Father of the Internet | Philip Emeagwali | Nigerian, African | Black Inventions and their Inventors


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] [Philip Emeagwali Internet] I’m Philip Emeagwali.
Parallel supercomputing is an entirely new approach
to modern computer science. Yet, there is a limit
to the theoretically unlimited speed of the parallel supercomputer.
Looking back, in 1946 the fastest computer in the world
used only one scalar processing unit. In 1988, the fastest computer
in the world still computed with only one
vector processing unit. Shortly after the U.S. Independence Day of
1989, the media reported that an African supercomputer wizard
in the United States of America had discovered
how the most massively parallel supercomputer ever built
can massively compute with 65,536 commodity processors
and solve 65,536 computational physics problems
and solve them simultaneously. Nine in ten supercomputer cycles
are executed while solving extreme-scaled systems
of equations of algebra and physics. I had figured out
how to finesse my 64 binary thousand processors, enabling them to communicate and collaborate
to reduce the time-to-solution of extreme-scale systems of equations
of algebra—and to reduce that time-to-solution
from 65,536 days, or 180 years, on one isolated processor
to just one day across an ensemble of 65,536 processors. That new knowledge enabled
those processors to compute quickly and accurately
and to make the impossible-to-solve systems of equations of
extreme-scale algebra possible-to-solve.
I introduced how to use that new knowledge in algebra
and thus build digital replicas of petroleum reservoirs
and the Earth’s climate. I want to be remembered
as the first person to witness the transition
from the computer that did one thing at a time to the supercomputer
that did many things at once. I believe that our children’s children
will coin a new word for their supercomputers.
They will invent supercomputers that are science fiction to us. I discovered a new way of thinking
about the new fastest supercomputer and about the supercomputer
of tomorrow not as a computer per se
but as a global network of tightly-coupled processors
that is an internet. My discovery was processor-agnostic
and was a blueprint for a never-before-seen internet.
The invention of a faster supercomputer is a milestone of human progress.
That invention made some impossible-to-solve problems
arising in physics, algebra, and calculus possible-to-solve. [American Newspaper Mention of Philip Emeagwali
in 1974] I’m Philip Emeagwali. I remember the day
I first programmed a supercomputer. It was June 20, 1974.
I remember that date, in part, because I was on the cover of a local newspaper
that was published three weeks later and because then U.S. President
Richard Nixon was forced to resign 18 days later.
Back in mid-July 1974, the half dozen Nigerians in Polk County
of Oregon were proud to see my photo
on the cover of their local newspaper. That newspaper was on the newsstands
of the Oregonian cities of Monmouth and Independence.
The Nigerians that read that article came to congratulate me.
Nigerians crowded into my tiny one-room studio apartment
that was at 195A South Knox, Monmouth, Oregon.
That evening, we talked about the recent resignation
of then U.S. President Richard Nixon. That evening we went to see
a performance in Monmouth (Oregon) that was delivered
by the mentalist called “The Amazing Kreskin.”
I remember the day my discovery of practical parallel supercomputing
was highlighted by The Wall Street Journal—and remember it
as June 20, 1990— not because I was in The Wall Street Journal per se
but because I started programming conventional supercomputers exactly sixteen years earlier—on
June 20, 1974—and at 1800 SW Campus Way, Corvallis, Oregon, United States.
I remember by association, not memorization, and for that reason,
friends say that I have a photographic memory,
an elephant memory called an “eidetic memory.” [Contributions as a Father of the Internet] I was asked: “How did Philip Emeagwali
become a father of the Internet?” When I began supercomputing,
back on June 20, 1974, in Corvallis, Oregon, United States,
I did not embark on a quest to become a father of the Internet.
But if the father of the airplane is the person that invented
the first airplane then the father of the Internet
should be the person that invented the first internet. I am the only father of the Internet
that invented a new internet. And I am known as the first person
to program a new internet that I visualized
as a new global network of 64 binary thousand processors
that I also visualized as being equal distances apart
from each other. Those 65,536 processors
had separate memories from each other
with each processor operating its own operating system.
It made the news headlines in 1989 that I discovered that new internet
to be a virtual supercomputer. My physical experiments across
my ensemble of tightly-coupled commodity-off-the-shelf processors
gave me the street cred that is akin to that of the prophet
that became a political prisoner or that of the poet
whose wife committed suicide. [What is Philip Emeagwali Famous For?] I’m Philip Emeagwali.
Students writing school reports on Great Inventors often ask? “What is Philip Emeagwali known for?” In abstract geometrical terms,
I’m known for defining and delineating the technology called parallel processing
and for precisely describing it as the vital technology
that enables supercomputing across the surface of a globe.
That globe is embedded within a sixteen-dimensional hyperspace.
And I’m known for discovering that supercomputer
as a never-before-seen internet that is a new global network of
two-raised-to-power sixteen, or 65,536, tightly-coupled processors
that were identical to each other that shared nothing between each other
and with each processor operating its own operating system.
Back in 1989, I was in the news for discovering
practical parallel processing, the technology
that enables the modern supercomputer to solve many real-world problems
at once, instead of solving only one problem
at a time. Massively parallel processing
enabled me to solve one grand challenge problem
of mathematical physics that is an ensemble of
65,536 challenging problems of computational physics
and solve them synchronously. Loosely speaking and in theory,
the computer that is powered by only one processor
can solve a grand challenge problem that the parallel supercomputer
that is powered by one billion processors
can solve. However, the computer takes
one billion days, or nearly three million years,
to solve a grand challenge problem that the parallel supercomputer
takes only one day to solve. However, it took me sixteen years—onward
of March 25, 1974—to understand the physics, calculus, algebra,
and arithmetic, or to understand the human process
of solving that grand challenge problem. I had to understand that process
before I can instruct my ensemble of
64 binary thousand processors on how to massively parallel process
the grand challenge problem that I divided into
as 65,536 smaller problems. I was in the news because
I discovered practical parallel supercomputing
or how to solve many problems at once (or in parallel) and how to simultaneously
solve 65,536 problems across 65,536 tightly-coupled processors and solve them at the same time. [Philip Emeagwali Internet] What is the Philip Emeagwali Internet? Even after I had won the top prize
in supercomputing, and won it after sixteen years
of supercomputing, it took another sixteen years
for many supercomputer scientists to understand
that I had parallel processed across a new internet
and that I invented a new internet that was a new global network of
64 binary thousand processors. That sixteen year delay,
or adjustment period, was due to the fact that
parallel processing across a new internet was very difficult to understand. Parallel processing empowered me
to invent a virtual supercomputer, that is a new internet,
that retains the illusion of being a computer per se. On the blackboard, my new internet exists
almost to the point of complete abstraction.
My new internet is the invisible and the marginal technology
that haunts the transitory zones where the boundaries between mathematical
physics and computational physics
and between computing and supercomputing are blurred.
My definition of an internet is a metaphor that destabilizes
the textbook meaning of the word “computer,” that, in turn, was first used in print two
thousand years ago and first used by the Roman author
Pliny the Elder. I was asked: “Why is Philip Emeagwali
called a father of the Internet?” I am called
a father of the Internet because I am the only father of the Internet
that invented a new internet. [Why Are Great Inventors Rare?] Inventing a parallel supercomputer
that costs more than the annual budget of each of the forty poorest nations
in the world is tougher than writing a book of poetry,
and tougher, in part, because to invent is to make the impossible possible.
That’s why 50,000 fiction books are published each year
in the United States alone. That’s why 300,000 books
are published each year in the United States alone,
with the average book selling less than 250 copies.
In contrast, it took half a century to invent a new supercomputer
and to progress from the theorized supercomputer
of 1939 that, in theory, could solve a system of 29 equations of algebra.
It took 50 years to progress to the parallel supercomputer
of 1989 that made the news headlines when I used it to solve
24 million equations of large-scale algebra that was then a world record.
For this reason, inventing a new supercomputer
is rarer than writing a bestselling book. The number of self-published books
is over one million a year. You cannot read the same book
ten times. However, ten thousand programmers
can program the same supercomputer and do so at once.
If you’re a writer, you can write one thousand words
every day. If you’re a mountain climber,
you cannot become the first person to climb Mount Everest,
the highest mountain, and climb it every day.
You cannot break that historical record every day.
If you’re an inventor, you cannot invent a new internet
every day. The reason it is easier to write
than to invent is that the writer creates her literature,
hence the term “creative writer.” But it is impossible to have a
[quote unquote] “creative discoverer.”
You can write one page a day and complete a novel in one year.
But you cannot write one page a day and invent a new supercomputer
or invent a new internet and do so every year. Writing is infinite
but inventing is finite. Great scientific discoverers are rare
simply because ground breaking discoveries that are prerequisites
to becoming a great discoverer are also rare. Great scientific discoverers
are rare because they can only discover a thing that pre-exists
and the discoverer’s genius has nothing to do with the pre-existence
of her discovery. Great inventors are rare because
the inventor can only invent what’s possible to be invented. Great inventors are rare
because they cannot invent a law of physics
or invent a perpetual motion machine. [Changing the Way We Look at the Computer] Two thousand years,
the Roman author Pliny the Elder became the first person
to use the word “computer.” For two millennia, the name “computer”
remained the same. However, the basic premise
that defined the fastest computer has changed.
It changed from the supercomputer that computed
only one thing at a time, or in sequence, to the supercomputer that solved
millions of problems across millions of processors
and at once, or in parallel, and in a one-problem to one-processor
corresponded manner. The supercomputer
continuously re-defined itself, just as each generation
of supercomputer scientists re-defined itself. For simplicity and uniformity
and to avoid being a prisoner of details, I use the word “computer”
to describe computing machineries that my generation also call
CPUs or processors, nodes or cores,
parallel computers or quantum computers,
micro computers or supercomputers, and so on. What does
a supercomputer look like? A supercomputer
needs email wires that totaled 200 miles of cables.
A supercomputer can consume five thousand gallons of water
per minute and do so to stay cool.
A supercomputer can consume as much electricity
as ten thousand homes. A supercomputer can weigh
as much as a commercial airplane. Parallel processing
is the vital technology that powers the world’s most powerful supercomputers.
The use of parallel processing to solve the toughest problems
is limited to the imagination of supercomputer scientists
of tomorrow. What is parallel processing? Imagine that 200 million Nigerians
were invited to queue in only one line and to vote
at the rate of one voter per minute. This process will take
200 million minutes, or 380 years. Allowing only one person
to vote at a time and only at one polling station
is akin to solving only one problem at a time
and only at one processor. This sequential processing technology
was the basic knowledge behind the old one-processor technology
that powered the old supercomputers, including the conventional
supercomputers of the 1940s through the vector supercomputers
of the 1980s. On the Fourth of July 1989,
I discovered practical parallel processing and I discovered it
as the vital technology that now underpins
every supercomputer, and hopefully, will underpin every computer.
The incorporation of parallel processing technology
into every supercomputer is the reason the supercomputer
that was formerly the size of the refrigerator
now occupies the space of a soccer field. [Inventing Future Internets] I believe that a word that has been used
for two thousand years, is likely to be used
for another two thousand years. The word “computer”
was in human vocabulary for two thousand years.
The word “computer” could remain in our descendants vocabulary
for another two thousand years. But the computer of two thousand years from
today is expected to be vastly different
from the computer of today. I believe that
by the end of the 21st century that our children’s children
will develop a new internet technology that will encapsulate the internet
that I invented as processors that encircled a globe
and did so in the manner the Internet encircles planet Earth.
That new internet will be a new supercomputer
that will be a subset of the entire planetary-sized Internet.
The computer has always been and could always be
a machinery that is used to perform the fastest computations
and that solves the most computation-intensive problems,
and solves them automatically and, sometimes, in parallel.
By definition and by necessity, the supercomputer of the future
will be the planetary-sized computer that performs the fastest computations.
I believe that in a century, the internet,
will become the network of humans that will be directly wired into the
Internet and that automatically sends
and receives the fastest telepathic email communications,
as opposed to a network of only processors and computers
that it is today. [Philip Emeagwali Supercomputer] [Paradigm Shifting to Parallel Supercomputing] Parallel processing is the crown jewel
inside every supercomputer. Parallel processing
was the stone that was mocked as rough and unsightly
and rejected. Parallel processing originated
as a vague science fiction story that was dated February 1, 1922.
From 1958 to 1989, the usefulness of the parallel supercomputing
was debated in computer science literature.
Parallel processing was the stone the builders of supercomputers
rejected as rough and unsightly only for it to become the crown jewel
inside every supercomputer. My discovery of
practical parallel supercomputing that occurred on the Fourth of July 1989
made the news headlines because that new knowledge
was considered to be a paradigm shift, or a change in the way
we look at what makes the supercomputer super.
