Podcast cover
Open Compute Project · Technology

Open Compute Project

This is the place to find all the OCP related videos from OCP Summits, Hackathons, Video Blogs and more. What is OCP all about? Hacking Conventional Computing Infrastructure The Open Compute Project Foundation is a 501(c)6 organization which was founded in 2011 by Facebook, Intel, Rackspace, Goldman Sachs and Andy Bechtolsheim. Our mission is to apply the benefits of open source software to hardware and rapidly increase the pace of innovation to hardware design and engineering. Why Open Hardware? By releasing Open Compute Project technologies as open hardware, our goal is to develop servers and data centers following the model traditionally associated with open source software projects.

Episodes

Episode cover

DWDM Fabric platform for energy efficient bandwidth scaling for AI clusters

24 Oct 2024
17m
AI processed

In this podcast episode, we explore the pressing issue of bandwidth scalability in AI data centers and discover how Xscape is tackling these challenges with innovative solutions. Vivek discusses the drawbacks of traditional optical technologies and introduces a groundbreaking approach centered around their advanced mul...

Episode cover

Panel Discussion Opportunities, Challenges, and Road Ahead in Near Data Computing

24 Oct 2024
1h 4m
AI processed

The panel discussion on data-centric computing delved into the challenges and opportunities presented by near-data processing, particularly the high costs associated with data movement in today’s computing landscape. Experts from both academia and industry shared insights on various strategies, such as embedding comput...

Episode cover

Near Memory Compute for AI Inferencing

24 Oct 2024
20m
Episode cover

Near Data Computing Paradigm

24 Oct 2024
19m
Episode cover

Near Data Computing Brings Sustainability Value

24 Oct 2024
14m
Episode cover

Interfaces in Near Data Computing

24 Oct 2024
16m
Episode cover

Exploring the Performance Benefits of HBM and Near Memory Processing on Sparse Multi physics

24 Oct 2024
15m
Episode cover

DPU Accelerated Peta Scale Storage Subsystem for Near Data Computing

24 Oct 2024
25m
Episode cover

Checkpoint Offloading SSD Enhancing Performance and Scalability in LLM Training

24 Oct 2024
16m
AI processed

This presentation explores a new checkpoint uploading SSD aimed at enhancing the training of Large Language Models (LLMs). The main concept involves shifting the less demanding optimizer step of the training process to the SSD. This shift alleviates the bandwidth strain on PCIe and network connections between the GPU a...

Episode cover

Towards a Standardized Representation for Deep Learning Collective Algorithms

24 Oct 2024
28m
Episode cover

Making a GPU into a Data Access Engine

24 Oct 2024
26m
Episode cover

Leverage the Full Ecosystem to Enable AI

24 Oct 2024
27m
Episode cover

Large Scale Interconnect Technology

24 Oct 2024
9m
Episode cover

From Compilers to Code Whisperers Can Generative AI Solve the Optimization Puzzle

24 Oct 2024
29m
Episode cover

Connecting Intelligence Interconnects and AI

24 Oct 2024
45m
Episode cover

Panelist Discussion AI for AI System Design Hope or Hype

24 Oct 2024
48m
Episode cover

Welcome & Kickoff

23 Oct 2024
7m
Episode cover

Standards update Reducing Optical Power Consumption

23 Oct 2024
19m
Episode cover

Panel What is the Right Path Forward for the Industry?

23 Oct 2024
22m
Episode cover

Optical Compute Interconnect Co packaged optics for AI and compute infrastructure 1

23 Oct 2024
14m
Page 5

Follow this podcast in Podwise

Sign in to get AI summaries, transcripts and mind maps for any episode, including new ones.

Open in Podwise