The rapidly-changing deep learning landscape presents a unique opportunity for building inference accelerators optimized for specific datacenter-scale workloads. We propose Full …
With slowing technology scaling, specialized accelerators are increasingly attractive solutions to continue expected generational scaling of performance. However, in order to …
With the increasing size of DNN models and the growing discrepancy between compute performance and memory bandwidth, fusing multiple layers together to reduce off-chip …
The Streaming Engine (SE) is a Coarse-Grained Reconfigurable Array which provides programming flexibility and high-performance with energy efficiency. An application program …
The relentless advancement of artificial intelligence (AI) and machine learning (ML) applications necessitates the development of specialized hardware accelerators capable of …
KY Chen, CS Yang, YH Sun, CW Tseng… - IEEE Journal of Solid …, 2024 - ieeexplore.ieee.org
We present domain adaptive processor (), a programmable systolic-array processor designed for wireless communication and linear algebra workloads. uses a globally …
Y Liang, Q Xiao, L Lu, J Xie - IEEE Transactions on Computer …, 2021 - ieeexplore.ieee.org
Convolution features huge complexity and demands high computation capability. Among hardware platforms, field programmable gate array (FPGA) emerges as a promising solution …
L Zulberti, M Monopoli, P Nannipieri… - 2023 European Data …, 2023 - ieeexplore.ieee.org
The adoption of Machine Learning solutions directly onboard in satellite missions is becoming more and more attractive for the space sector. Among the various kinds of …
Stream processing, which involves real-time computation of data as it is created or received, is vital for various applications, specifically wireless communication. The evolving protocols …