2

Many developers envisage Ethereum's potential to harness distributed computational processing rate to potentially/hypothetically overtake our worlds most non-distributed clusters.

http://www.distributedcomputing.info/projects.html

https://www.top500.org/lists/2016/11/

^ According to this site's November 2016 ranking;

Sunway TaihuLight clocks@ 125,435.9 TFlop/s

and

Tianhe-2 (MilkyWay-2) clocks@ 54,902.4 TFlop/s

Assuming the Ethereum platform can successfully synchronise peers, do we have any mathematicians here that can model how many distributed Ethereum nodes it would take to compete?

Perhaps as part of the future Ethereum protocol we could ask contributors to partition only 5-10% of their CPU's power (not affecting an average users other/daily processing requirements)?

Personally for me, this is why I think Ethereum has great importance! This would be disruptive to the currently commercially available software suites, promoting the development of "everyday" "Ethereum Powered" DApps from Media editing to realtime GIS applications, initially. However I think with active collaboration with existing non-distributed cluster projects could greatly advance our current scientific modelling capabilities and increase our overall efficiency. Just a thought for the EF to approach, many of these projects are open source/non-proprietary licensed too?

We could dynamically adjust gas/eth price to dramatically offer these applications for a fraction of the price offered by leading commercial software providers - and make it even cheaper for registered educational/research institutional hubs to use.

I think project Golem have similar scope but it's not at EVM protocol level and already separately tokenised?

| improve this question | |
3

We are working right now on such a project - coupling ethereum and decentralized BOINC. You can find preliminary white paper here: http://sonm.io/Sonm1.pdf

Rob, is it possible to make a contact with you for our CTO in order to discuss more the issues, which you mention above? Also it s interesting what do you think about the white paper and the concept.

| improve this answer | |
2

As I understand it, Golem and possibly others are working on "processing on demand" (my term), i.e. pooling surplus CPU/GPU power. The idea is people might buy and sell firepower.

It might be possible to aggregate power for apps that are well-suited to parallelism. If that can be done, it might resemble an immense distributed super-computer with properties that are similar (but different) from actual super-computers.

Such a thing would have needs for managing incentives, settlement, even proofs of honest (and correct) computations. Smart contracts might be helpful at that management level. They might be the administrative glue that binds the raw power together into something like a bid/ask price discovery market. Smart Contracts could arrange presentation of resources, possibly cluster formation and they could ensure payment is processed, for example.

Having said that, Ethereum's hash power, while impressive, isn't useful for the raw processing power of such a scheme because it's not designed to scale performance. The EVM doesn't process any faster regardless of how much power we throw at it. That's by design. Proof-of-Work is designed to scale security. It raises the theshold an attacker would have to overcome for a successful 51% attack.

The EVM is a very reliable state machine but not so much of a number-cruncher at the app level.

Hope it helps.

| improve this answer | |
  • Nice one Rob, very helpful, thanks! Was really just a postulation into Ethereum's future potential. So how about when we change hashing protocol? I am still learning but I think the community wishes active developers all the best to offer a solution(s) to the processing of the Ethereum blockchain. Whether this becomes an elegant Proof of Stake or an evolved/electrically efficient means of Proof of Work, I'm sure you guys will give it best shot. Perhaps there will come a time when EVM needs to accommodate scaling computational processing capabilities as part of the trade off - thanks again : ) – SHA256 Jan 4 '17 at 21:02
  • Glad it was helpful. I imagine people look at the immense hash power and their intuition leads a certain way. It's part of the journey. You're right. I could say this is all based on my current understanding of the EVM we have today. I expect it to remain approximately correct even after some foreseeable consensus algo changes. – Rob Hitchens Jan 4 '17 at 21:23
  • Yes, I think you are right by current design - would be super cool though! : )) (big thumbs-up) – SHA256 Jan 4 '17 at 21:32
  • Shamelessly points to the little arrow above the 0 ^ ... Please feel free to vote up if I answered your question. :-) – Rob Hitchens Jan 4 '17 at 21:40

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.