Events

Math Faculty Computing Facility Presents……..

Computing Session for Math Grads - Scientific Blogging with R and Blogdown

Improve your science communication and share your work by learning how to host a static blog at UW which includes MathTeX, code and visualizations

Friday, October 6, 2023

1:30-3:00

MC3006

(limited seating)

RSVP to mfcfhelp@uwaterloo.ca

Agenda: Presentation by Aiden Huffman, Applied Math followed by a hands-on session.

Christopher Parisien, Senior Manager of Applied Research at NVIDIA, will deliver the NVIDIA Lecture hosted by Math Innovation, with support from MFCF, on February 4, 2025, from 10:00-11:00am in MC 5501. A UW grad (BMath '06) with a PhD in Computational Linguistics from the University of Toronto. During his time in industry, he helped build the first generation of mainstream chatbots, developed systems to understand medical records, and served as Chief Technology Officer at NexJ Health, a patient-centred health platform. His current focus at NVIDIA is to bring trustworthy language models to large enterprises. The lecture will introduce NeMo Guardrails' key functionalities, emphasizing responsible AI development. Students interested in AI, Machine Learning, and Foundation Models can gain insights into creating reliable AI solutions. Registration is required. Questions can be directed to Alexandra Kraushaar in the Math Innovation Office.

Tarini Bhatnagar, Senior Solutions Architect at NVIDIA, will lead the NVIDIA Lecture hosted by Math Innovation, with support from MFCF, on February 12, 2025, from 10:00-11:00am in MC 5501. Tarini, who holds a Master’s in Data Science and Earth & Environmental Science, supports technical customer engagements in Western Canada, helping organizations adopt NVIDIA technology. She is actively involved with several organizations to foster a supportive community for women in tech. The lecture will focus on NVIDIA Modulus, an open-source framework for developing physics-informed neural networks (PINNs). Students passionate about AI, Machine Learning, and Computational Physics will explore how Modulus solves complex, physics-based problems through AI. The lecture will introduce solving complex, physics-based problems using accelerated computing solutions and AI. Registration is required. Questions can be directed to Alexandra Kraushaar in the Math Innovation Office.

Math Faculty Computing Facility

Presents:

Dr. Ryan Curtin

Tuesday, February 10, 2026

10:30am - 12:00pm DC 1302

R.S.V.P to mfcfhelp@uwaterloo.ca

"Bandicoot: Efficient GPU linear algebra via C++ template metaprogramming"

Abstract:

It's not too much of a stretch to say that linear algebra is the backbone of modern computational science; by that token, efficiency is of paramount importance.  For over 15 years, the Armadillo C++ linear algebra library has provided efficient linear algebra implementations via template metaprogramming, using expression templates and delayed evaluation techniques (which were originally developed at Waterloo in the late 90s!).  Recently, the Bandicoot project introduced the same techniques for GPU linear algebra using an Armadillo-compatible API for easy drop-in usage.  Bandicoot is not specific to particular hardware; it can be used with any CUDA or OpenCL device, and additional backends (HIP/ROCm, Metal, Vulkan) are actively being developed.  Bandicoot is able to both optimize linear algebra expressions at compile-time in the same way Armadillo can, and also generate efficient GPU kernel code with fused optimizations.  I will discuss each of these optimizations, how they all fit together into Bandicoot, and show how existing Armadillo applications can be easily adapted to the GPU with Bandicoot.

Bio:

Dr. Ryan Curtin is an independent researcher and open-source software developer, leading the development and maintenance of several packages in the C++ scientific software ecosystem.  During his Ph.D. at Georgia Tech he focused on the formalization of dual-tree algorithms, a class of geometric branch-and-bound algorithms that can be used to solve subproblems relevant to machine learning techniques.  These algorithms underlie the efficient mlpack C++ machine learning library, which he has led since 2010.  In his free time, he races go-karts, so he never escapes from trying to go fast in one way or another.