born in 1998. Master candidate. His main research interests include deep learning hardware acceleration and fault-tolerant chip design
born in 1984. PhD, associate professor. His main research interests include domain-specific accelerator design, fault-tolerant computing, and near-data computing
born in 1977. PhD, professor. His main research interests include fault-tolerant computing and onboard computing
born in 1999. Master candidate. His main research interests include deep learning algorithm and accelerator design, and fault-tolerant deep learning
born in 1985. PhD, professor. His main research interests include approximate/error-tolerant computing, VLSI design, and energy-efficient accelerators
born in 1974. PhD, professor. Her main research interests include EDA, approximate computing, fault-tolerant computing, and VLSI verification and test
born in 1964. PhD, professor. Member of IEEE. His main research interests include VLSI test, fault-tolerant computing, and hardware security
Fault-tolerant deep learning accelerator is the basis for highly reliable deep learning processing, and is also critical to deploy deep learning in safety-critical applications such as avionics and robotics. Since deep learning is known to be both computing-intensive and memory-intensive, traditional fault-tolerant approaches based on redundant computing will incur substantial overhead including power consumption and chip area. To this end, we propose to characterize deep learning vulnerability difference across both neurons and bits of each neuron, and leverage the vulnerability difference to enable selective protection of the deep learning processing components from the perspective of architecture layer and circuit layer respectively for the sake of lower fault-tolerant design overhead. At the same time, we observe the correlation between model quantization and bit protection overhead of the underlying processing elements of deep learning accelerators, and propose to reduce the bit protection overhead by adding additional quantization constrain without compromising the model accuracy. Finally, we employ Bayesian optimization strategy to co-optimize the correlated cross-layer design parameters at algorithm layer, architecture layer, and circuit layer to minimize the hardware resource consumption while fulfilling multiple user constraints including reliability, accuracy, and performance of the deep learning processing at the same time.
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |