|
Title: How would something like this work in mining? Post by: JackH on June 27, 2014, 09:21:52 PM I cant say I am a hardware engineer or even come close to understanding how to approach to solve double SHA256 via ASIC processors or the like. While I have mined myself, I am a novice in regards to hardware and its architecture.
However this: http://cognimem.com/ just poses the question of, how it would do in Bitcoin mining (giving the correct software was made for it)? Would love to hear from an expert how and if something like this would be beneficial for mining? Or is it a dead end completely? Title: Re: How would something like this work in mining? Post by: DeathAndTaxes on June 27, 2014, 09:28:03 PM Nothing beats an ASIC. Without even looking at the details it may (longshot) have been a plausible contender against GPU or FPGAs but not ASICS. An ASIC does one thing and one thing only. A general purpose processor can do lots of different "things" but that flexibility means the chip is never fully used (every transistor, every gate, every possible bit of performance). An SHA-256d mining ASIC does nothing else. There isn't a single wasted transistor, it only has exactly what it needs. The flip side of that is it is worthless for any other task even a very similar one.
Simple version: the only thing which "beats" a SHA-256d mining ASIC is a more efficient SHA-256d mining ASIC. Title: Re: How would something like this work in mining? Post by: JackH on June 27, 2014, 09:51:04 PM But cant a chip like this one, be made into an ASIC version, yet keep doing what it does the way it does it? Its not based on the von Neumann bottleneck, so it should get to the solution differently (faster?)
Title: Re: How would something like this work in mining? Post by: DeathAndTaxes on June 27, 2014, 10:04:27 PM But cant a chip like this one, be made into an ASIC version, yet keep doing what it does the way it does it? Its not based on the von Neumann bottleneck, so it should get to the solution differently (faster?) Well all chips are "ASICs" however a general purpose pattern recognition chip isn't going to out perform a hyper optimized single purpose chip. Also there is no practical VN bottleneck in SHA-256d mining. Title: Re: How would something like this work in mining? Post by: BurtW on June 27, 2014, 10:09:43 PM Here are the things they say it is good at:
Based on this list it is safe to say that it would not be good at Bitcoin mining. |