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 : Rambus (RMBS) - Eagle or Penguin -- Ignore unavailable to you. Want to Upgrade?

To: pheilman_ who wrote (81614)3/15/2002 3:56:49 PM
From: John Walliker  Read Replies (2) | Respond to of 93625
 
pheilman,

You are comparing triangles per second for the Sun device with vertices per second for the nVidia.

So the comparison should be 57.3M vs 136M vertices per second. Maybe not so bad for a design which is "at least two generations behind current silicon".

Something else puzzles me. If the memory bandwidth of the Sun device is 6.5 times less than the nVidia, how does it manage only to be 2.4 times slower?

Finally, were the screen resolutions the same for these comparisons?

John



To: pheilman_ who wrote (81614)3/15/2002 4:05:14 PM
From: h0db  Read Replies (2) | Respond to of 93625
 
pheilman, you should click on the link...

I really didn't do it justice. It's a modular design; the simplest version (the XVR-1000) has 360MB of memory-- 32MB of RDRAM for the GPU, 72MB of eRAM for framebuffer, and 256MB of SDRAM for textures. Sun's roadmap projects it scaling to over 4,000 M triangles/sec. But I'm sure that the GF4 is better at Quake 3 Arena <G>


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