The Megahertz War

It is with a sense of deja-vu that I am revisiting a topic that I had once touched upon in this page–that of processor clock speeds. To recap what I had said then–the mad race for megahertz has to end and improving megahertz will not necessarily improve PC performance.

But megahertz has for long been the only visible measure of performance, with the automatic equation–higher the CPU speed better the performance. The last two years have seen a sea-saw battle between Intel and AMD for megahertz supremacy, with AMD for the first time pulling ahead of Intel in the clock-speed bragging rights game. But that is now history, with AMD processors falling behind Intel in the clock-speed race, and AMD starting to chant a different mantra–that clock speed is not an accurate measure of performance.

AMD is not the first to embark on this journey. For many years now, Apple has been conducting demonstrations where Macs running CPUs at half the speed, routinely beat PCs running Intel processors. AMD now has up on its website, a certificate by Anderson (consulting?) that the benchmark claims by AMD are fair.

You may well ask: Is their point right? Before you search for the answer, you need to first ascertain what is the point that they (or any one else, for that matter) are making. The point that megahertz is not an accurate measure is secondary. The actual point that AMD, like any other marketing company, is trying to make is that their products are better. Let us not be under any illusion that AMD has woken up to reality only now and is out to set the record straight. Remember that they also played the clock-speed game as long as it suited them.

At the speeds that are being talked about, it does not make too much of a difference to you or I whether one chip runs a few megahertz more or less than another. You will not be able to make out any difference in performance between a CPU that gives 98 fps and another that provides 128. Both are equally smooth for the human eye.

AMD has for long been the underdog in the processor industry, and enjoys the empathy of many
a geek.

Will AMD succeed in its new quest? The question, unfortunately, is not just about which CPU is better. It is not about which is actually faster. It is about who will make the most noise in establishing its point of view. It is about who will give better support and, more important, better margins to the sales channel. It is about who will spend more money in advertising. Selling technology products, for better or for worse, is no different from selling anything else.

In short, whether AMD will succeed will depend more on their being market savvy and the depth of their purse than on whether they do indeed have a product that performs equally well, if not better.