Chris Lattner: More than you ever wanted to know

This was last updated in June 2025, and may be out of date. If you have questions, please contact me.

I am an innovator well-known for building multiple large-scale production systems that are used by millions of people, as well as building teams and communities that make them possible. I cofounded the LLVM Compiler infrastructure, the Clang compiler, the Swift programming language, the MLIR compiler infrastructure, the CIRCT project, and have contributed to many other commercial and open source projects at Apple, Tesla, Google, and SiFive.

I lead Modular AI, and serve on the board of directors of the LLVM Foundation.

Contents:

• Work History
• Education
• Notable Writing
• Public talks and other appearances
• Awards
• Academic Publications
• Other Interests and Activities

Work History:

Qualcomm: EVP, Advanced AI and Platforms

...

Modular AI: CEO and Co-Founder

January 2022-Aug 2026

Modular started on January 4, 2022 with big ideas and a dream, which we then built over 4 1/2 years until it was eventually acquired and turned into a business unit of Qualcomm for ~$4.5B (total deal consideration).

We started with several (at the time!) contrary ideas, including that we could make a fundamental leap in AI software systems if we invested years into R&D, that AI was important enough the world to be worth doing that, that inference would turn out to be more important than training, and that the world would end up needing heterogenous accelerators. This was heretical in a world in early 2022 (pre-ChatGPT!), but today it is obvious. Across that time, we achieved numerous milestones as a team and company:

• We scaled the team from 2 cofounders to almost 200 people - a deeply technical team of folks who believed that unifying heterogenous compute was possible and worthwhile.
• We raised $380M from a small group of incredible investors, including GV, General Catalyst, USIT and DFJ across three rounds. When acquired, we had nearly $150M in the bank, and extensive runway.
• We built fundamental new technologies, including Mojo, MAX, and Modular cloud: with Mojo hitting 1.0, MAX scaling to support a wide range of models, and Modular cloud scaling to serving trillions of tokens per day.
• We built the basis for a thriving commercial business with many paying customers, an extensive partner network, and a thriving open source developer community.
• Most importantly, we proved that our unified infrastructure platform really works - by our ModCon 2026 event, we showed we could serve models on accelerators from 6 different vendors - NVIDIA, AMD and Apple GPUs, Qualcomm NPUs, Google TPUs and AWS Trainium.
• We also showed that the same infrastructure could bring up support for new hardware architectures quickly, and scale to smaller devices, including embedded, laptop, and desktop devices. This included things like NVIDIA DGX Spark, AMD Strix Halo, Apple Studio Ultra, Qualcomm X2 Ultra, and Arduino devices.

Ultimately we decided to join Qualcomm because Qualcomm shares our vision of a unified compute platform. We’re also jointly ambitious - we want to scale this technology much faster than we could achieve as a startup, to maximize the impact on the world and break down the barriers that prevent novel hardware from getting adopted. It’s a joy to join the Qualcomm leadership team!

SiFive: President, Engineering and Product

January 2020 - January 2022

I joined SiFive in January 2020, right before the COVID pandemic struck. In the summer of 2020, the board decided to make major changes to the company (“SiFive 2.0”) - separating management of the silicon services team (initially known as OpenFive, later sold off to Alphawave) from SiFive’s RISC-V endeavors, hiring a new CEO, and rebooting the RISC-V organization. I stepped up to lead the RISC-V Product and Engineering organizations (everything excluding HR, finance, sales, customer support). My major accomplishments over this time are:

• Leadership, processes, and execution - I hired new VPs of Hardware, Software, and Product, built a new Program Management Organization, reorganized and realigned hundreds of people, canceled and sunsetted less-critical projects, and worked with our CEO and CTO to focus the company on high performance products. SiFive now has an amazing culture of collaboration and a clear path to conquer the world.
• Entirely new product lines - we introduced the "SiFive Intelligence" line of AI products, the SiFive Performance line of application processors (P270), the first SiFive out-of-order processor (P550), the 6-series in-order product line, and the highest performance RISC-V processor ever (P650AP). I personally created SiFive Intelligence, a “software first” approach to AI acceleration, and drove everything forward.
• Product updates - we shipped countless incremental updates to new products, as well as a developer board, an education platform, ASICs, and formed many partnerships with important industry collaborators.
• MLIR Compilers for Hardware Design - I cofounded the LLVM CIRCT Project, applying MLIR compiler technology to chip design: I built a team around it and drove it through major milestones. This work delivered 10X+ improvements to SiFive's development flows. More information in this tech talk.
• Business Impact - We drove major new revenue streams and dramatically increased the valuation of SiFive by ~5x from ~$500M in 2021 (Series E) to $2.5B in 2022 (Series F).

I'm proud of this progress and the path ahead for SiFive is very strong. The team and mission are very dear to me, and I maintained a formal advisor relationship with SiFive’s leadership and chip design team through 2023. I continue to be amazed by SiFive’s passion, drive, and rapid growth.

Google: Senior Director and Distinguished Engineer, TensorFlow Infrastructure and Technologies

August 2017 - January 2020

The TensorFlow group is a dynamic and fast moving team, incorporating multiple cross-cutting concerns that I loved to work on and with. This included complex product issues, Open Source infrastructure, deep technical challenges, new hardware platforms, and a race with the rest of the industry. These are the main projects that I advocated for, built, and scaled:

• TensorFlow Infrastructure Team: I led the TensorFlow Infrastructure team, which included responsibility for TensorFlow's CPU, GPU, TPU ("Tensor Processing Units"), and mobile infra. This involves a wide range of compiler and runtime technologies, including the XLA compiler team, TensorFlow graph transformations, quantization technologies, kernels written with Eigen and other approaches, etc.

