We’ve earlier reported at a couple of occasions about tests and reviews of AMD’s new 65nm core. A core many hoped would bring new life to AMD. While system builders are most likely happy about the reduced power consumption, the consumers are less thrilled about the lack of performance we heard rumors about. In part 2 of Anandtech’s review of Brisbane they’ve found out what caused some of the odd results in part 1 as the 65nm processor was noticeably slower than the 90nm counterpart. AMD has now answered to this and claimed it was due to higher memory latencies and this was very much the case, one cycle had been added. What AMD neglected to mention was that it had also increased the latency for the L2 cache to almost the double, from 12 to 20 cycles.
“The original K8 core, in both 130nm and 90nm flavors, had a 12-cycle L2 cache. With Brisbane, as reported by both CPU-Z and ScienceMark, 65nm K8 now has a 20-cycle L2 cache. Generally speaking you move to a higher latency cache if you’re planning on introducing a larger cache size, but a quick glance at AMD’s roadmaps doesn’t show anything larger than a 1MB L2 per core for the next year. The argument for higher clock speeds isn’t valid either as the highest clock speed on AMD’s roadmaps thus far is only 3.2GHz.”
:: Read on in part 2 at Anandtech
No active posts found.