Philip Emeagwali

Philip Emeagwali

Philip Emeagwali

LECTURE TRANSCRIPT: My Contributions to Mathematics, Physics, and the Modern Supercomputer 10.1.1     Emeagwali’s Equations for Computational Physics As a research computational mathematician of the 1970s and ‘80s that executed supercomputer calculations from Corvallis (Oregon, United States) to Los Alamos (New Mexico, United States), I believe that they are more mathematical equations to be yet discovered. I believe that they are partial differential equations beyond the blackboard and that has never been scribbled on the blackboard. For that reason, my quest for a new internet was motivated by my need to execute the fastest mathematical computations and to execute the fastest companion email communications that must arise while executing those computations across my ensemble of 65,536 processors that defined that new internet. That quest for the fastest mathematical computations and email communications was preceded by another quest for the correct system of coupled, non-linear, and time-dependent partial differential equations of modern mathematics and extreme-scale computational physics. Those partial differential equations defined the initial-boundary value problem of modern calculus that was at the computational testbed for my calculations that I executed across my global network of 65,536 processors that, in turn, outlined and defined a new internet. That is, I wanted to go beyond recording the fastest computational speeds. I wanted to record those speeds across my new internet. I wanted to not only record speeds that were previously unrecorded but to record those speeds while solving the correct partial differential equations. Recording those speeds required that I mathematically discover the century-old mathematical error that was unknown to mathematical physicists that formulated the initial-boundary value problem of modern calculus that was at the mathematical foundation of petroleum reservoir simulators. To record those supercomputing speeds required that I invent the correct partial differential equations. I invented thirty-six [36] mathematical terms, called partial derivatives that measure changes in velocity, both in time and space Those mathematical terms encoded inertial forces that were not accounted for in the Second Law of Motion of physics and that were not coded into petroleum reservoir simulators. I contributed to modern algebra by inventing thirty-six [36] partial difference terms of extreme-scale algebra and computational physics. Those algebraic terms decoded, or discretized, the thirty-six [36] partial derivative terms that I invented. Those terms defined the nine partial differential equations and defined the nine partial difference equations that I invented and that are called the Emeagwali’s Equations and that could be used by computational physicists to simulate and enhance the amount of oil and gas that i 10.1.2 Stabilizing Unstable Computer Algorithms I mathematically discovered that research computational mathematicians of the oil and gas industry should go back to their blackboards and correctly re-derive their core equations from first principle, or from the Second Law of Motion of physics. Philip Emeagwali Lecture 180123-2

Philip Emeagwali

Philip Emeagwali

Philip Emeagwali Lecture 180125-1

For complete transcript and lecture series,  visit http://emeagwali.com. For live speaking engagements or tour schedules, call  202-203-8724 or email [email protected] or http://emeagwali.com. LECTURE TRANSCRIPT: Philip Emeagwali: My Struggles to Invent a New Supercomputer that is a New Internet At 10:15 a.m. New York Time Tuesday the Fourth of July of 1989 I experimentally discovered how and why parallel processing makes new computers faster and makes new supercomputers fastest and I invented how and why to use that new supercomputer knowledge to build a new supercomputer that encircled a globe and encircled it in the manner the internet encircled a globe. The reason my experimental discovery made the news headlines was that for the four decades onward of 1946 the parallel processing machine was a supercomputer-hopeful that no supercomputer scientist understood what made it super. The new supercomputer, in turn, gave birth to the new field of computational science. And a new supercomputer gives birth to a new computational science. The importance of computational science was underscored in an article that was in the May 8, 1987 issue of The Chronicle of Higher Education, the flagship newspaper that presents news to universities. That article was written by computer and information technology writer Judith Axler Turner. The article was titled: [quote] “Some Hail ‘Computational Science’ as Biggest Advance Since Newton, Galileo.” [unquote] My Fourth of July of 1989 experimental discovery of how and why to use massively parallel processing to solve initial-boundary value problems of a new calculus and of the fastest computational physics made the news headlines as the biggest advance in computational science. My world’s fastest supercomputer algebraic calculations made the news headlines and entered into the June 20, 1990 issue of the Wall Street Journal. A week later, the computer and information technology writer, named Judith Axler Turner, wrote in the June 27, 1990 issue of The Chronicle of Higher Education that I—Philip Emeagwali— [quote] "took on an enormously difficult problem.” [unquote] That enormously difficult problem that I solved and that made the news headlines was the toughest problem in extreme-scale computational science. Judith Axler Turner continued in her Chronicle of Higher Education article that Philip Emeagwali [quote] “solved it alone, has won computation's top prize, captured in the past only by seasoned research teams.” [unquote] My discovery that made the news headlines back in 1989 was the tipping point of the increasing speeds of the supercomputer. That turning point in massively parallel processing supercomputing of the Fourth of July of 1989, led to a new computer. 13.1.2 School Reports on Philip Emeagwali I was asked to explain why American children are writing school reports on my early life in Nigeria, Africa and on my contributions to the development of the fastest supercomputer. Teaching the groundbreaking discovery of any historical scientist is not mandated in U.S. schools. However, it’s included in the guidelines known as the Core Knowledge Series. It’s included in social studies standard. Each teacher decides how to incorporate stories about scientists into her curriculum. The computer was not invented by super-intelligent aliens from the moon that are disguised as humans. Therefore, the fathers of the modern computer should be studied in schools that use computers. Philip Emeagwali is studied in American schools because I experimentally discovered how and why parallel processing across a new internet is faster than computing within any vector processing supercomputer that was the state-of-the-art technology of the 1980s. Ironically, I am mostly studied in schools in the United States, not in my country of birth, Nigeria (Africa). Historically, if a scientist—such as Albert Einstein or Thomas Edison or Alexander Graham Bell—is studied in American schools, that scientist will later be studied in schools all over the world. But if a scientist is only studied in schools in Nigeria, that scientist will only be studied in schools in Nigeria. My experimental discovery of how and why parallel processing makes computers faster first made the news headlines in 1989 in the United States and my discovery story spread to American schools and to newspapers in other countries. 13.1.3 A World Without Supercomputers The human species evolved from Africa and evolved about two hundred thousand years ago. The reason our human ancestors discovered was to make their world a more knowledgeable place Our ancestors invented to make their world a better place. Fire is man’s first invention, or rather man’s first discovery. Philip Emeagwali Lecture 180125-1

