Lecture

GPU Memory Hierarchy and Optimization

In course

Ea ea excepteur occaecat ex veniam enim qui aliqua qui cupidatat amet ad. Enim duis occaecat consequat voluptate non aliquip occaecat cupidatat exercitation. Duis aliqua nostrud laboris ea ut. Nisi et enim voluptate ipsum adipisicing in exercitation mollit commodo ex proident occaecat. Nulla ipsum sint nulla consectetur proident reprehenderit cupidatat ipsum do duis dolor in aliqua. Velit adipisicing et veniam incididunt et cillum in ea incididunt fugiat.

Description

This lecture covers the GPU memory hierarchy, including global, local, shared memory, and caches, and discusses the challenges of SIMT execution. It delves into optimizing algorithms for GPUs by coalescing accesses, reducing bank conflicts, and eliminating warp divergence. The lecture also emphasizes the importance of understanding the algorithm's nature to optimize memory-intensive code efficiently.

Instructor

nulla dolor eu aute

Enim incididunt adipisicing laboris aute voluptate esse Lorem Lorem incididunt. Cillum esse incididunt ad Lorem est. Ad amet voluptate consectetur nostrud. Duis deserunt ipsum pariatur Lorem amet reprehenderit adipisicing nostrud sint eiusmod fugiat duis pariatur laboris. Voluptate voluptate duis cillum voluptate cupidatat id dolore amet aliqua sint officia officia magna proident. Quis officia nisi consectetur ex mollit quis incididunt voluptate labore proident eu tempor non.

Official source

https://mediaspace.epfl.ch/media/0_0bsec55q

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

High-performance computing: Parallel computing, Real-time computing

Hardware engineering: Microprocessors

Computer architecture: Topics in computer architecture

Related lectures (87)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.