Athlon, Core 2 architectural efficiencies compared

If you go shopping for sub-$100 processors right now, you’ll be faced with two main contenders: Core 2-based Intel chips and AMD Athlon X2s. The Athlons typically have higher clock speeds for the price, but their Intel rivals often perform better. Why?

A good two years after the debut of the Core 2 Duo, Real World Technologies has put together an in-depth comparison of the Athlon and Core 2 designs. Rather than delve into the obscure architectural details of the two offerings, RWT used apps called VTune and CodeAnalyst to poke around under the hood and get hard numbers for things like instructions per clock, branch predictor accuracy, and how the chips handle their L1 and L2 caches.

The results are quite interesting. Kanter compared a 2.8GHz Athlon 64 FX-62 with a 2.93GHz Core 2 Extreme X6800 in four games, and he found that the Core 2 split instructions into more μops than the Athlon, and—unsurprisingly—processed a greater number of instructions per clock (around 5-10% more). Branch prediction tests showed “vastly” greater accuracy on the Intel front, with “about 50% fewer mispredicted branches per instruction retired.” Kanter does nonetheless point out that branch-prediction accuracy was comfortably above 90% for both chips. Finally, on the cache front, Kanter found that AMD had a more effective L1 cache, while Intel’s L2 cache had “about 50% fewer misses per instruction retired.”

That said, we should note that Kanter compares a 90nm dual-core Athlon with a first-gen Core 2 Duo. Things might look a bit different in new Phenoms, 65nm Athlons, and 45nm Penryn CPUs (like the 2.5GHz Pentium E5200), and they’ll probably change even more once we start comparing Intel’s Core i7 processors with AMD’s 45nm Phenoms.

Comments closed

Pin It on Pinterest

Share This

Share this post with your friends!