Philip Emeagwali

Philip Emeagwali

Philip Emeagwali

For complete transcript and lecture series,  visit http://emeagwali.com. For live speaking engagements or tour schedules, call  202-203-8724 or email [email protected] or http://emeagwali.com. LECTURE TRANSCRIPT: I’m Philip Emeagwali. I’m a research supercomputer and internet scientist. My scientific story is more fragmented than the story of the theoretical physicist Albert Einstein. It was the story of my journey to the frontier of extreme-scale computational physics. That journey to discover how to solve the toughest problems in mathematical physics was interrupted during the last thirty months of the 1960s. That journey was interrupted when I fled from my all-boys Catholic boarding school—named Saint George’s Grammar School, Obinomba (Nigeria). I fled from Saint George’s Grammar School in late April 1967 and I fled because the Nigerian Civil War was in the air. I fled to become a 12-year-old refugee in the break-away and short-lived nation of Biafra. Two months after I fled from Obinomba (Nigeria) to Agbor (Nigeria) to Onitsha (Biafra), and on the Sixth of July of 1967 that Nigeria-Biafra War began. On the Fourth of October of 1967, my ancestral hometown of Onitsha (Biafra) was heavily bombarded for 24 hours and bombarded from Asaba (Nigeria) and bombarded from across the River Niger. The following day, that artillery bombardment of Onitsha (Biafra) by the Nigerian army was followed by the invasion of my hometown. That night, Onitsha was invaded by a 10-boat armada that carried five thousand [5,000] Nigerian soldiers. Those Nigerian soldiers were led by Murtala Mohammed, who would later become the president of Nigeria. One in fifteen Biafrans died when that Nigerian Civil War ended. The Nigerian Civil War was a nightmare and a bloodbath. The Nigerian Civil War ended after thirty months of non-stop fighting and on January 15, 1970. One million soldiers died at the war fronts of the Nigerian Civil War. And about half a million women and children died in Biafran refugee camps. I survived two years in Biafran refugee camps and survived six months of bloodbath near the Oguta War Front. I survived a war that was described as Africa’s bloodiest war. 14.1.2 One Day We Had to Run! Biafra was located in the southeastern region of Nigeria, West Africa. My family of seven children lived in six refugee camps within Biafra. For two years and three months, onward of April 1967, my family lived in refugee camps in the Biafran cities of Onitsha, Ogidi, Oba, Awka, Awka-Etiti, and Ndoni. During the months of January, February, and March of 1968, Russian Ilyushin bombers and Mig fighters were bombing and strafing our neighborhoods of around 14 Mba Road, Onitsha. On my 14th birthdate of August 23, 1968, my postal address was: Chukwurah Philip Emeagwali Saint Joseph’s Refugee Camp, Awka-Etiti, Biafra, West Africa. On the cover of the TIME magazine that was dated August 23, 1968 is an artist’s portrait of “Colonel Ojukwu,” the leader of Biafra. The cover story of that issue of TIME magazine was titled “Biafra’s Agony.” For us, the agony was real. Half of the refugees at our Saint Joseph’s Refugee Camp, Awka-Etiti, Biafra, were living skeletons. My father, Nnaemeka James Emeagwali, was the live-in refugee camp nurse at Saint Joseph’s Refugee Camp. In August 1968, my father told me that half of the children in our refugee camp, including my two-year-old brother, Peter, had kwashiorkor, a rare malnutrition disease caused by lack of protein. At Saint Joseph’s Refugee Camp of Awka-Etiti (Biafra), children and grandparents that did not survive kwashiorkor were buried without funerals and buried at our backyard. In Biafra, meat, pepper, and even salt were almost as scarce as gold. Three charity organizations —The Red Cross, the Roman Catholic relief organization, named Caritas, and the World Council of Churches—provided to our refugee camp cornmeal, Norwegian dried stock fish named “okporoko,” and powdered milk. The relief foods were secretly flown into Uli airstrip of Biafra. That 27-month refugee experience was the reason the United Nations has the portrait of Philip Emeagwali —along with the portraits of the likes of Albert Einstein— in its Gallery of Refugees Who Made a Difference. Philip Emeagwali Lecture 180125-2