• The MLIR Compiler Infrastructure: MLIR is an open source compiler infrastructure that underlies TensorFlow, providing support for a very wide range of high performance accelerators. The need is driven by requirements for better usability, integration, and increased generality of the stack. This work is particularly important as the "End of Moore's Law" leads to a proliferation of new hardware, which needs software support: rapid bringup is essential, even with occasionally wildly different capabilities and target markets. This is a large scale project pushing the boundaries of fundamental compiler technology - building on decades of experience building compilers.

  MLIR is defined in a framework-agnostic way and is successfully aligning the largest hardware manufacturers in the world. For more information, see the announcement and the intro talk. Google contributed MLIR to the non-profit LLVM Foundation, which contributed to its rapid industry-wide adoption.

• TensorFlow / TPU Bringup: I drove the cross-functional effort (spanning TensorFlow, Cloud, and Hardware teams) to bring up the TensorFlow TPU platform, productize the software stack, and help launch the product in Google Cloud. This was a technically challenging project with aspects spanning the entire stack, and required significant cross-functional social alignment. TPUs are now used extensively across Google and are setting new industry records for performance and scale, unlocking research that is leading to key new models (including BERT, XLNet, EfficientNet, and countless others), new techniques for large scale training, and internal product improvements across the board.

• TensorFlow "TFRT" Runtime: I led the charge to build a next-generation runtime for TensorFlow. The goal of the runtime is to provide a single consistent platform that dramatically increased performance and flexibility, which supports both training and inference, server and mobile. I defined the architecture and led the implementation (i.e. wrote most of the code) and overall design.

• Swift for TensorFlow: This project rethought machine learning development by opening the programming language to extension and change - allowing us to solve old problems in new ways. This project includes a combination of compiler, runtime, and programming language design and implementation work. I imagined, advocated for, coded the initial prototype and many of the subsystems after that; recruited, hired and trained an exceptional engineering team; we drove it to an open source launch as well as many subsequent milestones (including internal launches that shipped on all Android Pixel phones). For more information, see the MLSys paper that summarizes the project.

In addition to leading large teams of exceptional engineers, my roles at Google included designing and implementing many technologies from first principles, hiring the engineering team and building the engineering culture around them, and growing the engineering leaders who eventually took them over and continue driving them today. I consider myself very privileged to be able to work with such an amazing team and to be able to build such fundamental technologies in a critical and fast-paced community.

Tesla: VP Autopilot Software

January 30 - June 20, 2017

When I joined Tesla, it was in the midst of a hardware transition from "Hardware 1" Autopilot (based primarily on MobileEye for vision processing) to "Hardware 2", which uses an in-house designed TeslaVision stack. The team was facing many tough challenges given the nature of the transition. My primary contributions over these fast five months were:

• We evolved Autopilot for HW2 from its first early release (which had few capabilities and was limited to 45mph on highways) to effectively parity with HW1, and surpassing it in some ways (e.g. silky smooth control).
• This required building and shipping numerous features for HW2, including: support for local roads, Parallel Autopark, High Speed Autosteer, Summon, Lane Departure Warning, Automatic Lane Change, Low Speed AEB, Full Speed Autosteer, Pedal Misapplication Mitigation, Auto High Beams, Side Collision Avoidance, Full Speed AEB, Perpendicular Autopark, and 'silky smooth' performance.
• This was done by shipping a total of 7 major feature releases, as well as numerous minor releases to support factory, service, and other narrow markets.
• One of Tesla's huge advantages in the autonomous driving space is that it has tens of thousands of cars already on the road. We built infrastructure to take advantage of this, allowing the collection of image and video data from this fleet, as well as building big data infrastructure in the cloud to process and use it.
• I defined and drove the feature roadmap, drove the technical architecture for future features, and managed the implementation for the next exciting features to come.
• I advocated for and drove a major rewrite of the deep net architecture in the vision stack, leading to significantly better precision, recall, and inference performance.
• I ended up growing the Autopilot Software team by over 50%. I personally interviewed most of the accepted candidates.
• I improved internal infrastructure and processes that I cannot go into detail about.
• I was closely involved with others in the broader Autopilot program, including future hardware support, legal, homologation, regulatory, marketing, etc.

Overall I learned a lot, worked hard, met a lot of great people, and had a lot of fun.

Apple: 2005 - January 2016

• Apple: Developer Tools Department
  Senior Director and Architect, Developer Tools Department
  January 2013 - January 2017

  In January 2013, I took over management and leadership of the entire Developer Tools department at Apple (~200 people). In addition to languages (Swift and Objective-C), compilers and low-level tools, I took on responsibility for the Xcode IDE, Instruments performance analysis tool, Apple Java releases, and a variety of internal tools.

