Lex Fridman Podcast

Chris Lattner: Compilers, LLVM, Swift, TPU, and ML Accelerators

May 13, 2019

Chris Lattner, Senior Director at Google and the mastermind behind LLVM and Swift, dives deep into the world of compiler technologies. He shares insights on the evolution of programming from BASIC to complex compilers like LLVM and the unique challenges of developing Swift. The discussion extends to how neural networks and compilers intersect and the remarkable capabilities of TPUs in machine learning. Lattner also reflects on the cultural contrasts between Apple and Google regarding open source, and the intriguing symbolism behind the LLVM dragon logo.

01:13:15

Creator website

Episode guests

Chris Lattner

Highlights

AI Chapters

Episode notes

Elon Musk attracts talent through a compelling vision of the future, inspiring b…

02:09

The Evolution of TPUs and the Importance of Hardware-Software Co-design

01:23

Intro

2min

Evolution of Programming: From BASIC to LLVM

19min

Compilers vs. Neural Networks: Optimizing the Future

9min

The Evolution of LLVM and Swift

27min

Innovating Machine Learning with TPUs: The Hardware-Software Connection

3min

Advancements in Machine Learning Compilers: The MLIR Project

2min

Open Source Journeys: Apple vs. Google

8min

The Symbolism of the Dragon Logo in Compiler Design

2min

Chris Lattner is a senior director at Google working on several projects including CPU, GPU, TPU accelerators for TensorFlow, Swift for TensorFlow, and all kinds of machine learning compiler magic going on behind the scenes. He is one of the top experts in the world on compiler technologies, which means he deeply understands the intricacies of how hardware and software come together to create efficient code. He created the LLVM compiler infrastructure project and the CLang compiler. He led major engineering efforts at Apple, including the creation of the Swift programming language. He also briefly spent time at Tesla as VP of Autopilot Software during the transition from Autopilot hardware 1 to hardware 2, when Tesla essentially started from scratch to build an in-house software infrastructure for Autopilot. If you would like to get more information about this podcast go to https://lexfridman.com/ai or connect with @lexfridman on Twitter, LinkedIn, Facebook, Medium, or YouTube where you can watch the video versions of these conversations.