Title | ||
---|---|---|
An Energy-Efficient Deep Neural Network Training Processor with Bit-Slice-Level Reconfigurability and Sparsity Exploitation |
Abstract | ||
---|---|---|
This paper presents an energy-efficient deep neural network (DNN) training processor through the four key features: 1) Layer-wise Adaptive bit-Precision Scaling (LAPS) with 2) In-Out Slice Skipping (IOSS) core, 3) double-buffered Reconfigurable Accumulation Network (RAN), 4) momentum-ADAM unified OPTimizer Core (OPTC). Thanks to the bit-slice-level scalability and zero-slice skipping, it shows 5.9... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/COOLCHIPS52128.2021.9410324 | 2021 IEEE Symposium in Low-Power and High-Speed Chips (COOL CHIPS) |
DocType | ISSN | ISBN |
Conference | 2473-4683 | 978-1-6654-1503-3 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Donghyeon Han | 1 | 39 | 10.66 |
Dongseok Im | 2 | 12 | 6.21 |
Gwangtae Park | 3 | 20 | 3.41 |
Youngwoo Kim | 4 | 0 | 0.34 |
Seokchan Song | 5 | 0 | 0.34 |
Juhyoung Lee | 6 | 3 | 1.40 |
Hoi-Jun Yoo | 7 | 0 | 0.34 |