HyperTransport Spec Receives Upgrade

"Increased bandwidth and low latency"

Search News

  • Scrolling Image
HyperTransport Spec Receives Upgrade HyperTransport specifications table
The HyperTransport Consortium has announced HyperTransport 3.1, a specification that pushes the interconnect technology to a theoretical 51.6 gigabytes per second. The HyperTransport group also announced HTX 3, an upgrade to the physical connector used by servers and other computing devices.
Technically, the new specification extends the 2.6-GHz clock speed of HyperTransport 3.0 to 3.2 GHz, and up to 6.4 gigatransfers per second, or 51.6 gigabytes per second. According to the HT Consortium, the upgraded specs mean that the spec now has a 60 percent headroom in clock rate and a 220 percent overhead in terms of bandwidth versus commercially available parts.
Likewise, the HTX specification was also upgraded to "connectorize" the HT 3.1 specification inside the HTX connector. HTX3 will also allow for 5.2 gigatransfers per second. Another improvement includes link splitting, which allows designers to place one x16 link, one x8 link or two x8 links on a single connector.
HT 3.1 specifications link here
Will HT 3.1 allow the standard to maintain its lead as the industry’s highest performance and most efficient interconnect?
Discuss in our forum
«Prev 1 Next»

Most Recent Comments

14-08-2008, 18:51:41

I have a non- O.C. eVGA nVidia GTX 260 and would like to overclock it. What would be the best software to use to overclock the 260 - rivatuner, nvtweak, coolbits or eVGA's Precision O.C. software.

Also could some tell me what a stable O.C. number set would look like for the 260 in terms of "GPU Clock/CPU Clock/Mem". The factory default is set at 576/1242/999.


14-08-2008, 18:58:54

You shoulda got the ATi instead. But whats the point now its too late. Anyways I would recommend that you slowly o/c it to its full potential rather than ask somebody here for the best o/c

15-08-2008, 05:57:10

This is what I did last night with my 7900GT :P

1. Download ATI Tool.

2. Download Rivatuner.

3. Install both.

4. Overclock using Rivatuner on the core & shader only by 10mhz.

5. Open ATI Tool and scan for Artifacts for 5 minutes (keep an eye on the temperature).

6. If there are no errors then repeat step 4 & 5 until there are; then back off by 10mhz.

7. Then with the core & shader overclocked, do the same process with the memory.

8. Then you are done and have found the max stable overclock for you core, shader and memory.

Remember better cooling = better overclock and longer life of the card. Also each individual card overclocks differently so don't expect to match someone else's overclock just because they have the exact same card as you.

15-08-2008, 12:56:17

Thanks a ton, this was exactly what I was looking for. Appreciate it.

17-08-2008, 11:55:07

No probs.

20-08-2008, 05:48:39

some Really good advice,

Can I ask a nooby question: Core shader and Memory: does this refer to the Core: the CPu, shader: the gpu and memory the RAM ?

and when u over clock are you just increasing the Voltage or somehting else?
Finally, whats the ideal temperature, and whats the max temp u'd let ur system rise to whilst attempting to OC, Mine is Water cooled, but only with a 750 lph pump. Thanks

Ollie :D

Register for the OC3D Newsletter

Subscribing to the OC3D newsletter will keep you up-to-date on the latest technology reviews, competitions and goings-on at Overclock3D. We won't share your email address with ANYONE, and we will only email you with updates on site news, reviews, and competitions and you can unsubscribe easily at any time.

Simply enter your name and email address into the box below and be sure to click on the links in the confirmation emails that will arrive in your e-mail shortly after to complete the registration.

If you run into any problems, just drop us a message on the forums.