Using a Million Processors to Solve Unsolved Problems | Famous Mathematicians and their Inventions

Using a Million Processors to Solve Unsolved Problems | Famous Mathematicians and their Inventions


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] [Solving the Toughest Problem in Calculus] My mathematical quest
for the solution of the toughest problem in calculus
was like searching for a black goat at night.
Briefly, this is my supercomputing story.
I experimentally discovered how to open the door
that takes the modern calculus across a new global network of
tightly-coupled processors
that were already available in the market
that shared nothing, or across a new internet
that is a new supercomputer and a new computer.
That invention is my contribution
to computational mathematics and to the modern calculus.
That mathematical invention was the cover story of the June 1990 issue
of the SIAM News. The SIAM News
is the number one publication for those applied and computational mathematicians
that are interested in learning about new mathematics,
such as new partial differential equations
that have not yet entered into mathematics textbooks.
At the National Computer Conference that took place in New York City
from June 7 to 10, 1976 the foremost supercomputer experts
warned that parallel processing machines
will be too large and too clumsy and a huge waste of everybody’s time.
In the nineteen eighties [1980s], I could count the number of
computational mathematicians that were massively parallel processing
and count them on my fingers. I know because I was logged on
twenty-four seven [24/7] on the most massively
parallel processing supercomputer in the world.
Today, that supercomputer will cost the budget of a small nation.
I—Philip Emeagwali— was the most extreme-scaled
computational mathematician that programmed
the most massively parallel processing supercomputer ever built.
I programmed that supercomputer alone. Today, a thousand
supercomputer scientists program only one supercomputer.
I was the lone wolf programmer of the precursor
to the modern supercomputer because computational mathematicians
were heeding the warnings that it will forever remain impossible
to harness the power of thousands of processors.
In the November 29, 1989 issue of The New York Times,
Neil Davenport, the president of Cray Computer Corporation
—the sister company to the company that manufactured
seven in ten supercomputers— warned that: [quote]
“We can’t find any real progress in harnessing
the power of thousands of processors.” [unquote] In an earlier article that was distributed
on September 2, 1985 and distributed to the print media
and distributed by the United Press International, or UPI,
and in that article, John Rollwagen,
the president of Cray Research Incorporated that was the company
that manufactured seven in ten supercomputers,
described his company’s use of 64 processors as: [quote]
“more than we bargained for.” [unquote] I was the lone wolf supercomputer programmer
of my new global network of 65,536 tightly-coupled processors.
I was the lone wolf because supercomputer scientists
of the 1980s believed that it will be impossible
to use 64 processors and use those processors
to cooperatively solve the toughest problems
arising in calculus. The supercomputer scientists
of the 1980s believed that it will be impossible
to use 64 processors and use those processors to solve
the most extreme-scaled problems arising in algebra.
The supercomputer scientists of the 1980s
believed it will be impossible to use 64 processors
and use those processors to execute
the computation-intensive floating-point operations
arising in arithmetic that I executed
as the world’s fastest computation and executed
on the Fourth of July 1989. I was the lone wolf
internet scientist and supercomputer programmer
of my new internet that comprised of
my new global network of 65,536 tightly-coupled processors
that were already available in the market
that shared nothing and that was one thousand
and twenty-four times [1,024] beyond the perceived limit
of the supercomputer industry. The computational mathematicians
that read the supercomputer textbooks cited Amdahl’s Law
to argue that parallel processing an initial-boundary value problem
of modern calculus and parallel processing those problems
across an ensemble of 64 binary thousand
processors would forever remain impossible,
or at least remain impractical. I’m Philip Emeagwali.
I’m keeping this conversation alive at emeagwali dot com. It’s been said that:
Out of the heart, the mouth speaks. I have spoken a lot since the 1970s
and spoken about how I witnessed the invention
of the massively parallel processing supercomputer. The words I spoke
came from my discoveries, inventions, heart, and brain.
I’m giving this lecture because I experimentally discovered that the fastest
supercomputer must be powered by
the largest ensemble of processors. I’m giving this lecture because
I contributed to the development of the massively parallel processing
supercomputer. I’m giving this lecture because
I invented how to solve the toughest problems
arising in extreme-scale computational physics.
I’m giving this lecture because I invented
the massively parallel processing supercomputer that became the most expensive
instrument of extreme-scale computational physics.
I’m giving this lecture because my invention
of the massively parallel processing supercomputer
was the inflection point that opened new possibilities
in the world of the computer and in the fields of extreme-scale computational
mathematics and computational physics
that must be used to foresee otherwise unforeseeable global
warming and that must be used
to discover and recover otherwise elusive
and unrecoverable crude oil and natural gas.
My words in these lectures will define me for posterity.
To witness a discovery that has rich, fertile, and far-reaching consequences
is like walking into a forest and witnessing a lot of leaves
fall on your head. [Wild applause and cheering for 17 seconds] Insightful and brilliant lecture

Leave a Reply

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