Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Technology Stocks : Advanced Micro Devices - Moderated (AMD) -- Ignore unavailable to you. Want to Upgrade?

To: eracer who wrote (195192)	4/26/2006 5:55:54 PM
From: Joe NYC	Respond to of 275872

eracer, I also believe HT 3.0 should be backwards compatible with HT 1.0 and HT 2.0. It is specifically stated in the specs, no need to guess. My guess is that the K8L design was more or less finalized before the HT 3.0 specs were set. However it is possible that AMD designed K8L using earlier preliminary HT 3.0 specs which could be very similar or identical to the ratified HT 3.0 specs. In that case K8L would only need minor tweaks, or perhaps no tweaks at all, to be HT 3.0 compliant by launch time. K8 family is very modular. I doubt the HT interfaces of the crossbar will slow down the core release. That's all there is to it. On one end, there is the cross bar, on the other HT - either 2.0 or 3.0 interface. The risk is low. AMD can always fall back on HT 2.0 interface if there are problem with 3.0 specs. There needs to be a higher perforence cross bar as well... Joe

To: eracer who wrote (195192)	4/26/2006 8:01:35 PM
From: Petz	Read Replies (2) \| Respond to of 275872

As further evidence that HT 3.0 is coming sooner rather than later, AMD highlighted it in their Opteron 3rd Anniversary press release and said the following: HyperTransport™ 3.0 Specification Now Available... Future AMD64 processors are planned to be able to take advantage of the increased bandwidth and other features offered by HyperTransport 3.0, which is designed to provide even faster processor-to-processor and processor-to-I/O throughput in multiprocessor server and multi-system environments. amd.com "multi-system" a hint at non-CPU nodes, perhaps? Petz