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 : Advanced Micro Devices - Moderated (AMD)
AMD 214.93+0.7%3:59 PM EST

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: TGPTNDR who wrote (68915)1/25/2002 3:01:48 PM
From: fyodor_Read Replies (3) of 275872
 
TGPTNDR: and besides that the P4 is hopeless

It isn't the killer chip one could have expected, considering the die size and the resources thrown at it. However, calling it "hopeless" is a far cry from the reality.

Intel shot themselves in the foot by coupling P4 exclusively with Rambus memory from day 1. With DDRSDRAM chipsets, as well as plain-old SDRAM chipsets, now available, P4 is starting to sell really well.

Have you looked at the Northwood benchmarks?

Performance is actually quite good:

Content Creation (SysMark and Winstone) performance is up an amount corresponding to a speed grade increase (i.e. a NW @ 2GHz performs as an old P4 would at 2.1GHz).

3D Rendering (Maya, Bryce and 3DSMax) performance is up 1-3 speed grades.

3D Gaming (Q3, RTCW, Serious Sam, Max Payne) performance is up 2-3 speed grades.

There are plenty of other benchmarks that show the same pattern - only very few show little to no gain (UT and multimedia encoding are the only two I can think of).

Also noteworthy, power consumption and die size are both down ~30%.

And what happens when HyperThreading is turned on?

I've seen no 3rd party benchmarks yet, but going by the Intel PR&#133 Well&#133 Let's just say that calling P4 "hopeless" is just not in line with reality.

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