Dr. Chen Liu, an Associate Professor in the Department of Electrical and Computer Engineering at Clarkson University, recently served as guest editor of a Special Journal Issue on Heterogeneous Computation in Specific Domain Accelerations by Future Generation Computer Systems.
Data is being generated at an unprecedented rate in the Internet of Things (IoT) era across various applications. How to process Big Data in a timely manner is a major obstacle that we face today. We have been orienting towards heterogeneous computing with hardware accelerators for the rescue. However, the growing diversity and heterogeneity of hardware platforms just add another layer of difficulty. Even though heterogeneous platforms such as Graphic Processing Units(GPUs), Many Integrated Cores (MICs), and Field Programmable Gate Arrays (FPGAs) have been widely adopted, how to utilize these different hardware accelerators effectively and efficiently remains a challenge for heterogeneous computing researchers. To address these issues, we need algorithms, models, and tools for heterogeneous computing to accelerate the performance, to improve energy efficiency, and to enhance the reliability of heterogeneous platforms for specific domains and applications, from edge to cloud and in between.
This special issue of heterogeneous computation in specific domain accelerations (HC-SDA), contains twelve articles from around the globe covering a wide spectrum of aspects of HC-SDA research, including concurrent kernel execution, soft error, task scheduling and mapping, data-flow and innovative architectures, performance portability, and parallelization.
Future Generation Computer Systems (FGCS), published by Elsevier, is a premium journal aiming to lead the way in advances in distributed systems, collaborative environments, high performance and high-performance computing, Big Data on such infrastructures as grids, clouds and the Internet of Things (IoT). For more information, please check the editorial for this special issue at https://doi.org/10.1016/j.future.2021.05.017