Mix-GEMM: An efficient HW-SW Architecture for Mixed-Precision Quantized Deep Neural Networks Inference on Edge Devices
Enrico Reggiani, Alessandro Pappalardo, Max Doblas, Miquel Moretó, Mauro Olivieri, Osman Ünsal, Adrián Cristal
Abstract
Deep Neural Network (DNN) inference based on quantized narrow-precision integer data represents a promising research direction toward efficient deep learning computations on edge and mobile devices. On one side, recent progress of Quantization-Aware Training (QAT) frameworks aimed at improving the accuracy of extremely quantized DNNs allows achieving results close to Floating-Point 32 (FP32), and provides high flexibility concerning the data sizes selection. Unfortunately, current Central Processing Unit (CPU) architectures and Instruction Set Architectures (ISAs) targeting resource-constrained devices present limitations on the range of data sizes supported to compute DNN kernels.This paper presents Mix-GEMM, a hardware-software co-designed architecture capable of efficiently computing quantized DNN convolutional kernels based on byte and sub-byte data sizes. Mix-GEMM accelerates General Matrix Multiplication (GEMM), representing the core kernel of DNNs, supporting all data size combinations from 8- to 2-bit, including mixed-precision computations, and featuring performance that scale with the decreasing of the computational data sizes. Our experimental evaluation, performed on representative quantized Convolutional Neural Networks (CNNs), shows that a RISC-V based edge System-on-Chip (SoC) integrating Mix-GEMM achieves up to 1.3 TOPS/W in energy efficiency, and up to 13.6 GOPS in throughput, gaining from 5.3× to 15.1× in performance over the OpenBLAS GEMM frameworks running on a commercial RISC-V based edge processor. By performing synthesis and Place and Route (PnR) of the enhanced SoC in Global Foundries 22nm FDX technology, we show that Mix-GEMM only accounts for 1% of the overall area consumption.