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 : Intel Corporation (INTC) -- Ignore unavailable to you. Want to Upgrade?


To: Paul Engel who wrote (63731)9/1/1998 2:02:00 PM
From: Tenchusatsu  Respond to of 186894
 
Raw Clock speeds are not silly - they are essential METRICS of a given process/design capability.

Actually, it's much tougher to answer than that. Some CPU's are architected from the beginning to run at very high clock frequencies, like the Digital Alpha and perhaps Intel's future processors. Other CPU's are architected to try and squeeze the most performance out of every clock cycle as possible, like Cyrix's MII.

I would guess that the PowerPC is architected to run at slightly lower clock speeds. But then again, that kind of mystifies me, since PowerPC is supposed to be RISC, allowing for a cleaner design that can be easily clocked at high speeds, right? Meanwhile, Intel takes all the x86 baggage of 15 years and pushes the pure MHz envelope faster than the PowerPC? The SpecInt95 and SpecFP95 numbers of both the 400 MHz PPC and the 450 MHz PII are very close. Hmmmm.

As for power consumption and cooling, these indeed are important and the PowerPC has lower power consumption than an equivalent Pentium II - but people don't buy "Watts" - they buy performance.

People do indeed buy "Watts" indirectly, if lower watts means lower system costs due to easier cooling. Also, in the mobile market, power consumption is king, so we can expect the very nice Apple Powerbook line to benefit first from the 400 MHz PPC.

So far, the first fruits of copper technology look nice, if not breathtaking.

Tenchusatsu



To: Paul Engel who wrote (63731)9/1/1998 2:03:00 PM
From: Greg Jung  Read Replies (1) | Respond to of 186894
 
You said it yourself, but I'll edit it and
see if you agree. A true statement is embedded in your message:

 
Raw Clock speeds are
(not silly - they are essential) METRICS of a given
(process/) design (capability).

RESULT:
Raw clock speeds are metrics of a given design.

Yes.