Kunle Olukotun

Oyekunle Ayinde "Kunle" Olukotun is the Cadence Design Systems Professor in the Stanford School of Engineering, Professor of Electrical Engineering and Computer Science at Stanford University and the director of the Stanford Pervasive Parallelism Lab.[1] Olukotun is known as the “father of the multi-core processor”, and the leader of the Stanford Hydra Chip Multiprocessor research project.[2][3] Olukotun's achievements include designing the first general-purpose multi-core CPU,[4] innovating single-chip multiprocessor and multi-threaded processor design,[5][6] and pioneering multicore CPUs and GPUs, transactional memory technology and domain-specific languages programming models.[7][8][9] Olukotun's research interests include computer architecture, parallel programming environments and scalable parallel systems, domain specific languages and high-level compilers.[10][11]

Kunle Olukotun
Born
London, England
Alma materUniversity of Michigan (MS, PhD)
Calvin College (BS)
Known for
Awards
Scientific career
Fieldshigh-performance computer architecture; parallel computing
InstitutionsStanford University
Doctoral advisorTrevor N. Mudge

Education

Olukotun did his undergraduate studies at Calvin College,[12] in Grand Rapids, Michigan. He earned an MS (1987) and PhD (1991) from University of Michigan, in Computer Science and Engineering. His advisor was Trevor N. Mudge.[13]

Career

Olukotun joined Stanford's Department of Electrical Engineering in 1991. While at Stanford, Olukotun became the leader of the Stanford Hydra chip multiprocessor (CMP) research project which allowed for the development of multiprocessors with support for thread-level speculation.[14] In 2000, he founded Afara Websystems,[15] a company that designed and manufactured high-throughput, low power processors for server systems with chip multiprocessor technology. Afara was purchased by Sun Microsystems in 2002.[2] The Afara multicore processor Niagara, developed by Olukotun was acquired by Sun. Niagara derived processors currently power all Oracle SPARC-based servers and have generated billions of dollars of revenue.[9] While at Sun, Olukotun was one of the architects of the 2005 UltraSPARC T1 processor.[16]

In 2017 Olukotun and Chris Ré founded SambaNova Systems. SambaNova Systems is developing a next-generation computing platform to power machine learning and data analytics.[17] Olukotun now leads the Stanford Pervasive Parallelism Lab, which focuses on making heterogeneous parallel computing easy to use, and he is a member of the Data Analytics for What’s Next (DAWN) Lab, which is developing infrastructure for usable machine learning.[8]

Research

Olukotun's research focus is in computer architecture, parallel programming environments and scalable parallel systems, domain specific languages, and high-level compilers.

Olukotun leads the Stanford Hydra chip multiprocessor (CMP) research project, revolutionizing computing by bringing multi-core technology to consumers and high-end computing systems.[18]

In the mid-1990s, Olukotun and his co-authors argued that multi-core computer processors were likely to make better use of hardware than existing superscalar designs.[19]

In 2008, Olukotun returned to Stanford, and founded the Pervasive Parallelism Laboratory at Stanford after gathering US$6 million in funding from several computer-industry corporations.[20] His recent work focuses on domain-specific programming languages that can allow algorithms to be easily adapted to multiple different types of parallel hardware including multi-core systems, graphics processing units, and field-programmable gate arrays.[21]

Olukotun is also a member of the board of advisors of UDC, a Nigerian venture capital firm.[12] He was elected as a Fellow of the Association for Computing Machinery in 2006 for his "contributions to multiprocessors on a chip and multi threaded processor design".[22] He became a Fellow of the IEEE in 2008.[23]

Olukotun has used several words from his Yoruba heritage in his research. Afara, the name of the company he founded, means "bridge" in the Yoruba language, and he has named his server at Stanford Ogun after the Yoruba god of iron and steel, a play on words since large computers are frequently called big iron.[24]

Olukotun directs the Stanford Pervasive Parallelism Lab (PPL) which seeks to proliferate the use of parallelism in all application areas. He is also a member of the Data Analytics for What's Next (DAWN) Lab.[25]

Olukotun holds 12 U.S. patents.[26] He has published more than 150 scientific papers and wrote two textbooks.

