Loading…
This event has ended. Visit the official site or create your own event on Sched.
Back To Schedule
Wednesday, August 8 • 5:00pm - 5:15pm
Fast and efficient multicore processing over the cloud with Julia and Techila Distributed Computing Engine

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
Abstract
Harnessing the Julia multicore features requires an in-depth knowledge of cloud infostructures which is typically beyond the reach of many organizations. The Techila Distributed Engine efficiently distributes applications over the cloud dramatically speeding-up the idea-to-deployment cycle in Julia.

Description
Julia is a language that enables quick development and fast execution of complex applications in many fields related to finance and economics. The language provides an intuitive multiprocessing environment that allows programs to run on multiple processes in separate memory domains at once. Even with this excellent infostructure, building and deploying applications over the cloud requires a comprehension of cloud infostructures. Such sort of experience is often not readily available in an academic setting and may make the final cost of a distributed solution too costly for many financial organizations.
Techila Distributed Computing Engine Overview is a distributed computing middleware and management solution developed by Techila Technologies Ltd. It is an autonomic computing solution, which brings rocket speed to computing. It is designed to save the time of business users and IT experts, to solve challenges related to parallel application development and deployment, and to speed up the idea-to-deployment cycle.
The talk discusses a package that allows using the TDCE for the Julia language. It highlights its strengths regarding development and deployment time. A single macro creates a Julia cloud environment and parallelizes execution over hundreds of cores. The cloud environment replicates the user’s own installation facilitating deployment.
We demonstrate the power of the TDCE and Julia in practice with two applications. The first is the calculation of the Value at Risk of a large portfolio of financial instruments. The second is forecasting US non-farm-payroll one and two months ahead using a dataset which comprises around 100 macroeconomic and financial variables. A live test will show that these applications can be made to run on 400 cores in a matter of minutes.

Speakers
avatar for Tuomas Eerola

Tuomas Eerola

Vice President, Techila Technologies
Tuomas Eerola is passionate about solving computationally demanding problems in the area of quantitative innovation. His interests include the problems and solutions in the intersection of computing, data, and financial engineering.Tuomas works in Techila Technologies, the provider... Read More →


Wednesday August 8, 2018 5:00pm - 5:15pm BST
Sir Ambrose Fleming LT G06