Topic: Top500 Supercomputers (Read 13577 times)

Are we there yet?

http://www.bitcoinwatch.com/

Tianhe-1A is a mixed architecture: 14366 CPUs + 7168 GPUs. A rough estimate of hashing power is 14366 * Xeon X5670 (8 Mhps) + 7168 * nVidia M2050 (100 Mhps) = 831 Gh/s. Xeon X5670 peak performance is rated as 2.93 GHz * 4 DP * 6 cores = 70.32 DP Gflops (DP == double-precision floating point as used to measure performance in Top500). nVidia states that M2050 achieves 515.2 DP Gflops. Thus for the CPU the Gflops/Mhps ratio is 8.8 and for the GPU it is 5.2. The combined CPU+GPU ratio is 5.7. For a single HD5870 GPU this ratio is 1.5 (544 Gflops and 375 Mhps).

There are few mixed CPU/GPU computers in Top500. Amongst the top 10 are only Tinahe-1A, Nebulae and TSUBAME. Roadrunner is using Cell processors which are similar to CPUs in performance. There are only 10 systems using nVidia technology at the Top500 list from November 2010. All other supercomputers are only CPU based thus the combined Gflops/Mhps ratio for the whole Top500 group would be around 8. At 43.6 Tflops combined this leads to an estimate of about 5.5 Thps. We are currently at 3.5 Thps.

As most miners are running GPU and not CPU miners, I think the estimated Tflops rate of the Bitcoin network is a very large overestimate: 42895 Tflops / 3377 Ghps = 12.7 is a ridiculous ratio. It's most likely that the ratio should be around 2 or 3, depending on the portion of remaining CPU miners.

Oh, I think you're right that the more useful question is the question of how much hashing power other computer systems have.  But, some people just want to know how many flops the bitcoin network has for this reason:

Well, I think you've got that backwards. The question is, in terms of "strength" of the network it is more important to know what the hash power of the competition could likely be, rather knowing the flop power of our network .... i.e. they are not going to attack us with flops but hashes.

So the flops-equivalent of BTC network number should properly be converted into a hash-equivalent of a possible attacker ... but I think people are mostly too lazy to bother doing that so just do it backwards and think forwards, if you know what I mean.

Sure, measuring bitcoin hashing performance in flops is wrong, but what we want to know is what the flops of the computers in the bitcoin network would be if they were doing something that required floating point operations?  Maybe there's just no way to know, but that's the question, I think.

That's true, but nearly every supercomputer in the top list are optimized for floating point operations.  That metric is simply an estimate of relative performance, so that the user can, at a glance, compare apples to oranges.

The funny thing is that FLOPS means floating point operations (per second) and SHA256 computations (the core Bitcoin hashing algorithm) take exactly 0 (zero) floating point ops as they consist of integer and bitwise ops only. Besides floating point operations are usually slower than integer and logical ones.

Bottom line is - measuring Bitcoin performance in FLOPS is wrong!

I don't understand the question.

I dont think the computing power of the total network is that exciting or the most important factor.

Eg, for a few million USD ($30 million) somebody like China could crush Bitcoin's network strength with simple custom made GPU like cards.


What is amazing,  and why I am betting on Bitcoin is ... The growing collective intelligence of the community.

  It seems to be growing really fast, its like more and more smart people are joining forces everyday, and Bitcoin itself has lots of ability to be adjusted to face problems.

When the eye of sauron turns on Bitcoin I am betting on Bitcoin

So my rough estimate i made in my head was really true. Damn, that sux that i didnt stay crunching btc in july 2010 and went to search for aliens again..... doh

Well done miners...

anyone thought about a wet cellar drying business?

Tianhe-1A hashing power, very accurately IMO has been estimated as 850 Ghps. Assuming the rest of top 500 supercomputers have the same TFLOPS/Ghps ratio than bitcoin needs to hit 8Thps to dwarf all top 500 supercomputers combined. We are more than halfway there already. Another difficulty increase or two and 50% attack with supercomputers would require all those babies in top 500 list combined. Moreover while they configure them to do something bitcoin network would double once more.

Are we there yet?

I am an folder myself, and have been for almost 2 years now. CPU's are actually better then lets say an 580 for example, if they have 8 threads and are doing bigadv. We just do it for the cure, and for the competition. Once you get into a team such as evga or ocn it's fun to do and hang around in the forum threads. No we don't win anything with it except for some good team spirit
Nvidia cards are way way better at folding then ati/amd cards, the opposite is true for bitcoin. So we aren't really taking bites out of eachothers computing power.
Folding is mostly based on floating point performance where hashing is all about integer performance. Nvidia doesn't care too much about integer performance because floating point performance is generally a lot more important in games. I'm not sure how amd makes up for that (i guess the amount of shaders).

Stanford doesn't rent out it's donors...

Also yes, I guess steps toward curing sickle-cell disease (drepanocytosis), Alzheimer's disease, Parkinson's disease, Bovine spongiform encephalopathy, cancer, Huntington's disease, cystic fibrosis, osteogenesis imperfecta, alpha 1-antitrypsin deficiency, and other aggregation-related diseases does have economical value.

Perhaps you should read into the project a bit more, http://en.wikipedia.org/wiki/Folding@home

and the university behind it http://en.wikipedia.org/wiki/Stanford_University before you go all conspiracy theorist/big-brother-business on us.

They also started in 2000, they have 100x more trust than bitcoin will have in the near future.

Actually yes.  Although I'm impressed that all that research has it's basis in the Folding@Home project, I did notice that most of that same research were subjects with real economic value.  Said another way, Folding@Home seems to be used as a means for research companies to get research done on the cheap.  If the Folding@Home contributiers knew that they were being exploited for the profit of others, particularly "big pharma" would they still participate?

http://folding.stanford.edu/English/Papers



Any other questions?

I'm sure that all that processing power that is contributed to folding@home makes the contributers feel good and a part of something, but what has come of that project?

Bitcoin, on the other hand, has tangible benefits for both the community and the contributer.  It is no shock to me at all that Bitcoin's total power leapfrogged right past them.

LOL...how are you comparing power to number? That's just a graph of how many CPU's, not the total power. The total number of GPU's the mining community has compared to the F@H community's CPU's is indeed much smaller. However, their GPU's are also many times faster than the CPU's. Also, CPU power is not totally wasted, and many people there will buy hexacores/octacores just like people here will buy 5870's.

True, but bear in mind that they too have a large number of GPU crunchers. I don't know if they've got more then us but I suppose that can be easily found out, no?

When that is a list of active "CPUs"... yes, I think we can.

Our GPUs are approximately 100X faster than their CPUs.