AMD was pitching the AMD Opteron 2350 against Intel's Xeon 5345 which both clocked the same at 2.0 GHz. The results in selected benchmarks were going quite nicely for AMD, and then SPECint_2006 score showed just a 5% performance deficit behind Intel - contrary to performance data achieved by Intel Xeons, showing that Xeons have a more tangible lead.
One of the slides on AMD's Powerpointy day
Dirk started to explain the difference, the guilty party supposedly being Intel's compiler, quoted being "nothing more than a benchmark compiler." When SPECint_2006 was ran with the Intel vs. PGI compiler, Opteron 2350 has 5% performance deficit, but when SPECint_base2006 was ran with both systems running publicly available gcc compiler, AMD has a performance lead of 9%.
Is this the real deal or just smoke in mirrors? Decide yourself. In any case, to answer some of the boffs that like sending ego-exercising e-mails at 4AM, we're just the messenger here. µ