Comparative Evaluation of Memory Technologies for Synaptic Crossbar Arrays- Part 2: Design Knobs and DNN Accuracy Trends Article Swipe
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2408.05857
Crossbar memory arrays have been touted as the workhorse of in-memory computing (IMC)-based acceleration of Deep Neural Networks (DNNs), but the associated hardware non-idealities limit their efficacy. To address this, cross-layer design solutions that reduce the impact of hardware non-idealities on DNN accuracy are needed. In Part 1 of this paper, we established the co-optimization strategies for various memory technologies and their crossbar arrays, and conducted a comparative technology evaluation in the context of IMC robustness. In this part, we analyze various design knobs such as array size and bit-slice (number of bits per device) and their impact on the performance of 8T SRAM, ferroelectric transistor (FeFET), Resistive RAM (ReRAM) and spin-orbit-torque magnetic RAM (SOT-MRAM) in the context of inference accuracy at 7nm technology node. Further, we study the effect of circuit design solutions such as Partial Wordline Activation (PWA) and custom ADC reference levels that reduce the hardware non-idealities and comparatively analyze the response of each technology to such accuracy enhancing techniques. Our results on ResNet-20 (with CIFAR-10) show that PWA increases accuracy by up to 32.56% while custom ADC reference levels yield up to 31.62% accuracy enhancement. We observe that compared to the other technologies, FeFET, by virtue of its small layout height and high distinguishability of its memory states, is best suited for large arrays. For higher bit-slices and a more complex dataset (ResNet-50 with Cifar-100) we found that ReRAM matches the performance of FeFET.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2408.05857
- https://arxiv.org/pdf/2408.05857
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4402387133
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4402387133Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2408.05857Digital Object Identifier
- Title
-
Comparative Evaluation of Memory Technologies for Synaptic Crossbar Arrays- Part 2: Design Knobs and DNN Accuracy TrendsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-08-11Full publication date if available
- Authors
-
Jeffry Victor, Chunguang Wang, Sumeet Kumar GuptaList of authors in order
- Landing page
-
https://arxiv.org/abs/2408.05857Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2408.05857Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2408.05857Direct OA link when available
- Concepts
-
Crossbar switch, Computer science, Computer architecture, TelecommunicationsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4402387133 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2408.05857 |
| ids.doi | https://doi.org/10.48550/arxiv.2408.05857 |
| ids.openalex | https://openalex.org/W4402387133 |
| fwci | |
| type | preprint |
| title | Comparative Evaluation of Memory Technologies for Synaptic Crossbar Arrays- Part 2: Design Knobs and DNN Accuracy Trends |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10502 |
| topics[0].field.id | https://openalex.org/fields/22 |
| topics[0].field.display_name | Engineering |
| topics[0].score | 0.9998000264167786 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2208 |
| topics[0].subfield.display_name | Electrical and Electronic Engineering |
| topics[0].display_name | Advanced Memory and Neural Computing |
| topics[1].id | https://openalex.org/T12808 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.998199999332428 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2208 |
| topics[1].subfield.display_name | Electrical and Electronic Engineering |
| topics[1].display_name | Ferroelectric and Negative Capacitance Devices |
| topics[2].id | https://openalex.org/T10472 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9843000173568726 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2208 |
| topics[2].subfield.display_name | Electrical and Electronic Engineering |
| topics[2].display_name | Semiconductor materials and devices |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C29984679 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7039624452590942 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1929149 |
| concepts[0].display_name | Crossbar switch |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.5315475463867188 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C118524514 |
| concepts[2].level | 1 |
| concepts[2].score | 0.391152024269104 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q173212 |
| concepts[2].display_name | Computer architecture |
| concepts[3].id | https://openalex.org/C76155785 |
| concepts[3].level | 1 |
| concepts[3].score | 0.2498045265674591 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q418 |
| concepts[3].display_name | Telecommunications |
