[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: Micro$loth Windoze 95 Badges - how they should be
- Subject: Re: Micro$loth Windoze 95 Badges - how they should be
- From: Patrick O'Neil <patrick@howard>
- Date: 1995/09/12
- Newsgroups: comp.sys.mac.misc, comp.sys.mac.hardware.misc, aus.computers.ibm-pc, aus.computers.sun, aus.computers.os2, aus.computers.amiga, comp.sys.amiga.misc, comp.sys.apple2, comp.sys.ibm.pc.misc, comp.sys.intel, comp.sys.mac.programmer.misc, comp.sys.misc, comp.sys.newton.misc, comp.sys.next.misc, comp.sys.sgi.misc, comp.sys.sun.misc, comp.os.ms-windows.misc, comp.os.ms-windows.win95.setup, comp.windows.misc, comp.os.ms-windows.win95.misc
- Organization: University of Utah Computer Center
- References: <Pine.ULT.3.91.950904132020.12842B-100000@student.uq.edu.au> <42f93k$chn@data.interserv.net> <demo-0509952118130001@netblazer1-s35.telalink.net> <42ob3i$r0t@data.interserv.net> <mjoseph1-0809951250580001@b32.public.swarthmore.edu>
On 8 Sep 1995, mathew joseph wrote:
> This is an INCREDIBLE statement! Let me think...last I checked the
> Pentium, which performs very poorly against today's RISC processors (i.e.
> PPC, MIPS, Alpha, etc.) had absolutely no way of upgrading to a P6 since
> they use different pin designs. And last I checked the P6 ran 16 apps
> SLOWER than the P5 and and 32 bit apps only marginally faster while
Actually, it depends on what benchmark software you use. Floating point,
for instance, is not a Pentium strong point, though the P120s and P133s
are roughly equivalent in fp with 602s (certainly it is when compared to
a 601). That said, it is also rather unfair to strike at the P6 for
being slower operating a 16 bit app...a PowerPC is also slow with such
software, being optimized for 32 bit apps. Running a P6 on 16 bit apps
is much like running DOS/Windows software on a PowerPC...pisspoor because
it has to use a software emmulator to do so, which gives it a performance
on such software in the lower x86 Intel processor range. If I recall
properly, the PowerPC running a DOS or Windows app or game (of which
there still are far more available than for a Mac of any flavor, let
alone for any 32-bit operating system) is comparable to a 486DX or DX2.
Not bad, but not great either.
Soon, most apps will be written in 32 bit code, in which case, Windows95
will run comparable to OS/2 and WindowsNT...some people, not having the big
bucks, will hang on to Win95 for a long time. When most apps are 32bit,
the the P6 will do swimningly...even IBM seems to think that the
processor competition between Intel/HP and IBM/Motorola will be interesting
and tight. The "best" processor will be a matter of taste and
application, not simply architecture...and Intel processors are becoming
more and more RISC-like anyway (this naturally neglects the other
processors and os's because they tend to be isolated and for very special
niche use...Joe and Jane Blo are never going to be Unix-heads, nor Amiga
users, nor Alpha chip owners).
By the way, at Barnes and Noble there is a book entitled _The Computer
Hardware Bible_. It gets quite technical into the details of various
chips from the DEC Alpha to the PPC to the MIP to the x86 and P6. It goes
over RISC and finds that "RISC" is not a real clear term with a solid
boundary between non-RISC and RISC. A PPC may be MORE RISC-like than a
Pentium, but it isn't all that much. And in comparison to others, it may
seem more CISC-like.
For you Unix people...also at Barnes and Noble, amongst the Unix books, is
a book entitled _Why Unix Must Die_. Interesting book covering the
ugliness,ungainliness, and plain chaos of Unix design. It goes over all
the supposed good points of Unix and, point for point, debunks the myths.
It doesn't address Linux at all so perhaps Linux is saved from the flaws of
Unix. >:)
patrick@corona.med.utah.edu