Silicon Investor (SI) -- The First Internet Community

STOCKTALK

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 : AMD:News, Press Releases and Information Only! -- Ignore unavailable to you. Want to Upgrade?

To: Bill Jackson who wrote (4439)	2/17/1998 12:43:00 AM
From: Kevin K. Spurway	Read Replies (2) \| Respond to of 6843

I don't think it's reasonable to expect the K6-3D to perform any better than a standard K6 at the same clock speed, unless it has the benefit of using its 3D instruction set. Clearly what this amounts to is performance slightly below a Pentium II at the same clock speed, although the performance differential might be a bit less than comparing PII-233 at 66mhz bus to K6-233 with 66mhz bus, since socket 7 benefits more from a 100mhz bus.

To: Bill Jackson who wrote (4439)	2/17/1998 10:46:00 AM
From: Ali Chen	Read Replies (2) \| Respond to of 6843

Bill, <There is a lot of "testcraft" being done with video card makers optimizing drivers for the Z-D, and other benchmarks...> This is a clear misunderstanding. What "testcraft" are you talking about? Drivers are part of an OS. Most sellable OS is Windows95. Z-D benchmarks use GENERAL PURPOSE APPLICATIONS for Windows (MS Word, WordPro, Paradox, CorelDRAW, MS Access, Excel, Netscape...) that make the only API calls for this OS. There is no special "crafting" here. Therefore, there is nothing wrong in writing a better driver for the most "popular" OS. Microsoft API layers get gradually improved with each "Service Release" or "version" . All this AUTOMATICALLY improves Z-D benchmark scores. Driver just are getting from junky kludges to a little bit better ones, but could be improved even better. Is it what you call "crafting"? <those figures could easily be an artifact of the benchmark.> You seem to be unfamiliar with the Z-D benchmarks (see above). If you are a user of other application/OS, feel free to write your own driver (for your card) and your personal benchmark, and then you will be well equipped to make your purchase decision for your unique machine. Millions of other users should be satisfied with Z-D scores, and there is no "artifacts" as you tend to think.