Well if you ever wanted to be 'out there' Chuck's processor would be a great place to start. Chuck Moore invented Forth and has been building machines that can run Forth efficiently for years. Think of it as a Turing machine that can do useful work. He has pushed the edge of computation per watt for years.<p>That being said, I've heard him talk about this chips for years and it is great to see it finally see the light of day. If you were familiar with the Transputer technology, this is a better take on that, if you are familar with FPGAs you can think of it as an FPGA with processors instead of CLBs.<p>Things that it can do are similar to what Intel is doing with Larrabee or some of the CUDA stuff that nVidia has done. It doesn't have a GDDR3 interface to a GB of memory so you can't custom build your own GPU, but you could do your own PhysX type engine with it.<p>It also makes a helluva differential cryptanalysis tool, or a signals analysis tool in general.
Not being much of a hardware geek, I'm having a hard time evaluating how fast each core is.<p>From the site: "With instruction times as low as 1400 picoseconds and consuming as little as 7 picojoules of energy, each of the 144 computers can do its work with unprecedented speed for a microcontroller and yet at unprecedentedly low energy cost, transitioning between running and suspended states in gate delay times. When suspended, each of the computers uses less than 100 nanowatts."<p>How does this instruction time compare to other modern processors?<p>It sounds to me like some of the benefit to be had here may be from the low amount of power necessary per core. Power and associated cooling is a MAJOR source of cost for datacenters, and so if this really is a significantly lower power consumption (again, I don't know how much power the alternatives use), then it could have a big impact on the cost of commodity computation power.
Glad to see this thread. G144A12 does better than you'd expect for 18 bit ALUs doing 32 bit circular shifts and adds, but that costs enough extra instructions that for this particular algorithm at any Bitcoin-useful combination of throughput/energy/cost we can't compete with the genuine 32-bit ALUs of the bigger ATI GPUs. Ya can't be perfect for <i>all</i> problems <i>all</i> the time :) Nevertheless we'll be posting an app note eventually on SHA256 as an illustration of techniques in pipelining. The $20 price is for small quantities. Standard exponential decay curves apply for production quantities; we want to see our chips in people's products and are priced to encourage that. As for 20 somethings, nobody in our company gets a paycheck (yet) so someone has to be willing to work for nothing, but if you have a <i>practical</i> idea for an app note and want to work with us to get it done and published please email greg at greenarraychips dot com and let's discuss it. Thanks for your interest, folks - Greg Bailey, GreenArrays, Inc.
I certainly should voice my opinion here.<p>I've done analysis of GA144 before: <a href="http://news.ycombinator.com/item?id=1810641" rel="nofollow">http://news.ycombinator.com/item?id=1810641</a><p>Most of the Chuck Moore design (I reviewed several, starting from M17) can be described by quote from Devil Wears Prada: "the same girl- stylish, slender, of course... worships the magazine. But so often, they turn out to be- I don't know- disappointing and, um... stupid". Chuck Moore designs are all slick, slender, stylish, worship Forth, but they turn out to be disappointing and stupid in the end. The only beneficiary often is Chuck Moore itself. You just cannot apply his experience to other places in the world of computing.<p>Let's see what we have here in GA144.<p>The memory inside all cores is way too small for general purpose programs, even if you split your program into 144 parts and spread them across cores. 64 words of RAM, ie, 128 bytes. 128 bytes times 144 - 18Kbytes. Same for the (program) ROM, and you should factor communication code in there. Communication cost affects RAM as well.<p>They offer no compiler from high-level language like C. You had to learn a specific dialect of Forth and some bizarre (albeit small) assembly language.<p>The only benefit for general population from this affair is the relative ease of the desing of asynchronous hardware.<p><a href="http://en.wikipedia.org/wiki/Asynchronous_system" rel="nofollow">http://en.wikipedia.org/wiki/Asynchronous_system</a>
In past Forth threads I've complained the the Forth model for a computer seems just too at odds with how modern CPUs actually work for me to want to learn it. Well, I look at this thing and its like the soft draft of the future slipping underneath the door, whispering that maybe I should learn Forth after all.
Love the guy and his passion for its chips, but this 144-computer chip looks like a solution in search of a problem:
what is trying to solve? How's the inter-core communication handled? On the other hand, creating weird chips like these, just because you can, is awesome and stimulating a hacker's mind.
You can buy a 10 pack of evaluation chips from Green Array's web site or single from schmartboard's website <a href="http://www.schmartboard.com/index.asp?page=products_csp&id=532" rel="nofollow">http://www.schmartboard.com/index.asp?page=products_csp&...</a>
I think this sounds ridiculously cool and at $20 I could probably afford to play around with it. But I have no knowledge of hardware, just programming. To me chips just look like thin green rectangular prisms. How would I get it to actually, you know, do stuff?
The Propeller chip <a href="http://www.parallax.com/propeller/" rel="nofollow">http://www.parallax.com/propeller/</a> is another embedded market chip in the same vein although nowhere near as many cores. Having something like this make for some interesting embedded designs.<p>Also, check the site for the arrayForth stuff.<p>On another note, it would be interesting if something like these existed in the 64-bit size. Larrabee is interesting, but if it was a simpler stack machine at around this price point then perhaps some work could be done on different ways to do parallelism.
This is all new to me. Does anyone know if these chips could be used for bitcoin mining?<p>However, I believe you would have to write completely new programs if it is possible.