If you read the description, they started with 35,000x, then tripled the number of cores to get 68,000x. If your triple the cores and wind up with less than twice the performance, your scaling isn't very good.
It's very difficult to get a 32x speedup from 32 cores as there are always parts that are inherently serial, so it's more likely they tested it on a 64 core machine or something like that.
Presumably it's parallelizable. Double the clockspeed, 16x the cores... that'll get you 32x improvement right there, but you've also got way more L3 cache, which might help considerably.
Damn. 41.93 million cores is quite a lot.
Even if they are rather specialized cores.
And 14nm is not THAT far behind, and the previous machine in that series used 28nm process node.
And I suspect it being SMIC's 14nm node also matters a lot.
Gota be fully domestic and homegrown on all fronts.
I guess with their 2 year timeline they were using at least 3250x whatever they define as a standard CPU - I wouldn't be surprised if it was simply 3250 cores @ 2 years or an equivalent higher number and less time.
I'd be interested about the actual specs of the hardware if anyone see's that info pop up.
reply