  In this time period, my team shipped a number of major Xcode releases, including Xcode 4.6, 5.x, 6.x, 7.x, and 8.x, each with major feature enhancements. Some of my more notable contributions include:

  • ARM64: Over a 3 year span, I drove definition, bringup and implementation work of the ARM64 (aka Aarch64) compiler toolchain - the first production quality compiler for this architecture in the world - which shipped in Xcode 5. This enabled the iPhone 5s, which shocked the world with its 64-bit support and superb performance. In addition to compiler work, I contributed to the design of a new Objective-C runtime object model for the architecture, and I personally contributed the "TBI" feature to ARM, which was incorporated in the Aarch64 architecture.
  • iPhone GPU Compiler: we implemented a completely new LLVM-based runtime GPU shader compiler. This started shipping in iOS7 to support the iPhone 5s - which featured a VLIW PowerVR Rogue GPU derivative, and has been extended to support later iPhone hardware as it comes out. Compared to the vendor compiler it replaced, this GPU compiler produces code that runs slightly faster, and takes much less compile time to generate it.
  • Xcode 5 was a major release, notable for me in that it was the first release with a completely LLVM-based low-level toolchain (Clang, LLDB, etc) - it dropped the last support for GCC and GDB. This transition was largely driven by the ARM64 architecture transition.
  • Swift: The most prominent feature of Xcode 6 was Swift, a new programming language that I had been personally driving since 2010. In addition to the language design and implementation, I drove much of the compiler architecture (e.g. the SIL high-level IR), the REPL and Playgrounds feature designs, drove and coordinated the rest of the team to implement full Xcode and documentation support for a language that was still rapidly evolving. We managed to keep extremely tight secrecy until a great launch at WWDC 2014.
  • I was the primary proponent for the Official Swift Blog and wrote many of the posts.
  • I drove Swift Open Source to happen, and was extensively involved defining exactly what that meant.
  • Apple Watch: In 2015, we introduced support for building Apple Watch (and TV) apps, and introduced the requirement that all apps submitted to the store be built using LLVM bitcode. Three years later, it was revealed that this work enabled a completely seamless architectural transition to more power efficient and faster chips.
  • I was one of the few core people who drove Swift Playgrounds for iPad, including conception, design, implementation, and iteration.
  • I was a member of Apple's senior executive leadership team, and drove a number of internal things that I can't talk about.
  
  
• Apple: Developer Tools Group
  Director and Architect, Low-Level Tools
  September 2011 - January 2013

  This timeframe has included numerous technical and team achievements across a wide range of domains. For example:

  • Apple shipped the Mac OS X 10.8 and iOS 6 releases, and they were built with Clang - llvm-gcc is obsolete, and GCC is long gone.
  • We invested major effort into compiler implementation and tuning for the custom Apple CPU design known as the "Apple A6". The exceptional CPU performance of the iPhone 5 was a result of a joint effort between the Apple silicon and LLVM teams.
  • I personally drove LLDB to production quality and to become the default debugger in Xcode.
  • I drove the new "Objective-C Literal Syntax" language extensions, making many common situations in Objective-C much more syntactically elegant.
  • We shipped Xcode 4.3, 4.4, and 4.5 releases, and I was a key part of the high level feature planning and decision processes that defined the features and shaped the releases.
  
  
• Apple: Developer Tools Group
  Senior Manager and Architect, Low-Level Tools
  June 2010 - September 2011

  I managed the teams responsible for compilers, the LLDB debugger, Objective-C and C++ runtimes, assembler, linker, dynamic loader, etc. I am continuing my work improving the Apple developer tools, and continue to contribute daily to the open source LLVM technologies. During this time period my team switched Mac OS/X Lion and iOS5 to build with llvm-gcc and clang (off of GCC 4.2) and oversaw the final release of Xcode 4.0 in March (as well as subsequent updates).

  Xcode 4.2 was a specific achievement in that it is the first release where all of its compilers are LLVM-based (GCC 4.2 is no longer included). Xcode 4.2 also includes the "Automatic Reference Counting (ARC) Objective-C language feature (see also wikipedia). ARC has revolutionized Objective-C programming by automating memory management without the runtime overhead of a garbage collector. I personally defined and drove this feature late in the schedule of iOS5 and Lion. This is notable for the short schedule for the project, the extensive cross-functional work required, and the extensive backwards compatibility issues that had to be addressed (making it a very technically complex problem).

• Apple: Developer Tools Group
  Senior Manager of Compilers and Low-Level Tools, Compiler Architect
  September 2009 - June 2010

  My work in this time period culminated in the release of the Xcode 4 preview at WWDC, which included a preview release of Clang C++ support, a new C++ Standard Library, a much faster and memory efficient system linker, a new X86 assembler (which is integrated into the clang compiler, providing faster compile times), and countless smaller improvements throughout the toolchain.

  Xcode 4 itself now features deep integration of the Clang parser for code completion, syntax highlighting, indexing, live warning and error messages, and the new 'Fix-It' feature in which the compiler informs the UI how to automatically corrects small errors. LLVM-GCC is the default compiler in Xcode 4.

  The Xcode 4 preview also includes the first public release of LLDB to which I served as a consultant and contributed directly to turning it into an open source project.

• Apple: Developer Tools Group
  Manager of Compilers and Low-Level Tools, Compiler Architect
  July 2008 - September 2009

  In this time period, I was a second level manager running the teams responsible for Clang, LLVM, GCC, and other parts of the Apple toolchain (assembler, linker, etc). I directly managed the Clang team, contributed daily to both the Clang and LLVM projects, and continued in my role as compiler architect and lead on the Open Source LLVM/Clang projects.

  During this period my team brought Clang 1.0 to production quality as a brand new C and Objective-C compiler for X86-32 and X86-64. We also productized and shipped the Xcode static analyzer, a new compiler-rt library (which replaced libgcc in Snow Leopard) and many enhancements to existing components in the operating system.

• Apple: Developer Tools Group
  LLVM Compiler Group Manager and Compiler Architect
  December 2006 - July 2008

  In this time period, my group expanded use of LLVM within Apple, supported new clients, built new features, and extended LLVM in many ways. We shipped llvm-gcc 4.2 in the Xcode 3.1 and major improvements for it in the Xcode 3.1.1 release.

