Over the past 100 years, high-end IBM machines have consistently ranked among the most powerful on the planet. When IBM ® Blue Gene ® was unveiled in 2004, it was both the most powerful supercomputer and the most efficient, consuming only a fraction of the energy and floor space of any other supercomputer.
The introduction of Blue Gene ushered in a new era of high-performance computing, continuing a long IBM tradition. Developed and manufactured in collaboration with the US Department of Energy's Lawrence Livermore National Laboratory in California, Blue Gene was originally built to help biologists observe the invisible processes of protein folding and gene development. Hence the name.
From an engineering standpoint, the guiding principle was simple but innovative: do more with less. When a small team of IBM engineers and scientists began developing the prototype for the Blue Gene ®/L in 1999, they were looking to make a radical departure from how supercomputers were being designed at the time. For decades, supercomputers had defined the state-of-the-art in high-performance computing and communications; but if their architecture stayed the same, the machines would soon require football field-sized buildings to house them. Worse, they would use enough electricity in one year to power a mid-size town, and they would require yet more power to prevent them from overheating.
Enter Blue Gene and a US$100 million, five-year development effort by IBM. Designed to harness thousands of low-power, cooler-running processors, the first IBM Blue Gene/L was built at the IBM lab in Rochester, Minnesota. On September 29, 2004, the new machine surpassed NEC's Earth Simulator as the fastest computer in the world.
Whereas IBM’s previous champ, IBM Deep Blue ®, had 32 processors and could calculate about 200 million potential chess moves per second in its historic six-game victory over a chess grand master in 1997, Blue Gene/L used 131,000 processors to routinely handle 280 trillion operations every second. A single scientist with a calculator would have to work nonstop for 177,000 years to perform the operations that Blue Gene could do in one second. The Blue Gene/L was also noteworthy for its choice of operating system, Linux ®, and its support for the development of open source applications.
Perhaps more important than its speed was the way Blue Gene/L revolutionized the economics of supercomputing, due to its small size and power efficiency. Each Blue Gene rack contained 1024 dual-processor nodes in a footprint that dramatically reduced floor space. The processors were engineered to be so tiny that 32 of them fit on a single microchip.
Blue Gene/L was a landmark in supercomputing, but its real work had only begun. IBM researchers then began to explore the wide range of applications that would run on the system. The computer’s speed and expandability enabled universities, governments and commercial research labs to address a wide range of problems that had simply been too complex to tackle. And leaders could also make more informed decisions—not just in life sciences, but also in astronomy, climate, drug development, cosmology and many other fields.
In September 2009, United States President Barack Obama recognized IBM and the Blue Gene family of supercomputers with the National Medal of Technology and Innovation, the country's most prestigious award given to leading innovators for technological achievement. And the influence of the Blue Gene/L energy-efficient design and computing model can be seen today across the information technology industry.
Blue Gene systems have helped map the human genome, investigated medical therapies, simulated radioactive decay, replicated brain power, flown airplanes, pinpointed tumors, predicted climate trends and identified fossil fuels. Much more progress lies ahead. When Blue Gene ®/P, the family’s second generation, was unveiled in 2007, it nearly tripled the performance of Blue Gene/L, immediately becoming the most energy-efficient and space-saving computing package built, at that point in time.
On February 8, 2011, IBM announced the 10-petaflop Blue Gene/Q supercomputer “Mira,” in collaboration with the US Department of Energy's (DOE) Argonne National Laboratory located near Chicago, Illinois. Mira was designed to enable significant advances in designing ultra-efficient electric car batteries, understanding global climate change, exploring the evolution of our universe and more. IBM continues to explore the cutting edge of high-performance computing as part of its ongoing quest to change the way research and science can be done.
Today, 17 of the top 20 most energy-efficient supercomputers in the world are built on IBM high-performance computing technology, according to the latest supercomputing “Green500 List,” including the Blue Gene/Q, which was named the “Greenest Supercomputer in the World” by Green500.org in November 2010. And other Blue Gene machines, with similar architectures, have held many of the top spots on successive TOP500 lists of the world’s fastest computers.