Bambu: an open-source research framework for the high-level synthesis of complex applications

F Ferrandi, VG Castellana, S Curzel… - 2021 58th ACM/IEEE …, 2021 - ieeexplore.ieee.org
This paper presents the open-source high-level synthesis (HLS) research framework
Bambu. Bambu provides a research environment to experiment with new ideas across HLS …

Bridging python to silicon: The soda toolchain

NB Agostini, S Curzel, JJ Zhang, A Limaye, C Tan… - IEEE Micro, 2022 - ieeexplore.ieee.org
Systems performing scientific computing, data analysis, and machine learning tasks have a
growing demand for application-specific accelerators that can provide high computational …

Automated generation of integrated digital and spiking neuromorphic machine learning accelerators

S Curzel, NB Agostini, S Song, I Dagli… - 2021 IEEE/ACM …, 2021 - ieeexplore.ieee.org
The growing numbers of application areas for artificial intelligence (AI) methods have led to
an explosion in availability of domain-specific accelerators, which struggle to support every …

Edge-connected jaccard similarity for graph link prediction on fpga

P Sathre, A Gondhalekar… - 2022 IEEE High …, 2022 - ieeexplore.ieee.org
Graph analysis is a critical task in many fields, such as social networking, epidemiology,
bioinformatics, and fraud de-tection. In particular, understanding and inferring relationships …

SPARTA: High-Level Synthesis of Parallel Multi-Threaded Accelerators

G Gozzi, M Fiorito, S Curzel, C Barone… - ACM Transactions on …, 2024 - dl.acm.org
This article presents a methodology for the Synthesis of PARallel multi-Threaded
Accelerators (SPARTA) from OpenMP annotated C/C++ specifications. SPARTA extends an …

Towards automatic and agile ai/ml accelerator design with end-to-end synthesis

JJ Zhang, NB Agostini, S Song, C Tan… - 2021 IEEE 32nd …, 2021 - ieeexplore.ieee.org
Domain-specific designs offer greater energy efficiency and performance gain than general-
purpose processors. For this reason, modern system-on-chips have a significant portion of …

End-to-end synthesis of dynamically controlled machine learning accelerators

S Curzel, NB Agostini, VG Castellana… - IEEE Transactions …, 2022 - ieeexplore.ieee.org
Edge systems are required to autonomously make real-time decisions based on large
quantities of input data under strict power, performance, area, and other constraints. Meeting …

Towards automated generation of chiplet-based systems invited paper

A Limaye, C Barone, NB Agostini… - 2024 29th Asia and …, 2024 - ieeexplore.ieee.org
The Software Defined Architectures (SODA) Synthesizer is an open-source compiler-based
tool able to automatically generate domain-specialized systems targeting Application …

Lock-free triangle counting on GPU

Z Zheng, G Wan, J Jiang, C Hu, H Liu… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Finding the triangles of large scale graphs is a fundamental graph mining task in many
applications, such as motif detection, microscopic evolution, and link prediction. The recent …

Cyclebite: Extracting task graphs from unstructured compute-programs

BR Willis, A Shrivastava, J Mack, S Dave… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Extracting portable performance in an application requires structuring that program into a
data-flow graph of coarse-grained tasks (CGTs). Structuring applications that interconnect …