  In addition to llvm-gcc, much of the work during this time was focused on Mac OS 10.6 development. I made major contributions to design and implementation of the "Blocks" language feature as well as to the architecture and design of the language and compiler aspects of the OpenCL GPGPU technology.

  Finally, during this period I architected and started implementation of a suite of front-end technologies based on LLVM, named "Clang".

• Apple Computer Inc: Developer Tools Group
  Senior Compiler Engineer and Tech Lead
  June 2005 - December 2006

  I drove LLVM productization, features and applications at Apple. LLVM link-time optimization support is now integrated into the Apple system linker, and LLVM is used by the Apple OpenGL group for several different purposes. My main contributions during this time was a new llvm-gcc4 front-end, significant improvements to the X86 and PowerPC backends, a wide range of optimization improvements and new optimizers, significant improvement to the target-independent code generator, and leadership for the rest of the team.

Graduate School Work

• University of Illinois at Urbana Champaign
  Research Assistant
  Fall 2000 - Spring 2005

  I worked on numerous projects at UIUC, the most important being LLVM and Data Structure Analysis (DSA). At Illinois, I designed and built most of the fundamental aspects of LLVM, establishing the architecture for things to come and building most of the scalar, loop and interprocedural optimizers. I also built most of the target-independent code generator, X86 backend, JIT, llvm-gcc3 front-end, and much more. Finally, I wrote many papers.

• Microsoft Research: Programmer Productivity Research Center
  Research Intern
  Summer 2004

  I worked on the Microsoft Phoenix compiler infrastructure, building an experimental bridge between the Microsoft compiler and the LLVM compiler (which allowed LLVM to compile and run .NET code).

Education

University of Illinois, Urbana-Champaign - Urbana, Illinois - GPA: 4.0

• Ph.D. Computer Science: Spring 2002 - Spring 2005
  Thesis: "Macroscopic Data Structure Analysis and Optimization"
• M.S. Computer Science: Fall 2000 - Fall 2002
  Thesis: "LLVM: An Infrastructure for Multi-Stage Optimization"

University of Portland - Portland, Oregon - GPA: 3.9

• B.S. Computer Science: Fall 1996 - Spring 2000

Notable Writing

Here are some of the more interesting things I've written:

• Jul 2026: The LLVM Compiler Infrastructure: From federally funded academic research to worldwide impact on computing. A survey at Communications of ACM about LLVM's impact, arguing that we need more funding for fundamental research.
• Feb 2026: The Claude C Compiler: What It Reveals About the Future of Software: A look inside the first AI-generated C compiler, unpacking what it is, and what it means for the future of hybrid human/AI software design.
• Feb 2025-: Democratizing AI Compute: A multi-part blog series talking about CUDA, how it became dominant in GPU/AI compute, and why other technologies like OpenCL, AI Compilers, and eDSLs haven't replaced it.
• Feb 2020: MLIR: A Compiler Infrastructure for the End of Moore's Law: The canonical paper about MLIR describing its approach and architecture. We prefer for work built on top of MLIR to cite this paper.
• Jan 2020: Swift for Good Book Forward: a forward summarizing evolution of Swift, supporting Black Girls Code.
• Mar 2019: Usage of 'Const' in MLIR, for core IR types: MLIR makes a significant design divergence from LLVM in the way it uses Const, this doc explains why.
• Jun 2018: MLIR Specification: The original MLIR spec was joint work between 6 people, and evolved a lot into the final IR specification.
• May 2018: Response to "I am leaving llvm" email: Public statement responding to a case where a prominent LLVM member left because of Code of Conduct and diversity programs.
• May 2018: MLIR: The case for a simplified polyhedral form: One of the scientific contributions of MLIR is a new approach to using the 'math' of polyhedral compiler optimizations without the pieces that lead to other compile and other limitations.
• Jan 2017: Swift Concurrency Manifesto: a proposed multiyear journey to bring Swift memory safe concurrency features.
• May 2011: What Every C Programmer Should Know About Undefined Behavior: a treatise about undefined behavior in C, describing how it works, why, and why it is so problematic. I wrote this when working on Swift, and because I was tired of explaining the same old problems in C over and over.
• 2011: A chapter on LLVM for "The Architecture of Open Source Applications," a book on software design. It explains traditional compiler design, what makes LLVM different, how library-based design impacts applicability of the code, and how some simple optimizations work.

• SE-0313: Improved control over actor isolation.
• SE-0306: Actors: A major step forward in memory safety and design patterns for task based concurrency.
• SE-0302: Sendable and @sendable closures: a cornerstone feature to enables Swift Concurrency model to be memory and race safe in practice.
• Swift Concurrency Whitepapers: "Actors are reference types, but why classes?", "Actor isolation for Global State", "Type System Considerations for Actor Proposal".
• SE-0216: Introduce user-defined dynamically "callable" types. Implemented in Swift 5.
• SE-0195: Introduce User-defined "Dynamic Member Lookup" Types. Implemented in Swift 4.2.
• SE-0169: Improve Interaction Between private Declarations and Extensions. Implemented in Swift 4.
• SE-0109: Remove the Boolean protocol. Implemented in Swift 3.
• SE-0099: Restructuring Condition Clauses. Implemented in Swift 3.
• SE-0066: Standardize function type argument syntax to require parentheses. Implemented in Swift 3.
• SE-0049: Move @noescape and @autoclosure to be type attributes. Implemented in Swift 3.
• SE-0048: Generic Type Aliases. Implemented in Swift 3.
• SE-0036: Requiring Leading Dot Prefixes for Enum Instance Member Implementations . Implemented in Swift 3.
• SE-0029: Remove implicit tuple splat behavior from function applications. Implemented in Swift 3.
• SE-0023: API Design Guidelines. Implemented in Swift 3.
• SE-0004: Remove the ++ and -- operators. Implemented in Swift 3.

