HyperTransport speeds up
Matches Intel's QPI just before IDF opens
STILL REMEMBER HyperTransport? Well, the fast chip-to-chip interconnect, now in its seventh year of existence, has not given up just because a bad day - let's make it a year - at the AMD processor races.
Companies including Broadcom, Altera, Nvidia and such are actively pushing HT in a variety of apps not exactly related to the AMD CPUs, like ultrafast networking, FPGAs and non-X86 CPUs. And, it is matching its new competitor, Intel QuickPath, in the speed department right now.
In about eight hours, Mario Cavalli, GM of HyperTransport consortium, is to announce the HyperTransport 3.1 spec, which adds the 2.8, 3.0 and 3.2 GHz clock speed settings to bring the 2 x 16 bit bidirectional standard implementation bandwidth towards 6.4 gigatransfers per second, or 51.2 Gigabytes/s for us ordinary mortals.
The HTX3 matching spec for the slot and board products accessing the HT-enabled CPUs directly was also updated to the full HT3 speeds (5.2 gigaxfers/s right now) plus link splitting on a single connector to allow two HT CPUs - or, why not, GPUs - to access a single cards simultaneously. Now this would allow some interesting successor designs for the CrossFire and SLI, with larger GPU arrays connected on HTX slots.
Importantly, with the updated HTX slot and board spec, HyperTransport has fully defined ultrafast chip-to-chip, board-to-board AND box-to-box links. QPI still lacks on the last two, which in my mind is a miss - as Intel's initial workstation & HPC server Nehalems are only DP Gainestowns, a defined " External QPI" spec at this point would help offer a competitive solution to AMD four and eight socket MP servers, getting more popular as the "fat node" concept is coming back with a vengeance.
Talking about coming back with a vengeance, AMD CPU group is still far from that - but some good vibes are spread around: besides somewhat improved recent 65 nm quad core OC results above the 3.3 GHz mark, the rumour is that the 45 nm 6 MB L3 parts, if you're lucky, might give you 4 GHz in OC mode. Would that translate into faster default speed bins? I surely would like to see a 3.2 GHz Shanghai part, at least would compete very well against Nehalems in the HPC area. µ
Comments
Yay!
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?
this is getting to me now
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.
Interesting
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.HT was never slow...
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.
Is this correct?
2 x 16-bit = 32-bit. 32-bit = 4 bytes. 4 x 6.4GT/s = 25.6GB/sec. Not 51.2GB/sec.x2
Bidirectional (2x25.6=51.2)