EXASCALE COMPUTERS COMING IN 2022 

 DIGITAL COMPUTERS MERELY count on two fingers, 1, 0, on, off; but they do so amazingly quickly. And the faster they count, the more things they accomplish.

Recent articles in Science magazine identify that a new high is coming in this finger counting: Both China and the United States are developing computers that are able to carry out more than a quintillion (10¹⁸) calculations per second. 

Clock Rate Heritage. As noted in Wikipedia, the first commercial PC, the Altair 8800 had a clock rate of 2 MHz (2 million cycles per second). The original IBM PC (c. 1981) had a clock rate of 4.77 MHz (4,772,727 cycles per second).

By the year 2000, the 1 GHz milestone was reached; in 2002, an Intel Pentium 4 model was introduced as the first CPU with a clock rate of 3 GHz (three billion cycles per second). 

Processor Cores Are Important Too. Computers with multiple cores are capable of multitasking; in a sense, of having more pairs of fingers. To some extent, this affects computer performance, just as clock rate does. “What is Processor Speed and Why Does It Matter,” by Sophie Sirois, HP Tech Takes/…, December 18, 2018, discusses the interplay of computer clock rate and processor core. 

Sirois summarizes, “If you’re running a lot of applications at once or playing complex games, you’ll likely need a 4 or even 8 core processor. If you’re just looking for a computer to get basic tasks done efficiently, a dual-core processor will probably work for your needs.”

“For CPU intensive computing like video editing or gaming,” she says, “you’ll want a higher clock speed close to 4.0 GHz, while basic computing needs don’t require such an advanced clock speed.” 

The Six Giants: Kilo, Mega, Giga, Tera, Peta, and Exa. Our computers have made kiddy stuff of the kilo (10³). As noted here at SimanaitisSqys, my Apple iMac operates at 3.2 GHz, with 1.0-terabytes of disc storage.

And, to put this in perspective, as described in “A Need For (Computer) Speed?”, November 18, 2012, “In June 2012, the IBM Sequoia hit a top speed of 16.32 petaflops…. Then, only a few days ago, it was announced that the Titan supercomputer, a Cray XK7, raised the bar even more. This machine (actually, like the others, a linkage of hundreds of thousands of processors) has operated at a rate of 17.59 petaflops, with a theoretical speed of 20 petaflops.” A petaflop is 10¹⁵ operations per second, equivalent to those two fingers counting very quickly indeed.

The Latest. In its News section, Science, December 24, 2021, reports “China Debuts Exascale Computers. “China,” Science says, “has yet to officially announce the machines, for reasons that remain unclear. And details about their performance have yet to appear on the TOP500 list of supercomputers, which ranks the world’s top machines based on common benchmarks. But according to technology watchers, the new supercomputing champs are Sunway Computer Co.’s OceanLight and the National Supercomputing Center’s Tianhe-3.” Science continues, “Installation of what will be the first U.S. exascale computer, Frontier, is underway at Oak Ridge National Laboratory; it is slated to come online in 2022.”

“Exascale supercomputers,” Science notes, “are expected to enable the marriage of artificial intelligence with massive data sets, transforming fields such as personalized medicine and materials discovery and generating more realistic models of climate change and the accelerating expansion of the universe.”

Breakthrough 2021. In fact, Science, December 17, 2021, chose “Protein Structures for All” as its 2021 Breakthrough of the Year. At its heart is super-powerful computers using Artificial Intelligence to model the shapes of proteins. “Biological workhorses,” Science calls proteins: “They contract our muscles, convert food into cellular energy, ferry oxygen in our blood, and fight microbial invaders.”

“Yet despite their varied talents,” Science observes, “all proteins start out with the same basic form: a linear chain of up to 20 different kinds of amino acids, strung together in a sequence encoded in our DNA. After being assembled in cellular factories called ribosomes, each chain folds into a unique, exquisitely complex 3D shape. Those shapes, which determine how proteins interact with other molecules, define their roles in the cell.”

Science summarizes, “… it’s still a daunting task to visualize most of the large, multi­protein complexes that carry out myriad jobs in cells. But this year’s explosion of A.I.-driven advances offers a view of the dance of life as never seen before, a panorama that will forever change biology and medicine.” 

And exascale computers will expand this panorama. ds 

© Dennis Simanaitis, SimanaitisSays.com, 2022