R
R.D. Blanton
Researcher at Carnegie Mellon University
Publications - 158
Citations - 2948
R.D. Blanton is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Automatic test pattern generation & Fault model. The author has an hindex of 31, co-authored 153 publications receiving 2707 citations. Previous affiliations of R.D. Blanton include University of Pittsburgh.
Papers
More filters
Proceedings ArticleDOI
CompactNet: High Accuracy Deep Neural Network Optimized for On-Chip Implementation
TL;DR: It is demonstrated that, CompactNet provides pareto-optimal designs to make trade-offs between accuracy and resource requirement, and the applications of CompactNet can be extended to datasets like ImageNet, and into models like MobileNet.
Proceedings ArticleDOI
Maintaining Accuracy of Test Compaction through Adaptive Re-learning
Sounil Biswas,R.D. Blanton +1 more
TL;DR: An adaptive scheme that uses stratified sampling to check the accuracy of a correlation function at various time instances and re-learns a function when its accuracy dips below some tolerable threshold is described.
Proceedings ArticleDOI
Efficient built-in self test of regular logic characterization vehicles
Ben Niewenhuis,R.D. Blanton +1 more
TL;DR: This work describes a BIST scheme that achieves 100% input-pattern fault coverage with an 86.9% reduction in test time for a reference design and all of these properties are achieved with a minimal hardware overhead.
Journal ArticleDOI
Reducing test cost of integrated, heterogeneous systems using pass-fail test data analysis
TL;DR: A methodology for identifying the redundant tests of an integrated, heterogeneous system that has only binary pass-fail test data is described and it is shown that 14 out of 40 HSS tests and 11 out of 36 PLL tests are redundant.
Journal ArticleDOI
DFM Evaluation Using IC Diagnosis Data
TL;DR: Virtual data is used to demonstrate that the DFM rule most responsible for failure can be reliably identified even in light of the ambiguity inherent to a nonideal diagnostic resolution, and a corresponding rule-violation distribution that is counter-intuitive.