Public talks and other appearances

1. Podcast Interview "Every Engineer Is a Manager Now 🤖"
   An hour long discussion with Luca Rossi: AI coding is here to stay, but it is far from obvious how to get the most value out (rather than tokenmax'ing lol). Ignoring them would be like ignoring git 15 years ago! Luca and I explored how AI tooling is "forcing" best practices in SW (good CI, fast testing, etc), discussed the challenges of getting teams to adapt (productively!) to new tools, how these tools are challenging OSS projects and proprietary SW moats, among many other topics. It was wonderful to spend time with Luca talking about the evolving nature of software design.
   Refactoring.fm with Luca Rossi, April 2026.
2. Podcast Interview "That's good Mojo - Creating a Programming Language for an AI world"
   A 40 minute audio podcast with Scott Hanselman, talking about modern SW design in the context of today's fast-paced AI tools, the role of SW engineers, and give some advice for folks growing in their careers. I also share why Mojo is designed for modern hardware.
   THE HANSELMINUTES PODCAST with Scott Hanselman, February 19, 2026.
3. Video Interview "From Swift to Mojo and high-performance AI Engineering with Chris Lattner"
   An hour long discussion talking about building large scale systems, the journey to build and launch Swift at Apple, how that a "nights and weekends" project scaled to aupport millions of programmers. It then goes on to connect that to current work building Mojo to unify AI hardware end enable a new generation of AI/GPU developers.
   The Pragmatic Engineer Podcast with Gergely Orosz, November 7, 2025.
4. Video Discussion "Build to Last: Jeremy Howard and Chris Lattner on software craftsmanship and AI"
   An hour long discussion with Jeremy Howard talking about the impact of AI coding tools on software development, software engineers careers, and how "AI anxiety" is holding many people back. This is intended to be an optimistic and uplifting take on a complicated subject.
   fast.ai blog, October 5, 2025.
5. Audio Podcast "Why ML Needs a New Programming Language"
   An hour long discussion with Yaron Minsky, discussing how GPUs work and why a new programming language techiques are valuable. Ron shares early experiences using Mojo at Jane Street, and I talk about the path ahead. It was a fun and pretty accessible discussion.
   Signals and Threads Podcast, September 3, 2025.
6. Video/Audio Podcast "Mojo on Software Unscripted [Video]
   An hour long technical discussion about programming languages and how modern hardware is changing the game and requiring a rethink. This also discusses a FAQ: Why do programming langauges matter in a world of AI coding? (deep link).
   Software Unscripted Podcast, July 25, 2025.
7. Video/Audio Podcast + Transcript: "The Shape of Compute" - Hour long podcast
   Conversation about Modular's path and progress, AMD and NVIDIA GPU programming, unlocking the development community, Modular's approach vs endpoint companies, plus discussion about Google's AI progress, various personal habits and misc other topics.
   Latent Space Podcast, June 13, 2025.
8. Tech Talk: "Mojo🔥 + AMD: High Performance GPU Programming"
   AMD Advancing AI 2025 Luminary Talk, June 12, 2025.
9. Community Talk:LLVM's First 25 Years - and the Road Ahead [video]
   A short talk highlighting many contributions to LLVM throughout the year and celebrating the role of the LLVM Developer Meeting. This was a keynote for the first AsiaLLVM Developer Meeting.
   Asia LLVM Developer Meeting, June 10, 2025.
10. Tech Talk:"Mojo and Building a CUDA Replacement with Chris Lattner - Hour long discussion.
    Software Engineering Daily, May 22, 2025.
11. Tech Talk:"Mojo: Modular’s unified device accelerator language" - 2hr long Deep dive video
    A 2 hour long tech talk / deep dive explaining how Mojo unlocks the power of GPU programming in a new way, targetted at folks who write GPU kernels.
    GPU Mode community, May 2, 2025.
12. Marketing Talk:"Next-Gen GPU Programming: Hands-On with Mojo & MAX @ Modular HQ" - 1 hour video explaining what Modular is up to
    Modular Community Meeting, Apr 24, 2025.
13. Written interview: "An interview with Chris Lattner"
    A short written interview talking about my learnings building many systems, lifestyle, and how programming languages influenced my thinking for Mojo and other systems.
    Programming Language DataBase, Jan 28, 2025.
14. Panel Discussion: "Is MLIR feature complete? Production ready?"
    Discussion with several people about the state of the MLIR compiler infrastructure and its ecosystem.
    2024 LLVM Developers' Meeting, Oct 24, 2024.
15. Video Interview: "Mojo Language discussion on Software Unscripted"
    A nerd-out session with Richard Feldman (a fellow language implementor) talking about various language design topics.
    Software Unscripted Podcast by Richard Feldman, Aug 30, 2024
    Written summary at The New Stack
16. Written Profile/Interview: "Can one of the architects of modern software development help unlock AI’s true potential?"
    A few page summary of how I got interested in AI in the first place, as an extension of the developer tools ecosystem. What I saw through that journey and why Modular and MAX are necessary to get AI up to the standards of general software engineering.
    The Angle by Darrell Etherington, Aug 29, 2024
17. Video Interview: "Harper Carroll AI"
    A 27 minute interview aimed at early-career developers, with advice for how to start their journey as a developer.
    Harper Carroll Interview, July 19, 2024
18. Video Interview: "Primeagen Interview"
    An hour long interview that is accessible to general tech folk, talking about the social side of launching Swift within Apple, lessons learned that flow into Mojo's design and how Mojo is a significant next step for programming languages.
