry. Examples of such architectures are PRIME [26], Pinatubo [27], CIM-Accelerator [28], etc. This architecture focuses on special circuits in the peripherals to realize, for example, bit-wise logic operations [27,29], matrix-vector multiplication [6,30], etc.…”
Section: A Cim Concept and Classificationmentioning
confidence: 99%
“…Memristor-based Computation-In-Memory (CIM) concept was proposed to eliminate the communication between the CPU and memory by leveraging memristors for both storage and computation in the same physical crossbar [3,12,13]. Here, we use the CIM to realize an accelerator we refer to as Memristive Vector Processor (MVP).…”
Section: Memristive Devices For Vector Processingmentioning
confidence: 99%