The time zone for all times mentioned at the DATE website is CEST – Central Europe Summer Time (UTC+1). AoE = Anywhere on Earth.

M01 Modern High-Level Synthesis for Complex Data Science Applications

Start
End
Room
Marble Hall
Organiser
Antonino Tumeo, Pacific Northwest National Laboratory, United States
Organiser
Fabrizio Ferrandi, Politecnico di Milano, Italy
Organiser
Nicolas Bohm Agostini, Pacific Northwest National Laboratory and Northeastern University, United States
Organiser
Serena Curzel, Pacific Northwest National Laboratory, US and Politecnico di Milano, Italy
Organiser
Michele Fiorito, Politecnico di Milano, Italy

Data Science applications (machine learning, graph analytics) are among the main drivers for the renewed interests in designing domain specific accelerators, both for reconfigurable devices (Field Programmable Gate Arrays) and Application-Specific Integrated Circuits (ASICs). Today, the availability of new high-level synthesis (HLS) tools to generate accelerators starting from high-level specifications provides easier access to FPGAs or ASICs and preserves programmer productivity. However, the conventional HLS flow typically starts from languages such as C, C++, or OpenCL, heavily annotated with information to guide the hardware generation, still leaving a significant gap with respect to the (Python based) data science frameworks. This tutorial will discuss HLS to accelerate data science on FPGAs or ASICs, highlighting key methodologies, trends, advantages, benefits, but also gaps that still need to be closed. The tutorial will provide a hands-on experience of the SOftware Defined Accelerators (SODA) Synthesizer, a toolchain composed of SODA-OPT, an opensource front-end and optimizer that interface with productive programming data science frameworks in Python, and Bambu, the most advanced open-source HLS tool available, able to generate optimized accelerators for data-intensive kernels. We will further show how SODA integrates with OpenROAD flow, providing a truly automated end-to-end open-source compiler toolchain from high level machine learning frameworks to Silicon.

M01.1 Session 1: Modern High-Level Synthesis for Complex Data Science Applications

Session Start
Session End
Presentations

M01.1.1 Agile hardware design for complex data science applications: opportunities and challenges

Start
End
Presenter
Antonino Tumeo, Pacific Northwest National Laboratory, United States

Introductory material, context, state-of the art, and research opportunities

M01.1.2 Bambu: an Open-Source Research Framework for the High-Level Synthesis of Complex Applications.

Start
End
Presenter
Fabrizio Ferrandi, Politecnico di Milano, Italy

Advanced materials on High-Level Synthesis methods

M01.1.3 End-to-end demonstration from high-level frameworks to Silicon with SODA-OPT, Bambu, and OpenROAD

Start
End
Presenter
Nicolas Bohm Agostini, Pacific Northwest National Laboratory and Northeastern University, United States
Presenter
Serena Curzel, Pacific Northwest National Laboratory, US and Politecnico di Milano, Italy

Hands on on the end-to-end toolchain

M01.1.4 Advanced High-Level Synthesis with Bambu

Start
End
Presenter
Serena Curzel, Pacific Northwest National Laboratory, US and Politecnico di Milano, Italy
Presenter
Michele Fiorito, Politecnico di Milano, Italy

Hands on on advanced High-Level Synthesis with Bambu