    ThePrimeTime, July 10, 2024
19. Video Interview: "Founder Fireside with Chris Lattner | Ep 04 | Accel | Open Source"
    A 30 minute discussion about building open source techonologies and languages, and balancing governance and company building aspects as a founder.
    Accel Open Source Founder Summit, May 1, 2024
20. Marketing Talk: "Get off proprietary endpoints with Modular"
    A talk for AI Engineers explaining how Modular's MAX AI solutions help get "beyond the endpoint" to control your AI.
    AI Engineer World's Fair 2024, June 27, 2024
21. Tech Talk: "Unlocking Developer Productivity across CPU and GPU with Mojo" with Mostafa Hagog
    Overview of the MAX platform and how to unifies CPU + GPU programming.
    2024 NVIDIA GTC AI Conference, March 19, 2024
22. Tech Talk: "Modular: A new tech stack for next gen AI research
    Neurips ML for Systems Workshop, December 16, 2023
23. Tech Talk: "Mojo 🔥: A system programming language for heterogenous computing [Video] with Jeff Niu and Abdul Dakkak
    Overview of the internals of the Mojo compiler and compilation model, aimed at compiler engineers an programming language enthusiasts.
    2023 LLVM Developer's Meeting, October 12, 2023
24. Panel Discussion: "From Inception to Iconic: What it Takes to Succeed in AI" (transcript)
    Discussion about entrepreneurial journey and advice for founders.
    TechCrunch Disrupt, Oct 2, 2023.
25. Podcast+Transcript: "Doing it the Hard Way: Making the AI engine and language 🔥 of the future" (89 minutes).
    Deep dive into the AI infrastructure part of the Modular Engine, how it works, how we approached it, and why Mojo🔥 had to be built.
    Latent Space Podcast, September 14, 2023.
26. Podcast: "Expanding AI chip capabilities beyond Nvidia with Modular CEO Chris Lattner | E1808" (63 minutes).
    This Week in Startups, September 13, 2023.
27. Podcast: "Modular CEO Chris Lattner on Raising $100M to Fix AI Infrastructure for Developers" (34 minutes).
    How Modular started, the origins of Mojo🔥 (and Swift!), why we need $100M to advance AI for the world, and what it means for the future of programming!
    AI Chat Podcast, September 12, 2023.
28. Podcast: "Mojo: A Supercharged Python for AI with Chris Lattner"
    TWIML: This Week in ML, June 19, 2023.
29. Long Podcast: "Chris Lattner: Future of Programming and AI". [summary/index]
    A 3.5 hour long overview of what Modular is up to, what the Mojo programming language is and how it works, how AI accelerators and hardware in general is evolving, and more.
    Lex Fridman Podcast #381, June 2, 2023.
30. Marketing Talk: "May 2023 Product Launch Keynote".
    Modular AI emerges from stealth and unveils our AI engine, cloud solutions, hardware approach, and Mojo, a new language in the Python family.
    May 2, 2023.
31. Interview Transcript: "Lessons from LLVM" - Discussing LLVM history, how learnings led to MLIR, what is next.
    Supercomputing 2021, December 27, 2021.
32. Podcast: "World’s Biggest GPU, plus Software-First AI Chip Design with SiFive’s Chris Lattner.
    Discussing the challenges of AI accelerators at the HW/SW boundary, particularly for production deployment of ML algorithms.
    AI with Sally Ward-Foxton, December 9, 2021.
33. Tech Talk: "CIRCT: Lifting hardware development out of the 20th century [video] with Andrew Lenharth - Discussing application of MLIR for hardware design.
    Keynote at 2021 LLVM Developer's Meeting, November 17, 2021.
34. Podcast: "A tower of capabilities with John Sundell - Swift Concurrency, ongoing evolution of the language, and importance of design for languages and APIs.
    Swift by Sundell Podcast, July 2, 2021.
35. Marketing Talk: "Enhancing RISC-V Vector Extensions to Accelerate Performance on ML Workloads"
    Linley Spring Processor Conference 2021, April 23, 2021.
36. Tech Talk: "The Golden Age of Compilers, in an era of Hardware/Software co-design" [video]
    A discussion about accelerator design, benefits of reducing fragmentation by standardizing non-differentiated parts of large scale HW/SW systems.
    International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2021), April 19, 2021
37. Panel Discussion: "tinyML inference SW - where do we go from here?"
    tinyML Summit 2021, March 24, 2021
38. Podcast: "Can Open-Source Semiconductors Upend the Chip Industry?" - High level discussion about RISC-V and SiFive.
    Odd Lots Podcast with Joe Weisenthal and Tracy Alloway, February 1, 2021.
39. Long Podcast: "Chris Lattner: The Future of Computing and Programming Languages"
    Topics spanning: programming language design, value semantics, RISC-V, SiFive, MLIR, social commentary, and more. [Summary of Leadership Philosophy]
    Lex Fridman Podcast #131, October 18, 2020
40. Interview Video: "PLDI Ask Me Anything with Chris Lattner", hosted by Cristian Cadar.
    Programming Language Design and Implementation (PLDI) 2020
41. Interview Video: "Swiftly Speaking 11: Chris Lattner" - backstory and Q&A about Swift origins [transcript]
    Swiftly Speaking, June 18, 2020.
42. Long Podcast: "Interview: Four Letter Technologies"
    Accidental Tech Podcast, Episode 371, March 25, 2020.
43. Tech Talk: "MLIR: Multi-Level Intermediate Representation Compiler Infrastructure"
    International Symposium on Code Generation and Optimization (CGO) 2020, February 26, 2020
44. Tech Talk: "Thoughts on Tensor Code Generation in MLIR" [slides] - an informal talk
    MLIR Open Design Meeting, January 23, 2020
45. Marketing Talk: "MLIR Keynote Talk"
    TensorFlow World, October 31, 2019
46. Long Podcast: "Swift's past, present and future"
    Swift by Sundell Podcast, June 20, 2019
47. Long Podcast: "Video interview with Lex Fridman"
    Artificial Intelligence Podcast, May 13, 2019 (recorded in March)
