Improving Julia's Scheduler - One Task at a Time
The Julia Programming Language via YouTube
-
31
-
- Write review
Build the Finance Skills That Lead to Promotions — Not Just Certificates
Most AI Pilots Fail to Scale. MIT Sloan Teaches You Why — and How to Fix It
Overview
Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
Explore Julia's task-based parallelism system and scheduler optimizations in this 28-minute conference talk from JuliaCon Global 2025. Discover how Julia's Tasks provide lighter abstractions than OS threads through user-space scheduling that avoids expensive context switches. Learn about the fundamental workings of Julia's scheduler, understand how to write code that cooperates effectively with the scheduling system, and examine the significant performance improvements implemented throughout the year. Gain insights into task-based parallelism advantages, scheduler performance considerations, and practical techniques for optimizing concurrent Julia applications through better understanding of the underlying scheduling mechanisms.
Syllabus
Improving Julia's scheduler, one Task at a time | Baraldi | JuliaCon Global 2025
Taught by
The Julia Programming Language