Saved in:
Bibliographic Details
Main Authors: Li, Wei, Zou, Yang, Liang, Yixin, Moura, José, Blanton, Shawn
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.23746
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914578776981504
author Li, Wei
Zou, Yang
Liang, Yixin
Moura, José
Blanton, Shawn
author_facet Li, Wei
Zou, Yang
Liang, Yixin
Moura, José
Blanton, Shawn
contents Modern IC complexity drives test pattern growth, with the majority of patterns targeting a small set of hard-to-detect (HTD) faults. This motivates new ATPG algorithms to improve test effectiveness specifically for HTD faults. This paper presents DEFT (Differentiable Automatic Test Pattern Generation), a new ATPG approach that reformulates the discrete ATPG problem as a continuous optimization task. DEFT introduces a mathematically grounded reparameterization that aligns the expected continuous objective with discrete fault-detection semantics, enabling reliable gradient-based pattern generation. To ensure scalability and stability on deep circuit graphs, DEFT integrates a custom CUDA kernel for efficient forward-backward propagation and applies gradient normalization to mitigate vanishing gradients. Compared to a leading commercial tool on a wide range of benchmarks, DEFT reduced the pattern count by 27.3% on average and by up to 75.9%. DEFT also supports practical ATPG settings such as partial assignment pattern generation, producing patterns with 19.3% fewer 0/1 bits while still detecting 35% more faults. These results indicate DEFT is a promising and effective ATPG engine, offering a valuable complement to existing heuristics.
format Preprint
id arxiv_https___arxiv_org_abs_2512_23746
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DEFT: Differentiable Automatic Test Pattern Generation
Li, Wei
Zou, Yang
Liang, Yixin
Moura, José
Blanton, Shawn
Software Engineering
Modern IC complexity drives test pattern growth, with the majority of patterns targeting a small set of hard-to-detect (HTD) faults. This motivates new ATPG algorithms to improve test effectiveness specifically for HTD faults. This paper presents DEFT (Differentiable Automatic Test Pattern Generation), a new ATPG approach that reformulates the discrete ATPG problem as a continuous optimization task. DEFT introduces a mathematically grounded reparameterization that aligns the expected continuous objective with discrete fault-detection semantics, enabling reliable gradient-based pattern generation. To ensure scalability and stability on deep circuit graphs, DEFT integrates a custom CUDA kernel for efficient forward-backward propagation and applies gradient normalization to mitigate vanishing gradients. Compared to a leading commercial tool on a wide range of benchmarks, DEFT reduced the pattern count by 27.3% on average and by up to 75.9%. DEFT also supports practical ATPG settings such as partial assignment pattern generation, producing patterns with 19.3% fewer 0/1 bits while still detecting 35% more faults. These results indicate DEFT is a promising and effective ATPG engine, offering a valuable complement to existing heuristics.
title DEFT: Differentiable Automatic Test Pattern Generation
topic Software Engineering
url https://arxiv.org/abs/2512.23746