The Inquirer-Home

Pentium 4 works better with hyperthreading off, AMD claims

Updated Shocking suggestion
Tue May 13 2003, 15:35
AN ARTICLE earlier today where we questioned by AMD switched hyperthreading off when it compared a Pentium 4 to its newly fledged 3200+ Athlon XP has been answered by the firm.

And the answer is somewhat surprising.

Damon Muzny, a representative for the product review department of AMD Public Relations, said that the Pentium 4 performed better with hyperthreading switched off than when it was turned on. That's with the Canterwood motherboard.

He said: "That's why we have our benchmarks normalised to an HT disabled platform".

He said that AMD had chosen the best platform and configuration it had available to test the Pentium 4 against its 3200+ processors at the time of its benchmark audit.

He added: "Past benchmarks have shown that on many industry standard benchmarks, AMD processors typically outperform Intel processors with HyperThreading enabled by even a higher percentage. AMD will share those additional new benchmarks using the AMD Athlon XP processor 3200+ when they are available".

And, he continued: "On May 8 we were able to begin benchmark testing against Intel's 3.0GHz P4 on Canterwood. Against this new platform, the AMD Athlon processor 3200+ performs an average of 6 percent better than the Intel offering with HyperThreading turned off. So like I mentioned, AMD processors typically outperform Intel processors with HyperThreading enabled by even a higher percentage in the benchmark suite we test with".

An Intel UK representative told the INQUIRER: "HT Technology provides an immediate benefit to threaded applications and in many multitasking scenarios, where the end user is running two or more existing applications at the same time. Thus enables a better user experience. You can find benchmarks and multi-tasking scenarios here". µ

See Also
AMD XP 3200+ benchmarks disable Intel hyperthreading

 

Share this:

blog comments powered by Disqus
Advertisement
Subscribe to INQ newsletters

Sign up for INQbot – a weekly roundup of the best from the INQ

Advertisement
INQ Poll

Heartbleed bug discovered in OpenSSL

Have you reacted to Heartbleed?