Modeling Gate-Level Abstraction Hierarchy Using Graph Convolutional Neural Networks to Predict Functional De-Rating Factors

Balakrishnan, Aneesh; Lange, Thomas; Glorieux, Maximilien; Alexandrescu, Dan; Jenihhin, Maksim

doi:10.1109/ahs.2019.00007

Cited by 10 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It could be useful to solve the issue of the training data set by using Graph Convolutional Neural Network (GCN) [10], that needs only 5% − 10% of training data. Recent research work about this idea had published in [11]. Another development direction is to develop acceptable prediction over gate-level netlist with the node2vec feature matrix and with more advanced graphbased deep neural architectures.…”

Section: B Results Analysis : Dnnmentioning

confidence: 99%

The Validation of Graph Model-Based, Gate Level Low-Dimensional Feature Data for Machine Learning Applications

Balakrishnan,

Lange,

Glorieux

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Section: B Results Analysis : Dnnmentioning

confidence: 99%

The Validation of Graph Model-Based, Gate Level Low-Dimensional Feature Data for Machine Learning Applications

Balakrishnan,

Lange,

Glorieux

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

“…Node2vec [1], Graph Convolutional Networks (GCN) [2] and GraphSAGE [3] have recently gained much attention from researchers for node embedding process. The application of graph-based neural network algorithms (GCN and node2vec) for circuit's reliability modeling, have proposed in papers [4] and [5] respectively. There is sufficient literature for machine learning (ML) applications in system reliability engineering.…”

Section: B Related Workmentioning

confidence: 99%

Composing Graph Theory and Deep Neural Networks to Evaluate SEU Type Soft Error Effects

Balakrishnan,

Lange,

Glorieux

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Rapidly shrinking technology node and voltage scaling increase the susceptibility of Soft Errors in digital circuits. Soft Errors are radiation-induced effects while the radiation particles such as Alpha, Neutrons or Heavy Ions, interact with sensitive regions of microelectronic devices/circuits. The particle hit could be a glancing blow or a penetrating strike. A well apprehended and characterized way of analyzing soft error effects is the fault-injection campaign, but that typically acknowledged as time and resource-consuming simulation strategy. As an alternative to traditional fault injection-based methodologies and to explore the applicability of modern graph based neural network algorithms in the field of reliability modeling, this paper proposes a systematic framework that explores gate-level abstractions to extract and exploit relevant feature representations at lowdimensional vector space. The framework allows the extensive prediction analysis of SEU type soft error effects in a given circuit. A scalable and inductive type representation learning algorithm on graphs called GraphSAGE has been utilized for efficiently extracting structural features of the gate-level netlist, providing a valuable database to exercise a downstream machine learning or deep learning algorithm aiming at predicting fault propagation metrics. Functional Failure Rate (FFR): the predicted fault propagating metric of SEU type fault within the gate-level circuit abstraction of the 10-Gigabit Ethernet MAC (IEEE 802.3) standard circuit.

show abstract

Gate-Level Graph Representation Learning: A Step Towards the Improved Stuck-at Faults Analysis

Balakrishnan

Alexandrescu

Jenihhin

et al. 2021

2021 22nd International Symposium on Quality Electronic Design (ISQED)

View full text Add to dashboard Cite

Modeling Gate-Level Abstraction Hierarchy Using Graph Convolutional Neural Networks to Predict Functional De-Rating Factors

Cited by 10 publications

References 5 publications

The Validation of Graph Model-Based, Gate Level Low-Dimensional Feature Data for Machine Learning Applications

The Validation of Graph Model-Based, Gate Level Low-Dimensional Feature Data for Machine Learning Applications

Composing Graph Theory and Deep Neural Networks to Evaluate SEU Type Soft Error Effects

Gate-Level Graph Representation Learning: A Step Towards the Improved Stuck-at Faults Analysis

Contact Info

Product

Resources

About