In the old way called sequential processing,
or vector processing, the supercomputer
had only one electronic brain. In my new way
called parallel processing, the supercomputer
is powered by 65,536 brains and can be powered by a billion brains.
That was how I invented the Philip Emeagwali Formula
for the world’s fastest supercomputer that then U.S. President Bill Clinton
described in his White House speech of August 26, 2000. [Contributions of Philip Emeagwali to Supercomputing] My signature invention
was the fastest supercomputer that was not a computer per se
but that was a new internet de facto that was a new global network of
65,536 processors that were tightly-coupled
to each other that were equal distances apart
from each other that shared nothing between each other.
Each processor operated it’s own operating system.
The discovery of the new knowledge that is used to make
the fastest computer super that occurred on the Fourth of July 1989
was my Eureka Moment! My contribution
to the development of the computer is this: I answered a grand challenge question
that was posed sixty-seven years earlier, back on February 1, 1922. [Evolution of Philip Emeagwali in Supercomputing] My invention timeline was this:
Back in 1970 in Nigeria I computed with a slide rule,
or a manually operated computer. Then on June 20, 1974,
at 1800 SW Campus Way, Corvallis, Oregon, United States,
I began programming an automatic, programmable supercomputer
that was rated at one million instructions per second
and ranked as the world’s fastest supercomputer when it was manufactured
back in December 1965. That supercomputer was only automatic within
only one processor. The Philip Emeagwali Formula
that then U.S. President Bill Clinton spoke about on August 26, 2000
was my discovery that we can solve a grand challenge
initial-boundary value problem that is the toughest
and the most important problem in science and engineering
and solve them automatically both within and across
each processor of my new internet that is a new global network of
65,536 processors that were tightly-coupled to each other.
My contribution to the development of the supercomputer is
this: I discovered
how to make the supercomputers of the 1940s through ‘80s
to become obsolete. Within the new supercomputer
that I discovered on the Fourth of July 1989, 65,536 processors
replaced the singular processor that computed alone. I invented
practical parallel supercomputing and I did so in two stages.
First, I programmed all my two-raised-to-power sixteen,
or 65,536, processors to automatically send and receive
my emailed codes and data and do so across
sixteen times as many email wires and to communicate
with each of my 64 binary thousand processors. Second, I programmed each processor
to automatically compute and do so simultaneously
and across all 65,536 processors that uniformly encircled a globe
as a new internet and encircled the globe
in the manner computers encircle the Earth. [Philip Emeagwali Internet] An “internet”
is a global network of processors that encircles a globe.
That internet might occupy the space of
a soccer field or might encircle the Earth itself.
That internet might be a supercomputer de facto
or might be the Internet itself per se. The technology defines the name,
not the name defines the technology. For my discovery
of practical parallel supercomputing that occurred on the Fourth of July 1989
that subsequently made the news headlines,
I defined my globe the way mathematicians prefer, namely, as
a sixteen-dimensional hypersphere within a sixteen-dimensional hyperspace.
I visualized the two-raised-to-power sixteen,
or 64 binary thousand, processors that I programmed and used to solve
grand challenge problems as being equal distances apart
and distributed across the fifteen-dimensional hypersurface
of that hypersphere. In contrast to my neatly organized
and interconnected processors, the computers
that outline the Internet that encircled the Earth
were added organically and incrementally
and are non-identical to each other and non-equidistant from each other.
And as a result of those irregularities and non-uniformities,
the email communications between the computers on the Internet
must be asynchronously sent and received
and for that reason, the Internet itself cannot be harnessed
and used to solve the grand challenge initial-boundary value problems
that is a recurring decimal in extreme-scale mathematics
and computational physics. The email messaging within my supercomputer
is processor-to-processor emailing, not your everyday
person-to-computer-to-computer-to-person emailing. I discovered
practical parallel supercomputing when I figured out
how to automatically program across my new internet
and how to communicate synchronously while computing simultaneously
and doing both as the precondition for recording the fastest computation
that can arise from within the fastest computer in the world. That [quote unquote] “fastest computer”
is not a computer per se. I discovered that the fastest computer
is a virtual supercomputer that is an internet de facto. I was in the news headlines because
I figured out how to harness the slowest processors in the world
and harness them around a new internet and do so to record speeds
in supercomputing that were previously unrecorded.
I invented the world’s fastest computer
that computes across a new internet that is a new global network of
two-raised-to-power sixteen, or 65,536, commodity-off-the-shelf processors
that were equal distances apart from each other
and that were identical to each other
and that were tightly-coupled to each other
and that tightly-encircled a globe
that is shaped like a sixteen-dimensional hypersphere
in sixteen-dimensional hyperspace. I also envisioned
my new global network of 64 binary thousand processors
as married together as one cohesive supercomputing machinery
and married together by sixteen times two-raised-to-power sixteen,
or 1,048,576, bi-directional email wires that were uniform and regular
and that were etched onto the fifteen-dimensional surface
of that globe that was shaped like a
sixteen-dimensional hypersphere in hyperspace.
In the modern configuration of supercomputers
and at one foot per email wire, those email wires
will total 200 miles of cables. This never-before-seen internet
is called the Philip Emeagwali Internet. My Eureka Moment—of 8:15
in the morning of the Fourth of July 1989—made the news headlines
around the globe in 1989 and did so because
I was the first person to discover how to compute simultaneously
and around a globe, or how to compute around
a new internet that is a new global network of
tightly-coupled processors that shared nothing between each other.
That is, I de facto invented the world’s fastest computer
and I invented it by discovering how and why
parallel processing is the vital technology
that will make every supercomputer super. My world’s fastest computation occurred
after I discovered how to communicate synchronously
and do so around a new global network of powers-of-two processors
that is called the Philip Emeagwali Internet. [My Struggles to Invent a New Internet] In the 1970s, my ideas
on massively parallel supercomputing were not fully formed.
For that reason, my earliest research reports
were mocked and ridiculed and I was off handedly dismissed
for espousing a beautiful theory that lacked
an experimental confirmation. In the 1970s and ‘80s,
massively parallel processing was dismissed
as a supercomputing theory that will never gain many adherents.
That is, the idea of harnessing the potential supercomputing power
of an ensemble of 65,536 processors was ludicrous.
That was the reason I was the only full time programmer
of that ensemble of two-raised-to-power sixteen processors.
For the ten years onward of 1979, my research report
on the then unorthodox parallel supercomputer
grew from a few pages to 1,057 pages.
In 1989, my 40-page highlights of my 1,057-page research report
won the top prize in supercomputing and made the news headlines.
Looking back to the 1980s in the U.S., a rejection pattern that repeated itself
dozens of times was this: I would get a telephone interview
for a job that was advertised and get it because
I had the most hands-on experience in supercomputing.
During the interview, the interviewer is taken aback
when he discovers that I am black and African-born.
In the 1970s and ‘80s, they were so few black
vector supercomputer scientists that even I would have been shocked
if I had seen a black African giving my lecture on
massively parallel supercomputing. I experienced this cognitive dissonance
the first time I attended a research seminar lecture
in Minneapolis, Minnesota, in 1992, that was delivered by
a very dark skinned mathematician of African descent.
She was known to the white mathematicians
but I—the only black mathematician in the audience—was the only person
in the auditorium that was in a state of denial.
It’s ironic that the only black male mathematician
in the audience of mathematicians was the only person
that denied that the black female mathematician
was a genius. Her lecture was on the ergodic theory
of dynamical systems. I presumed that she might not have
the command of her materials. She proved me wrong. Similarly, it was presumed that
it will be impossible to find a young, black,
and gifted mathematician that can solve the toughest problem
arising in extreme-scale computational mathematics.
That was the reason only one person
attended my research seminar on supercomputing
that I delivered in November 1982 in a large auditorium
that was a short walk from The White House, Washington, D.C.
My subsequent discovery of practical parallel processing
that occurred seven years later and that made the news headlines
was theorized in that supercomputing seminar
that all but one person boycotted. By the late 1980s, I realized that
my discovery that practical parallel processing
will become the vital technology that will underpin every supercomputer
will only be accepted if and only if, white supercomputer scientists
think that I am white. That was the reason I mailed
the research report on my invention of practical parallel supercomputing
to an independent committee of supercomputer scientists
that were 2,500 miles away in San Francisco, California.
The four members of that supercomputer committee
were appointed by the President of The Computer Society
that was the largest branch of the IEEE, the acronym for the Institute of Electrical
and Electronics Engineers that is the world’s largest
technical society. The Computer Society
was the world’s largest of its kind. That committee of foremost experts
in supercomputing were tasked with awarding the top prize
in supercomputing. The essence of the forty-page report
that I submitted to the IEEE and the detailed
1,057-page research report that won the top prize
in supercomputing is this: I discovered that
practical parallel processing will become the vital technology
that will underpin every supercomputer. The news of my invention
of practical parallel supercomputing spread like wildfire
and quickly made it to the dailies in many countries.
I discovered how to harness a new internet
that comprised of a global network of 65,536 processors
that encircled a globe and how to harness that new internet
to solve the toughest mathematical problems
arising in science and engineering and I discovered how to solve
grand challenge problems and solve them 65,536 times faster
than one processor solving the same problem alone. What is the future of the Internet? I believe that in one thousand years,
our descendants will not have computers around them.
Their computers will be within them, instead of around them.
Our post-human descendants of Year Million
will not need computers because they will be computers
that encircle and enshroud planet Earth.
Our post-human descendants will be half humans and half processors
that are akin to the cyborgs in science fiction movies. [Supercomputers Are Used in Africa] [Why I Won the Top Prize in Supercomputing] I won the top award
in supercomputing in 1989 and I did so for my contributions
to the development of the practical parallel supercomputer.
After years of being denied credit for my inventions,
I learned to take the credit for my invention
of practical parallel processing, the technology that underpins
every supercomputer. I owe it to the 12-year-old
writing an inventor biography on Philip Emeagwali
to keep the credit for my contributions that he or she is reporting on.
That was the reason I spoke up for myself back in 1989
and showcased my contributions to the development of the computer. [Efforts to Sabotage My Research] Success breeds jealousy and haters.
Becoming a famous supercomputer scientist
was like putting a large target on my back.
Like any prominent black inventor of the past, I had doubters
who envied me and worked tirelessly and anonymously to discredit my science.
In 1989, I won the top prize in the field of supercomputing
and did so for discovering how to solve a grand challenge problem
and, specifically, for figuring out how to solve them across
an ensemble of 65,536 processors. In 1989,
I was the supercomputer scientist behind my discovery of how to harness
a new parallel supercomputer and how to use that new technology
to solve the toughest real-world problems,
such as fluid dynamical calculations called general circulation models
of atmospheric and oceanic flows that are used to predict global warming
and petroleum reservoir simulators that are used to recover more crude oil
and natural gas that are buried one mile deep
and within an oilfield that is the size of a town.
As the inventor of practical parallel supercomputing,
I was the only person that could deliver the first public lecture
that answers that grand challenge question.
Being the inventor created deep grooves of my ownership
of practical parallel supercomputing and, most importantly,
I was the only supercomputer scientist of the 1980s
that can show someone else how to massively parallel process
and how to do so across a new internet that is a new global network of
65,536 processors. That command of materials
and deep knowledge of mathematics, physics, and supercomputing
and that control, via emails, of my 64 binary thousand processors
made my lectures on massively parallel supercomputing
more authoritative as well as compelling. [Why I Invented Practical Parallel Supercomputing
Alone] As a research mathematician,
I stood out because I was the only person
that recorded the world’s fastest speed in supercomputing
and did so while solving the initial-boundary value problem
of mathematical physics. That achievement was the reason
I was the only person that won the top prize
in the field of supercomputing and won it alone and did so when
up to fifty persons are teaming up to win that prize.
A century ago, the average scientific paper
had only one author. Today, the average scientific paper
has six authors. The paper on the experimental discovery of
the Higgs Boson had 3,061 co-discoverers
of the Higgs Boson. A boson is an elementary particle
that is believed to be responsible for all physical forces. [Supercomputers Are Also Used in Africa] For my country of birth, Nigeria,
poverty cannot be reduced by searching for
a huge deposit of crude oil and natural gas
and discovering it in Sokoto of the far northeastern region
of Nigeria. Poverty alleviation
cannot be achieved from recovering only 50 percent of that crude oil deposit
and then paying 40 percent of that 50 percent as exploration royalty
to a foreign oil company. That’s like recovering only 30 percent
of the crude oil and natural gas that was originally discovered.
