Vector-Matrix Multiplication Engine for Neuromorphic Computation with a CBRAM Crossbar Array [Slides]
- Arizona State Univ., Tempe, AZ (United States)
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
The core function of many neural network algorithms is the dot product, or vector matrix multiply (VMM) operation. Crossbar arrays utilizing resistive memory elements can reduce computational energy in neural algorithms by up to five orders of magnitude compared to conventional CPUs. Moving data between a processor, SRAM, and DRAM dominates energy consumption. By utilizing analog operations to reduce data movement, resistive memory crossbars can enable processing of large amounts of data at lower energy than conventional memory architectures.
- Research Organization:
- Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA); Defense Threat Reduction Agency (DTRA)
- DOE Contract Number:
- NA0003525
- OSTI ID:
- 1846087
- Report Number(s):
- SAND2022-2012R; 703599
- Country of Publication:
- United States
- Language:
- English
Similar Records
Energy scaling advantages of resistive memory crossbar based computation and its application to sparse coding
Integration of Ag-CBRAM crossbars and Mott ReLU neurons for efficient implementation of deep neural networks in hardware
Journal Article
·
Tue Jan 05 23:00:00 EST 2016
· Frontiers in Neuroscience (Online)
·
OSTI ID:1236485
Integration of Ag-CBRAM crossbars and Mott ReLU neurons for efficient implementation of deep neural networks in hardware
Journal Article
·
Tue Aug 29 00:00:00 EDT 2023
· Neuromorphic Computing and Engineering
·
OSTI ID:1997290