DeepAI
Log In Sign Up

Mix and Match: A Novel FPGA-Centric Deep Neural Network Quantization Framework

12/08/2020
by   Sung-En Chang, et al.
6

Deep Neural Networks (DNNs) have achieved extraordinary performance in various application domains. To support diverse DNN models, efficient implementations of DNN inference on edge-computing platforms, e.g., ASICs, FPGAs, and embedded systems, are extensively investigated. Due to the huge model size and computation amount, model compression is a critical step to deploy DNN models on edge devices. This paper focuses on weight quantization, a hardware-friendly model compression approach that is complementary to weight pruning. Unlike existing methods that use the same quantization scheme for all weights, we propose the first solution that applies different quantization schemes for different rows of the weight matrix. It is motivated by (1) the distribution of the weights in the different rows are not the same; and (2) the potential of achieving better utilization of heterogeneous FPGA hardware resources. To achieve that, we first propose a hardware-friendly quantization scheme named sum-of-power-of-2 (SP2) suitable for Gaussian-like weight distribution, in which the multiplication arithmetic can be replaced with logic shifter and adder, thereby enabling highly efficient implementations with the FPGA LUT resources. In contrast, the existing fixed-point quantization is suitable for Uniform-like weight distribution and can be implemented efficiently by DSP. Then to fully explore the resources, we propose an FPGA-centric mixed scheme quantization (MSQ) with an ensemble of the proposed SP2 and the fixed-point schemes. Combining the two schemes can maintain, or even increase accuracy due to better matching with weight distributions.

READ FULL TEXT
09/16/2020

MSP: An FPGA-Specific Mixed-Scheme, Multi-Precision Deep Neural Network Quantization Framework

With the tremendous success of deep learning, there exists imminent need...
10/07/2022

A Closer Look at Hardware-Friendly Weight Quantization

Quantizing a Deep Neural Network (DNN) model to be used on a custom acce...
01/08/2020

Training Progressively Binarizing Deep Networks Using FPGAs

While hardware implementations of inference routines for Binarized Neura...
03/22/2018

A Quantization-Friendly Separable Convolution for MobileNets

As deep learning (DL) is being rapidly pushed to edge computing, researc...
03/13/2020

Edge-Tailored Perception: Fast Inferencing in-the-Edge with Efficient Model Distribution

The rise of deep neural networks (DNNs) is inspiring new studies in myri...
07/20/2022

SumMerge: an efficient algorithm and implementation for weight repetition-aware DNN inference

Deep Neural Network (DNN) inference efficiency is a key concern across t...
10/30/2021

RMSMP: A Novel Deep Neural Network Quantization Framework with Row-wise Mixed Schemes and Multiple Precisions

This work proposes a novel Deep Neural Network (DNN) quantization framew...