hackertube.io

RAAIS 2017 - Simon Knowles, Co-Founder and CTO of Graphcore

The Research and Applied AI Summit - RAAIS · talk · Watch on YouTube

Computer architecture & CPUsMachine learning & deep learning

What it is

Simon Knowles, co-founder and CTO of Graphcore, talks about "intelligence processors", chips designed specifically for machine learning. The talk was given at the RAAIS 2017 summit and covers Graphcore's architecture.

Why Hacker News recommends it

HN points to it as a technical talk from a chip designer on why AI hardware should put memory close to compute and use async data transfers.

  • 3 people recommended it
  • 3 different months
  • 0 strong recommendations
  • first 2017, last 2018

What HN commenters said

  1. “Moving computation close in with memory, and making data transfers async will speed up DL.”

    Graphcore's approach of memory near compute and async transfers.

    visarga, 2017-07 · Recommendation · in “Neuromorphic Computing with Nanoscale Spintronic Oscillators”

  2. “Here's a nice technical talk from Graphcore's CTO about that”

    Technical talk from Graphcore's CTO on new AI chips.

    midko, 2017-11 · Recommendation · in “Intel to Develop Discrete GPUs, Hires AMD's Raja Koduri as Chief Architect”

  3. “isn't quite the presentation I saw, but it has quite a lot of overlap.”

    Overlaps heavily with a talk on Graphcore's tile architecture and power.

    maffydub, 2018-04 · Recommendation · in “The Looming Battle Over AI Chips”

Excerpts from Hacker News comments, linked to the originals. Summaries and labels were written by a language model from those comments.

Topics: graphcore, ai hardware, deep learning, processor architecture, memory bandwidth

Also recommended by the same people