Replies to post #3519 on Advanced Micro Devices Inc (AMD)

[dougSF30]

EP-- Re: While it's true that Xeon doesn't beat or match Opteron on many benchmarks, it still does on quite a few and we haven't seen a new Xeon speed bin released in quite some time. I expect newer versions to make a much better showing. Perhaps not closing all the gaps but a substantial improvement is reasonable to expect.

That's a commendably objective comment.

But of course newer versions of Opteron will also make much better showings, and attempt to preserve the performance gap. And of course, the 64-bit-capable gap will never be closed, unless a Yamhill-type Xeon sees the light of day, but of course that would severely damage the Itanium market, whether deservedly so or not.

Doug

[sgolds]

Elmer, I fully expect Prescott will match Opteron on single processor benchmarks, at least in 32-bit mode. However, Prescott is still hampered by that shared bus, so it will have problems due to scaling limitations. There is just so much you can do with cache for 2-way, 4-way and higher systems.

Just as PCI made EISA, ISA and MCA bus systems look old (and took Intel to a new level), aHT is an elegant architecture which is making all previous PC busses look old.

So I agree that Prescott will be very impressive internally. All AMD has to do is deliver on the technology which they now own and Xeon platforms will quite literally be last year's technology.

[fyodor]

Elmer: While it's true that Xeon doesn't beat or match Opteron on many benchmarks, it still does on quite a few and we haven't seen a new Xeon speed bin released in quite some time. I expect newer versions to make a much better showing. Perhaps not closing all the gaps but a substantial improvement is reasonable to expect.

Ain't competition grand?

;-)

-fyo