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 231.83+1.7%Jan 16 9:30 AM EST

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: wanna_bmw who wrote (57583)10/7/2001 3:55:45 PM
From: TGPTNDRRead Replies (1) of 275872
 
wanna_bmw, re. your 57583.

I think you missed my point which was surely *NOT* that there should be a dearth of demand for new machines.

In fact, as soon as additional processing capacity exists the programmers will use it & obsolete all prior generations of hardware.

They will use power that isn't there yet in hopes that it'll get there. And the CPU makers come through for them again and again.

The software engineers *DEMAND* that the hardware engineers make full use of Moore's law just as the hardware engineers demand the tool makers make full use of it!

And if you want to do the things the latest generation of software allows you must pay the piper.

I'd agree with you on:
MP3 Encoding/Sound Editing
DVD Encoding/Movie Editing
CD/DVD Recording in a multi-tasking real time case, and on some Games.

I'd add speech recognition & computer control.

And if you do mostly any one of them it makes sense to look at a benchmark that represents how well the *MACHINE* does at that task.

What I was saying was that the benchmarking biz is fuzzy.

Around here big things are made out of 10% performance differences. It's a lot of fun.

IMO, however, unless there's around 50% difference in a task that you perform a lot and *that is computer bound* the user isn't going to discern the difference.

And tell me what widely used benchmark reflects the ability of the CPU to handle large database queries?

Then tell me the benchmark isn't IO bound on any reasonably current X-86 system without F/W-SCSI & RAID.

Or what widely used benchmark reflects the ability of the CPU to serve active web pages, & how parallel processing isn't a lot cheaper and safer than high cpu capacity.

And INTC (and you) should applaud that fact. It's what X86 is best at.

That's the kind of point(s) I was trying to make.

I guess it didn't work. Maybe it still didn't.

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