SI
SI
discoversearch

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 : Intel Corporation (INTC) -- Ignore unavailable to you. Want to Upgrade?

To: wanna_bmw who wrote (151156)12/5/2001 11:59:02 AM
From: Charles Gryba  Read Replies (2) | Respond to of 186894
 
wbmw, ok that sheds more light. Now, we 'll have to break down the amount of cycles that decoding a complex and a simple instruction takes. It sounds to me that the 2Ghz P4 should be slower than a 2Ghz P3 but not as slow as a 1Ghz P3 in this test. What I mean is, what benefit ( in cycles ) does the P3 get from the extra added simple decoder? It can't be 100%.

p.s.
Why would the P4 team omit something as lightweight as a simple decoder?



To: wanna_bmw who wrote (151156)12/5/2001 2:26:22 PM
From: Joe NYC  Read Replies (1) | Respond to of 186894
 
wbmw,

Re: simple / complex decoders of Piii

I guess we can fix it by changing the statement in the case statements from ADD to a complex instruction. Which single instruction do you know for sure is a complex instruction, so that we can use it in the test code (thus denying Piii the opportunity to use the simple decoder in parallel)?

Joe


HomeMailHotSubjectMarksPeopleMarksKeepersSettings
Terms Of UseContact UsCopyright/IP PolicyPrivacy PolicyAbout UsFAQAdvertise on SI
© 2025 Knight Sac Media.  Data provided by Twelve Data, Alpha Vantage, and CityFALCON News