Economic growth for oil producing nations,
such as Nigeria, resides in having the brain power
to earn the remaining seventy percent of the potential revenue
from the Niger Delta oilfields of the southeastern region of Nigeria. The
first step in alleviating poverty in Africa
is to increase Africa’s intellectual capital and do so by reversing
the brain drain from Africa to the United States,
and do so by also attracting skilled non-Africans,
such as African-Americans, to live and work in Africa,
and do so by Africans being at the frontier of human knowledge
and Africans being at that unknown world
where African innovators could imagine the unimaginable. [New Knowledge is the Lifeblood of Humanity] Discoveries and inventions
are to science and technology what new songs and new movies
are to the entertainment industries. The invention is to technology
what the new song is to music. Inventions make living easier
for everybody. Discoveries make the world a better place,
and a more knowledgeable one. Thank you. I’m Philip Emeagwali. [Father of the Internet] The Internet
has many fathers and mothers as well as aunts and uncles
that did not invent a new internet. The father of the Internet
should at least invent a new internet. I am called a father of the Internet because
I am the only father of the Internet that invented a new internet. [Philip Emeagwali Internet] [Inventing a New Internet From Science Fiction] Back in 1989,
I was in the news headlines because I was the first person
to discover how to parallel process
real-world problems and how to do so across
millions upon millions of processors that were tightly-coupled to each other.
In parallel supercomputing across my new internet
that was a new global network of 65,536 processors
that were identical to each other the most important knowledge
is to fully understand how to control and harness
every processor that was within my global network of processors.
Each processor operated its own operating system.
In 1989, I made the news headlines when I recorded
the maximum possible speed increase across my ensemble of
65,536 commodity-off-the-shelf processors. That parallel processed speed increase
of a factor of 65,536 that was then considered impossible
led to my discovery that parallel supercomputing
will be the vital technology that will make computers faster
and make supercomputers fastest. I discovered
practical parallel supercomputing and did so
by making a one-to-one corresponded and metaphorical mapping
and doing so from the vertices of the hypercube
to each processor and by making another
one-to-one corresponded mapping from the bi-directional edges
of the hypercube to my email wires. Unlike your cube,
my hypercube was defined in sixteen-dimensional hyperspace
and therefore has two-raised-to-power sixteen,
or 64 binary thousand, vertices and sixteen times as many,
or one binary million, bi-directional edges.
Programming 64 binary thousand tightly-coupled processors
to work together to forecast the weather was in the realm of science-fiction
and would have been dismissed as an act of insanity
and dismissed when I began programming supercomputers
back on June 20, 1974 at 1800 SW Campus Way,
Corvallis, Oregon, United States. But on the Fourth of July 1989
in Los Alamos, New Mexico, United States, I discovered
how to turn that science fiction into non-fiction
that is used to forecast the weather for your evening news.
As the first person to make the news headlines
for discovering practical parallel supercomputing,
I visualized the vertices and the edges of a hypercube
that were etched onto the surface of a hypersphere.
I invented the Philip Emeagwali Internet
as corresponding to the cut-out silhouette
that was my topological metaphor for the appearance of my new internet
that was a new global network of 65,536 processors
that were identical to each other and that were tightly-coupled
to each other. That new supercomputer
and that new internet were like tightly-conjoined twins
with only one superbrain. In 1989, I was in the news headlines because
I discovered practical parallel supercomputing,
and invented it as the vital technology that now underpins every supercomputer
and that enabled me to compute faster and across my new internet
and to compute faster than any supercomputer that ever existed.
I envisioned my new virtual supercomputer
as my new internet. My first visions of my new internet
began as a dark shape and as an outline
of a blank global network of processors that were connected with email wires
that were empty of messages. That dark shape of my new internet remained
visible inside my mind. It’s impossible for me to work alone
and program that new internet and do so without intellectually seeing the
exact positions in sixteen dimensional space
of each of my 65,536 processors. It’s also impossible
for me to send and receive email messages across
my 1,048,576 bi-directional email wires and do so correctly
without knowing, in advance, the exact positions in hyperspace
of my 65,536 processors. As the first
parallel supercomputer scientist, I was not trying to see
with my naked eyes, any of my 65,536 processors
or any of my 1,048,576 bi-directional email wires
that married my commodity processors together and did so to form a new internet
that tightly-circumscribed a globe in sixteen-dimensional hyperspace.
In contrast, I only saw my new supercomputer
and my new internet inside my mind, not with my naked eyes
as was often presumed. In a sense, I saw my new internet,
in its entirety, the way you saw our planet Earth
in its entirety and understood that it is not flat
and do so with you mind, not by encircling around the Earth
in a space craft. [Inventing a New Internet] [Email Messages Across a New Internet] I visualized how to email
my 65,536 computer codes as well as email
the as many sets of data that I used
at the mathematical physics core of my initial-boundary value problems.
That was how I pre-loaded each of my 65,536 processors.
I visualized how to continuously pump
my email messages across my new internet.
I visualized each of my email messages
as having five subject lines and having no message body
and as traversing across my new global network of
1,048,576 email wires that outlined my new internet.
In my mind, I sketched my silhouette as the dark shadow
of a new internet that encircles the Earth.
That shadow was created by the Sun. [Testbed for a New Internet] The partial differential equations
that I invented are the most advanced expressions
in calculus. Those partial differential equations
are far more abstract than the quadratic equation
and, for that reason, the layperson cannot scribble them across
the blackboard or solve them on or across
motherboards. The system of nine
partial differential equations that I invented are abstract
and are de facto invisible. However, I used those
partial differential equations as my extreme-scaled
computational testbeds for inventing a new computer, a new supercomputer, and a
new internet. In the lecture series
on my contributions to mathematics that I posted on YouTube dot com
slash emeagwali, I described in prose,
rather than in abstract mathematics, how I coded
my initial-boundary value problem that were governed by a system of
partial differential equations of calculus and I did so differently.
I did not code my initial-boundary value problem
for only one processor, as was done by other
computational mathematicians. I paradigm shifted
by parallel supercomputing my initial-boundary value problem
and doing so across a new internet that is a new global network of
64 binary thousand processors. That solitary act of repetitive coding
for each processor that defined and outlined that new internet
was my form of meditation. The very essence
of my ensemble of processors was to use emails to weave together
my new global network of 64 binary thousand processors
and to invent a new internet that is one whole cohesive
virtual supercomputer that is not a computer per se.
In my mind, those 64 binary thousand slowest processors
were de facto the fastest supercomputer that was my metaphor
for a futuristic, thought-provoking, and poetic internet.
That is, I rethought my new computer as my new internet, and vice-versa. [Supercomputing Across a New Internet] I visualized my email messages
as traversing across the interior of the sixteen
dimensional hyperspace and along the bi-directional edges
of the hypercube in that hyperspace. I gave form to that ensemble
and gave form to it as a never-before-seen internet.
For me, that new global network of processors
that were tightly coupled to each other that were equal distances apart
from each other and that shared nothing
between each other became a mathematicised
and abstracted internet that is a singular virtual supercomputer. [Inventing Philip Emeagwali Internet] I was in the news in 1989, and thereafter,
because I was the first person to parallel process across
a new internet that was a new global network of
65,536 processors that shared nothing between them.
I was the first person to theoretically discover that
no upper limit exists when parallel supercomputing across
an infinite number of processors. Put differently, my inspiration is this:
the science fiction of planetary parallel supercomputing across
the entire internet that encircled planet Earth
could become the non-fiction of our descendants.
I was the first person to discover
how to parallel process across a new internet
that I visualized as a small copy of the planet sized internet.
For that invention, that was conceived back in 1974
and completed in 1989, whenever the phrase
“father of the Internet” is mentioned, the first name
that Google suggests is “Philip Emeagwali.” [Philip Emeagwali Internet] The contributions
to the development of the computer that are the subject of school reports
are inventions that are paradigm shifting or that changed the way
we look at the computer. The objective criterion
for measuring contributions to the development of the computer
is fixed, namely, the fastest computation
that was executed by any means necessary.
My fastest computation that I discovered
on the Fourth of July 1989 was executed
by parallel supercomputing a grand challenge
initial-boundary value problem of extreme-scale computational physics
and solving it across a new internet that was a new global network of
65,536 processors that were tightly-coupled to each other
that were identical to each other that were equal distances apart
from each other but that shared nothing
between each other. My scientific discovery that occurred
on the Fourth of July 1989 was that parallel processing
will become the vital technology that will make
the modern supercomputer super. That discovery made the news headlines because
it will change the way we look at the computer.
I discovered that we should look at the modern computer
not as a computing machinery per se but as a new internet de facto.
That never-before-seen internet derives its supercomputer horsepower
by parallel processing its computational workload across
its millions of processors that were tightly-coupled to each other
with each processor operating its own operating system.
For me, Philip Emeagwali, that technological breakthrough
in massively parallel processing was the supercomputer news headlines that
crossed the sea, from San Francisco (California)
to Onitsha (Nigeria) and crossed the sea because
it broke new grounds of supercomputing across
65,536 tightly-coupled processors that equidistantly encircled
a globe that defined and outlined a new internet.
Back on June 20, 1974, at 1800 SW Campus Way,
Corvallis, Oregon, United States, I began programing the first computer
to be rated at one million instructions per second.
The first supercomputer was invented in 1946.
That first supercomputer was 100 feet long, 10 feet tall,
and 3 feet deep. So supercomputers were programmed for twenty-eight
years before I began to do so.
But those supercomputers only solved one problem at a time
instead of solving a billion problems at once.
But at 8:15 in the morning of the Fourth of July 1989
in Los Alamos, New Mexico, United States, I became the first person to
discover practical parallel supercomputing.
That discovery made the news headlines because it was said to be impossible
to parallel process a grand challenge problem
and do so across a new internet
that is a new global network of unlimited number of processors
that were tightly-coupled to each other and that shared nothing
between each other. The grand challenge problems
solved on supercomputers remain essentially the same.
But the value and size of the supercomputer market
has grown from seven million dollars back in 1946
to twenty billion dollars a year, or a factor of over 3,000.
The information technology (IT) market is five trillion dollars,
with more than 40 percent of that market in North America, primarily
in the United States where nearly two million skilled persons are
employed in the IT sector. The supercomputer that Japan
has on its drawing board will cost 1.25 billion dollars.
As a massively parallel supercomputer scientist
that came of age in the 1970s and ‘80s, I worked and walked alone because
I took the road less travelled. But I also got noticed more
because I did my parallel supercomputer research
under unusual circumstances that took me from Onitsha to Oregon,
back on March 23, 1974. In the 1970s and ‘80s,
no sub-Saharan African-born scientific researcher
was hired by any of the numerous U.S. nuclear research laboratories
where most supercomputing research was conducted. [Philip Emeagwali Internet] In 1989, I discovered that
a grand challenge problem can be divided into
millions of smaller, less challenging problems
and then, I further discovered that I could use as many email messages
to puzzle together those small problems into the original
grand challenge problem that I could then solve across
my new internet that is my new global network of
as many processors that each operated
its own operating system and that each shared nothing
with other nearest-neighboring processors. I’m Philip Emeagwali. Back in 1989,
I was in the news headlines because I discovered
how the slowest processors can be parallel processed
and harnessed to solve once-impossible-to-solve problems
and solve them at previously impossible speeds.
My discovery created a need for the parallel supercomputer.
My discovery of practical parallel supercomputing
made the news headlines because it was akin to discovering
an undiscovered continent of the unknown world of the
new computer and the new internet. [Inventing Philip Emeagwali Internet] [Contributions of Philip Emeagwali to Supercomputing] The use of 64,000 human computers
to parallel process the weather was published as a science fiction story
back on February 1, 1922 and published in the book titled:
“Weather Prediction by Numerical Process.”
The contribution of Philip Emeagwali to the development of the computer
is this: “I upgraded parallel supercomputing
from fiction to non-fiction.” So for sixty-seven years onward of 1922,
parallel processing was the big and unanswered question
of the field of computing and for that reason
the quest to answer it was described as the
Grand Challenge Problem of the field of supercomputing.
For sixty-seven (67) years onward of 1922, mathematical scientists attempted
to solve the toughest initial-boundary value problems
and to solve them by dividing each into smaller problems
that could be parallel processed with one-problem to one-processor correspondence
and mapped onto one million identical processors
that were tightly-coupled to each other. Until my discovery
of the Fourth of July 1989, progress in solving
such grand challenge problems and solving them
by parallel processing them was a modest factor of eight.
