2018
DOI: 10.1109/tcsi.2017.2714101
|View full text |Cite
|
Sign up to set email alerts
|

Modeling and Analysis of Passive Switching Crossbar Arrays

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
51
0

Year Published

2018
2018
2023
2023

Publication Types

Select...
5
2
1

Relationship

3
5

Authors

Journals

citations
Cited by 63 publications
(52 citation statements)
references
References 43 publications
1
51
0
Order By: Relevance
“…These voltage drops are functions of the stored data and the wire resistance. At the expected feature size of F = 5nm of RRAMs, the wire resistance per cell reaches as high as 90Ω [4]. Fig.…”
Section: Introductionmentioning
confidence: 93%
See 2 more Smart Citations
“…These voltage drops are functions of the stored data and the wire resistance. At the expected feature size of F = 5nm of RRAMs, the wire resistance per cell reaches as high as 90Ω [4]. Fig.…”
Section: Introductionmentioning
confidence: 93%
“…The encoded output symbol z in+j , 0 ≤ i < m, 0 ≤ j < n, is stored at the (i, j)-th entry in the crossbar array (i.e., we vectorize the array row by row). Instead of using high-level models for the sneak path problem, such as in [6], [7], we use a SPICE-like simulator that is built based on accurate modeling of the resistive crossbar array [4]. This numerical simulator offers a fast alternative to SPICE simulators while maintaining the same simulation accuracy.…”
Section: Application To Resistive Crossbar Arrays a General Framentioning
confidence: 99%
See 1 more Smart Citation
“…The wire resistance is inevitable in nanostructure crossbar arrays. It is expected that the wire resistance would reach around 90Ω for 5nm feature size [35]. The wire resistance creates undesired IR voltage drops that accumulate across the columns in the array leading to unwanted paths between the input and output nodes.…”
Section: Inevitable Wire Resistance Problem In Crossbar Structuresmentioning
confidence: 99%
“…We perform systematic simulations on 4 parameters; On/Off ratio, line-resistance (Rline), array size, and weight pattern (for (a) random and (b) trained by the popular Softmax function often used in machine-learning algorithms) as shown in Figure 6-3. From the reported articles, device On/Off ratio varies from 2 to 100 for analog memristor operation [36], [51], [91]- [98] and the line resistance Rline can be up to 10Ω for nanoscale devices [90], [99]- [104]. In the simulation, randomized input patterns are applied and we show the resulting error of the last column, since it will experience stronger series resistance effects (worst case).…”
Section: Array Operation Conditions and Parasitic Effectsmentioning
confidence: 99%