YoVDO

Reducing OS Noise Using Offload Driver

Offered By: code::dive conference via YouTube

Tags

Code::Dive Courses Parallel Computing Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore a conference talk on reducing operating system noise using offload drivers for improved performance in highly parallel applications. Delve into the challenges posed by irregularities caused by events like timer interrupts, particularly in multi-core processors such as the Intel® Xeon Phi™ with up to 72 physical cores. Learn about the goal of optimizing core energy usage for essential work, minimizing OS interruptions and overhead to enhance computing performance and reduce power consumption. Discover how implementing an offload driver with Intel® Xeon Phi™ Processors can potentially outperform the tickless Linux kernel. Follow the presentation's structure, covering introduction, architecture, workflow, runtime performance, limitations, and conclusions to gain insights into this innovative approach for maximizing parallel computing efficiency.

Syllabus

Introduction
Welcome
Idea
Architecture
Workflow
Ovals
Runtime
Performance
Limitations
Conclusion


Taught by

code::dive conference

Related Courses

Intro to Parallel Programming
Nvidia via Udacity
Introduction to Linear Models and Matrix Algebra
Harvard University via edX
Введение в параллельное программирование с использованием OpenMP и MPI
Tomsk State University via Coursera
Supercomputing
Partnership for Advanced Computing in Europe via FutureLearn
Fundamentals of Parallelism on Intel Architecture
Intel via Coursera