That factor was erroneously decreed by Amdahl’s Law
of diminishing returns expected from the increase
in the speed of supercomputers. My contribution to supercomputing
is this: I figured out
how parallel supercomputing works and that discovery changed the way
we look at the supercomputer that occupies the space of a soccer field
and changed the way we look at the fastest computer
that can be placed on your desk. [The New Internet of Philip Emeagwali] The computer is a machinery
that performs fast calculations. The massively parallel supercomputer
is the fastest computer. The Philip Emeagwali Internet
is a global network of commodity-off-the-shelf processors
that were identical to each other that were tightly-coupled to each other
that were equal distances apart from each other
that shared nothing between each other. Each processor operated
its own operating system. My contributions to knowledge is this: I discovered a new internet
that is a new global network of processors (or tiny computers)
that is not a computer per se but that is a supercomputer de facto. [Philip Emeagwali: A Father of the Internet] Who invented the internet? The Internet
has many fathers and mothers as well as aunts and uncles.
But only one father of the Internet invented a new internet.
The father of the Internet should at least contribute
new technological knowledge that pertains to the Internet
and do so by inventing a new internet.
I am called a father of the Internet because I am the only father of the Internet
that invented a new internet. I was asked:
“When the games are over, how will you want to be remembered?” What’s been around the longest
will stay around the longest. One million years ago,
our pre-human ancestors counted on their fingers and toes.
I believe that in a million years, our post-human descendants
will count across their Year Million internet.
I will be remembered the longest for my contributions
to computational mathematics that changed the way
we count and changed it from counting
only one thing at a time to counting a billion things at once.
I will be remembered for my contributions
that changed the way we looked at the computer
and changed it from one isolated processor computing only one
thing at a time to one billion processors
supercomputing for the parallel processed solution
of the toughest real world problems. We remember mathematicians
from three thousand years ago, if and only if,
their contributions to mathematics is still relevant.
We remember Euclid as the father of geometry
because geometry is taught in schools. We will remember the
computational mathematician that changed the way we count.
Since prehistoric times, our pre-human ancestors counted
only one thing at a time. I discovered that we could solve
real world problems by counting a billion things at once,
or by parallel supercomputing the toughest mathematical problems.
We will remember the father of the internet, if and only if,
the Internet is still relevant in Year Million.
I am the only father of the Internet that invented a new internet.
I will be remembered as the first parallel supercomputer scientist
that came of age on the Fourth of July 1989.
That is my legacy—and my contribution to human knowledge—
that changed the world of computers. [Letters From Refugee Camps] I was inducted by the United Nations into
its Gallery of Prominent Refugees. The United Nations distributed
posters of Philip Emeagwali to refugee camps in Kenya,
Rwanda, and Sierra Leone and I was getting emails
from those refugee camps inviting me to visit their camps. What is Philip Emeagwali famous for? I became known by word of mouth
and as follows: In 1989, a twelve-year-old
wrote a school inventor report on the contributions of
Philip Emeagwali to the development of the computer. That school
inventor report is discussed with her classmates
and at her family dinner table or during conversations with her younger friends.
The following year, those younger friends
are more likely to write school inventor reports
on Philip Emeagwali. That word of mouth spreading
of school inventor reports and its stickiness
is more effective than media mentions. Often, students forget
how to spell the name Philip Emeagwali but they have no problem remembering
to search for the Nigerian who invented the fastest computer
or the African who invented a new internet
that is a new global network of processors.
I became known via newspaper and magazine articles
that were published after my discovery of practical parallel supercomputing
that occurred on the Fourth of July 1989. I discovered
practical parallel supercomputing and discovered it
as the vital technology that will make the supercomputer super.
The first audience to discover my story were American school children
writing school reports on the theme: “Famous Mathematicians
and their Contributions to Mathematics.” Or “Great Scientists in History.”
Or “Great Inventors and Their Inventions.” Some of those children
wrote school reports on “Philip Emeagwali” and did so, in part,
because their father (or mother) wrote a school report on
“Philip Emeagwali.” The second audience
that discovered my contributions to science
were Nigerians and Africans in the continent and in the diaspora. [World’s Fastest Computing Across a New
Internet] Shortly after the Christmas of 1989,
in San Francisco (California), the office of the largest
technical organization, called the IEEE, as well as some other institutions
issued press releases that announced that I had discovered
practical parallel supercomputing and discovered it as the vital technology
that will power every supercomputer. And that I had invented
how to harness 65,536 processors to solve the toughest
initial-boundary value problems arising in mathematical physics
and that I had discovered how to solve
that grand challenge problem and solve it at the world’s fastest
supercomputer speeds and that I had solved the problem
at the then unheard of speed of 3.1 billion floating point
arithmetical operations per second. Those 1989 press releases
on my discovery of practical parallel supercomputing
were picked up by newspapers and magazines.
And I began getting requests for media interviews.
For the decade preceding 1989, I was mocked and made fun of
while I worked alone on parallel supercomputing.
But as I became famous those vector supercomputer scientists
that mocked and made fun of me and that refused to work jointly with me and
become my co-discover of practical parallel supercomputing
turned around and insisted that they will now become
my new best friend and that I should allow them
to become my co-inventors. Their motive was this: If they had collaborated with me
and did so for only one minute, they would have gone to the court
to fight for a share of the credit for my invention
of practical parallel supercomputing and for the invention
that I had already invented and invented without any contribution
from them. In the old style of supercomputing,
the conventional supercomputer solves grand challenge
initial-boundary value problems arising in extreme-scale
computational physics and takes forever
to solve them in a step-by-step fashion that is called serial computing.
On the Fourth of July 1989, I discovered a new way of solving
those grand challenge problems, namely, chopping them into a million
smaller, less challenging initial-boundary value problems
and then simultaneously solving those problems across
a million processors and solving them in a one-problem to one-processor corresponded
mapping that will result in a million fold
speed increase. I visualized my processors
as identical to each other and as equal distances apart
from each other and as interconnected
by identical email wires that were lying on the surface
of a globe that was represented by
a hypersphere in a sixteen-dimensional hyperspace.
In my July 4, 1989 physical parallel supercomputing experiment
that made the news headlines in 1989, I divided the grand challenge
initial-boundary value problem of simulating the flow of crude oil, injected
water, and natural gas across an oilfield
that is one mile deep and that is the size of a town.
I did so by dividing that oilfield into two-raised-to-power sixteen,
or 65,536, smaller oilfields. I emailed my supercomputer codes
and their companion data that I used to simulate
each of my smaller oilfields and emailed them to and from
sixteen-bit long email addresses and I emailed them along sixteen times
two-raised-to-power sixteen email wires.
That is, I emailed my data and codes across a new internet
and into each processor within my new global network of
64 binary thousand processors that were equal distances apart
and that were on the surface of a globe in the sixteenth dimension.
That was how I solved the grand challenge problem
of supercomputing and how I discovered
how parallel processing makes the computer faster
and makes the supercomputer fastest, and discovered
how to always manufacture the world’s fastest computer
and do so with the technology of massively parallel processing. I was born on August 23, 1954
in a small hospital in the British West African colony
of Nigeria. The first house that I lived in
was the Boy’s Quarter, a small house for servants,
that was associated with a bigger house within a compound on the right side of Oke-Emeso
Street that was at the intersection
of Oke-Emeso Street and Oba Adesida Road,
Akure, Nigeria, British West Africa. My mother, Iyanma Agatha Emeagwali,
had just celebrated her fifteenth birthdate and did so six days before I was born.
The precursor to the modern computer was eight years old when I was born.
In 1954, the British Colony of Nigeria had a population of 40 million.
And then had only 150 lawyers, 160 medical doctors,
and one trained engineer. When I was born, the word “computer”
was not in the Nigerian vocabulary. Even in the U.S.,
the word “supercomputer” was not in the vocabulary
of computer programmers of 1946 through 1967.
The word “supercomputer” was first used in 1967. [What Does Philip Emeagwali Internet Look
Like?] When I say [quote unquote]
“the Internet” I mean the global network of computers that
encircles planet Earth. When I say [quote unquote]
“an internet” I mean a global network of processors
that encircles a globe. I use the word “internet”
to describe my global network of commodity-off-the-shelf processors
that were tightly-coupled to each other that shared nothing between each other.
I visualized the emails that I sent to and received from
each of my sixty-four binary thousand processors as having travelled along my
1,048,576 email wires that I visualized as etched onto
the fifteen-dimensional hypersurface of a globe that is a hypersphere
in my sixteenth-dimensional mathematical hyperspace. The actual global circulation model
that is used for climate studies that inspired my invention
of my new internet that is that new global network of
65,536 processors was also defined around a globe
in three-dimensional physical space. The geophysical flows of air and water
that are at the core of global warming simulations
were modeled by using a set of laws of physics
that always includes the Second Law of Motion of physics
that was discovered three hundred and thirty years ago.
The Second Law of Motion was encoded into a system of coupled, non-linear,
time-dependent, and three-dimensional
partial differential equations that I discretized and reduced to
a system of equations of algebra that I parallel processed across
sixty-four binary thousand commodity-off-the-shelf processors
that were tightly-coupled to each other and that shared nothing
between each other. That is, I discovered
how to simulate the planetary motions of the air and water
that enshroud the Earth that is a globe of 7,917.5 miles
in diameter. I discovered
how to simulate and parallel process around a new global network of processors
that is a new internet and a new supercomputer de facto.
That was how I invented a new internet that encircled a globe
and how I invented that internet and used it to solve
a grand challenge initial-boundary value problem
that enshrouded a globe, namely, planet Earth.
At its mathematical physics core, that grand challenge problem
is an extreme-scaled computational physics code
developed for the high-resolution simulation that must be used
to predict global warming. In the geometry of higher dimensions,
the globe is defined and outlined by a hypersphere
that, in turn, is defined as a set of points at equal distance
from a given point called the center. In my physical experiment
that revealed the world’s fastest supercomputer
and revealed it on July 4, 1989, I visualized my 64 binary thousand commodity-off-the-shelf
processors that used high-speed interconnects
that comprised of one binary million email wires
as evenly distributed around a mathematical globe
in the sixteenth dimension that, in turn, was projected
and etched onto the two-dimensional surface
of a physical globe in the third dimension.
The hypersphere that I used to define my two-raised-to-power sixteen commodity-off-the-shelf
processors is my generalization of the sphere
to the 16th dimension. The hypercube
is the similar generalization of the cube, from the third dimension
to the sixteenth. I visualized my virtual supercomputer
not as a computer as others did but as a new internet
that is a new global network of processors. I was in the news because
I figured out how to harness my 65,536 processors
and how to command and control them to automatically send
and synchronously receive the codes and data
associated with my as many initial-boundary value problems
of mathematical physics. Those codes and data
travelled through sixteen times two-raised-to-power sixteen,
or one binary million, bi-directional email wires
that had a one-email-wire to one-hypercube-edge correspondence
to the as many bi-directional edges of the hypercube
in the sixteenth dimensional mathematical hyperspace.
By comparison, your everyday emails are manually sent by you
and delivered via a computer. Your email that traveled from Nigeria
to the United States, was routed across the globe,
or the internet. That internet encircled planet Earth
that is a globe that has a diameter of 7,917.5 miles.
In contrast, my emails around my global network of processors
were automated and synchronized across an ensemble of 65,536 processors
that I visualized as a new internet in the sixteenth dimension.
I visualized my new internet as defined across the surface of
a hypersphere (that is a globe in higher dimensions)
that, in turn, tightly-enshrouded a hypercube (that is a cube
in higher dimensions). I visualized the sixteen times
two-raised-to-power sixteen, or the one binary million,
bi-directional edges as projected onto
its fifteen-dimensional hypersurface. [What Does Philip Emeagwali Honeycomb Internet
Look Like?] The honeycomb
was the first of my two diagrammatic expressions
of my new global networks of commodity-off-the-shelf processors
that were identical to each other that were equal distances apart
from each other that shared nothing between each other
in with each processor operated its own operating system.
To others, my honeycomb and hyperball diagrams, represented a supercomputer.
But I emphasized that it was also a new internet
that is a new global network of processors that tightly circumscribed
a globe in three-dimensional space and in sixteen-dimensional hyperspace, respectively.
That distinction was pivotal. Those two inventions were the reasons
I became the most searched for and the recurring decimal
in discussions on the contributions of the black man
that invented a new internet. I’m Philip Emeagwali. I am the only father of the Internet
that invented a new internet. [My Journey to the Unknown World] The inventor discovered
the possibilities in the world of the impossible.
