YoVDO

BLASPhemy - Improving BLAS Handling in Enzyme.jl

Offered By: The Julia Programming Language via YouTube

Tags

Julia Courses Code Generation Courses Multithreading Courses Automatic Differentiation Courses LLVM Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the challenges and improvements in differentiating BLAS and Lapack routines within the Julia ecosystem. Learn about the limitations of Enzyme.jl in handling black-box implementations and the initial workarounds involving generic openBLAS fallbacks. Discover the innovative approach using LLVM's code-generation capabilities to generate efficient differentiation rules for low-level BLAS calls. Understand how these improvements significantly enhance BLAS AD performance, prevent crashes with large matrices, and enable support for hardware-specific, multithreaded BLAS libraries. Gain insights into ongoing work aimed at further performance optimization through memory management techniques and their impact on downstream Julia applications.

Syllabus

BLASPhemy | Sebastian Drehwald | JuliaCon 2024


Taught by

The Julia Programming Language

Related Courses

Julia Scientific Programming
University of Cape Town via Coursera Julia for Beginners in Data Science
Coursera Project Network via Coursera Linear Regression and Multiple Linear Regression in Julia
Coursera Project Network via Coursera Decision Tree and Random Forest Classification using Julia
Coursera Project Network via Coursera Logistic Regression for Classification using Julia
Coursera Project Network via Coursera