Tcader: a tightly coupled accelerator design framework for heterogeneous system with hardware/software co-design

W Li, T Liu, Z Xiao, H Qi, W Zhu, J Wang - Journal of Systems Architecture, 2023 - Elsevier
Abstract Domain-specific architectures (DSAs) or hardware accelerators are typical
innovations that are leading computer architecture into a new golden age. In a …

Improved frequency comb operation of an InAs/GaAs hybrid multisection quantum dot laser on silicon

T Renaud, H Huang, G Kurczveil, D Liang… - Applied Physics …, 2023 - pubs.aip.org
This work reports on a systematic investigation of the frequency comb enhancement in
hybrid InAs/GaAs multisection quantum dot lasers on silicon. The colliding configuration …

Only buffer when you need to: Reducing on-chip gpu traffic with reconfigurable local atomic buffers

P Dalmia, R Mahapatra… - 2022 IEEE International …, 2022 - ieeexplore.ieee.org
In recent years, due to their wide availability and ease of programming, GPUs have emerged
as the accelerator of choice for a wide variety of applications including graph analytics and …

Exploiting data encoding and reordering for low-power streaming in systolic arrays

C Peltekis, D Filippas, G Dimitrakopoulos… - Microprocessors and …, 2023 - Elsevier
Systolic Array (SA) architectures are well-suited for accelerating matrix multiplications
through the use of a pipelined array of Processing Elements (PEs) communicating with local …

Energy-Efficient Bus Encoding Techniques for Next-Generation PAM-4 DRAM Interfaces

Y Su, S Lee, E Song, D Kim, J Han… - 2022 IEEE 40th …, 2022 - ieeexplore.ieee.org
In this paper, we introduce effective bus data en-coding schemes for next-generation
interfaces of DRAM with an analysis of their energy and lane efficiency characteristics. The …

[图书][B] Reducing Synchronization and Communication Overheads in GPUs

P Dalmia - 2023 - search.proquest.com
As programmable GPUs have become increasingly general-purpose, they are increasingly
used by a wide variety of applications that leverage them for accelerated computing. This …