My quest for a never-before-seen massively parallel supercomputer
that was a new internet de facto was to discover
the possibilities in the world of the impossible
or to show that the impossible-to-compute
is, in fact, possible-to-compute. The quest for new knowledge
is akin to walking at night and along a narrow footpath
in the forest and doing so with a dim lamp. My massively parallel supercomputer research
was my personal quest for the new way to the unknown world of the
never-before-seen ensemble of millions of processors
that were identical to each other that were equal distances apart
from each other that outline and define a new internet
that is a virtual supercomputer de facto. In the 1970s and ‘80s,
I walked alone along that path and I was only guided by a dim lamp. Kwame Nkrumah said:
“Socialism without science is void.” And said:
“Forward Ever, Backward Never.” Kwame Nkrumah also said:
“We face neither East nor West; We face forward.” I say that: science
moves humanity forward ever. [The Crown Jewel of Supercomputing] Back on the Fourth of July 1989,
I discovered that a new internet that is comprised of
a new global network of the slowest 65,536 processors
can be harnessed and used to solve the toughest problems
arising in science and engineering and used to solve those problems
faster than any supercomputer. China copied that massively
parallel supercomputing technology and updated it
from my 65,536 processors to its world’s fastest supercomputer
that is powered by 10,649,600 processors.
Parallel processing is the crown jewel inside every supercomputer.
My discovery of practical parallel supercomputing
helped China to assembly some of the world’s fastest supercomputers.
That discovery is the vital technology that upgraded China
as one of the world’s supercomputing superpower. However, the race to build the world’s fastest
supercomputer is the race to knowledge,
not the race to the Moon. My discovery
of practical parallel supercomputing that occurred on the Fourth of July 1989
put the super into the supercomputer.
My discovery of practical parallel supercomputing
is akin to having 10,649,600 election polling stations in Nigeria
and having only nineteen voters queued at each polling station
and, consequently, completing the election
in nineteen minutes, instead of in 380 years.
That reduction of election time from four centuries of time-to-election
to merely twenty minutes is the basic principle
that changed the way we understand how to put the super
into the supercomputer. The discovery
of practical parallel supercomputing that occurred on the Fourth of July 1989
opened our eyes and enabled us to see the supercomputer in
a different way. [How Does the Supercomputer Benefit You?] How does the new
parallel supercomputer benefit you? The next time the weather forecast
made you reach for your umbrella, you did so because
the parallel supercomputer was used to make that forecast. The next time you drive your car,
you did so, in part, because the parallel supercomputer
was used to discover and recover the crude oil
that was refined as the fuel in your car. That is the reason one in ten supercomputers
are purchased by the petroleum industry. If you were evacuating your family,
and doing so in response to a tsunami flooding,
or an earthquake warning, then you should send a thank you note
to your parallel supercomputer scientist for enabling the tsunami
or earthquake forecast that saved your family’s lives. And if you own a self-driving car,
you should credit that technology to the parallel supercomputer
that is within your self-driving car that enables it to train itself over time. And that’s how
the new parallel supercomputer benefits you. Thank you. [What Are Supercomputers Used For?] I’m Philip Emeagwali. The modern computer has existed
for three-quarters of a century. The vector supercomputer has existed since
the 1970s. In 1989, the vector supercomputer
had a billion dollars in sale. Today, the vector supercomputer
has been replaced with the parallel supercomputer
that, in turn, has a market size of twenty billion dollars a year.
A massively parallel supercomputer that is on the Japanese drawing board will
cost 1.25 billion dollars. In real-world computational physics,
the supercomputer that costs 1.25 billion dollars
is an inexpensive alternative to physical experiments
that range from modeling the flow of blood
through the cardiovascular system to simulating the flows of crude oil
and natural gas that are flowing one mile deep
and flowing underneath the surface of the Earth
and flowing across a porous medium that is the size of a town.
It is far cheaper to simulate a petroleum reservoir
and do so without constructing a cumbersome physical scale model
of the Niger-Delta production oilfield of the southeastern region of Nigeria.
The extreme-scaled computational physicist
don’t actively inject water into the petroleum reservoir.
The computational physicist plays “what if” simulation scenarios
and plays that game with her parallel processed simulations of
the multi-phase flows of crude oil, natural gas,
and injected water. That high-resolution, extreme-scale
petroleum reservoir simulation that is massively parallel processed across
millions upon millions of commodity processors
enables the petroleum geologist to be confident about pinpointing
the locations of crude oil and natural gas. Back in 1989, I won the top prize
in the field of supercomputing and I won it for my contributions
to the parallel supercomputer. The proof that my discovery
was ground breaking was that it made the news headlines
and was highlighted in the June 20, 1990 issue of The Wall Street Journal.
Prior to my discovery of parallel supercomputing
that occurred on the Fourth of July 1989, I did not have a record
of making major scientific discoveries. Back in the 1980s,
computational scientists rejected my research
on the massively parallel supercomputer and did so, in part, because they could not understand
how I was able to message-pass computational fluid dynamics codes
and do so to and from my 65,536 processors.
Because message-passing was unknown and was not in the textbooks
of the 1980s, my parallel supercomputing research
was rejected by research mathematicians on the grounds that
it was not a subfield of mathematics. My parallel supercomputing research
was rejected by research physicists on the grounds that
it was not a subfield of physics. And computer scientists rejected
my parallel supercomputing research and did so because
its computational fluid dynamics components—such as modeling
the weather above and below the surface of the Earth—was also not
a subfield of computer science. That rejection was the reason
I was the only full time programmer and the only person
that developed the ability to parallel process across
an ensemble of 64 binary thousand commodity-off-the-shelf processors
that were tightly-coupled to each other that shared-nothing between each other
and that were identical to each other. But most importantly, I understood that
I had to record a speed increase of a factor of 65,536
that was a world record in supercomputer speedup.
I had to use that unprecedented speedup as my performance metric
that will put a specific number on my contributions
to the development of the modern supercomputer.
I did not merely solve my initial-boundary value problem
on a processor or a computer. The reason I was the cover stories
of top publications in mathematics was that I discovered how to solve
initial-boundary value problems arising in physics, calculus and algebra
and discovered how solve them across a new internet
that is a new global network of powers-of-two processors.
My new internet was a new supercomputer de facto
that is a million times more complex than a singular computer
that was powered by only one processor that was not a member
of an ensemble of processors. My discovery of that speedup
across processors is my contribution to the development
of the modern supercomputer. My contribution changed the way
we do computational physics and changed it
from sequentially processed small-scaled computational physics
to parallel processed extreme-scaled computational physics. My contribution
to the development of the supercomputer changed the way we compute
and changed it from slowly computing in sequence
to supercomputing in parallel. My contribution
to the development of the fastest supercomputer
changed the way we compute and changed it from
counting only one thing at a time
to counting up to a billion things at once. My contribution
to parallel supercomputing is a paradigm shift
in computer science. [Contributions to Modern Supercomputing] [Turning Science-Fiction to Non-Fiction] Parallel supercomputing
was vaguely mentioned as a science fiction
back on February 1, 1922 and in the book titled:
“Weather Prediction by Numerical Process.”
For seven decades, thereafter, parallel supercomputing
remained in science fiction until I discovered it
on the Fourth of July 1989 in Los Alamos, New Mexico,
United States. My contribution
to the development of the computer is this: I moved the parallel supercomputer
from science fiction books to science textbooks. I was the lone wolf supercomputer inventor
that discovered parallel processing.
My confidence as a parallel supercomputer scientist
did not come from vector supercomputer scientists
who, in the first place, believed that the massively parallel supercomputer
will forever remain a huge waste of everybody’s time.
My confidence that I could solve the toughest problem
arising in supercomputing came from within me
and from the command of materials that I possessed.
Confidence comes from being the most prepared
and the most knowledgeable. Progress does not always come from
always being right. Progress comes from
not fearing to be wrong. [Fact Versus Fiction] There is a great difference
between a scientific fact and a science fiction.
Back on February 1, 1922, parallel processing was theorized
for accurate weather forecasting but the technology was not then
a scientific fact but was a science fiction.
On July 4, 1989 and sixty-seven years
after parallel processing was described as a science fiction, I discovered that parallel
supercomputing is a scientific fact.
I once asked a friend, why he left journalism
to become a fiction writer. He said: “Journalism deals with facts
while fiction deals with truths.” In the 1970s and ‘80s,
my quest for the fastest supercomputer that was then hidden
in the unknown world of massively parallel supercomputing
was for a scientific truth, not a science fiction.
My new parallel processed way of counting one billion things
at once, and across as many processors
is a mathematical truth, not a mathematical fiction.
The writer is a generalist. The poet chisels words.
The novelist describes the human condition.
But it’s the scientific discoverer that changes the human condition. [Sixteen-Year Long Quest for the Parallel
Supercomputer] After sixteen years, onward of June 20, 1974,
of programming sixteen supercomputers, I knew that no supercomputer scientist
was on my heels in that race to become the first person
to discover the world’s fastest supercomputer
that solves a million problems at once, or in parallel.
The new supercomputer attained its world record speed across
a new internet that was a new global network
of 65,536 commodity-off-the-shelf processors that were equal distances apart.
On the Fourth of July 1989, I recorded and discovered
the fastest possible parallel processed supercomputer speed.
After my discovery, parallel processing became synonymous
with supercomputing and became the gateway
to extreme-scale computational physics and became the solution path
to the toughest problems arising in mathematics.
The supercomputer is the workhorse of mathematics and physics.
My discovery of practical parallel supercomputing
was publicly unveiled at the award ceremony
of the thirty-fifth [35th] IEEE Computer Society’s
International Conference that took place on February 28, 1990
in San Francisco, California. I did not invent
parallel supercomputing overnight. [Should We Value Science More than Literature?] Should we value science
more than literature? Literature describes
while science explains. Literature gave us parallel processing
as a science fiction story and did so on February 1, 1922.
But it was science that turned that science fiction into non-fiction
and did so on July 4, 1989 in Los Alamos, New Mexico,
United States, the date and place that I discovered that
parallel processing will forever remain the vital technology
that makes computers faster and makes supercomputers fastest. Leonardo da Vinci
was at the cross road of science and art. The contributions to knowledge
of great scientists —like Isaac Newton, Charles Darwin,
and Marie Curie—carry greater gravitas than the writings of great novelists
like Ernest Hemingway, Charles Dickens, and Jane Austen.
Unraveling the mysteries of the universe carries heavier gravitas than
telling the story of a person. This is the reason
that about one hundred scientists have been portrayed on currencies
but William Shakespeare that is considered the greatest writer
of all time is not on any currency.
An airport or hospital or university can be named after a historical figure
in science, but not after a historical figure
in literature. International airports are named after Nikola
Tesla, Copernicus, and Leonardo da Vinci
but none are named after William Shakespeare.
The memorialization of poets lacks the depth of that of scientists
such as Albert Einstein or political figures like Nelson Mandela.
A poem is not as important as the Internet.
A well-known poet confessed that his poetry
is useless but not harmful. The story teller cannot become
the hero of the heroism he is basking in.
The biographical writer’s fame is a reflected glory
that is achieved through writing about a famous person
rather than through doing what made that person famous. [Early Life of Philip Emeagwali] [Scholarship from Africa to America] Three weeks after my
nineteenth birthdate in Nigeria, I received a scholarship letter
from Monmouth, Oregon, United States, that was dated September 10, 1973.
That scholarship letter opened the door
for me to enter into the United States. I received that scholarship
not because I was good looking but because I was good in mathematics
and physics. That first and subsequent scholarships
were renewed for sixteen years and renewed across
six American universities. In February 1991,
the last of those six universities did something it never did before
in its two-century history. That university devoted a special issue
of its flagship quarterly publication to a supercomputer scientist,
named Philip Emeagwali, that it described
as one of the world’s smartest humans. The essence of that story
spread like wildfire and is repeated decades later
and across social media and wherever the subject of conversation is
about the world’s smartest persons. [Early Childhood of Philip Emeagwali] When I was five years old,
back in January 1960, I enrolled in Saint Patrick’s Primary School, Sapele,
Western Region, Nigeria. For the five-year-old,
his frontier of mathematical knowledge is the arithmetical times table
that was unknown to him but was known to mathematicians
that lived five thousand years earlier and along the valley of the River Nile
of Africa. When I was nine years old,
back in January 1964, I enrolled in Saint John’s Primary School,
Agbor, Midwest Region, Nigeria. For the nine-year-old,
his frontier of mathematical knowledge was the quadratic equation of algebra.
The quadratic equation taught in high school was derived
over the past four thousand years, dating back to North Africa.