Philip Emeagwali

Philip Emeagwali

Philip Emeagwali

For complete transcript and lecture series,  visit http://emeagwali.com. For live speaking engagements or tour schedules, call  202-203-8724 or email [email protected] or http://emeagwali.com. TRANSCRIPT: My Contributions to Mathematical Physics - Lecture 180128 The nine partial differential equations of modern calculus —called Emeagwali’s equations— began as the Second Law of Motion of physics. I encoded that Second Law of Motion into eighty-one (81) partial derivative terms of Emeagwali’s system of equations that governs the multiphase flow of oil, water, and natural gas that was flowing a mile-deep and across a production oilfield, such as the Oloibiri Oilfield of Nigeria that was the first oilfield discovered in West Africa and discovered in 1956. As a research computational mathematician, I insisted that the petroleum reservoir simulator must obey the laws of physics at all times and simulations. My contributions to mathematical knowledge include the mathematical discovery that the system of nine coupled, non-linear, and time-dependent partial differential equations in the calculus textbooks of the petroleum industry were not equating to the reality within the oilfield the partial differential equations represent. For that reason, I invented the nine Emeagwali’s equations that contained thirty-six [36] partial derivative terms that equated with the four physical forces that exists within all production oilfields. Along those lines, I also had to invent nine finite difference algebraic algorithms that were not constrained by in inverted commas “dependency” and constrained when executing across my new internet that was outlined by an ensemble of 65,536 commodity-off-the-shelf processors that were identical to each other and that were equal distances afar and apart from each other. A necessary condition to making my experimental discovery of the Fourth of July of 1989 was that I simultaneously send email messages to all 65,536 processors on my new internet and that I synchronously receive my email replies from all 65,536 processors. That massively parallel processing supercomputer invention took a narrative identity all its own, namely, I—the storyteller—became the story and the subject of school reports. 7.1.2 My Contributions to Algebra Nine in ten supercomputer cycles are executed while solving extreme-scaled systems of equations of algebra. On the Fourth of July of 1989, the US Independence Day, I experimentally discovered how to finesse my 64 binary thousand identical and commodity processors to email each other and to work together 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 processor to just one day across an ensemble of 65,536 processors. I experimentally discovered how to compute quickly and accurately and how to make the impossible-to-solve systems of equations of extreme-scale algebra possible-to-solve and how to use that new knowledge of massively parallel processing extreme-scaled problems in algebra and doing so to build digital replicas of petroleum reservoirs and the Earth’s climate. I experimentally discovered a new supercomputer that encircled a globe and encircled it in the manner the internet encircled a globe and that could be used to solve never-before-solved problems in algebra. That new supercomputer is a new instrument that enables the computational mathematician and physicist to answer previously unanswerable  questions in the extreme-scale algebra that is the recurring decimal in their grand challenge problems. By definition, algebra is the generalization of arithmetic. In high school algebra, two letters represent two numbers. In the supercomputer algebra that arises from trying to discover and recover otherwise undiscoverable and unrecoverable oil and gas, one trillion letters must represent one trillion numbers arising from a system of one trillion equations of algebra. Those one trillion equations are evenly distributed across millions of processors that, in turn, solves the trillion equations in parallel, or solves them by computing one million calculations at once. In modern supercomputing, parallel processing is the disruptive technology that displaced sequential processing, a technology that established itself for half a century. Between sequential processing that was experimentally invented in 1946, and parallel processing that I experimentally invented in 1989, was vector processing that was the sustaining technology that yielded incremental gains in the supercomputer speeds of the 1970s and ‘80s. My world’s fastest supercomputer algebraic calculations made the news headlines and entered into the June 20, 1990 issue of the Wall Street Journal.

Philip Emeagwali