MétaCan
Menu
Back to cohort
Record W3216491306 · doi:10.1109/tvlsi.2021.3102088

High-Dimensional Many-Objective Bayesian Optimization for LDE-Aware Analog IC Sizing

2021· article· en· W3216491306 on OpenAlex
Tuotian Liao, Lihong Zhang

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueIEEE Transactions on Very Large Scale Integration (VLSI) Systems · 2021
Typearticle
Languageen
FieldEngineering
TopicVLSI and FPGA Design Techniques
Canadian institutionsMemorial University of Newfoundland
FundersNatural Sciences and Engineering Research Council of CanadaMemorial University of NewfoundlandCanada Foundation for Innovation
KeywordsSizingBayesian optimizationComputer scienceDimension (graph theory)Mathematical optimizationComputer engineeringElectronic engineeringEngineeringArtificial intelligenceMathematics

Abstract

fetched live from OpenAlex

With the advancement of complementary metal–oxide–semiconductor (CMOS) technologies, layout-dependent effects (LDEs) become increasingly influential to MOSFET characteristics and in turn analog integrated circuit performance. Early awareness of LDEs before the layout stage gets critical in order to help subsequent layout synthesis meet performance requirements and thus reduce design iteration. In this article, we propose a high-dimensional many-objective Bayesian optimization (HMBO)-based LDE-aware sizing methodology to address such challenges. It can effectively tackle the huge configuration space that is incurred by the increased number of optimization variables for considering the LDEs in addition to the conventional sizing variables. Moreover, our proposed method is able to aim for simultaneously satisfying multiple circuit specifications to identify an optimum design point within the enlarged configuration space. In addition, we propose a performance-driven pattern learning scheme called Gibbs-upper confidence bound (UCB) for better managing the dimension splitting. Our method is compared with several prevalent evolutionary algorithms as well as state-of-the-art Bayesian optimization works designed for analog circuit sizing problems. The experimental results demonstrate the high efficacy of our proposed sizing methodology.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.984
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.009
GPT teacher head0.218
Teacher spread0.209 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it