48. Long Lecture Videos: "Practical Deep Learning for Coders" Guest Lectures with Jeremy Howard
    University of San Francisco, Data Institute, April 23/30, 2019
49. Tech Talk: "MLIR: Multi-Level Intermediate Representation for Compiler Infrastructure" [video]
    European LLVM Developer Meeting '19, April 8, 2019
50. Marketing Talk: "Swift for TensorFlow: The Next-Generation Machine Learning Framework"
    TensorFlow Developer Summit '19, March 5, 2019
51. Tech Talk: "MLIR Primer: A Compiler Infrastructure for the End of Moore’s Law", first unveil of the MLIR Compiler Infrastructure.
    Compilers for Machine Learning Workshop, February 17, 2019
52. Podcast: "Interview: Origins of Swift [transcript highlights]
    Swift Community Podcast, January 16, 2019
53. Panel Discussion: "The Future of AI Software"
    PyTorch Developer Conference, Oct 10, 2018
54. Tech Talk: "Swift for TensorFlow: Graph Program Extraction".
    LLVM Developer Meeting, Oct 17, 2018
55. Marketing Talk: "Swift for TensorFlow", initial unveiling of S4TF.
    TensorFlow Developer Summit '18, March 30, 2018
56. Podcast: "Concurrency with Chris Lattner", discussing my proposed concurrency model for Swift 6
    Swift Unwrapped Podcast, September 4, 2017
57. Panel Discussion: "WWDC 2017 Swift Panel"
    Realm WWDC Panel, June 8, 2017.
58. Podcast: "Interview: My personal backstory"
    SwiftCoders Podcast, Episode 37, January 23, 2017.
59. Long Podcast: "Interview: Swift history and design" (transcript)
    Accidental Tech Podcast, Episode 205, January 19, 2017.
60. Tech Talk: "Swift: Opportunities for Language and Compiler Research"
    IBM PL Day 2016, Yorktown Heights, NY, December 2016.
61. Marketing Talk: "Swift 3 Introduction, Platform State of the Union" - Section starts at 16:30
    2016 Apple World Wide Developer Conference (WWDC), San Francisco, CA, June 2016.
62. Marketing Talk: "What's New in Swift 3" - Middle third of the talk
    2016 Apple World Wide Developer Conference (WWDC), San Francisco, CA, June 2016.
63. Marketing Talk: "Keynote: Swift & Xcode Playgrounds Demo"
    IBM Interconnect 2016, Las Vegas, NV, February 2016.
64. Tech Talk: "Swift's High-Level IR: A Case Study of Complementing LLVM IR with Language-Specific Optimization [video] - second half of talk
    2015 LLVM Developer's Meeting, San Jose, CA, November 2015.
65. Marketing Talk: Swift 2 Introduction, Platform State of the Union - Section starts at 56:40
    2015 Apple World Wide Developer Conference (WWDC), San Francisco, CA, June 2015.
66. Marketing Talk: What's new in Swift 2 - First half of talk
    2015 Apple World Wide Developer Conference (WWDC), San Francisco, CA, June 2015.
67. Marketing Talk: "Apple Keynote, Swift Launch Demo - Swift Launch, starts at 103:50 my demo starts at 107:15
    2014 Apple World Wide Developer Conference (WWDC), San Francisco, CA, June 2014.
68. Tech Talk: "LLVM - The Early Days - first half of a talk [video]
    2013 LLVM Developer's Meeting, San Francisco, CA, November 2013.
69. Tech Talk: "LLVM and Clang - Advancing Compilers and Tools
    Opening Keynote, 2013 Central and Eastern European Software Engineering Conference in Russia (CEE-SECR 2013), Moscow, Russia, October 2013.
    Selected as the best invited talk by conference attendees.
70. Marketing Talk: "What's New in Xcode 5
    2013 Apple World Wide Developer Conference (WWDC), San Francisco, CA, June 2013.
71. Marketing Talk: "Developer Tools Kickoff" (shared talk)
    2012 Apple World Wide Developer Conference (WWDC), San Francisco, CA, June 2012.
72. Tech Talk: "Increasing Industry Impact of Compiler Optimization Research"
    Opening Keynote, 2012 International Symposium on Code Generation and Optimization (CGO'12), San Jose, CA, April 2012.
73. Tech Talk: "LLVM and Clang: Advancing Compiler Technology
    Keynote, Free and Open Source Developers' European Meeting (FOSDEM'11), Brussels, Belgium, February 2011.
74. Marketing Talk: "What's New in the LLVM Compiler" (shared talk)
    2010 Apple World Wide Developer Conference (WWDC), San Francisco, CA, June 2010.
75. Tech Talk: "State of Clang" (shared talk)
    LLVM Developer Meeting, Cupertino, CA, Oct 2009.
76. Marketing Talk: "Developer Tools State of the Union" (shared talk)
    2009 Apple World Wide Developer Conference (WWDC), San Francisco, CA, June 2009.
77. Tech Talk: "Compiler State of the Union" (shared talk)
    2009 Apple World Wide Developer Conference (WWDC), San Francisco, CA, June 2009.
78. Tech Talk: "Introduction to the LLVM Compiler System"
    Plenary Talk, ACAT 2008: Advanced Computing and Analysis Techniques in Physics Research, Erice, Sicily, Italy, November 2008.
79. Marketing Talk: "Compiler State of the Union" (shared talk)
    2008 Apple World Wide Developer Conference (WWDC), San Francisco, CA, June 2008.
80. Tech Talk: "LLVM Compiler In Depth" (shared talk)
    2008 Apple World Wide Developer Conference (WWDC), San Francisco, CA, June 2008.
81. Tech Talk: "LLVM and Clang: Next Generation Compiler Technology"
    BSDCan 2008, Ottawa, Canada, May 16-17, 2008.
82. Tech Talk: "The LLVM Compiler System"
    2007 O'Reilly Open Source Convention, Portland, OR, July 2007.
83. Tech Talk: "LLVM 2.0 and Beyond!"
    Google Tech Talk, Mountain View, CA, July 25, 2007.
84. Marketing Talk: "Taking Advantage of Compiler Advances" (shared talk)
    2007 Apple World Wide Developer Conference (WWDC), San Francisco, CA, June 2007.
85. Tech Talk: "LLVM in OpenGL and for Dynamic Languages" (and several others)
    LLVM Developer Meeting, Cupertino, CA, May 2007.
86. Tech Talk: "The LLVM Compiler System"
    2007 Bossa Conference on Open Source, Mobile Internet and Multimedia, Recife, Brazil, March 2007.
87. Tech Talk: "Introduction to the LLVM Compiler Infrastructure"
    2006 Itanium Conference and Expo, San Jose, California, April 2006.