| keywords[0].id | https://openalex.org/keywords/crossbar-switch |
| keywords[0].score | 0.7039624452590942 |
| keywords[0].display_name | Crossbar switch |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.5315475463867188 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/computer-architecture |
| keywords[2].score | 0.391152024269104 |
| keywords[2].display_name | Computer architecture |
| keywords[3].id | https://openalex.org/keywords/telecommunications |
| keywords[3].score | 0.2498045265674591 |
| keywords[3].display_name | Telecommunications |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2408.05857 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2408.05857 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2408.05857 |
| locations[1].id | doi:10.48550/arxiv.2408.05857 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2408.05857 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5102694093 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-9487-8177 |
| authorships[0].author.display_name | Jeffry Victor |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Victor, Jeffry |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100773601 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-6709-3422 |
| authorships[1].author.display_name | Chunguang Wang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Wang, Chunguang |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5044276472 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-5609-9722 |
| authorships[2].author.display_name | Sumeet Kumar Gupta |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Gupta, Sumeet K. |
| authorships[2].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2408.05857 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-09-10T00:00:00 |
| display_name | Comparative Evaluation of Memory Technologies for Synaptic Crossbar Arrays- Part 2: Design Knobs and DNN Accuracy Trends |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10502 |
| primary_topic.field.id | https://openalex.org/fields/22 |
| primary_topic.field.display_name | Engineering |
| primary_topic.score | 0.9998000264167786 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2208 |
| primary_topic.subfield.display_name | Electrical and Electronic Engineering |
| primary_topic.display_name | Advanced Memory and Neural Computing |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2748952813, https://openalex.org/W2145932742, https://openalex.org/W2554791727, https://openalex.org/W1874409533, https://openalex.org/W1981395029, https://openalex.org/W2108083791, https://openalex.org/W4250137794, https://openalex.org/W2063341228, https://openalex.org/W2111673944 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2408.05857 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2408.05857 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2408.05857 |
| primary_location.id | pmh:oai:arXiv.org:2408.05857 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2408.05857 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2408.05857 |
| publication_date | 2024-08-11 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.1 | 47 |
| abstract_inverted_index.a | 66, 222 |
| abstract_inverted_index.8T | 102 |
| abstract_inverted_index.In | 45, 76 |
| abstract_inverted_index.To | 27 |
| abstract_inverted_index.We | 189 |
| abstract_inverted_index.as | 6, 85, 135 |
| abstract_inverted_index.at | 121 |
| abstract_inverted_index.by | 174, 198 |
| abstract_inverted_index.in | 70, 115 |
| abstract_inverted_index.is | 212 |
| abstract_inverted_index.of | 9, 14, 37, 48, 73, 91, 101, 118, 130, 155, 200, 208, 236 |
| abstract_inverted_index.on | 40, 98, 165 |
| abstract_inverted_index.to | 158, 176, 185, 193 |
| abstract_inverted_index.up | 175, 184 |
| abstract_inverted_index.we | 51, 79, 126, 229 |
| abstract_inverted_index.7nm | 122 |
| abstract_inverted_index.ADC | 142, 180 |
| abstract_inverted_index.DNN | 41 |
| abstract_inverted_index.For | 218 |
| abstract_inverted_index.IMC | 74 |
| abstract_inverted_index.Our | 163 |
| abstract_inverted_index.PWA | 171 |
| abstract_inverted_index.RAM | 108, 113 |
| abstract_inverted_index.and | 60, 64, 88, 95, 110, 140, 150, 205, 221 |
| abstract_inverted_index.are | 43 |
| abstract_inverted_index.but | 19 |
| abstract_inverted_index.for | 56, 215 |
| abstract_inverted_index.its | 201, 209 |
| abstract_inverted_index.per | 93 |
| abstract_inverted_index.the | 7, 20, 35, 53, 71, 99, 116, 128, 147, 153, 194, 234 |
| abstract_inverted_index.Deep | 15 |
| abstract_inverted_index.Part | 46 |
| abstract_inverted_index.been | 4 |
| abstract_inverted_index.best | 213 |
| abstract_inverted_index.bits | 92 |
| abstract_inverted_index.each | 156 |
| abstract_inverted_index.have | 3 |
| abstract_inverted_index.high | 206 |
| abstract_inverted_index.more | 223 |
| abstract_inverted_index.show | 169 |
| abstract_inverted_index.size | 87 |
| abstract_inverted_index.such | 84, 134, 159 |
