GR: In the age of clouds, massive data centers, AWS and Azure, what is a reasonable dedicated Supercomputer purpose? As an answer, outline the top 10 uses of supercomputers today, in 2022.
Supercomputer Purpose in 2022:
ChatGPT : Supercomputers are some of the most powerful computers available and are used for a variety of high-performance computing (HPC) applications.
Here are the 10 most common uses for supercomputers today:
- Weather prediction:
Supercomputers are used to process large amounts of data from weather satellites, radar, and other sources to create accurate weather forecasts. - Climate modeling:
Supercomputers are used to simulate and study the Earth’s climate, including the impact of human activities on the climate. - Molecular modeling:
Supercomputers are used to simulate and study the behavior of molecules and chemical reactions, which can help in the design of new drugs and materials. - Aerospace engineering:
Supercomputers are used to design and simulate aircraft and spacecraft, as well as to analyze the aerodynamics and structural integrity of these vehicles. - Financial modeling:
Supercomputers are used to analyze and predict market trends and evaluate the risks and potential returns of financial investments. - Oil and gas exploration:
Supercomputers are used to analyze and interpret data from seismic surveys and other sources to locate oil and gas reserves. - Protein folding:
Supercomputers are used to simulate and study the folding of proteins, which can help in the understanding and treatment of diseases. - Earthquake and disaster prediction:
Supercomputers are used to model and predict earthquakes and other natural disasters, which can help in the development of early warning systems and evacuation plans. - Drug discovery:
Supercomputers are used to simulate and study the behavior of potential drugs, which can help in the design and development of new medications. - Astronomy and astrophysics:
Supercomputers are used to simulate and study celestial objects and events, including the evolution of galaxies and the formation of stars.
.
See Also: Top 10 Applications of Computer Vision
OpenAI / ChapGPT v3.5 — 2022.12.24 Sat — 18:14 [TS]
We should also provide a definition of supercomputing, since this has shifted across the years. As we’ve stated elsewhere on this blog, an iPhone 14 Pro Max has more on-board processing power than the top 500 supercomputers in the world, combined, in 1995.
Excerpting from AI Circuit Design Software: Designing the Designers:
“I stared at my 9-pound state-of-the-art Sony laptop. Considered the chip controlling all of its awesome functions. Some 10 million transistors on that Pentium III, running about 900 million instructions per second, (MIPS)…
for comparison: my 1981 IBM PC (Intel 8088) had 30,000 some transistors, topped out at 5 mHz, and did about 750,000 instructions per second (1/1000th the speed).
My 2022 iPhone 14 Pro’s A16 Bionic chip has some 16 billion transistors, runs at a clock speed of 3.5 GHz, and performs, at peak, around 17 trillion operations per second (that’s the equivalent of about 20 million times the power of my ’81 PC, or 20,000x as fast as my sony laptop.. yet, fits in my pocket).”
Supercomputers are generally defined as the highest performance computing platforms in the world, which are contained within a single physical location and do not rely on externally networked machines for raw compute power (though they are often tasked and managed by network connected clients). Since Moore’s Law (the doubling of compute power every 18 months) is in effect, the definition of supercomputer, in terms of performance, is a continually moving bar.
Generally, the world’s fastest supercomputer, at any given time, is significantly faster than the 2nd place contender. This is evidenced by Japan’s recent leap to the top of the queue, with its RIKEN Fugaku supercomputer (440 petaflops) a full 30% faster than the 2nd place LUMI system at EuroHPC/CSC (Finalnd, 310 pFlops).
And now we have the Americans coming on strong, finally launching Frontier, the first exaflop (1,000 petaflop) supercomputer to ever exist on planet earth. It exists at the super secret Oak Ridge National Labs in Tenessee, the same lab where nuclear fusion reactors were pioneered in the 1970s. Which makes us wonder, what is this particular Supercomputer Purpose?
It is of note that Frontier achieves this insane performance at a very efficient power draw of “just” 20,000 kilowatts (20 million watts), which is actually only 2/3rds the energy consumption of Japan’s Fugaku… so Frontier achieves 3x the compute performance, at 2/3rds the operating cost. Not bad…
To track the growth of supercomputing performance across the eons, lets take a look at Kurzweil’s famous graph from his 2005 treatise, “The Singularity is Near”:
