Distributed computing performance has exceeded 81 million petaflops, but science only got 470, are you ready to participate?

Recently, one of the distributed computing programs - SETI@Home, used to search for a signal of intelligent origin, analyzing data received by the 300-meter Arecibo radio telescope, which is currently closed, also announced its closure, since all data since the commissioning of the telescope and before its closure were successfully processed. This became possible thanks to many millions of volunteers - ordinary users who provided free computing power of their devices for data analysis. Some of them even got into serious trouble with the law because of their passion - Admin stole computers to take the lead in SETI@Home.

And if the usefulness of spending so much computing power to find a signal from an intelligent civilization among the many other radio signals recorded by a telescope seems somewhat doubtful, then other projects like SETI@Home are more applied, even despite the fact that the same Folding@Home Donates Computing Power to Fight Coronaviruswhen there are many other diseases and tasks, perhaps no less important, and perhaps even more. On the other hand, the latest news added 400 adherents to the project in a very short period, which, in particular, will help in the future to invent medicines for other misfortunes.

But what is truly striking is the progressive Idiocracies of our world, and this year its particular aggravation can be traced. Folding@Home is currently the largest charitable distributed computing project for science, has 470 petaflops at its disposal, which is more than 2 times the performance of a supercomputing system Summit, but at the same time, 81000000/470 = 172 340 times less than the performance of the world's most powerful distributed computing system, which serves what do you think? Bitcoin! And it has a performance of almost 81 million petaflops.

This article is an attempt to draw attention to the problem, and perhaps switch the attention of someone involved in cryptocurrency mining to really vital tasks, because you can’t buy life for cryptocurrency and money, although, of course, there are benefits from mining. Manufacturers of computer farms, electricity suppliers and data centers earn on these people.

We, as a hosting provider, sometimes have free resources, but we are forced to pay very impressive electricity bills, which, as we see, are spent quite significantly if a school administrator managed to cause damage to the institution for 10 million dollars in 1,5 years. Therefore, we do not install such distributed computing systems on servers and do not encourage mining at all, since it is expensive and pointless, and no one likes peak loads on the network. Another thing is home or office individual users. If you have the opportunity to run some kind of computational process, in addition to mining cryptocurrencies, while using idle power, this can bring significant benefits to you and science in particular. Just register in one of the projects - Folding@Home or BOINC to choose from. And you will definitely make your contribution. Another thing is the contribution to what and will it really be as valuable as it is said?

BOINC is a program that provides unused time on your computer for scientific projects such as: SETI@home, Climateprediction.net, Rosetta@home, World Community Grid and many others. After installing BOINC on your computer, you will be able to choose and participate in several projects at the same time, which ones you decide for yourself. On the site https://boinc.berkeley.edu/ there is an opportunity to choose which calculations for science you want to carry out.

Folding @ Home (F@H, FAH) is a distributed computing project for computer simulation of protein folding. The project was launched on October 1, 2000 by scientists from Stanford University. In 2017, Bitcoin became the largest distributed computing project, overtaking Folding@Home. However, in March 2020, everything changed:

On March 14, 2020, technology giant NVIDIA Corporation called on gamers to use the power of their home computers to fight the coronavirus. A few days later, CoreWeave, the largest US miner on the Ethereum blockchain, announced that it was joining the fight against the coronavirus. The Russian telecom giant MTS also did not stand aside and announced that its cloud resources will be directed to the Folding@Home project in order to accelerate work to find a cure for the new coronavirus.

Four weeks after joining F@H in the fight against coronavirus, Greg Bowman said that 400 volunteers around the world had joined the project. With the influx of new users after the announcement that F@H is joining the fight against the new coronavirus, the project's capacity has increased to 000 petaflops. Thus, the Folding@Home project can be called the most powerful supercomputer in the world, second only to Bitcoin, whose power is 470 petaflops.

On March 26, 2020, the total computing power of the network exceeded 1,5 exaflops, which is almost equal to the total performance of all supercomputers in the TOP500 world ranking - 1,65 exaflops.

On April 12, 2020, the total computing power of the network exceeded 2,4 exaflops, and on April 23 - 2,6.

However, this is still well below the performance of the Bitcoin system, whose participants could also contribute. But perhaps poor awareness prevents this from being done, or maybe the reason is completely different?

