Deep-Learning-Based Pre-Layout Parasitic Capacitance Prediction on SRAM Designs Article Swipe

PDF

Shan Shen , Dingcheng Yang , Yuyang Xie , Chunyan Pei , Wenjian Yu , Bei Yu ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2507.06549

To achieve higher system energy efficiency, SRAM in SoCs is often customized. The parasitic effects cause notable discrepancies between pre-layout and post-layout circuit simulations, leading to difficulty in converging design parameters and excessive design iterations. Is it possible to well predict the parasitics based on the pre-layout circuit, so as to perform parasitic-aware pre-layout simulation? In this work, we propose a deep-learning-based 2-stage model to accurately predict these parasitics in pre-layout stages. The model combines a Graph Neural Network (GNN) classifier and Multi-Layer Perceptron (MLP) regressors, effectively managing class imbalance of the net parasitics in SRAM circuits. We also employ Focal Loss to mitigate the impact of abundant internal net samples and integrate subcircuit information into the graph to abstract the hierarchical structure of schematics. Experiments on 4 real SRAM designs show that our approach not only surpasses the state-of-the-art model in parasitic prediction by a maximum of 19X reduction of error but also significantly boosts the simulation process by up to 598X speedup.

Related Topics

Truth And Reconciliation Commission Of Canada

Reich Ministry Of Public Enlightenment And Propaganda

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2507.06549
PDF: https://arxiv.org/pdf/2507.06549
OA Status: green
OpenAlex ID: https://openalex.org/W4416102643

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4416102643

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2507.06549

Digital Object Identifier
Title: Deep-Learning-Based Pre-Layout Parasitic Capacitance Prediction on SRAM Designs

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-07-09

Full publication date if available
Authors: Shan Shen, Dingcheng Yang, Yuyang Xie, Chunyan Pei, Wenjian Yu, Bei Yu

