You are here

Deep Learning Processing Subsystem (DLPS): A HPSC-Compatible Deep Learning Coprocessor

Award Information
Agency: National Aeronautics and Space Administration
Branch: N/A
Contract: 80NSSC20C0349
Agency Tracking Number: 205909
Amount: $125,000.00
Phase: Phase I
Program: SBIR
Solicitation Topic Code: Z2
Solicitation Number: SBIR_20_P1
Timeline
Solicitation Year: 2020
Award Year: 2020
Award Start Date (Proposal Award Date): 2020-08-08
Award End Date (Contract End Date): 2021-03-01
Small Business Information
15400 Calhoun Drive, Suite 190
Rockville, MD 20855-2814
United States
DUNS: 161911532
HUBZone Owned: No
Woman Owned: Yes
Socially and Economically Disadvantaged: No
Principal Investigator
 Xiangrong (Sean) Zhou
 (240) 406-7749
 xzhou@i-a-i.com
Business Contact
 Robin Beahm
Phone: (301) 294-5220
Email: rbeahm@i-a-i.com
Research Institution
N/A
Abstract

In this proposed effort, we propose to develop a Deep Learning Processing Subsystem (DLPS) solution for HPSC system. The DLPS solution can significantly improve the performance and energy efficiency of HPSC system in processing deep learning algorithm. The key innovation of this proposal includes design and development of an low power and high performance deep learning processing system which include: (1) low-power and high performance DLPS hardware ; (2) HPSC-compatible software module to manage DLPS hardware and provide API to application layer; (3) DLPS toolchain to transform deep learning models from popular frameworks such as Keras, TensorFlow, and Caffe; (4) DLPS hardware implementation on space grade Xilinx FPGA platform for fault-tolerance design. Finally, all the proposed techniques will be integrated in a functional prototype to demonstrate the feasibility of proposed architecture.

* Information listed above is at the time of submission. *

US Flag An Official Website of the United States Government