The next supercomputer with NVIDIA's Wen-Mei Hwu

In this episode of ACM ByteCast, our special guest host Scott Hanselman (of The Hanselminutes Podcast) welcomes 2024 ACM-IEEE CS Eckert-Mauchly Award recipient Wen-Mei Hwu, Senior Distinguished Research Scientist at NVIDIA and Professor Emeritus at the University of Illinois, Urbana-Champaign. He was recognized for pioneering and foundational contributions to the design and adoption of multiple generations of processor architectures. His fundamental and pioneering contributions have had a broad impact on three generations of processor architectures: superscalar, VLIW, and throughput-oriented manycore processors (GPUs). Other honors and recognitions include the 1999 ACM Grace Murray Hopper Award, 2006 ISCA Most Influential Paper Award, 2014 MICRO Test-of-Time Award, and 2018 CGO Test-of-Time Award. He is the co-author, with David Kirk, of the popular textbook Programming Massively Parallel Processors.Wen-Mei discusses the evolution of Moore’s Law and the significance of Dennard Scaling, which allowed for faster, more efficient processors without increasing chip size or power consumption. He explains how his research group’s approach to microarchitecture at the University of California, Berkeley in the 80s led to advancements such as Intel’s P6 processor. Wen-Mei and Scott discuss the early days of processors and the rise of specialized processors and new computational units. They also share their predictions about the future of computing and advancements that will be required to handle vast data sets in real time, and potential devices that would extend human capabilities.Wen-mei Hwu Announced as the 2024 ACM-IEEE CS Eckert-Mauchly Award Recipient

Hanselminutes Podcast by Scott Hanselman

The Hanselminutes podcast

Fresh Tech Talk from Fresh Faces

[That's good Mojo - Creating a Programming Language for an AI world with Chris Lattner]

That's good Mojo - Creating a Programming Language for an AI world with Chris Lattner

Show #1037 Feb 19 2026
Podcast Player with Transcript Help edit or fix transcripts here! Permalink -->

What does it take to design a programming language from scratch when the target isn’t just CPUs, but GPUs, accelerators, and the entire AI stack? In this episode, I sit down with legendary language architect Chris Lattner to talk about Mojo — his ambitious attempt to rethink systems programming for the machine learning era.

We trace the arc from LLVM and Clang to Swift and now Mojo, unpacking the lessons Chris has carried forward into this new language. Mojo aims to combine Python’s ergonomics with C-level performance, but the real story is deeper: memory ownership, heterogeneous compute, compile-time metaprogramming, and giving developers precise control over how AI workloads hit silicon.

Chris shares the motivation behind Modular, why today’s AI infrastructure demands new abstractions, and how Mojo fits into a rapidly evolving ecosystem of ML frameworks and hardware backends. We also dig into developer experience, safety vs performance tradeoffs, and what it means to build a language that spans research notebooks all the way down to kernel-level execution.

####
Mailtrap

Please subscribe! We're on iTunes, Spotify, Google Play, Twitter,
or download the MP3.
Share on Twitter and
Facebook. Also, see our survey!

Edit and improve my show's PodScribe.ai transcripts here!

📺 Watch Scott's TEDx talk:
"Tech Promised Everything. Did it deliver?"

Previously on the podcast...

[The Rise of The Claw with OpenClaw's Peter Steinberger]

1036

The Rise of The Claw with OpenClaw's Peter Steinberger

[The AI Vampire with Gas Town's Steve Yegge]

1035

The AI Vampire with Gas Town's Steve Yegge

[Kinder Code Reviews with AI? with Qodo's Nnenna Ndukwe]

1034

Kinder Code Reviews with AI? with Qodo's Nnenna Ndukwe

[Run your AI Agent in a Sandbox, with Docker President Mark Cavage]

1033

Run your AI Agent in a Sandbox, with Docker President Mark Cavage

[Where is AI taking us? - with The Pragmatic Programmer Gergely Orosz]

1032

Where is AI taking us? - with The Pragmatic Programmer Gergely Orosz

[Fabulous Adventures in Data Structures and Algorithms with Eric Lippert]

1031

Fabulous Adventures in Data Structures and Algorithms with Eric Lippert

[Vjekoslav Krajačić on File Pilot and a return to fast UIs]

1030

Vjekoslav Krajačić on File Pilot and a return to fast UIs

[Loris Cro on the Rise of Zig]

1029

Loris Cro on the Rise of Zig

[Trusting Agentic AI with Dr. Dawn Song]

1028

Trusting Agentic AI with Dr. Dawn Song

[Human Agency in a Digital World with Marcus Fontoura]

1027

Human Agency in a Digital World with Marcus Fontoura

[Daniel Temkin and the Beauty of Esoteric Languages]

1026

Daniel Temkin and the Beauty of Esoteric Languages

[The Digital Runway: IT at the Philadelphia Airport with Camille Tomlin]

1025

The Digital Runway: IT at the Philadelphia Airport with Camille Tomlin

[C++ is Still Here, Still Powerful with Gabriel Dos Reis]

1024

C++ is Still Here, Still Powerful with Gabriel Dos Reis

[Why Postgres? and why now? with Claire Giordano]

1023

Why Postgres? and why now? with Claire Giordano

[The Past Still Boots with the Interim Computing Museum's Stephen Jones]

1022

The Past Still Boots with the Interim Computing Museum's Stephen Jones

[Cheat Codes for Junior Engineers with Kat Excellence]

1021

Cheat Codes for Junior Engineers with Kat Excellence

Hundreds more episodes over here...

tag,
and before any other scripts. Note that it may take up to 15
minutes to process and display information here after
instrumenting and opening your web page.
-->
tag,
and before any other scripts. Your first data will appear
automatically in just a few seconds.
-->

Original source