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 204.48-2.6%3:51 PM EST

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: andreas_wonisch who wrote (7034)8/30/2000 5:21:39 PM
From: jcholewaRead Replies (1) of 275872
 
> I'm no expert in graphic card, so I don't know the theoretical fps limit with ideal hardware (i.e. CPU as fast as possible, no
> memory bottlenecks etc.) on a GeForce 2 with a fillrate of ca. 650 megatexels per seconds. Could you (or someone
> else) give some figures on that?

Somebody here said that the benchmark score did indeed massively exceed the fill rate limitation. But I'm in the same house as you, being unable to determine for sure.

> Wow, these benchmark guys are fast. Intel must be working close with them... ;-)

AMD, too. I have been told that the Sandra SIMD tests are very favourable to AMD.

> Edit: One thing is still strange. Why does Sandra identify the 1 GHz P4 as a 250 MHz P4 when it should have support
> for it? Isn't this a relatively obvious issue (probably due to the quad-pumped FSB) that could be easily fixed?

The earlier version of Sandra did the opposite thing. It took the multiplier (which was based on the 100MHz bus clock) and multiplied it by the bus data rate. 400 x 8.0 = 3200MHz. (the true value was 100x8.0=800MHz)

You can see an example of this at fullon3d.com

This new version appears to have taken the multiplier (based on the bus data rate) and multiplied it by the bus clock. 100 x 2.5 = 250MHz. (the true value was 400x2.5=1000MHz)

Funky, eh? ;)

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