Intel: We're back

TalkBack 16 of 30:

Next »

« Previous

• Thread View
• Flat View

A few minor corrections

DDR2 will yield nothing other than improved power consumption.

Not so. Now that DDR2 is hitting maturity, its latency is down below DDR1's -- the clock latency is still higher, but the frequency has gotten to the point of making up for it.

That means that the cache-miss penalty goes down, which is good for both Intel and AMD but relatively better for AMD. The reason is that Intel is still bottlenecked on the FSB but has larger caches (thus fewer misses.)

HT3 is another gimmick - it solves nothing at this time that needs improving.

Again, not so. HT3 keeps the communications between multiple CPUs from becoming the bottleneck that Intels FSB is.

AMD has a relative advantage where the OS does NUMA well and the applications involve relatively independent processes (think virtualization) and where the sheer size of memory counts. Intel has a relative advantage where the operating system doesn't do NUMA well, since all memory accesses are equal (if slow). HT3 minimizes this advantage even if it doesn't negate it.

Posted by: Yagotta B. Kidding   Posted on: 06/26/06 You are currently: a Guest | Members login | Terms of Use

Alert moderator to an offensive message

Subscribe to this discussion via Email or RSS

SponsoredWhite Papers, Webcasts, and Downloads

• Three Steps You Need to Know to Stop Data Loss Varonis Sensitive data exposed to misuse or loss... it is the stuff of nightmares ... Download Now
• VMware Infrastructure: A Guide to Bottom-Line Benefits VMware Frustrated by the costs of maintain ever larger data centers?or building ... Download Now
• Reducing Server Total Cost of Ownership with VMware Virtualization Software VMware VMware virtualization enables customers to reduce their server TCO and ... Download Now