List of authors in order
Landing page: https://arxiv.org/abs/2507.06549

Publisher landing page
PDF URL: https://arxiv.org/pdf/2507.06549

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2507.06549

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4416102643
doi	https://doi.org/10.48550/arxiv.2507.06549
ids.doi	https://doi.org/10.48550/arxiv.2507.06549
ids.openalex	https://openalex.org/W4416102643
fwci
type	preprint
title	Deep-Learning-Based Pre-Layout Parasitic Capacitance Prediction on SRAM Designs
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2507.06549
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/2507.06549
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/2507.06549
locations[1].id	doi:10.48550/arxiv.2507.06549
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	cc-by
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id	https://openalex.org/licenses/cc-by
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.2507.06549
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5078618657
authorships[0].author.orcid	https://orcid.org/0000-0003-1383-463X
authorships[0].author.display_name	Shan Shen
authorships[0].author_position	first
authorships[0].raw_author_name	Shen, Shan
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5100636872
authorships[1].author.orcid	https://orcid.org/0000-0001-6117-554X
authorships[1].author.display_name	Dingcheng Yang
authorships[1].author_position	middle
authorships[1].raw_author_name	Yang, Dingcheng
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5002856991
authorships[2].author.orcid	https://orcid.org/0000-0003-3152-1936
authorships[2].author.display_name	Yuyang Xie
authorships[2].author_position	middle
authorships[2].raw_author_name	Xie, Yuyang
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5032253165
authorships[3].author.orcid
authorships[3].author.display_name	Chunyan Pei
authorships[3].author_position	middle
authorships[3].raw_author_name	Pei, Chunyan
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5053437305
authorships[4].author.orcid	https://orcid.org/0000-0003-4897-7251
authorships[4].author.display_name	Wenjian Yu
authorships[4].author_position	middle
authorships[4].raw_author_name	Yu, Wenjian
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5051340429
authorships[5].author.orcid	https://orcid.org/0000-0001-6406-4810
authorships[5].author.display_name	Bei Yu
authorships[5].author_position	last
authorships[5].raw_author_name	Yu, Bei
authorships[5].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/2507.06549
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Deep-Learning-Based Pre-Layout Parasitic Capacitance Prediction on SRAM Designs
has_fulltext	False
is_retracted	False
updated_date	2025-11-28T08:54:33.103737
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2507.06549
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/2507.06549
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/2507.06549
primary_location.id	pmh:oai:arXiv.org:2507.06549
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/2507.06549
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/2507.06549
publication_date	2025-07-09
publication_year	2025
referenced_works_count	0
abstract_inverted_index.4	127
abstract_inverted_index.a	60, 75, 145
abstract_inverted_index.In	55
abstract_inverted_index.Is	35
abstract_inverted_index.To	0
abstract_inverted_index.We	97
abstract_inverted_index.as	49
abstract_inverted_index.by	144, 159
abstract_inverted_index.in	7, 27, 69, 94, 141
abstract_inverted_index.is	9
abstract_inverted_index.it	36
abstract_inverted_index.of	90, 106, 123, 147, 150
abstract_inverted_index.on	44, 126
abstract_inverted_index.so	48
abstract_inverted_index.to	25, 38, 50, 64, 102, 118, 161
abstract_inverted_index.up	160
abstract_inverted_index.we	58
abstract_inverted_index.19X	148
abstract_inverted_index.The	12, 72
abstract_inverted_index.and	20, 31, 81, 111
abstract_inverted_index.but	152
abstract_inverted_index.net	92, 109
abstract_inverted_index.not	135
abstract_inverted_index.our	133
abstract_inverted_index.the	41, 45, 91, 104, 116, 120, 138, 156
abstract_inverted_index.598X	162
abstract_inverted_index.Loss	101
abstract_inverted_index.SRAM	6, 95, 129
abstract_inverted_index.SoCs	8
abstract_inverted_index.also	98, 153
abstract_inverted_index.into	115
abstract_inverted_index.only	136
abstract_inverted_index.real	128
abstract_inverted_index.show	131
abstract_inverted_index.that	132
abstract_inverted_index.this	56
abstract_inverted_index.well	39
abstract_inverted_index.(GNN)	79
abstract_inverted_index.(MLP)	84
abstract_inverted_index.Focal	100
abstract_inverted_index.Graph	76
abstract_inverted_index.based	43
abstract_inverted_index.cause	15
abstract_inverted_index.class	88
abstract_inverted_index.error	151
abstract_inverted_index.graph	117
abstract_inverted_index.model	63, 73, 140
abstract_inverted_index.often	10
abstract_inverted_index.these	67
abstract_inverted_index.work,	57
abstract_inverted_index.Neural	77
abstract_inverted_index.boosts	155
abstract_inverted_index.design	29, 33
abstract_inverted_index.employ	99
abstract_inverted_index.energy	4
abstract_inverted_index.higher	2
abstract_inverted_index.impact	105
abstract_inverted_index.system	3
abstract_inverted_index.2-stage	62
abstract_inverted_index.Network	78
abstract_inverted_index.achieve	1
abstract_inverted_index.between	18
abstract_inverted_index.circuit	22
abstract_inverted_index.designs	130
abstract_inverted_index.effects	14
abstract_inverted_index.leading	24
abstract_inverted_index.maximum	146
abstract_inverted_index.notable	16
abstract_inverted_index.perform	51
abstract_inverted_index.predict	40, 66
abstract_inverted_index.process	158
abstract_inverted_index.propose	59
abstract_inverted_index.samples	110
abstract_inverted_index.stages.	71
abstract_inverted_index.abstract	119
abstract_inverted_index.abundant	107
abstract_inverted_index.approach	134
abstract_inverted_index.circuit,	47
abstract_inverted_index.combines	74
abstract_inverted_index.internal	108
abstract_inverted_index.managing	87
abstract_inverted_index.mitigate	103
abstract_inverted_index.possible	37
abstract_inverted_index.speedup.	163
abstract_inverted_index.circuits.	96
abstract_inverted_index.excessive	32
abstract_inverted_index.imbalance	89
abstract_inverted_index.integrate	112
abstract_inverted_index.parasitic	13, 142
abstract_inverted_index.reduction	149
abstract_inverted_index.structure	122
abstract_inverted_index.surpasses	137
abstract_inverted_index.Perceptron	83
abstract_inverted_index.accurately	65
abstract_inverted_index.classifier	80
abstract_inverted_index.converging	28
abstract_inverted_index.difficulty	26
abstract_inverted_index.parameters	30
abstract_inverted_index.parasitics	42, 68, 93
abstract_inverted_index.pre-layout	19, 46, 53, 70
abstract_inverted_index.prediction	143
abstract_inverted_index.simulation	157
abstract_inverted_index.subcircuit	113
abstract_inverted_index.Experiments	125
abstract_inverted_index.Multi-Layer	82
abstract_inverted_index.customized.	11
abstract_inverted_index.effectively	86
abstract_inverted_index.efficiency,	5
abstract_inverted_index.information	114
abstract_inverted_index.iterations.	34
abstract_inverted_index.post-layout	21
abstract_inverted_index.regressors,	85
abstract_inverted_index.schematics.	124
abstract_inverted_index.simulation?	54
abstract_inverted_index.hierarchical	121
abstract_inverted_index.simulations,	23
abstract_inverted_index.discrepancies	17
abstract_inverted_index.significantly	154
abstract_inverted_index.parasitic-aware	52
abstract_inverted_index.state-of-the-art	139
abstract_inverted_index.deep-learning-based	61
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	6
citation_normalized_percentile