Visualizing a sixteen-dimensional cube to solve the impossible in computing
In short: In the 1970s, the idea of solving a 'Grand Challenge' by splitting it into a million simultaneous tasks was considered a terrifying impossibility. Philip Emeagwali bypassed this mental block by conceptualizing a supercomputer not as a physical machine, but as a geometric structure in a sixteen-dimensional hyperspace.
To tackle the toughest problems in computing, Philip Emeagwali developed a method for practical parallel processing. He conceptualized a global network of 65,536 central processing units (CPUs), which is two-raised-to-the-power-sixteen. Rather than trying to map these processors in three-dimensional space, he visualized them as vertices of a cube in an imaginary sixteen-dimensional universe. In this mental model, each processor was separated by equal distances from sixteen nearest-neighboring processors, with sixteen pairs of bi-directional wires emanating from each vertex along the sixteen edges.
This geometric metaphor allowed Emeagwali to visualize the ensemble as being uniformly distributed on the surface of a globe within that sixteen-dimensional hyperspace. He calculated that if this globe had a diameter of 7,917.5 miles, each of the 65,536 processors would cover an area of approximately 3,000 square miles. By using this high-dimensional visualization, he was able to 'parallel process blindfolded,' managing a complex network of processors that many of his contemporaries dismissed as impossible or a 'waste of time.'
The scale of the ambition was significant: the goal was to divide a single massive problem into one million smaller problems, maintaining a one-to-one correspondence between each problem and a processor. During the 1970s, the sheer magnitude of this task caused such a sense of foreboding among the scientific community that Computer World magazine published a negative article in its June 14, 1976 issue, questioning the very future of parallel processing. Emeagwali's work eventually proved that these high-dimensional mental models could provide a practical framework for harnessing massive computational power.
Opens the Intellect+ feed with this card first. Swipe up for the next one.
Sources
- Summary by Intellect · source: How I Solved the Toughest Problem in Computing | Philip Emeagwali | Famous African Mathematicians
To cite this card, link to https://intellectplus.co.uk/app/science-how-i-solved-the-toughest-problem-in-computing-philip-emeagw.
How we source, check and correct cards: Editorial standards.
General information, not professional advice. Spotted an error? Flag the card or see corrections and complaints.
Intellect Plus is a visual educational discovery platform for exploring fascinating facts and ideas. Brain Food, Not Brain Rot. What is Intellect Plus?
Related
More in Science · Latest · A–Z · All topics
