Never mind, then.

I was under the impression that the 20% speed increase for AVX2 over AVX.

If I may give my uninformed opinion based on regurgitating the opinions of people that tend to impress me:

There are a few possibilities for the future:

(1) Wider data pipes, processing things in bigger chunks, 128-bit, 256-bit, and so on.

(2) 3-d chips: By either slowing down parts, or maybe finding a different way to lower temperatures, we can go 3-d and pack more stuff in.

(3) Since everybody wants to imitate the human brain, how about thousands of tiny chips with multi-kilobyte caches that work in tandem to do things like find cat videos on Youtube, or decide the 3 year old in the road is a rather unusual obstacle to deal with.

[QUOTE=chalsall;308069]And let's be honest -- when many of us wear computers on our hips which are more powerful than what used to be called super computers, just how much more computing power does the average person really need?[/QUOTE]Here is an example of that.
[url]http://mersenneforum.org/showpost.php?p=308438&postcount=42[/url]
That prime was initially found on a true super-computer (1982).
:busy:

[QUOTE=ixfd64;308163]
On the other hand, Haswell's AVX2 and FMA3 will likely reduce the gap between [B]actual performance and that projected by Moore's law[/B]. It probably won't offer twice the speed of Sandy (Ivy) Bridge, but I'd imagine that the performance boost would be similar to that of Sandy Bridge over non-AVX chips.
[/QUOTE]

Rubbish. Moore's Law never said anything about CPU speed or performance. It only talked about tpsi (transistors per square inch).

dear [URL="http://venturebeat.com/2012/11/30/raspberry-pi-model-a-production/"]Raspberry Pi[/URL] A comes before B!