Awards and Recognition

Notable awards:

• 2016: Recognized as one of Wired's "25 Geniuses who are creating the future of business".
• 2014: Received the Test of Time Award for the most influential paper of CGO 2004 (awarded at CGO 2014).
• 2013: Received the 2013 Distinguished Alumni Achievement Award by the University of Illinois Computer Science Department.
• 2012: LLVM was awarded the ACM Software Systems Award which recognizes a software system that has had a lasting influence, reflected in contributions to concepts, in commercial acceptance, or both (across the entire software industry). Previous recipients include Java, Apache, the World-Wide Web, SMALLTALK, UNIX, and many other notable software systems.
• 2010: Received the ACM SIGPLAN Programming Languages Software Award in recognition of my work on LLVM. SIGPLAN is the ACM Organization focusing on Programming Language Design and Implementation. Being the first year this was awarded is notable, because all programming language software systems were eligible.

Academic Publications

Since joining industry, I rarely take time to write papers about my work, preferring instead to focus on building new great things. That said, I've had the opportunity to colaborate on the following papers:

1. "Swift for TensorFlow: A portable, flexible platform for deep learning"
   MLSys 2021, San Jose, California, April 2021
2. "MLIR: Scaling Compiler Infrastructure for Domain Specific Computation"
   CGO 2021, Virtual, February 2021
3. "Making Context-sensitive Points-to Analysis with Heap Cloning Practical For The Real World"
   PLDI 2007, San Diego, CA, June 2007
4. "Automatic Pool Allocation: Improving Performance by Controlling Data Structure Layout in the Heap"
   PLDI 2005, Chicago, IL, June 2005.
   Awarded PLDI 2005 Best Paper Award
5. "Automatic Pointer Compression for Linked Data Structures"
   ACM SIGPLAN 2005 Workshop on Memory System Performance (MSP'05) Chicago, IL, June 2005.
6. "Memory Safety Without Runtime Checks or Garbage Collection"
   2005 Transactions in Embedded Computing Systems (TECS'05)
   Journal Publication
7. "The LLVM Compiler Framework and Infrastructure Tutorial"
   LCPC'04 Workshop on Compiler Research Infrastructures, West Lafayette, Indiana, Sep. 2004.
8. "LLVM: An Aggressive Compilation Framework for Life-Long Program Analysis and Transformation"
   CGO 2004, San Jose, CA, March 2004.
   Best Student Presenter Award
   Test of Time Award for the most influential paper of CGO 2004 (awarded at CGO 2014).
9. "LLVA: A Low-level Virtual Instruction Set Architecture"
   MICRO-36 2003, San Diego, CA, December 2003.
10. "Memory Safety Without Runtime Checks or Garbage Collection"
    Proc. Languages Compilers and Tools for Embedded Systems 2003 (LCTES 03), San Diego, CA, June 2003.
11. "Architecture For a Next-Generation GCC"
    First Annual GCC Developers' Summit, Ottawa, Canada, May 2003.
12. "Automatic Pool Allocation for Disjoint Data Structures"
    ACM SIGPLAN 2002 Workshop on Memory System Performance (MSP'02), Berlin, Germany, June 2002.
13. "Developing a Graphical Robotics Simulator"
    IASTED International Conference, Modeling & Simulation (MS'99)

Other Interests and Activities

In addition to technical activities:

• I am married (to Tanya), have two kids (Zac and Riley), and two dogs (Copper, Annie).
• I enjoy woodworking, downhill skiing, snowboarding, swimming, hiking, and walking our dogs.
• I was a competitive fencer and was president of the University of Illinois Classical Fencing club. I taught an introduction to fencing class in 2003-2004, with a class of ~15 people.