For some, Bitcoin conjures ideas of a utopian decentralised currency, but many others these days think of it as a quick way to make a buck. Countless hordes of Bitcoin prospectors are now using their computers to “mine” for Bitcoins by solving specific hashed values. Now, the processing power of these miners is being estimated to be six to eight times greater than the top 500 supercomputers combined. Which is quite mind boggling.
A Bitcoin-centric site called The Genesis Block recently broke down the data that shows just how powerful the Bitcoin mining network actually is. The processing power estimates passed one exaflops (1018 floating-point operations per second) recently, and that is no small feat.
Sequoia, one of the world’s fastest supercomputers, is capable of 16.32 petaflops, but that’s only 1.6 per cent of the estimated power of the Bitcoin mining network. As it turns out, the processing power of these computers dedicated to mining for Bitcoins is somewhere between six and eight times greater than all of the top 500 supercomputers combined.
Keep in mind, however, the fact that these estimates aren’t perfect. As Bitcoin mining doesn’t rely on floating point operations, these estimates are based on opportunity costs. Now that we have hardware with application-specific integrated circuits (ASIC) designed from the ground up to do nothing but mine Bitcoins, these estimates become even more fuzzy. Even so, the sheer muscle of this distributed computing is undeniably jaw dropping. Even the most sceptical among us has to be dumbfounded by the power.
Unfortunately, this isn’t just a feel-good “look at all these damn flops” situation. Some people are getting rather upset that all of this horsepower is being wasted on solving meaningless problems for cold, hard cash.
Instead of looking for virtual money, this network could be used to help us understand physics or even cure diseases. While it would most certainly be better for humanity to fold proteins or search for radio signals with distributed computing of this scale, it just isn’t that appealing. The fact is, none of that is as enticing as getting paid.
Regardless of motivations, this is a perfect example of why distributed computing is such an amazing technique. 500 of the world’s fastest computers can only do a small fraction of what a network of this size can accomplish. If we can take what we’ve learned from Bitcoin mining and apply it to scientific endeavours, we might just get something meaningful accomplished. Think how fast these miners would jump on Folding@home if the US government promised massive rewards for curing diseases.
For more on matters Bitcoin-related, see One Bitcoin by the numbers: Is it still possible to make a profit, and AMD thrashes Nvidia at Bitcoin mining – will the gap ever be closed?