Olukotun, a pioneer of multi-core processors, is a professor of electrical engineering and computer science at Stanford University, and director of the Pervasive Parallelism Laboratory at Stanford who led the Stanford Hydra research project which eventually gave birth to the first chip multiprocessors.
He dared to think differently
In 1994, when programmers figured that whatever code they wrote would run at least 50 percent faster on a ’95 machine and 50 percent faster still on a ‘96 system and therefore coding would continue as it always had with instructions designed to be executed one after the other.
Olukotun was skeptical. Microprocessors of the day couldn’t scale up as efficiently as you’d expect through the mere addition of ever more and ever faster transistors, the two things that Moore’s Law provided.
And true enough the rising density of transistors on a chip intensified the hot spots in CPUs. This, more than the resource-to-performance ratio was the problem that seemed most likely to stop Moore’s Law in its tracks. Intel engineers also showed that if trends in microprocessors were to continue, by 2010 they’d burn as hot as the surface of the sun.
Olukotun’s answer in1998 was Hydra, a processor whose parallelism came not from redundant circuits within a single complex CPU, but from building four copies of a simpler CPU core on one chip. This saves on interconnects and the time lost casting instructions out and reeling answers back in. Hydra utilizes parallel processing without all the delay-inducing complexity. His thinking was way beyond the times, slowing down the CPU’s clock and adding more cores. That way, more is gained from the extra parallelism than that lost from the slower processing making chips to gobble less power and generate less heat. In his words “ We wrapped up the hardware portion of the project and declared victory.
In 2000, Olukotun founded Afara Websystems, a company that designed and manufactured multi-core SPARC-based computer processors for data centers. Afara (meaning ‘bridge’ in Yoruba) was purchased by Sun Microsystems in 2002 and the intellectual property became the foundation of the CoolThreads line of processors. While at Sun, Olukotun was also one of the architects of the 2005 UltraSPARC T1 processor.
New Vision, New Strides
In 2008, Olukotun returned to Stanford, and founded the Pervasive Parallelism Laboratory at Stanford to help shape the future of software, as he did with hardware. 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.
In 2012, Professor Olukotun and two colleagues won a grant of $1.3 million to develop core techniques and software libraries for high-throughput DNA sequencing to address challenges in human genetics and metagenomics.
Olutokun’s contributions to multiprocessors on a chip and multi threaded processor designed to lower the energy consumption of server computers is testament to the visionary Nigerian spirit; one always seeking answers to better humanity. Olukotun embodies the true Nigerian spirit of invention and innovation.