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.
Politics : Formerly About Advanced Micro Devices
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: Charles R who wrote (91825)2/6/2000 2:47:00 PM
From: Scumbria  Read Replies (3) of 1577119
 
Chuck,

- Do you see a reason to support higher MHz than Athlon can do for 2000?

Willamette.

- Don't you think the Sledgehammer core coming in 2001 could be sufficient to keep up with the competition?

If it is being done by the Nexgen team, it will probably be junk.

- What is your take on Winchip's 18-stage pipeline for Winchip 5 (or some other WInchip)

The right thing to do to make money.

- How do you see the impact of a longer pipeline on server class products (long qual cycles, frequency ramp issues with large on-die caches and impact of reduced Integer performance on a per MHz basis)

Servers tend to be bandwidth limited rather than latency. A deep pipe allows for high MHz, and thus high bandwidth.

- How deep would you have gone and why?

After about 20 stages, the latch delays and clock skew tend to dominate over the logic. I would put a 20 stage pipe as about the upper limit.

Scumbria
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  

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