Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Technology Stocks : Advanced Micro Devices - Moderated (AMD) -- Ignore unavailable to you. Want to Upgrade?

To: dale_laroy who wrote (73898)	3/7/2002 2:39:12 PM
From: Ali Chen	Read Replies (2) \| Respond to of 275872

dale, "Up until Intel started with the P4, the industry consensus was that optimum performance would be achieved with a pipeline of between 8 and 12 stages, depending upon the complexity of the ISA. Longer pipelines could lead to higher clock rates, but the cost to IPC would negate this increased clock rate." Yes, and I think the consensus is still correct. P4 loses to Athlon on every classic CPU benchmark kernel. SPEC_CPU benchmarks are valid only for a tiny layer of computational scientists, since profiling and two-pass compilers are applicable only to a predefined set of data. For most applications the data sets are not defined apriori, so the specific optimization most likely will not work. However, for mainstream commercial applications, where the volumes are, Intel found a workaround: they have changed the paradigm of computing using advantages of their higher-bandwidth platforms. They convinced public that "streaming" apps is what they are going to need, and devised new benchmarks to stress this. The AMD "well-balanced" platform goes out of balance and slightly loses in those benchmarks. - Ali