Changing the Way We Look at Computers | Philip Emeagwali on Inventing the World's Fastest Computer

A 12-year-old writing a school report on the contributions of Philip Emeagwali to the development of the computer asked me: “How do we increase the speed of quantum computers?” I answered: In classical parallel computing, I experimentally discovered how to solve all sixty-five thousand five hundred and thirty-six [65,536] challenging problems and how to solve them at the same time and how to solve them across a global network of one million forty-eight thousand five hundred and seventy-six [1,048,576] commodity email wires that fed data and answers from initial-boundary value problems







and fed them to and from
sixty-five thousand
five hundred and thirty-six [65,536] commodity processors.
I discovered
how to solve extreme-scale problems
in computational physics.
My physical surroundings entered into
my initial-boundary value problems
of a new calculus
and of the fastest computational physics.
I’m surrounded
by the air and the water
that entered into
my general circulation models
that I executed across
my ensemble of 64 binary thousand commodity processors.


Changing the Way We Look at the Computer

The Inside of a Quantum Computer

I was asked:
“What does a quantum computer
look like?”
The inside of a quantum computer
is one of the coldest places
in the known universe.
The inside of a quantum computer
is minus 273 degrees Celsius.
The inside of a quantum computer
is 150 times colder than
interstellar space.
The first quantum computer
is not quite a quantum computer.
That first quantum computer
is a monolithic black box
that’s 12 feet by eight feet by ten feet tall. That first quantum computer
fills a small bedroom.
The quantum computer
will not make the massively
parallel processing supercomputer
obsolete.
The reason is that a quantum computer
will not be a general-purpose computer.
The quantum computer
might look like a refrigerator
because it needs to be cooled.
In quantum computing,
the computer memory
and the processor
must be isolated.

How to Reduce 180 Years to One Day

I experimentally discovered
how to reduce the time-to-solution
from one hundred and eighty [180] years,
or sixty-five thousand
five hundred and thirty-six [65,536] days, within one processor
to only one day of time-to-solution
across a new internet
that’s powered by
a global network of
sixty-five thousand
five hundred and thirty-six [65,536]
commodity processors.
Those processors were used to
solve all sixty-five thousand
five hundred and thirty-six [65,536] challenging problems
and solve them at the same time.
I began sequential processing supercomputing
in the summer of
nineteen seventy-four [1974]
and I began by wanting to discover
the massively parallel processing supercomputer
in nineteen seventy-four [1974].
I began parallel processing supercomputing without being able to visualize
the modern supercomputer
and visualize it
in nineteen seventy-four [1974].
I began modern supercomputing
without being able to even articulate
the modern supercomputer
and to do so back in nineteen seventy-four [1974].
In the 1970s, my grand challenge
was to visualize the shape
of my internet
and to visualize it
as a 7,918-miled diameter internet.
And, most importantly,
articulate that internet
as the source of the fastest computations, both present and future.
But back in nineteen seventy-four [1974],
or even in the late nineteen seventies,
I wasn’t sure how my
experimental discovery
of massively parallel processing
will be contextualized
with calculus, algebra, arithmetic,
codes, and emails.
The reason the speedup of
sixty-four binary thousand
that I experimentally discovered
made the news headlines
in nineteen eighty-nine [1989]
was that
the new knowledge
that parallel processing works
could not be proven wrong.
Like any scientific discovery,
my experimental discovery
was one hundred percent doubt-free.
That experimental discovery
was the end-product
of an acid test type experiment
that I conducted
across a new internet
that’s a global network of
sixty-five thousand
five hundred and thirty-six [65,536] commodity processors.
The supercomputer
that is sixty-four
binary thousand times faster
than the computer
is immensely more complex
than the computer.





TAGS
Black Inventors, Black Scientists,supercomputer how to build, supercomputer iq, Cosmic Computer as the world’s largest supercomputer, supercomputer of the future, parallel supercomputer versus quantum supercomputer, supercomputer vs mainframe

Philip Emeagwali 180125 1 6 of 8

Philip,Emeagwali,Lectures,supercomputer how to build,supercomputer iq,Cosmic Computer as the world’s largest supercomputer,supercomputer of the future,parallel supercomputer versus quantum supercomputer,supercomputer vs mainframe,black scientists,black inventors,