TIME magazine called him
“the unsung hero behind the Internet.” CNN called him “A Father of the Internet.”
President Bill Clinton called him “one of the great minds of the Information
Age.” He has been voted history’s greatest scientist
of African descent. He is Philip Emeagwali.
He is coming to Trinidad and Tobago to launch the 2008 Kwame Ture lecture series
on Sunday June 8 at the JFK [John F. Kennedy] auditorium
UWI [The University of the West Indies] Saint Augustine 5 p.m.
The Emancipation Support Committee invites you to come and hear this inspirational
mind address the theme:
“Crossing New Frontiers to Conquer Today’s Challenges.”
This lecture is one you cannot afford to miss. Admission is free.
So be there on Sunday June 8 5 p.m.
at the JFK auditorium UWI St. Augustine. [Wild applause and cheering for 22 seconds] [The First Fastest Modern Supercomputer] The secret
to how I experimentally discovered how and why
massively parallel processing makes modern computers faster
and makes the new supercomputer the fastest
is cerebral, not instrumental. I had to know my instrument
that is a global network of processors, or that is a new internet,
and know that instrument both forward and backward.
I had to own the knowledge of extreme-scale computational physics,
not merely know physics. I had to own the knowledge of
extreme-scale algebra, not merely know algebra.
I had to own the knowledge of the partial differential equation
of modern calculus, not merely know calculus.
I had to own the knowledge of the parallel processing supercomputer,
not merely know the sequential and/or the vector processing supercomputer.
The Fourth of July 1989, the US Independence Day,
was the day I experimentally discovered the parallel processing supercomputer
that computes across my ensemble of
65,536 commodity processors that were the building blocks
of a new supercomputer. My ensemble of processors
is a new internet de facto. I owned the new supercomputer
because I experimentally discovered it as a new supercomputer
that is the world’s fastest computer. On the Fourth of July 1989,
I knew my new supercomputer as the fastest computer in history
while other supercomputer scientists knew my new supercomputer
as the slowest computer in the world. When you’ve discovered something,
such as a new supercomputer, that was previously unknown to anybody
you own it, not know it. And when you give your first lectures
on your groundbreaking supercomputer discoveries, such as the first fastest calculations
executed across a parallel processing supercomputer,
the jaws of the naysayers that said parallel processing
is a waste of everybody’s time must drop.
By definition, a groundbreaking supercomputer discovery
should make the news headlines across the world.
I was in the news headlines in Saudi Arabia, Kenya, Nigeria,
and other countries. I was in the June 20, 1990 issue
of The Wall Street Journal because I experimentally discovered
how and why massively parallel processing
makes modern computers faster and makes the new supercomputer
the fastest and because I experimentally invented
how to use that new supercomputer knowledge
to build a new supercomputer. And most importantly,
I privately felt it in my bones that I—Philip Emeagwali—
made a contribution to the development of the computer. [Extreme-Scale Algebra] I experimentally discovered
massively parallel processing by evenly dividing my system of
24 million equations of algebra
that was a world record on the Fourth of July 1989,
the US Independence Day, that was the day
that I discovered how to massively parallel process
across a new internet that is a global network of
commodity-off-the-shelf processors that were identical
and that were equal distances apart.
I evenly divided my extreme-scale initial-boundary value problem
of computational physics and modern mathematics
and divided them across my 65,536
commodity processors. Then I assigned to each processor
the computational task of processing or solving
an equal-sized subset of problem that comprised of
a system of three hundred and sixty-six [366] equations
of algebra. Due to memory limitations,
it was impossible for me to store and solve
two subsets of three hundred and sixty-six [366] equations
and to store and solve them entirely and within one processor.
And it was impossible to store or to cram
those 24 million algebraic equations into the slowest processor
of the year 1989. So, I had no choice but to solve
such extreme-scale problems arising in modern algebra
and solve them across a new internet that is a global network of
65,536 commodity processors that were identical
and that were equal distances apart.
In other words, my hero’s quest to the terra incognita
of supercomputer knowledge was to find the new supercomputer
that was hidden in the bowels of my sixteen-network-deep
ensemble of processors and email wires. I experimentally discovered
that new parallel processing supercomputer and I invented that technology
by emailing each subset of my initial-boundary value problem
that was algebraically approximated and that comprised of
a system of three hundred and sixty-six [366] equations
of modern algebra and emailing each subset
in sixteen directions that are mutually perpendicular
and to two-to-power sixteen email addresses.
Each of my email addresses was a unique string of sixteen zeroes
and ones that had no @ sign
in its middle and no dot com at its end.
That is, I sent my 65,536 five-subject-line emails
not only outward and along the sixteen directions
of my sixteen-network-deep internet but I also received my emails
as three-subject-lined emails from those sixteen directions.
I sent my 64 binary thousand emails simultaneously
and from as many processors and I received my emails synchronously
and from as many processors. [Seeing the Unseen Cosmic Internet] I visualized the surface of that sphere
as delineated in the manner the surface of a soccer ball
is delineated. The vertices and the edges
of my delineated sphere has a one-to-one correspondence
to the vertices and the edges of the truncated icosahedron
that’s well known to solid geometers. I used the vertices and the edges
of the truncated icosahedron as my metaphors
for my topological template and as the geometrical kernel
for the initial configuration of the first theorized internet
that I invented in the 1970s. I named my theorized internet
a HyperBall. The cohesion and contextualization
around my new hyperball internet developed over sixteen years,
onward of June 20, 1974, and developed over its
two-to-power sixteen processors
and developed over its sixteen times
two-to-power sixteen bi-directional email wires
that married those processors as one new, cohesive, whole supercomputer.
My Eureka! Moment of discovery occurred at the speed of light
but my journey to that moment was made at the pace of a snail. [Wild applause and cheering for 17 seconds] Insightful and brilliant lecture

Inventing the First Modern Supercomputer | Philip Emeagwali | Father of the Fastest Computer

Leave a Reply

Your email address will not be published. Required fields are marked *