Independent project. Not a U.S. government website.

Support our project (opens Buy Me a Coffee)
USASI

Kunle Olukotun

Co-founder and Chief Technologist of SambaNova; Cadence Design Professor at Stanford University

  • Co-founder and Chief Technologist, SambaNova231
  • Cadence Design Professor of Electrical Engineering and Computer Science; Director of the Pervasive Parallelism Lab, Stanford University12

Kunle Olukotun is a co-founder and the Chief Technologist of SambaNova, which builds dataflow chips and systems for AI, and the Cadence Design Professor of Electrical Engineering and Computer Science at Stanford University. Olukotun led the Stanford Hydra chip multiprocessor project, founded Afara Websystems, whose Niagara multicore processor was acquired by Sun Microsystems, and directs Stanford's Pervasive Parallelism Lab.12

Research

Olukotun's research centers on multicore and parallel processor design. Olukotun led the Stanford Hydra chip multiprocessor research project and, as director of the Pervasive Parallelism Lab, works on infrastructure for usable machine learning, including as a co-leader of the DAWN research program.125

Stanford's profile lists Olukotun as an ACM Fellow and an IEEE Fellow, the latter for contributions to chip multiprocessor design and its commercialization.1

Companies

Olukotun founded Afara Websystems to build high-throughput, low-power multicore server processors; Sun Microsystems acquired the company in 2002, and its Niagara processor went on to power SPARC-based servers.12

In 2017 Olukotun co-founded SambaNova with Stanford colleague Christopher Ré and semiconductor executive Rodrigo Liang. SambaNova describes Olukotun's chip multiprocessor work and Ré's machine learning systems work as the two starting points for the company, where Olukotun leads as Chief Technologist.31

Work

  • Niagara multicore processor

    Founded Afara Websystems to build the Niagara high-throughput, low-power multicore server processor, which was acquired by Sun Microsystems and went on to power SPARC-based servers.12

  • SambaNova SN40L (external site: arxiv.org)

    Co-author of the 2024 paper describing SambaNova's SN40L dataflow accelerator and its approach to the AI memory wall through dataflow and a composition of experts.4

  • Stanford DAWN project (external site: arxiv.org)

    Co-author, with Peter Bailis, Christopher Ré and Matei Zaharia, of the 2017 paper laying out the Stanford DAWN research program on infrastructure for usable machine learning.5

Career timeline

  1. 2002

    Afara Websystems, which Olukotun founded, was acquired by Sun Microsystems.2

  2. 2017

    Co-founded SambaNova Systems with Christopher Ré and Rodrigo Liang.13

  3. May 22, 2017

    Co-authored the paper introducing the Stanford DAWN project on infrastructure for usable machine learning.5

  4. May 13, 2024

    Co-authored the SambaNova SN40L paper on dataflow and composition of experts.4

Other documented roles

Roles the sources document but that are not confirmed as current.

  • Founder (acquired by Sun Microsystems in 2002), Afara Websystems21

Honors and recognition

  • ACM Fellow · Association for Computing Machinery, 20071
  • IEEE Fellow · Institute of Electrical and Electronics Engineers, 20071
  • Harry H. Goode Memorial Award · IEEE Computer Society, 20181
  • Member of the National Academy of Engineering · National Academy of Engineering, 20211
  • Member of the American Academy of Arts and Sciences · American Academy of Arts and Sciences, 20221
  • Eckert-Mauchly Award · ACM and IEEE Computer Society, 20231

More sourced profiles at the same organization, in the same field, or from the same school.

Is this you?

Profiles cover public professional work only, and every line cites a source. If something is out of date, missing or wrong, send a correction with a link to an official page and we will update it. Suggest a correction

Profile on USASIAdd this badge to your website or GitHub profile README. It links back to this page. It is not an endorsement or a rating.

Markdown (for a README)

[![Kunle Olukotun — Profile on USASI](https://unitedstatesofamericasuperintelligence.com/badges/profile.svg)](https://unitedstatesofamericasuperintelligence.com/people/kunle-olukotun/)

HTML

<a href="https://unitedstatesofamericasuperintelligence.com/people/kunle-olukotun/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/profile.svg" alt="Kunle Olukotun — Profile on USASI" height="20"></a>

This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.

References · reviewed Oct 21, 2026

  1. 1.
    Kunle Olukotun — Stanford Profiles (external site: profiles.stanford.edu)

    Stanford University · Official page · accessed Oct 21, 2026 · evidence reviewed Oct 21, 2026

  2. 2.
    SambaNova team (external site: sambanova.ai)

    SambaNova · Official page · accessed Oct 21, 2026 · evidence reviewed Oct 21, 2026

  3. 3.
    About SambaNova (external site: sambanova.ai)

    SambaNova · Official page · accessed Oct 21, 2026 · evidence reviewed Oct 21, 2026

  4. 4.
    SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts (arXiv 2405.07518) (external site: arxiv.org)

    arXiv · Paper · published May 13, 2024 · accessed Oct 21, 2026 · evidence reviewed Oct 21, 2026

  5. 5.
    Infrastructure for Usable Machine Learning: The Stanford DAWN Project (arXiv 1705.07538) (external site: arxiv.org)

    arXiv · Paper · published May 22, 2017 · accessed Oct 21, 2026 · evidence reviewed Oct 21, 2026

Support Us

Help keep USASI useful.

Optional. No USASI account required. Payment takes place on the linked provider’s website (Buy Me a Coffee).

About supporting this project