I personally knew about the SETI@Home project, and even took part for some time in 2004-2006, until I decided that the value of these calculations tends to 0, but did not know at all about Folding@Home, which has many planned studies on years of calculations ahead and probably more valuable (unless you take into account that they succumbed to the worldwide hysteria to develop a vaccine for only one disease, while many other studies are suspended). And successfully became part of the network for a while:

Distributed computing performance has exceeded 81 million petaflops, but science only got 470, are you ready to participate?

Nevertheless, after only a short use (about a week of intensive computing), after giving my Mac for cleaning, the service told me: “we replaced the thermal paste on your video card, since it simply dried up, you were actively working with graphics”?

Are you ready to carry out this kind of calculation for free for the sake of “science”, when it is not clear which people prioritize COVID-19, which, as has already been proven in Sweden, does not cause any particular problems, while other studies become secondary for some reason, although perhaps more important? Or for the sake of dubious numbers in the Bitcoin wallet, which obviously will not cover your expenses for powering and maintaining your computer (and even if they do, they are of no practical use)?

Personally, I don't. Therefore, he removed the Folding@Home program, deciding for himself that all these “distributed computing” are about as useful as Bitcoin. After all, it became obvious to me that if something is developed thanks to these calculations, then, alas, it will be sold to pharmaceutical corporations for quite real money, which will charge you and me for medicines. And if we are charged for medicine, it is logical that the participants be paid some money for their computing resources, then the research program recorded in the road map will be more sensible (and not at the Seti@Home level, from which, as a result, more harm, than good, since a huge amount of resources was used without any concrete result), and these studies should be paid primarily by pharmaceutical companies that will sell certain drugs to you and me.

And since few would-be drug developers are willing to share the budget and fund Folding@Home and its users, the value of the project is highly questionable. Otherwise, why aren't pharmaceutical corporations funding the project and their users en masse?

After all, it would be possible to attract even more people to the project, promising, albeit small, but a fee for their resources. Which would be honest and reflect the level of utility. Funds to pay users could be taken from pharmaceutical companies that need distributed computing resources to produce certain drugs, and they could be distributed proportionally among users, depending on how much of the resources they provided for this or that study. And also from state budgets and taxes, because for some reason the hadron collider is financed? Why not fund a more useful project if it helps get cures for Parkinson's, cancer, and other diseases?

Obviously, the benefits of these projects are about the same as the benefits of the project to search for extraterrestrial civilizations, otherwise it would all be financed by pharmaceutical companies and would actively use the results obtained. Or these "charitable" organizations are already selling data to them, motivating users, attracted to the project for free, to think that they are working for the benefit of all mankind. While they bring only a small share of the benefit, and specifically to those who work in these projects as administrators, after all, who prevents you from contacting someone from the organization and motivating him a little financially to push through this or that research?

Surprisingly, for some reason on the net, no one has ever raised these questions. Moreover, large companies like Amazon and even mobile operators have joined the project, assuring ordinary people - potential "victims" of marketing, of the extreme benefit of this whole thing.

What is your opinion on this matter? Perhaps I am mistaken and science develops only due to sacrificial collective participation in something? How much does life cost or $ 2,1 million per injection: miraculous gene therapy - perhaps this article will be a good answer to the second question and will make many people think before they sacredly believe in philanthropists.

Some ads 🙂

Thank you for staying with us. Do you like our articles? Want to see more interesting content? Support us by placing an order or recommending to friends, cloud VPS for developers from $4.99, a unique analogue of entry-level servers, which was invented by us for you: The whole truth about VPS (KVM) E5-2697 v3 (6 Cores) 10GB DDR4 480GB SSD 1Gbps from $19 or how to share a server? (available with RAID1 and RAID10, up to 24 cores and up to 40GB DDR4).

Dell R730xd 2 times cheaper in Equinix Tier IV data center in Amsterdam? Only here 2 x Intel TetraDeca-Core Xeon 2x E5-2697v3 2.6GHz 14C 64GB DDR4 4x960GB SSD 1Gbps 100 TV from $199 in the Netherlands! Dell R420 - 2x E5-2430 2.2Ghz 6C 128GB DDR3 2x960GB SSD 1Gbps 100TB - from $99! Read about How to build infrastructure corp. class with the use of Dell R730xd E5-2650 v4 servers worth 9000 euros for a penny?

Source: habr.com

Add a comment