BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Synthesizing Accelerators for FPGAs the Functional Way - Christoph
 e Dubach (McGill University)
DTSTART:20230601T130000Z
DTEND:20230601T140000Z
UID:TALK201907@talks.cam.ac.uk
CONTACT:Timothy M Jones
DESCRIPTION:FPGAs (Field Programmable Gate Arrays) have become the substra
 te of choice to implement accelerators. They deliver high performance with
  low power consumption\, while offering the flexibility of being re-progra
 mmable. But they are notoriously hard to program directly using HDLs (Hard
 ware Description Languages). Traditional HLS (High-Level Synthesis) are fa
 r from being perfect as programmers are still required to write hardware-s
 pecific code and existing HLS tools often produce suboptimal designs.\n\nT
 his talk will present current efforts to address these shortcomings\, usin
 g a multi-level functional IR (Intermediate Representation). As we will se
 e\, a functional IR makes optimizations via rewrite rules simple to expres
 s\, and abstract away the hardware details. This approach has the advantag
 e of generating high performance designs in a predictable way\, drasticall
 y reducing design time. This talk will show how neural networks are easily
  represented using functional hardware-agnostic constructs. The resulting 
 FPGA synthesized designs achieve near-peak performance and are competitive
  with the output produced by current HSL tools.\n\nChristophe Dubach is an
  Associate Professor jointly appointed in the department of Electrical and
  Computer Engineering (ECE) and the school of Computer Science (CS) at McG
 ill University. He also holds a Canada CIFAR AI Chair at Mila. Up until 20
 19\, he was a Reader (Associate Professor) at the University of Edinburgh.
  He received a PhD in Informatics from the University of Edinburgh in 2009
  and an MSc degree in Computer Science from EPFL in 2005. In 2010\, he spe
 nt one year as a visiting researcher at the IBM Watson Research Center (US
 A) working on the LiquidMetal project. His current research interests incl
 ude high-level programming models for heterogeneous systems\, co-design of
  both computer architecture and optimising compiler\, high-level synthesis
 \, and the application of machine learning to these areas. \n
LOCATION:SS03\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR