Replies to post #81526 on Advanced Micro Devices Inc (AMD)

[chipguy]

Barcelona L3 latency < 38 cycles ?

Impressive. That's less than 19 ns at 2 GHz. Of course HP was
doing 8.33 ns 4 MB off chip caches with commodity SRAM
connected to the PA-8200 about a decade ago. ;-)

[wbmw]

Look at this "important update" towards the end:

George Ou of ZDNet has just alerted us to the fact that not only are these estimated results inaccurate, they are based on outdated Intel results. When the actual results are compared, the Barcelona's advantage is only 1% at 2.6 GHz. Even this advantage is only theoretical as the fastest Barcelona processors to be released initially will only run at 2.0 GHz. For more details on the latest, certified benchmark results, check out George Ou's post here.

George also points out that AMD removed the "simulated" benchmark results from their website on July 6th, and promised to post proper benchmark results of their Barcelona processor. However, we received the very same benchmark results just last week. If these results have already been officially junked by AMD, why are we still being served the same poo?


AMD is still peddling their screwy benchmarks, it seems....