🚀 go-pugleaf

In article <1992Aug6.172138.10883@crd.ge.com> davidsen@crd.ge.com (bill davidsen) writes:
>In article <DOCONNOR.92Aug4081003@potato.sedona.intel.com>, doconnor@sedona.intel.com (Dennis O'Connor) writes:
>| 
>| doon@equinox.unr.edu (Harry W Reed) writes:
>| ] In article <> johna@psdcae1.gvg.tek.com (John Abt) writes:
>| ] >Your right - there has been so much publicity - the whole world knows what
>| ] >the "P5" is.
>| ]
>| ] Ok then could you please enlighten us as to what exactly the P5 will be like?
>| 
>| (-: It will be like an Intel486(tm) on steroids and amphetamines. :-)
>| (-: What more do you need to know ?                               :-)
>
>  But the Intel handouts show a RISC processor in there, and imply large
>gains in performance if you "simply recompile for maximum performance."
                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This is almost always true for any CPU that is backwards compatable.
In general, trace flow, branch prediction, variable lifetime analsys and
lots of other good compiler optimizations are now happening.  Heck, 
recompiling the original program on a "good" modern compiler can do
wonders.

I also think that they mentioned something to the effect that just
recompiling to the 486 would yield a signifciant performance increase.

>If the diagram in _EE Times_ (I believe) is correct, then the CISC is
>there, but you are expected to use the RISC processor to get a real
>performance boost.
>
>  Is the P5 really going to be faster than the 486 (a) at the same clock
>speed, and (b) running 486 code?
>
>  I don't expect an answer, Intel suddenly tells me they "don't comment
>on unannounced products," even though we have done non-disclosure with
>them before, and are probably covered under another product agreement I
>can't mention.
>
>-- 
>bill davidsen, GE Corp. R&D Center; Box 8; Schenectady NY 12345
>    I admit that when I was in school I wrote COBOL. But I didn't compile.
                                               ^^^^^^
ARGH!  AAAAAAAHHHHHHHHH!  Run away!!!!!!!!


--
askah@acvax.inre.asu.edu      "Only Nixon could make it to China"
hougland@enuxha.eas.asu.edu         -- old Vulcan probverb
Throw the Scrabble game if anyone starts with "Bezique".
Here are 4 four letter words people don't use "hope, give, kind, and help" --me