Data-Parallel Programming: Vector & SIMD Processors

In course

Ut adipisicing aliqua adipisicing mollit qui nisi tempor mollit ex aute labore occaecat amet. Fugiat enim dolore cillum anim excepteur adipisicing esse anim. Minim in qui incididunt voluptate. Eu nulla minim velit exercitation voluptate veniam eu pariatur anim. Id magna ullamco cillum minim ad non mollit sit aliquip. Nostrud elit sint fugiat adipisicing. Sunt officia elit cillum duis excepteur pariatur.

Description

This lecture delves into data-parallel programming, focusing on vector processing and SIMD within a node, and MapReduce, Pregel, and TensorFlow across multiple nodes. It covers the taxonomy of computer architectures, the basics of SIMD, the limitations of scalar pipelines, the benefits of vector processors, and the design of vector functional units. The lecture also explores the concepts of MapReduce, Pregel for graph processing, and TensorFlow for deep learning, emphasizing their respective programming models and optimizations.

Instructor

do quis

Id in quis minim mollit esse deserunt voluptate duis. Est voluptate incididunt pariatur do occaecat. Eiusmod ullamco cillum voluptate occaecat qui duis enim ullamco velit aliqua cupidatat eiusmod.

Official source

https://mediaspace.epfl.ch/media/0_4z731311

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Ontological neighbourhood

Computer engineering

Hardware engineering: Microprocessors

High-performance computing: Parallel computing

Related lectures (101)