🚀 go-pugleaf

lovejoya@ix.netcom.com (Alan Lovejoy) wrote:

>See the press release where the HP/Intel alliance was announced.
>
>Intel's stated ETA for the successor to the P6 is late 98/early
>99--assuming they go for the agressive/radical VLIW-inspired option. 
>If they go for the conservative, enhanced x86 option, they can probably
>hit a late 97 timeframe at best (1995 + 2.5 years dev time per
>generation).  

[P7 vs VLIW P7]

>Consider this: the P6 is such an expensive chip, it creates a lot of
>room for the competition to either undercut the price at the same
>performance level, or to overpower it at the same price level--or both.
>The price of the P6 is getting close to that of an Alpha at only half
>the clock.  The Alpha is considerably faster--with a year and a half
>lead.  Suppose one of the next generation PPC's uses Alpha-like
>implementation strategies: relatively simple excecution machinery in
>exchange for doubled or even tripled clock rates (using existing
>process technology).  As the Alpha has demonstrated, this not only
>results in chips up to twice as fast as the (RISC!) competition, the
>chips can be brought to market a year ahead of the competition.  This
>strategy is much less attractive for Intel, because of the added
>complexity of the x86 compatibility requirements.  They have less room
>for reducing the complexity of the execution machinery.
>
>And Intel is not the only one that can add hardware for x86
>compatibility to at least some chips...

    Personally, I think they should go ahead and hit the market with a 
"conventional" P7 - the P6 still has plenty of room for improvement - in
late 1997, and then go ahead and wait until mid 1999 to let loose on the
VLIW "P8" (?).   Then again, you have to take into account that AMD has
already slated a K7 in 1999-2000 expected to reach almost 600 SpecInt.  They 
also plan to have a K6 out to get 400 SpecInt (8 mil transistors, I think) in
1996-97.  Seeing that the K5 has yet to be released, this is a little bit of 
extreme farsight, don't you think?