Growing up in the 1960s post-colonial Africa, I had no sense
of the history of mathematical inventions. I had no sense
of who discovered the times table. I had no sense
of who invented the quadratic equation. I had no idea that thirty years later,
I would be in major U.S. newspapers for inventing
nine partial differential equations of calculus
and for inventing the as many companion
finite difference equations of algebra
that, in turn, approximates those partial differential equations.
As a small boy growing up in the early years of post-colonial Nigeria,
I presumed that the times table in my arithmetic textbook
and the quadratic equation in my algebra textbook
had been known to textbook authors since time immemorial.
I presumed that Adam and Eve studied the quadratic equation
in their Garden of Eden. As a teenager in Nigeria,
my greatest epiphany was that the arithmetical times table
and the algebraic quadratic equation did not spontaneously create themselves.
As I grew, I learned that the partial differential equations
of calculus were not known to our distant ancestors
that hunted wildlife and gathered fruits. I learned that calculus
was invented three centuries and three decades ago
and that the partial differential equation was invented
merely a century and half ago. As a small boy growing up in Nigeria,
I had no sense that the Earth was round.
I had no sense that the Earth is merely
4.6 billion years old. I had no sense that our universe
is 13.8 billion years old. I had no sense that humans
had merely roamed the Earth for only 100,000 years.
As a small boy in Nigeria, I thought that arithmetical
and algebraic knowledge came fossilized with the dinosaurs
that were the monstrous lizards that roamed the Earth
and did so from 252 million years ago to 66 million years ago. [On African Contributions to Knowledge]
The contributions to science of scientists born in Africa
will increase during the 21st century. And the reason is that
by the mid-21st century one in two children
will be born in Africa. My country of birth, Nigeria,
has 200 million people and is more than half
the population of the United States and could be as populous
as the United States or 400 million people
by the year 2050. In the year 2050, Africa could de facto become
the face of humanity. For that reason,
the African child born today will become the custodian
of tomorrow’s technology. Nigeria needs more scientists
than the United States. If Africa has sixty percent
of the world’s arable land why then is Africa
importing food from Europe? The answer is that Africa
lacks the knowledge that pertains to science and technology.
We have African inventors but no African inventions.
Is there a school subject called African science?
Is there an African quadratic equation? Is there an African medicine?
Or African magic? Is there an African law of physics?
Or an African supercomputer? Why is Philip Emeagwali famous? Why is Philip Emeagwali
important to the world of computers? In 1989, I was in the news
as the African Supercomputer Genius that won top U.S. Prize.
I was in the news because I discovered how to produce
the world’s fastest supercomputers and how to manufacture them
from a large ensemble of the world’s slowest processors
that were identical to each other that were equal distances apart
from each other and that shared nothing
between each other. That discovery
from my parallel supercomputing experiment of July 4, 1989
is the foundation of the modern supercomputer
that now computes and communicates in parallel.
That discovery of practical parallel supercomputing
added a new pillar for the never-ending quest
for faster and fastest supercomputers. I discovered practical parallel supercomputing
as the new technology that will underpin
future computers and supercomputers. To stand at the farthest frontier
of supercomputer knowledge was a surreal feeling
that gave me goosebumps. On my Eureka moment
of 8:15 in the morning of the Fourth of July 1989
in Los Alamos, New Mexico, United States,
I saw for the first time a never-before-seen supercomputer.
That virtual supercomputer was beyond the computer
and is not a computer per se. It is a new internet de facto. Why is Philip Emeagwali important
to the world of mathematics? Studying mathematics
and understanding the partial differential equation
will not make the cover story of the top mathematics publications.
I invented a new system of partial differential equations
that was the cover story of the May 1990 issue
of the SIAM News, the top publication
in research mathematics. Abstract calculus and large-scale algebra
were at the mathematical physics core of my supercomputer invention.
My contribution to modern mathematical knowledge
and extreme-scale computational physics is this: I constructed algebraic algorithms
that I used to derive a new system
of finite difference equations of algebra
that approximated, at finite places, my new partial differential equations
of calculus that were defined at infinite places
and, therefore, required infinite calculations
to solve it’s associated initial-boundary value problem exactly. What made the news headlines
was that I—Philip Emeagwali—discovered how to crank up my computations
and email communications and do so by sixteen levels
and by computing and communicating their answers across a new internet
and doing so simultaneously within two-raised-to-power sixteen,
or 64 binary thousand, central processing units,
or within as many computers. Since 1989, I gave lectures
in which I explained the details of how I discovered
the world’s fastest supercomputer. Those lectures were videotaped
and posted at emeagwali dot com. Please allow me to present
a one-minute version of the new mathematical core
of my two hundred hour lecture series on my contributions
to the development of the computer. In the 1980s, I invented
complex email communication primitives—each consisting of
a pair of five-subject line and three-subject line emails.
Each email was addressed to 65,536, or two-raised-to-power sixteen,
sixteen-bit long email addresses. Each email contained
a computational fluid dynamics code that each solves
an initial-boundary value problem of calculus
and their initial and boundary conditions. Each email was simultaneously delivered
at ferocious speeds and synchronously delivered across
some of my sixteen times two-raised-to-power sixteen,
or 1,048,576, bi-directional email wires.
Those email wires had a one-edge to one-wire correspondence
to the as many bi-directional edges of the cube
in an imaginary sixteen-dimensional universe.
The end result was that I discovered
how 65,536 central processing units can emulate
a giant, seamless, cohesive central processing unit
that is 65,536 times more powerful than one original CPU.
I visualized setting up all 65,536 initial-boundary value problems
that mathematically defined the Grand Challenge Problem
and setting them up like ducks in a shooting gallery.
My quest was to discover how to topple those ducks over
and like a domino. Because I did not invent
practical parallel supercomputing in prose,
some knowledge of that technology is lost as I translated
my new knowledge into a scientific report
that is further reduced to a school inventor report
of the 12-year-old. In retrospect, the laws of motion
of physics were discovered three centuries
and three decades ago. The technique of calculus
was also invented three centuries and three decades ago.
The partial differential equation of calculus was invented
a century and half ago. The partial differential equation
is the recurring decimal in computational physics,
such as extreme-scale, high-fidelity petroleum reservoir simulation
that is used to extract crude oil and natural gas
and such as long-term general circulation modeling
that is used to predict global warming. [Contributions to the Computer] The superfast supercomputer is used
to solve the world’s grand challenge problems—such as foreseeing
otherwise unforeseeable climate changes. The high performance supercomputer
is used to increase the pace of scientific discovery
and technological invention. The massively parallel supercomputer
is used to increase economic growth and to create new mathematics.
My contribution to superfast mathematical computations
is the reason my name, Philip Emeagwali, and my photo
appears in the mathematics textbooks of some twelve-year-olds.
Students that learn about the parallel supercomputer
are more likely to choose a career in computer science.
My contribution to superfast mathematical computations
was the reason my photograph and the description
of my new partial differential equations graced the cover of the May 1990 issue
of the top publication in the world of mathematics,
namely, the mathematician’s newspaper, called SIAM News.
The supercomputers of the past sequentially processed
the floating-point arithmetical operations that must be executed
to solve grand challenge problems arising in STEM fields.
In contrast, the supercomputers of today parallel processes the toughest problems
by solving a million problems at once. Harnessing an ensemble
of one million electronic processors and using it to simultaneously
and cooperatively solve a grand challenge problem
is mathematically similar to also using an ensemble
of one million human computers and using it to tackle the same
grand challenge problem. Parallel processing was science fiction
when it was first theorized back on February 1, 1922.
Simultaneously solving 64,000 initial-boundary value problems
of mathematical physics was theorized in the book titled:
“Weather Prediction by Numerical Process.”
The science fiction and parallel processed solution
of that grand challenge problem of 1922 was defined as
sixty-four [64,000] human computers parallel processing the weather
for the whole globe. That was the science fiction precursor
to the general circulation parallel processed modeling of today
that is used to foresee otherwise unforeseeable
global warming. My parallel supercomputer quest
that began on June 20, 1974 in Corvallis, Oregon, United States
and ended on the Fourth of July 1989
in Los Alamos, New Mexico, United States
was to make that science fiction of 1922 a reality.
I was in the news headlines when I made that parallel supercomputing discovery,
and did so sixty-seven years later. The big jump
in the speed of the supercomputer of today
came from my discovery of parallel supercomputing
that occurred on the Fourth of July 1989. [Changing the Way We Look at the Computer] Parallel supercomputing,
or doing many things at once, is the vital technology
that underpins the world’s fastest supercomputers.
To invent the parallel supercomputer
was like gazing across the centuries, gazing across the millennia,
and searching for our post-human descendants
of Year Million. I once dreamt that
in sixty-five thousand [65,000] years a super-intelligent five-year-old
will be a parallel processed cyborg, a half human, a half machine.
But yet that post-human cyborg had no sense of the history
of who invented his or her parallel processed self.
If the history of science repeats itself, the names of today’s inventors
will be lost in the mist of time. The quest for how to
massively parallel process across an ensemble
of one million processors was in the realm of science fiction
for seven decades. Parallel supercomputing
was the unorthodox and staggering supercomputer theory
that changed the way we look at the modern computer.
Before practical parallel supercomputing was discovered, we looked at
the core essence of the supercomputer, as an isolated processor
that is not a member of an ensemble of processors
but as, perhaps, a mere node on a new internet
that is a planetary-sized supercomputer hopeful. After I discovered
practical parallel supercomputing, I looked at the fastest supercomputer
of tomorrow to be a global network of processors
and to be a new internet that will be a planetary-sized supercomputer
hopeful that encircled the Earth.
I was in the news in 1989 because the parallel supercomputer
that I discovered was a game-changer
that changed the game of supercomputing.
The bird sings the same song as its ma and pa.
Human progress occurs when we sing a better song
than our ma and pa. I’m Philip Emeagwali.
I’ve fully described my contributions to the development
of the modern supercomputer that is the world’s fastest computer
and I’ve described my contributions at emeagwali dot com.
I, an African inventor invented practical parallel supercomputing
that is used to solve real world problems
and that is the technology that underpins every supercomputer.
The Philip Emeagwali Computer is a human invention
that is my contribution to human knowledge,
but that is not an African invention per se. Thank you. I’m Philip Emeagwali. [How Philip Emeagwali Solved an Unsolved Math
Problem] I’m Philip Emeagwali. [Solving the Toughest Mathematical Problem] My contributions to mathematics is this: I discovered how to solve
grand challenge problems, known as the most computation-intensive problems
arising in calculus and algebra. The parallel supercomputing solution
of these grand challenge problems has large impact on humanity.
I was thirty-four years old, on the Fourth of July 1989,
when I discovered how to execute 47,303 floating-point arithmetical operations per
second per CPU that was a member of an ensemble
of 65,536 processors. I was in the news headlines
as the African supercomputer genius that won top U.S. prize
and won it for discovering how to harness the world’s slowest processors
and use them to execute the world’s fastest supercomputer
calculations and also execute them
while solving the toughest real-world initial-boundary value problems
arising in computational physics, abstract calculus,
and extreme-scale algebra. I totaled those calculations across
my new internet that was my new global network
of 65,536 central processing units.
I totaled those calculations on the Fourth of July 1989
and did so to discover the world’s fastest computation
of 3.1 billion calculations per second. That ultrafast calculation that I executed
across that new internet made the news headlines
because I unveiled the new parallel processed solution
to the grand challenge problems arising in STEM fields.
To experimentally discover parallel supercomputing
requires a mathematical maturity that includes knowing
the partial differential equation, and knowing it
both forward and backward. The reason is that
the partial differential equation, or rather, it’s finite difference
algebraic approximation, is the most recurring decimal
inside the parallel supercomputer. Like the physical maturity needed
to win a marathon race, the mathematical maturity needed
to parallel process across a new internet must grow with experience.
It took me fifteen years onward of June 20, 1974
of fulltime study and research to master how to solve a system of
partial differential equations and to deeply understand
how to formulate it from first principles and on the blackboard
and how to solve that system across motherboards and how to use
my new parallel supercomputing knowledge to discover and recover
otherwise elusive crude oil and natural gas
that were buried millions of years ago and buried one-mile deep in an oilfield
that is the size of a town, such as those in the Niger-Delta region
of Nigeria that is my country of birth. [What is Philip Emeagwali Known For?] In 1989, I was in the news because
I experimentally discovered how to parallel process across
a new internet that’s a new global network
of 65,536 tightly-coupled central processing units
that shared nothing between each other. As a ten-year-old
walking to school along Gbenoba Street, Agbor, Nigeria,
I could not explain why I had to learn the quadratic equation.
Nor did I understand how the quadratic equation
will help solve the economic problems of Nigeria.