| abstract_inverted_index.that | 33, 145, 170, 191, 231 |
| abstract_inverted_index.this | 49, 77 |
| abstract_inverted_index.with | 227 |
| abstract_inverted_index.(PWA) | 139 |
| abstract_inverted_index.(with | 167 |
| abstract_inverted_index.ReRAM | 232 |
| abstract_inverted_index.SRAM, | 103 |
| abstract_inverted_index.array | 86 |
| abstract_inverted_index.found | 230 |
| abstract_inverted_index.knobs | 83 |
| abstract_inverted_index.large | 216 |
| abstract_inverted_index.limit | 24 |
| abstract_inverted_index.node. | 124 |
| abstract_inverted_index.other | 195 |
| abstract_inverted_index.part, | 78 |
| abstract_inverted_index.small | 202 |
| abstract_inverted_index.study | 127 |
| abstract_inverted_index.their | 25, 61, 96 |
| abstract_inverted_index.this, | 29 |
| abstract_inverted_index.while | 178 |
| abstract_inverted_index.yield | 183 |
| abstract_inverted_index.31.62% | 186 |
| abstract_inverted_index.32.56% | 177 |
| abstract_inverted_index.FeFET, | 197 |
| abstract_inverted_index.FeFET. | 237 |
| abstract_inverted_index.Neural | 16 |
| abstract_inverted_index.arrays | 2 |
| abstract_inverted_index.custom | 141, 179 |
| abstract_inverted_index.design | 31, 82, 132 |
| abstract_inverted_index.effect | 129 |
| abstract_inverted_index.height | 204 |
| abstract_inverted_index.higher | 219 |
| abstract_inverted_index.impact | 36, 97 |
| abstract_inverted_index.layout | 203 |
| abstract_inverted_index.levels | 144, 182 |
| abstract_inverted_index.memory | 1, 58, 210 |
| abstract_inverted_index.paper, | 50 |
| abstract_inverted_index.reduce | 34, 146 |
| abstract_inverted_index.suited | 214 |
| abstract_inverted_index.touted | 5 |
| abstract_inverted_index.virtue | 199 |
| abstract_inverted_index.(DNNs), | 18 |
| abstract_inverted_index.(ReRAM) | 109 |
| abstract_inverted_index.(number | 90 |
| abstract_inverted_index.Partial | 136 |
| abstract_inverted_index.address | 28 |
| abstract_inverted_index.analyze | 80, 152 |
| abstract_inverted_index.arrays, | 63 |
| abstract_inverted_index.arrays. | 217 |
| abstract_inverted_index.circuit | 131 |
| abstract_inverted_index.complex | 224 |
| abstract_inverted_index.context | 72, 117 |
| abstract_inverted_index.dataset | 225 |
| abstract_inverted_index.device) | 94 |
| abstract_inverted_index.matches | 233 |
| abstract_inverted_index.needed. | 44 |
| abstract_inverted_index.observe | 190 |
| abstract_inverted_index.results | 164 |
| abstract_inverted_index.states, | 211 |
| abstract_inverted_index.various | 57, 81 |
| abstract_inverted_index.(FeFET), | 106 |
| abstract_inverted_index.Crossbar | 0 |
| abstract_inverted_index.Further, | 125 |
| abstract_inverted_index.Networks | 17 |
| abstract_inverted_index.Wordline | 137 |
| abstract_inverted_index.accuracy | 42, 120, 160, 173, 187 |
| abstract_inverted_index.compared | 192 |
| abstract_inverted_index.crossbar | 62 |
| abstract_inverted_index.hardware | 22, 38, 148 |
| abstract_inverted_index.magnetic | 112 |
| abstract_inverted_index.response | 154 |
| abstract_inverted_index.CIFAR-10) | 168 |
| abstract_inverted_index.ResNet-20 | 166 |
| abstract_inverted_index.Resistive | 107 |
| abstract_inverted_index.bit-slice | 89 |
| abstract_inverted_index.computing | 11 |
| abstract_inverted_index.conducted | 65 |
| abstract_inverted_index.efficacy. | 26 |
| abstract_inverted_index.enhancing | 161 |
| abstract_inverted_index.in-memory | 10 |
| abstract_inverted_index.increases | 172 |
| abstract_inverted_index.inference | 119 |
| abstract_inverted_index.reference | 143, 181 |
| abstract_inverted_index.solutions | 32, 133 |
| abstract_inverted_index.workhorse | 8 |
| abstract_inverted_index.(ResNet-50 | 226 |
| abstract_inverted_index.(SOT-MRAM) | 114 |
| abstract_inverted_index.Activation | 138 |
| abstract_inverted_index.Cifar-100) | 228 |
| abstract_inverted_index.associated | 21 |
| abstract_inverted_index.bit-slices | 220 |
| abstract_inverted_index.evaluation | 69 |
| abstract_inverted_index.strategies | 55 |
| abstract_inverted_index.technology | 68, 123, 157 |
| abstract_inverted_index.transistor | 105 |
| abstract_inverted_index.(IMC)-based | 12 |
| abstract_inverted_index.comparative | 67 |
| abstract_inverted_index.cross-layer | 30 |
| abstract_inverted_index.established | 52 |
| abstract_inverted_index.performance | 100, 235 |
| abstract_inverted_index.robustness. | 75 |
| abstract_inverted_index.techniques. | 162 |
| abstract_inverted_index.acceleration | 13 |
| abstract_inverted_index.enhancement. | 188 |
| abstract_inverted_index.technologies | 59 |
| abstract_inverted_index.comparatively | 151 |
| abstract_inverted_index.ferroelectric | 104 |
| abstract_inverted_index.technologies, | 196 |
| abstract_inverted_index.non-idealities | 23, 39, 149 |
| abstract_inverted_index.co-optimization | 54 |
| abstract_inverted_index.spin-orbit-torque | 111 |
| abstract_inverted_index.distinguishability | 207 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile |