Supercharging HPC for Object Oriented Languages

This month we welcome Dmitri Goloubentsev to talk to us about a technique for hugely boosting performance of repetitive calculations.

As usual we'll be meeting virtually. Once the venue is set up, registered attendees will get the details.

We're also pleased to say that this event will be sponsored by G-Research, who will be giving away a £100 Amazon voucher - so look out for that (and they might have a job for you, too!)

We can still fit in a short/ lightning talk (5-15 minutes) if anyone is interested? - http://cppldn.uk/speak

---

Agenda:

19:00 Phil Nash - "Intro and News"

19:10 Chris O’Brien (Talent Acquisition, G-Research) - "G-Research Intro"

An introduction to what they do at G-Research, Europe’s leading Quantitative Research Firm.

19:15 Dmitri Goloubentsev - "Supercharging HPC for Object Oriented Languages with a touch of differentiable programming"

A new practical programming paradigm for parallel
computing with optional Automatic Adjoint Differentiation that brings leaps in performance
for repetitive calculations.

20:15(ish) "G-Research giveaway"

One lucky attendee will be randomly selected to receive a £100 Amazon gift voucher, courtesy of G-research, so be sure to stick around to the end of the talk!

Then: socialising in Remo. Stick around to chat with the speakers and other attendees. Drinks are optional (but you'll have to bring your own).

---

About the speaker(s):

Dmitri is head of Automatic Adjoint Differentiation in MatLogica.
Prior to establishing the company, he had 15 years of combined experience in model development working on C++ quant libraries. He worked as a Senior Quant Analyst in interest rate derivatives and played a leading role in delivering XVA solution at a major Canadian bank. Prior to focusing on AAD, he was responsible for construction of SIMM/MVA model. Dmitri earned his degree in Maths and Applied Maths from the Moscow State University.