Bit Prudent In-Cache Acceleration of Deep Convolutional Neural Networks
Authors:
- Xiaowei WangXWXiaowei Wang
- Jiecao YuJYJiecao Yu
- Charles AugustineCACharles Augustine
- Ravi IyerRIRavi Iyer
- Reetuparna DasRDReetuparna Das
- 1 February 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 81-93
Abstract
We propose Bit Prudent In-Cache Acceleration of Deep Convolutional Neural Networks - an in-SRAM architecture for accelerating Convolutional Neural Network (CNN) inference by leveraging network redundancy and massive parallelism. The network redundancy is exploited in two ways. First, we prune and fine-tune the trained network model and develop two distinct methods - coalescing and overlapping - to run inferences efficiently with sparse models. Second, we propose an architecture for network models with a reduced bit width by leveraging bit-serial computation. Our proposed architecture achieves a 17.7×/3.7× speedup over server class CPU/GPU, and a 1.6× speedup compared to the relevant in-cache accelerator, with 2% area overhead each processor die, and no loss on top-1 accuracy for AlexNet. With a relaxed accuracy limit, our tunable architecture achieves higher speedups.Keywords
This publication has 24 references indexed in Scilit:
- Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural NetworksIEEE Journal of Solid-State Circuits, 2016
- ISAACACM SIGARCH Computer Architecture News, 2016
- CnvlutinACM SIGARCH Computer Architecture News, 2016
- PRIMEACM SIGARCH Computer Architecture News, 2016
- EyerissACM SIGARCH Computer Architecture News, 2016
- EIEACM SIGARCH Computer Architecture News, 2016
- A 28 nm Configurable Memory (TCAM/BCAM/SRAM) Using Push-Rule 6T Bit Cell Enabling Logic-in-MemoryIEEE Journal of Solid-State Circuits, 2016
- The Xeon® Processor E5-2600 v3: a 22 nm 18-Core Product FamilyIEEE Journal of Solid-State Circuits, 2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- DaDianNao: A Machine-Learning Supercomputer2014