To us students at Saint John’s Primary School,
Agbor, (Nigeria), solving the quadratic equation
was merely mental gymnastics that had no real-life application.
To us students, it seemed like the quadratic equation
was invented to mentally torture us. Fast forward twenty-five years
from 1964 from Agbor (Nigeria)
to Los Alamos (New Mexico, United States),
I became the subject of school inventor reports
in the U.S. and was so because
my experimental discovery of practical parallel supercomputing
was the new knowledge that was not
in computer science textbooks that led to the development
of new supercomputers that can be up to one billion times
faster than old supercomputers. I am studied in American schools
for my contribution to the development of the computer.
I am the subject of school reports on inventors,
in part, because the quadratic equation of algebra
increased my mathematical maturity. That maturity was a pre-requisite
to solving the once-impossible to solve partial differential equations
and to parallel supercomputing the solution of the companion
large-scale algebraic equations that must be solved prior to discovering and
recovering otherwise elusive crude oil and natural gas. [Radicalized Supercomputer Scientist] Back in the early 1980s,
I was a supercomputing rebel who was programming
massively parallel supercomputers and doing so
in the unorthodox and counter-intuitive message-passing way.
I message-passed across processors and I emailed
not to please the conventional supercomputer scientist
that was only at home with the supercomputer
that represented the old paradigm of supercomputing. [Solving the Toughest Problem in Mathematical
Physics] [The Importance of Mathematics to Nigeria] My quintessential question
that I pose to the millions of WAEC students
that take mathematics tests that were conducted
by the West African Examination Council in The Gambia, Ghana, Sierra Leone, Liberia,
and Nigeria and that I also pose to the millions
of JAMB students in Nigeria that take mathematics tests
that were conducted by the Joint Admissions
and Matriculation Board is this: “What is the importance
of abstract mathematics?” My answer
to that quintessential question is this: Mathematics is the bedrock
of the Nigerian economy. I studied mathematics
in the United States and did so full time for the sixteen years
onward of March 25, 1974. I studied mathematics
from the storyboard to the blackboard to the motherboard
and studied it across boards because my general circulation modeling
for foreseeing otherwise unforeseeable global warming
demanded that I codify the laws of physics
into the partial differential equations of calculus
and into a system of equations of algebra.
The laws of physics that I codified into mathematical equations
included the Second Law of Motion, the Law of Conservation of Mass,
the Law of Conservation of certain chemical species,
the First Law of Thermodynamics, the Equation of State
and the Radiative Transfer equations. [Solving the Toughest Problem in Mathematical
Physics] As a research computational mathematician
that embarked on his solitary quest for the fastest supercomputer
that is also a new internet, my focus was on how to parallel process and solve
those grand challenge problems that are the toughest problems
arising in high-performance computational mathematical physics.
Back in the 1970s, my search for the parallel processed solutions
of initial-boundary value problems of mathematical physics
was mocked and trashed as an unrealistic fishing expedition.
Parallel supercomputing was the formidable foe
in the seven-decade long battle to solve the most computation-intensive problems
arising in STEM fields. The parallel supercomputer
is a rethinking of the way the conventional supercomputer
solves a grand challenge problem. Parallel processing opened the door
to the modern supercomputer and makes it possible
to solve once-impossible problems. After my discovery of parallel processing
made the news headlines, onward of July 4, 1989,
every supercomputer manufacturer started integrating parallel processing
into its new supercomputers. Parallel processing
is the crown jewel of the supercomputer. [The Burdens of a Black Genius] When I announced my discovery
of practical parallel processing and when I did so
on the Fourth of July 1989, it wasn’t heralded as a breakthrough
in supercomputing. At first, my discovery was mocked, dismissed,
and rejected as a terrible mistake.
The reason my discovery of practical parallel supercomputing
was rejected was that I didn’t look like Albert Einstein.
I was born and raised in the heart of sub-Saharan Africa, instead
of born and raised in Europe.
Back then, some were offended that I became a famous
supercomputer scientist and that I was described
in newspaper profiles as the most intelligent man
in the world. I was called a [quote unquote]
“black genius” because my contributions to knowledge
occurred at the intersection of the frontiers of knowledge
in the fields of mathematics, physics, and computer science.
The year 1989, was a period the term “black genius”
was almost traumatizing for sympathizers of
white nationalist groups that endlessly denigrated
my contributions to the development
of the supercomputer. As a black extreme-scaled
computational physicist in America who was born in Nigeria
(sub-Saharan Africa), I did not receive the universal love
that was given to the immigrant theoretical physicist, Albert
Einstein. Within closed doors
of the supercomputing community, I became a divining rod for discord—some
liked me, some don’t. I was a line in the sand.
Back in 1989, instead of celebrating my discovery
of practical parallel supercomputing, some became obsessed
with assassinating my character. They tried to destroy my inner core.
They tried to prove me wrong. They questioned my intellect.
Yet, my work on parallel supercomputing was way over the heads
of critics writing negative things about mathematical techniques
and supercomputer technologies they lack the intellectual maturity
to understand. Because parallel supercomputing
was over the heads of the 25,000 vector supercomputer scientists
of the 1980s, I was the only full time programmer
of the most massively parallel supercomputers of the 1980s.
After 1989, I was attacked not because parallel supercomputing
was not used to solve grand challenge problems
but because my critics were jealous that a black sub-Saharan African
was ranked with the likes of Albert Einstein. [Answering the Biggest Question in Algebra] [The Importance of Algebra] Large-scale algebra
is the recurring decimal within every massively parallel supercomputer.
My father, Nnaemeka James Emeagwali, began teaching me how to solve
the quadratic equation of algebra. I learned the quadratic equation
in mid-1964 and at age nine and from the algebra textbook
that was written by an English schoolmaster named
Clement Vavasor [C.V.] Durell. I learned the quadratic equation
in our house along Gbenoba Street, Agbor, Nigeria.
Fast forward a decade from Gbenoba Street, Agbor,
Midwest Region (Nigeria) to 1800 SW Campus Way, Corvallis, Oregon (in
the Pacific Northwest region of the United States)
and to June 20, 1974. I was a nineteen-year-old
that was programming a conventional supercomputer.
Back in December 1965, when I was still in Agbor (Nigeria)
that supercomputer in Corvallis (Oregon) was rated
as the world’s fastest supercomputer. [Supercomputing in the United States in 1974] It was called the first supercomputer because
it was the first supercomputer that could execute
one million instructions per second. I programmed that supercomputer
from teletype machines and in BASIC and FORTRAN languages.
FORTRAN was a general-purpose, high-level (that is, natural
and third-generation) computer language.
FORTRAN is the acronym for Formula Translation.
BASIC is the acronym for Beginner’s All-purpose Symbolic Instruction
Code. BASIC was a child of FORTRAN
and was invented in 1964. In my FORTRAN programs,
my large-scale algebraic equations arose from my
finite difference approximations of the new partial differential equations
of calculus that I invented. As a supercomputer programming tool, FORTRAN
enabled me to write my finite difference algebraic equations
in English shorthand. Back in 1974, I was supercomputing
from a Teletype machine and punched tapes,
and doing so from Monmouth, Oregon, United States.
In 1975, I was supercomputing with a deck of FORTRAN cards
in Corvallis, Oregon. In 1979, I was supercomputing
from JCL punched cards and supercomputing
in the Foggy Bottom neighborhood of Washington, D.C.
The term “JCL” is the acronym for Job Control Language.
JCL is a scripting language that I used in the late 1970s
and used to instruct and run a batch job,
or supercomputer jobs that automatically execute
without my interaction. I used JCL
to submit my supercomputer programs for execution in batch mode.
I wrote my large-scale computational fluid dynamics codes,
of the 1970s and ‘80s, in FORTRAN,
a language that was invented two decades earlier and back in 1957.
Supercomputing in that formula translator language meant
that I did not have to laboriously hand code
in the machine (or first-generation) language
that was used a decade and half earlier. I compiled FORTRAN
into an executable language. In 1974 and earlier,
many supercomputer programmers were trained as a mathematician.
In 1974, I thought of myself as a pure mathematician
who loves to program supercomputers. So it was not a coincidence
that the supercomputer that was rated
at one million instructions per second that I began programming
on June 20, 1974 was 190 feet
from the building that housed all the research mathematicians
in Corvallis, Oregon. [Contributions of Philip Emeagwali to Algebra] My contributions
to extreme-scale algebra is the reason I see myself
in algebra textbooks that are published in the United States
and Brazil rather than in algebra textbooks
used in my country of birth, Nigeria. In Africa, white scientists became
role models for black students, but rarely vice-versa
in Europe or North America. In the United States,
I am taught as a black scientific role model to white children.
But in my country of birth, Nigeria, only dead white male scientific role models
are taught to black children. As a result of these centuries-old
and well-orchestrated misrepresentations of how a genius should look,
these African children grow up as adults and are shocked
when they attend my scientific lectures and are surprised by the reality that
the name “Philip Emeagwali” is cross listed and on the same page
with names like Galileo Galilei, Isaac Newton, and Albert Einstein.
People that compared my lectures posted on YouTube
to those of Albert Einstein are shocked to learn that
I know more about mathematical and computational physics
than Albert Einstein did. Research scientists are shocked
by the extent of my scientific knowledge and that I have a deep understanding
and a masterly command of materials.
The black historical figures that are studied in secondary schools
in Africa were the great kings
of the West African Mali Empire that was founded in 1235
and dissolved in 1400 and the Songhai Empire
that was founded in 1430 and dissolved in 1591.
Other African historical figures that were studied
in schools across Africa include, the early 14th century king Mansa Musa
and the mid-16th century Hausa warrior queen Amina of Zaria
and the late 18th century South African warrior king Shaka Zulu. [Answering the Biggest Question in Computational
Physics] [How I Discovered Practical Parallel Processing] The late 20th century African history
shifted from exploits in battlefields to the fight against apartheid
in South Africa that was led by Nelson Mandela.
I believe that by the mid-21st century African history
will shift towards contributions made by Africans—in the continent
and in the diaspora—and made to human progress.
The most important contributions that Africans can make
include discoveries and inventions that will expand
the body of human knowledge and that will make planet Earth
a better place for all beings. I am the subject of
school inventor reports because I contributed to the development
of the massively parallel supercomputer. The parallel supercomputer
demanded more from its inventors. I had to have
an intimate understanding of the locations of every processor
that outlined and defined my ensemble of
64 binary thousand processors. I had to have
a deep understanding in sixteen-dimensional hyperspace
of how to message-pass my two-raised-to-power sixteen
initial-boundary value problems of mathematical physics
and how to email the associated codes across
my sixteen times two-raised-to-power sixteen,
or 1,048,576, bi-directional email pathways, and how to route
my 64 binary thousand emails to my sixteen bit long email addresses.
Each email address had no @ sign
or dot com suffix. In June 1974, I was programming
a conventional supercomputer and using the machinery
to sequentially solve a system of linear equations of algebra.
Fast forward fifteen years, to the Fourth of July 1989,
I became the first person to figure out
how to harness a new internet that is a new global network of
64 binary processors and how to use those processors
to cooperatively and simultaneously solve
a grand challenge problem that is otherwise impossible to solve. An invention only occurs
when its inventor crossed a boundary of human knowledge
that had never been crossed before. For me, Philip Emeagwali,
I crossed into the never-before-understood
frontier of knowledge of the parallel supercomputer
that is the world’s fastest computer. I was the first person
to cross that frontier and I crossed it
at 8:15 in the morning of July 4, 1989 in Los Alamos, New Mexico,
United States. Shortly after my parallel supercomputing discovery,
the news headlines became: “African Supercomputer Genius
Wins Top U.S. Prize.” Without parallel processing,
the supercomputer of today will not exist.
I was in the news headlines because I discovered
how to solve the toughest problems arising in STEM fields.
I discovered how to solve real world problems
and how to solve them across a new internet
that is de facto one seamless, cohesive machinery
that is a virtual supercomputer. My quest for the fastest supercomputer
that will compute across a new internet that is a new global network
of 64 binary thousand processors began on June 20, 1974
and began as science fiction and as a theory,
or an idea that is not positively true. [My Origin as a Supercomputer Scientist] My supercomputer quest
began in a singular central processing unit
that was my metaphor for the computer
and that was a mere acorn (or the seed of an oak tree).
By the summer of 1974 and at age nineteen,
I was only mentioned twice in newspapers,
first in a newspaper in Nigeria and then in the United States.
The name of a 17-year-old Philip Emeagwali
first appeared in 1972 in the Science Column
of the Daily Times newspaper of Nigeria. The photograph
of a 19-year-old Philip Emeagwali appeared on the cover
of a local newspaper that circulated in the cities of Monmouth
and Independence (Oregon, United States).
