I remember the first announcement some years ago from Tilera. Some persons shipped some emails to tilera asking for more details. Some just asked - like me - others also offered money to buy a cpu.
They all got a 'no'. But now that there are more details the chip sounds less impressive. Let's analyze based upon the vague information on the homepage. Lots of statements that a marketing department in India would write down as such are there as well; reformulating existing slogans into more political slogans, allowing you to deny later on that it performs very well. We know that trick just all too well. First of all homepage report it's 23 watts, yet doesn't say whether that's idle or under full load. It just says 'active'. Active is a vague way of formulating. I assume that's a core that isn't idle yet isn't under 100% load. So then it eats like a portion of the power. So probably it's a watt or 50 under full load. Then it says 64 cores in a grid @ 700Mhz. 700Mhz sounds as a possible Ghz frequency that you can get if you're a professional (if i'd build something count at it that it'll run 300Mhz or so). Doesn't seem like weird claim. 64 * 0.7 = 44.8Ghz measure Yet at the same time it claims on homepage 443 billion operations per second. What is an operation? Is that an internal iop? It says it's 32 bits VLIW. So that would mean it's processing each cycle 10 integers. Now we know from all other manufacturers they cheat factor 2, by double counting if just 1 instruction theirs is doing for example Fused Multiply Add. So we can divide it by 2 probably and get to 220 gflop. So then a vector would be 5 integers long, which seems like a weird measure. Maybe they rounded it up a tad and in reality mean 4 integers, sounds most reasonable. So then it's 64 cores in a grid executing vectors existing out of 4 units of 32 bits. Sounds plausible. If we compare that with some GPU's which are in our notebooks from a few years ago, then suddenly it's not so impressive. Vincent On Jan 24, 2012, at 5:24 PM, Eugen Leitl wrote: > > http://www.wired.com/wiredenterprise/2012/01/mit-genius-stu/ _______________________________________________ Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computing To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
