DeepAI AI Chat
Log In Sign Up

Cheetah: Mixed Low-Precision Hardware Software Co-Design Framework for DNNs on the Edge

by   Hamed F. Langroudi, et al.

Low-precision DNNs have been extensively explored in order to reduce the size of DNN models for edge devices. Recently, the posit numerical format has shown promise for DNN data representation and compute with ultra-low precision in [5..8]-bits. However, previous studies were limited to studying posit for DNN inference only. In this paper, we propose the Cheetah framework, which supports both DNN training and inference using posits, as well as other commonly used formats. Additionally, the framework is amenable for different quantization approaches and supports mixed-precision floating point and fixed-point numerical formats. Cheetah is evaluated on three datasets: MNIST, Fashion MNIST, and CIFAR-10. Results indicate that 16-bit posits outperform 16-bit floating point in DNN training. Furthermore, performing inference with [5..8]-bit posits improves the trade-off between performance and energy-delay-product over both [5..8]-bit float and fixed-point.


page 4

page 6

page 7

page 10


Deep Learning Training on the Edge with Low-Precision Posits

Recently, the posit numerical format has shown promise for DNN data repr...

Adaptive Block Floating-Point for Analog Deep Learning Hardware

Analog mixed-signal (AMS) devices promise faster, more energy-efficient ...

FAST: DNN Training Under Variable Precision Block Floating Point with Stochastic Rounding

Block Floating Point (BFP) can efficiently support quantization for Deep...

ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization

Quantization is a technique to reduce the computation and memory cost of...

Fixed-point quantization aware training for on-device keyword-spotting

Fixed-point (FXP) inference has proven suitable for embedded devices wit...