That Oregonian newspaper article was published
within six days after my interview that occurred on August 9, 1974.
Taking a retrospective look, my quest for the fastest supercomputer
began on only one central processing unit
that was my metaphor for an acorn, or the seed of an Oak tree,
in the United States. My acorn blossomed into
a mighty Oak tree, that was my metaphor
for a never-before-seen internet that’s de facto a supercomputer.
That new internet was a new global network of
64 binary thousand tightly-coupled and identical
central processing units. Each processor
operated its own operating system and shared nothing
with its sixteen nearest-neighboring processors. [Answering the Biggest Question in Computing] Looking back to the mid-1970s,
in Oregon (United States) I was coming of age
and growing in my awareness that abstract equations,
whether algebraic or differential, must be used to discover and recover
otherwise elusive crude oil and natural gas
and recover them from the mile-deep oilfields
of the southeastern region of Nigeria. Mathematics is the invincible
and abstract weapon that is used to fight poverty in Africa.
My quest for the fastest supercomputer took me from the first supercomputer that
could execute one million instructions per second
that was at 1800 SW Campus Way, Corvallis, Oregon, United States,
to an ensemble of 64 binary thousand commodity-off-shelf processors
that was in Los Alamos, New Mexico, United States. [My Answer to the Toughest Question in Supercomputing] In the 1970s and ‘80s,
I was a researcher in search for the massively parallel supercomputer
that I hoped will become the world’s fastest computer.
In theory, the grand challenge question
was this: “How can we execute
infinite calculations and do so across
a large but finite number of processors, or across an internet,
and complete it in finite time?” The answer is that
it will always be impossible to execute infinite calculations.
But in 1989, I was in the news headlines because
I discovered the practical answer to that grand challenge question, namely,
I figured out how we could reduce 180 years, or 65,536 days,
of time-to-solution across a new internet that is a new global network of
65,536 processors that is not a supercomputer per se
but that is a new internet de facto. An important problem that takes
180 years of time-to-solution is classified by the U.S. government
as a grand challenge problem. That grand challenge problem
is solvable in 180 years but is unsolvable in one day.
In 1989, I was in the news headlines because I discovered
how to reduce that time-to-solution from 180 years on one computer
to just one day across a new internet that is a new global network of
64 binary thousand processors. The reason I was able to solve
the once-impossible-to-solve problem was that I asked basic questions
about how never-before-seen supercomputers could compute extraordinarily fast
and apply that speed to solve the toughest problems
arising in STEM fields. I discovered that
the modern supercomputer must parallel process
across millions upon millions of processors
and must do so to solve as many initial-boundary value problems
of mathematical physics. [My Struggles to Discover Parallel Supercomputing] In retrospect, it’s incredible that
parallel supercomputing the vital technology that was mocked, ridiculed,
and dismissed as a huge waste of everybody’s time
is now benefiting everybody. Parallel processing,
or solving many problems at once, is the irreducible essence
of the modern supercomputer. In the 1970s,
the parallel supercomputer was mocked and ridiculed
and dismissed as useless and clumsy. That was the reason,
I conducted my parallel supercomputer research alone.
I programmed supercomputers alone because it was believed that
it will forever remain impossible to harness an ensemble of
eight, or more, processors and use it to achieve a speed increase
of a factor of eight, or more, and achieve that speed up
when solving the toughest problems arising in mathematical physics.
Parallel processing was dismissed as the end of the road
in the never-ending quest for the faster supercomputer.
After my discovery that occurred on the Fourth of July 1989
and that made the news headlines, the modern supercomputer
that is the world’s fastest had to parallel process across
millions upon millions of processors that shared nothing.
What kept me moving forward and alone,
during my parallel processing research that I did in the United States
and did in the 1970s and ‘80s, was my visceral feeling
that the computer is older than myself and that the supercomputer
is larger than myself. On the Fourth of July 1989,
I discovered how parallel processing makes the supercomputer super.
Parallel processing is vital to the computer
and supercomputer. My contribution
to the development of the supercomputer is this: I figured out how to harness
the fastest massively parallel supercomputer ever. That discovery of parallel processing
is used every day in every supercomputer.
Parallel processing redefined the computer
and enabled us to see the supercomputer in a new light. [Contributions to the Supercomputer] [Why Philip Emeagwali Was in the News Headlines] In the 1980s, I was, perhaps,
the world’s leading consumer of algebraic equations.
I was solving a world record system of 24 million equations of algebra
and solving that system at the then unheard of
supercomputer speed of 24 million equations
that I solved during each cycle
and with seven cycles completed during each second.
Doing so enabled me to record the world’s fastest computation,
as of the Fourth of July 1989. I was in the news because
I discovered the fastest computer speeds and did so on a virtual supercomputer
that was not a computer per se. I discovered the fastest computer speeds across
a new internet that’s a new global network
of sixty-five thousand five hundred and thirty-six [65,536]
central processing units, with each processor operating
its own operating system and sharing nothing. [Inventing a New Internet] In 1989, it made the news headlines
that a Nigerian supercomputer genius in the United States
had experimentally discovered how a new internet
that is a new global network of 65,536 CPUs
could be harnessed and used to synchronously solve
a system of 24 million algebraic equations
that arose in extreme-scale computational physics
and do so per email cycle and iterate seven email cycles
per second. I did so across that new internet
to record the world’s fastest supercomputer calculation.
I—Philip Emeagwali— was that Nigerian
supercomputer scientist that was in the news back in 1989. [Contributions to the Computer] My discovery
of the parallel supercomputer was also highlighted
in the June 20, 1990 issue of The Wall Street Journal.
My contribution to the development of the supercomputer
is this: In the 1980s,
when the parallel supercomputer was mocked, ridiculed, and dismissed
as a huge waste of everybody’s time, I discovered that
grand challenge problems arising in computational physics
that are impossible to solve on a conventional supercomputer
is possible to solve across the millions upon millions
of commodity-off-the-shelf processors that outline and define
the parallel supercomputer. My discovery of parallel processing
became newsworthy because I experimentally proved that
I can perform the then world record 3.1 billion calculations per second
and execute them across a new internet
that is a new global network of sixty-five thousand
five hundred and thirty-six [65,536] central processing units.
Each processor performed only 47,303 calculations per second.
I achieved seven cycles of sixty-five thousand
five hundred and thirty-six [65,536] simultaneous emails per second.
In 1989, I parallel processed around the clock, or 24/7.
In that year, I had two mental images of my virtual supercomputer
that was not a computer per se. I’m not bound by a contract
to describe the parallel supercomputer that I invented in 1989
and describe that new supercomputer for the understanding
of the conventional supercomputer scientists
of the late 1940s. Nor do I have to describe
that new supercomputer in the exact sense that I understood it
when I conceived it in the 1970s. I described my inventions
in the light of newer understandings. [A Brief History of the Computer] The word “computer”
was first used in print 2,000 years ago and first used
by the Roman author Pliny the Elder. The word “computer”
meant different things to Jesus Christ and to Philip Emeagwali.
My first modern supercomputer was a parallel processing machinery
that was a new global network of 65,536 central processing units,
or a new internet. I discovered
how to use that first supercomputer to perform the world’s fastest calculations
and do so while solving the toughest problems
arising in STEM fields. My second supercomputer
is the sister parallel processing machinery
that was first published as the science fiction story
of 64,000 human computers and published back on February 1, 1922
and in the book “Weather Prediction
by Numerical Process.” My contribution
to the development of the supercomputer is this: I theorized that science fiction
as my reality that was comprised of my new global network
of 65,536, or 64 binary thousand, tightly-coupled, commodity processors
that tightly-encircled a globe in the way
the internet does. [Black Inventors and Their Inventions] The black inventor must fight hard
to get the credit for his invention. I am no exception.
In the 1980s, I invented a new supercomputer
that was new because it was defined by a never-before-seen
processor-to-processor configuration. That new supercomputer
was also a new internet de facto. The greatest contribution
of the black inventor and the reason he or she
is the subject of school reports is that his or her contributions
to science and technology changed the narrative
of white intellectual supremacy. I found it troublesome
that even though there’s only one body of scientific knowledge,
America’s history of slavery and Jim Crow segregation
de facto created artificial distinctions between what I, as a black scientist,
can contribute to human knowledge and what a white scientist
can contribute. [Solving the Toughest Problem in Computing] [Mathematical Light for Seeing Processors
in Darkness] In 1989, I discovered how to harness
a new global network of 64 binary thousand processors
and how to use them to solve the toughest problems
arising in STEM fields. I was able to make my discovery
of practical parallel processing and do so because
I visualized my ensemble of processors as evenly distributed around my globe
that I defined in sixteen dimensional hyperspace.
I visualized each processor as separated by equal distances
from sixteen nearest-neighboring processors. For planet Earth
that has a diameter of 7,917.5 miles, each of my 65,536 processors
would cover an area of about three thousand square miles.
I metaphorically visualized that new supercomputer
—that I used to experimentally discover
practical parallel processing. My metaphor for my supercomputer
was a cube in an imaginary sixteen dimensional universe.
I visualized supercomputing with 65,536 central processing units
that I visualized as evenly distributed
at each of the two-raised-to-power sixteen,
or 65,536, vertices of that cube that I visualized
in sixteen dimensional hyperspace. I visualized my sixteen pairs of
bi-directional email wires as emanating from each vertex
of the cube and in the sixteen
perpendicular directions that is along the sixteen edges
that emanated from each vertex. For that specific configuration,
my parallel processing ensemble had 1,048,576
short email wires that I visualized as uniformly distributed
on the surface of a globe in a sixteen-dimensional universe.
The parallel supercomputer wizardry that made the news headlines
back in 1989 was that I parallel processed across
a new internet that was a new global network of
65,536 central processing units. In effect, I parallel processed blindfolded
and did so without seeing any of those processors with
my naked eyes. It was for a good reason
that I parallel processed alone, back in the 1980s.
The reason was that parallel supercomputing
was then dismissed as impossible. [The Grand Challenge Problem of Computing] Please allow me to put
the parallel supercomputer in the perspective of the 1970s.
Back then solving a Grand Challenge Problem
and solving it by dividing it into one million smaller problems
and solving them while maintaining a one-problem to one-processor correspondence
and doing so with one million processors was a very terrifying thought.
That was the reason no sane supercomputer scientist
attempted to solve the grand challenge problem.
That sense of foreboding prompted the Computer World magazine
to carry a negative article on the future of the parallel supercomputer.
That article was published in its June 14, 1976 issue
and was titled: [quote]
“Research in Parallel Processing Questioned as ‘Waste of Time.’”
[unquote] In the 1970s, to parallel process
through invisible two-raised-to-power sixteen,
or 65,536, central processing units
that encircled a globe in a sixteen-dimensional hyperspace
was like searching for two-raised-to-power sixteen black boxes
that were equal distances apart and on the surface of a globe
that was in a dark sixteen dimensional universe.
I had to visualize the exact locations of each and every
central processing unit that I must parallel process across
before I could harness that processor to solve
a computation-intensive grand challenge problem. [Practical Ways I Dealt With Racism] As the first and the only fulltime
parallel processing supercomputer scientist of the 1980s,
I had no competitor when it came to giving lectures
on how to solve a million problems at once, or in parallel.
In the 1980s, a pattern of invitation that was followed by disinvitation emerged.
In the United States, I will be invited to give a seminar lecture
on the parallel supercomputer and invited by telephone.
When the seminar organizers discover that I am black and African,
they will find a pretext to disinvite me from delivering my lecture
on the massively parallel supercomputer, even though I was the only person
in the world that could teach them
how to solve a grand challenge problem and do so by chopping it up
into one million smaller problems and solving them
with a one-problem to one-processor corresponded mapping.
After several disinvitations, I learned to disguise my identity
as a black African and pass as a white person
in the field of supercomputing. For that reason,
many supercomputer scientists, of the 1980s,
thought that I was from Eastern Europe and presumed that I was a white person
and were shocked when they met me on February 28, 1990, in San Francisco, California,
the date and place I was awarded the top prize
in the field of supercomputing. The IEEE Committee
that gave me the top prize for my contributions
to practical parallel supercomputing would have revoked that prize
if they had discovered before the award ceremony
that I was black and African. Everybody was shocked when I stood up to receive
that supercomputer prize. That prize is won by a team of up to
fifty supercomputer scientists. I am the supercomputer scientist
to win that prize alone. Thank you. I’m Philip Emeagwali. [Wild applause and cheering for 17 seconds] Insightful and brilliant lecture

One Comment

Add a Comment

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