Awards and Honors

  • IEEE Computer Society Harry H. Goode Award, 2018[8]
  • Michigan Engineering Alumni Merit Award, 2017[27]
  • ACM Fellow, 2006 [28]

Books

  • S. W. Keckler, K. Olukotun, and H. P. Hofstee, Multicore Processors and Systems (Springer Publishing Company, Inc., 2009).
  • K. Olukotun, L. Hammond, J. Laudon, Chip Multiprocessor Architecture: Techniques to Improve Throughput and Latency, Synthesis Lectures on Computer Architecture (Morgan Claypool Publishers, 2007).

References

  1. "Kunle Olukotun's Profile | Stanford Profiles". profiles.stanford.edu. Retrieved 2020-09-20.
  2. "SambaNova Systems Announces $150M Series B From Intel Capital and GV to Advance Its Breakthrough AI Platform". AP NEWS. 2019-04-01. Retrieved 2020-09-20.
  3. "Stanford profs' AI hardware startup scores $250M at unicorn valuation". www.bizjournals.com. Retrieved 2020-09-20.
  4. Nayfeh, B.A.; Olukotun, K. (September 1997). "A single-chip multiprocessor". Computer. 30 (9): 79–85. doi:10.1109/2.612253. ISSN 1558-0814.
  5. "Stanford grabs $6m to shape the future of software". www.theregister.com. Retrieved 2020-09-20.
  6. "SDSC Technology Forum with SambaNova Systems". UC San Diego Office of Innovation and Commercialization. Retrieved 2020-09-20.
  7. "DAWN: Data Analytics for What's Next - A Stanford University Industrial Affiliates Program" (PDF). Retrieved 2020-09-20.
  8. IEEE Harry H. Goode Award
  9. "Kunle Olukotun | IEEE Computer Society". Retrieved 2020-09-20.
  10. EE faculty listing, CS faculty listing, and (broken link) Pervasive Parallel Laboratory team listing Archived 2011-08-25 at the Wayback Machine, Stanford U., retrieved 2018-08-15.
  11. "For Black History Month, CSE Spotlights Faculty and Alumni in Academia= eecs.umich.edu". May 5, 2012. Retrieved November 9, 2019.
  12. About the company, UDC, retrieved 2011-04-01.
  13. The dates of his PhD vary by source. His personal web site and Stanford Engineering faculty profile (retrieved 2018-08-15) state it as 1991. It is also 1991 according to Oyekunle A. Olukotun at the Mathematics Genealogy Project. In the entry for his dissertation in the ACM digital library, the year is stated as 1992.
  14. "Kunle Olukotun". arsenalfc.stanford.edu. Retrieved 2020-09-20.
  15. Wayback Machine - www.afara.com
  16. Kongetira, P.; Aingaran, K.; Olukotun, K. (2005), "Niagara: a 32-way multithreaded Sparc processor", IEEE Micro, 25 (2): 21–29, doi:10.1109/MM.2005.35, S2CID 14455648.
  17. SambaNova Systems/News
  18. Alum Startup Collects $56M in Funding for AI Chip Research, 2018
  19. Olukotun, Kunle; Nayfeh, Basem A.; Hammond, Lance; Wilson, Ken; Chang, Kunyung (1996), "The case for a single-chip multiprocessor", Proc. 7th ACM Int. Conf. Architectural Support for Programming Languages and Operating Systems (ASPLOS-VII), pp. 2–11, doi:10.1145/237090.237140, S2CID 6595171.
  20. Vance, Ashlee (April 30, 2008), "Stanford grabs $6m to shape the future of software", The Register.
  21. PPL Projects Archived 2011-08-08 at the Wayback Machine, retrieved 2011-04-01.
  22. Oyekunle A Olukotun ACM Award Winner page, ACM, retrieved 2018-02-18.
  23. IEEE Fellows directory, retrieved 2011-04-01.
  24. Irele, Abiola; Jeyifo, Biodun (2010), The Oxford Encyclopedia of African Thought, 1, Oxford University Press US, p. 197, ISBN 978-0-19-533473-9. See also an email from Olukotun explaining the name, 2006, reproduced at Cognitive Diary.
  25. Stanford DAWN Research Project website
  26. Justia.com
  27. Michigan Engineering Alumni Merit Award, 2017
  28. ACM Fellow, 2006
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.