HiKonv: High Throughput Quantized Convolution with Novel Bit-wise Management and Computation

Xinheng Liu, Yao Chen, Prakhar Ganesh, Junhao Pan, Jinjun Xiong, Deming Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Quantization for Convolutional Neural Network (CNN) has shown significant progress with the intention of reducing the cost of computation and storage with low-bitwidth data inputs. There are, however, no systematic studies on how an existing full-bitwidth processing unit, such as CPUs and DSPs, can be better utilized to carry out significantly higher computation throughput for convolution under various quantized bitwidths. In this study, we propose HiKonv, a unified solution that maximizes the compute throughput of a given underlying processing unit to process low-bitwidth quantized data inputs through novel bitwise parallel computation. We establish theoretical performance bounds using a full-bitwidth multiplier for highly parallelized low-bitwidth convolution, and demonstrate new breakthroughs for high-performance computing in this critical domain. For example, a single 32-bit processing unit can deliver 128 binarized convolution operations (multiplications and additions) under one CPU instruction, and a single 27× 18 DSP core can deliver eight convolution operations with 4-bit inputs in one cycle. We demonstrate the effectiveness of HiKonv on CPU and FPGA for both convolutional layers or a complete DNN model. For a convolutional layer quantized to 4-bit, HiKonv achieves a 3.17× latency improvement over the baseline implementation using C++ on CPU. Compared to the DAC-SDC 2020 champion model for FPGA, HiKonv achieves a 2.37×: throughput improvement and 2.61× DSP efficiency improvement, respectively.

Original languageEnglish (US)
Title of host publicationASP-DAC 2022 - 27th Asia and South Pacific Design Automation Conference, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages140-146
Number of pages7
ISBN (Electronic)9781665421355
DOIs
StatePublished - 2022
Event27th Asia and South Pacific Design Automation Conference, ASP-DAC 2022 - Virtual, Online, Taiwan, Province of China
Duration: Jan 17 2022Jan 20 2022

Publication series

NameProceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC
Volume2022-January

Conference

Conference27th Asia and South Pacific Design Automation Conference, ASP-DAC 2022
Country/TerritoryTaiwan, Province of China
CityVirtual, Online
Period1/17/221/20/22

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'HiKonv: High Throughput Quantized Convolution with Novel Bit-wise Management and Computation'. Together they form a unique fingerprint.

Cite this