论文信息 - CASPER — Configurable design space exploration of programmable architectures for machine learning using beyond moore devices

CASPER — Configurable design space exploration of programmable architectures for machine learning using beyond moore devices

This research proposes a novel approach with vertical design space exploration (DSE) of several levels of configurable architecture design using Beyond Moore devices. ferrimagnets, Multistate Electrostatically Formed Nanowire transistors (MSET), and Magnetoresistive Random Access Memories (MRAM) are first set of devices used to explore the architectural space. Machine Learning (ML) and other scientific applications are accelerated using these architectures.

John Shalf | David Donofrio | George Michelogiannakis | Dilip P. Vasudevan

[1] Yu Ting Chen,et al. A Survey and Evaluation of FPGA High-Level Synthesis Tools , 2016, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[2] Péter Szolgay,et al. Configurable multilayer CNN-UM emulator on FPGA , 2003 .

[3] Y. Rosenwaks,et al. Dynamic and Power Performance of Multiple State Electrostatically Formed Nanowire Transistors , 2017, IEEE Transactions on Electron Devices.

[4] Eriko Nurvitadhi,et al. Accelerating recurrent neural networks in analytics servers: Comparison of FPGA, CPU, GPU, and ASIC , 2016, 2016 26th International Conference on Field Programmable Logic and Applications (FPL).

[5] Vladimir Stojanovic,et al. Design Requirements for a Spintronic MTJ Logic Device for Pipelined Logic Applications , 2016, IEEE Transactions on Electron Devices.