CLOSED Call for Papers: Special Issue on Machine Learning Acceleration
IEEE Micro seeks submissions for this special issue.
Share this on:
Submissions Due: 19 April 2019
Submissions due: CLOSED
Initial notifications: May 22, 2019
Revised papers due: June 21, 2019
Final notifications: June 28, 2019
Final versions due: July 12, 2019
Publication date: Sept/Oct 2019
In recent years, machine learning (ML) has become one of the most important pillars of computing industry, driven by the remarkable advances in the theory and their extensive use in real-world applications. To accomplish the phenomenal success, research and industry communities have exploited acceleration solutions, which deliver orders-of-magnitude greater performance and efficiency by specializing hardware and software for ML. As the importance of ML in the emerging applications increases, the ML accelerators have become the critical component of every modern computing system–from data centers to mobile/IoT devices. The community has not only extensively explored new architectures to improve the performance and efficiency of these accelerators, but also put significant effort on raising usability and programmability by offering programming models, high-level language, compiler, runtime software, and tools. This special issue of IEEE Micro will explore academic and industrial research on all topics, which relate to hardware and software acceleration solutions, specialized for ML. Such topics include, but are not limited to:
New design methodologies for ML-centric or ML-aware hardware accelerators
New microarchitecture designs of hardware accelerators for ML
ML workload acceleration on existing accelerators such as GPU, FPGA, CGRA, or ASIC
New compiler and optimization techniques for ML acceleration
New tools to design/build/optimize/debug the accelerated systems
New ML modeling, optimization, quantization, and compression for acceleration
Acceleration for new ML algorithms
ML acceleration for edge computing and IoT
ML acceleration for cloud computing
Comparison studies of different acceleration techniques