Bidirectional (2x25.6=51.2)

2 x 16-bit = 32-bit. 32-bit = 4 bytes. 4 x 6.4GT/s = 25.6GB/sec. Not 51.2GB/sec.

HT was never slow, not even the first one.
HT 800MT is more then fast enough to handle anything for the desktop at the moment.
The newer versions are simply faster, but that "extra speed" does nothing on Desktops as Chipset-manufacturers still force AMD to use their "chipsets" I wish HTX would simply replace 50% of the onboard stuff.
Then the AMD's can really show everybody what they are capable of, as PCI-e and "chipsets" are slowing them down.
Currently HT is simply too fast, the AMD problems are not located there.
PCI-e is a problem, as it needs silly conversions to HT that can be avoided by using HTX.

What I would really like to see is a hard drive or solid state implimentation of HT. I know that drives can't access remotely near these speeds, but a 15K rpm drive with 8GB of DDR3 would be awsome tied to an HT link. Even if there was a lot of IO overhead for translation.

I thought I could look over these things but its getting under my skin now: 
", FPGAs and non-X86 CPUs. And, it is matching its new competitor, Intel QuickPath, in the speed department right now."
that is not a sentence, its a fragment, if this was in the comments section it wouldn't be so bad.

And lo, yet Another AMD socket change is in the works.

Are they going to run this one in parallell to the THREE sockets they're already floating about in different guises?