Article View: comp.os.linux.hardware
Article #824Re: P4 vs Athlon for Linux latexing, is gcc-2.95 responsible?
From: Rowland McDonnell
Date: Tue, 18 Jun 2002 09:28
Date: Tue, 18 Jun 2002 09:28
55 lines
3803 bytes
3803 bytes
David Kastrup <David.Kastrup@t-online.de> wrote:
> real-address-in-sig@flur.bltigibbet (Rowland McDonnell) writes:
>
> > Giuseppe Bilotta <oblomov@freemail.it> wrote:
> >
> > > Robert Myers wrote:
> > > >
> > > > A processor that requires special code to get decent
> > > > performance is not especially attractive, and if the P4 weren't an Intel
> > > > product, no one would be using it.
> > >
> > > Well, Intel CPUs have always suffered from bad design problems which
> > > require hoop-jumping, contorsionism and loop unrolling to get decent
> > > performance.
> >
> > Back in the days of the 4040, this wasn't considered a problem.
>
> 4040? We aren't by chance confusing this with the 4004?
Highly likely. It might well be 10.19am BST but I've only just finished
a bottle of wine (up all night, y'see - I might even hit the sack
soonish).
(and `we'? I might be mad, but I've never attempted multiple
personality disorder ;-) )
> And the
> 8080 still was a rather clean design. The Z80, in constrast, was
> convenient but awful: the price you paid for some of its features was
> prohibitively high.
Hmm... Maybe, maybe - but was there anything missing from the Z80
compared to the 8080? (I never did use an 8080 myself, and I don't
recall doing any machine code[1] programming of a Z80 beyond the age of
about 14 - draw your own conclusions...)
> For example, one popular way to clear out a memory area was do store
> a 0 into its first position, then use the LDIR instruction to fill
> the rest. 21 cycles per byte. Unroll to LDI, get 16 cycles.
>
> Of course, the fast wa was to place the stack pointer at the end of
> the area, and do repeated PUSH HL. 11 cycles for _two_ bytes.
Interesting - ta.
Rowland.
[1] Yes, really - I had no assembler.
--
Remove the animal for email address: rowland.mcdonnell@dog.physics.org
PGP pub key 0x62DCCA78 Sorry - the spam got to me
http://www.mag-uk.org
UK biker? Join MAG and help keep bureaucracy at bay
Technical Details
Message-ID:
<1fdyxzl.1eky32lcx38cvN%real-address-in-sig@flur.bltigibbet>Path:
arc1-ca.pugleaf.net!archiver1.google.com!news1.google.com!newsfeed.stanford.edu!news-spur1.maxwell.syr.edu!news.maxwell.syr.edu!newsfeed.icl.net!newsfeed.esat.net!diablo.theplanet.net!easynet-monga!easynet.net!peer.news.zetnet.net!news.uklinux.net!real-address-in-sigReferences:
<3D0B57CB.5060406@nospam.com> <cVYO8.93284$pw3.4355@sccrnsc03> <MPG.1776a491ca74b5bf989edd@powernews.libero.it> <1fdyury.16lgkkf1d22zw9N%real-address-in-sig@flur.bltigibbet> <x5it4h2d58.fsf@tupik.goethe.zz>Show Full Headers
Complete Article Headers
X-Google-Language: ENGLISH,ASCII-7-bit
X-Google-Thread: f9e16,ea3300a83f1f851c
X-Google-Attributes: gidf9e16,public
X-Google-Thread: f65d0,ea3300a83f1f851c
X-Google-Attributes: gidf65d0,public
X-Google-Thread: 102b32,ea3300a83f1f851c
X-Google-Attributes: gid102b32,public
X-Google-Thread: 1045b9,ea3300a83f1f851c
X-Google-Attributes: gid1045b9,public
X-Google-ArrivalTime: 2002-06-18 02:28:51 PST
Path: arc1-ca.pugleaf.net!archiver1.google.com!news1.google.com!newsfeed.stanford.edu!news-spur1.maxwell.syr.edu!news.maxwell.syr.edu!newsfeed.icl.net!newsfeed.esat.net!diablo.theplanet.net!easynet-monga!easynet.net!peer.news.zetnet.net!news.uklinux.net!real-address-in-sig
From: real-address-in-sig@flur.bltigibbet (Rowland McDonnell)
Newsgroups: comp.os.linux.hardware,gnu.gcc,comp.sys.ibm.pc.hardware.chips,comp.text.tex
Subject: Re: P4 vs Athlon for Linux latexing, is gcc-2.95 responsible?
Date: Tue, 18 Jun 2002 10:28:55 +0100
Organization: The Pietertje Geeltje van der Sluis fan club
Lines: 55
Message-ID: <1fdyxzl.1eky32lcx38cvN%real-address-in-sig@flur.bltigibbet>
References: <3D0B57CB.5060406@nospam.com> <cVYO8.93284$pw3.4355@sccrnsc03> <MPG.1776a491ca74b5bf989edd@powernews.libero.it> <1fdyury.16lgkkf1d22zw9N%real-address-in-sig@flur.bltigibbet> <x5it4h2d58.fsf@tupik.goethe.zz>
NNTP-Posting-Host: bts-0576.dialup.zetnet.co.uk
X-Trace: s1.uklinux.net 1024392531 24484 194.247.50.64 (18 Jun 2002 09:28:51 GMT)
X-Complaints-To: abuse@uklinux.net
NNTP-Posting-Date: 18 Jun 2002 09:28:51 GMT
X-Face: (Erpd5b^8lQe0$9[22T;{kxJrMyksf[`sY^%O>$&p-T0LY;d.*%tDm8)~p}M"
02vxDj5)SRrR^Y@@kQoTf+hU"SNc#=u~S(X{@}:5uVIZXMV/*\$:[3KGy~`!N>C{_
User-Agent: MacSOUP/2.4.6