This is a multi-part message in MIME format.
------=_NextPart_000_0005_01C1A0A6.893EBCD0
Content-Type: text/plain;
charset="utf-8"
Content-Transfer-Encoding: quoted-printable
Linux Quake3 rocks Win-XP Quake3 on new P4
By Thomas C Greene in Washington
Posted: 18/01/2002 at 12:58 GMT
http://www.theregister.co.uk/content/4/23735.html
The new Northwood 2.2gHz 0.13-micron P4, as I mentioned earlier, seems =
made for Windows-XP. It's got special chipset drivers; it's got an =
'application accelerator'; it's got Rambus working overtime.=20
For Linux it's got nothing special to offer -- no accelerators or =
drivers. Just 2.2 in clock speed and a memory controller that exploits =
RDRAM nicely, which is definitely nothing to sneeze at. But it's got =
that on Windows as well.=20
So imagine my surprise when I benchmarked it with the only test I know =
that crosses the great divide between Linux and Windows -- the Quake-3 =
FPS benchmark -- and found that the performance of this Windows-loving =
kit was considerably better on Linux, at least in that context.=20
A brief re-cap of the hardware:=20
One Intel D850MVSE mobo with Northwood P4; 512M PC800 RDRAM; two Maxtor =
D740X 20G ATA-133 drives on the mobo's onboard ATA-100 controller, one =
booting Win-XP Pro on FAT and one booting SuSE 7.3 Pro on ReiserFS and =
both installed clean and subsequently patched; and a 64M DDR GeForce =
AGP4.=20
The Windows drive is patched with whatever the MS auto-update =
cloak-and-dagger process does to it. The Linux drive is patched to =
kernel 2.4.17. The video and OpenGL drivers for both OS's were upgraded =
with the most recent files from Nvidia's Web site.=20
On the Windows drive I installed all the Intel chipset drivers and the =
Application Accelerator. The Linux kernel is reasonably optimized for =
the HDD and the P4, but with APIC disabled, as it just won't run on the =
850 mobo otherwise.=20
But that's hardly a problem.=20
Both operating systems, obviously, had to be running at the same level =
of display detail, and the limitations of XFree86 pretty well determined =
that for me. Both desktops were set at 16-bit color depth, and in both =
cases Quake was set with the following display options for the first =
series of runs:=20
Mode: 1024x786=20
Color depth: 16-bit=20
Lighting: lightmap=20
Geometric detail: high=20
Texture Detail: maximum=20
Texture quality: 16-bit=20
Filter: trilinear=20
It seems a bit skimpy, but rich detail takes more from the graphics =
accelerator whereas less detail gives us a better look at the CPU, =
chipset and system memory.=20
Win-XP returned an average of 72.7 FPS, which is worse than I'd expect =
from a P3 800 on '98 with about 128M RAM, or a 486DX 100 on Win 3.1 with =
about 16M RAM. (You see the pattern here....)=20
Linux returned an average of 80.2 FPS, which is significantly better, =
though hardly brilliant. But let's keep in mind that the system I'm =
using here is virtually Linux-hostile. The next one won't be.=20
With even less detail, further reducing dependency on the graphics card, =
we got better numbers from the CPU. The breakdown was similar, though =
Windows narrowed the gap a bit.=20
Mode: 640x480=20
Color depth: 16-bit=20
Lighting: vertex=20
Geometric detail: low=20
Texture Detail: minimum=20
Texture quality: 16-bit=20
Filter: bilinear=20
This gave us averages of 272.2 FPS on Windows and 304.7 on Linux.=20
We can infer that Win-XP is so greedy for system resources that even the =
most potent (and most expensive) CPU on the market, coupled with a hefty =
chunk of very fast RDRAM (also very expensive), only suffices to make it =
work nicely.=20
Other considerations=20
It's quite difficult to compare the performance of a given system on =
both Linux and Windows. The Quake benchmark is a rare exception, but =
basically it's apples and oranges. For example, what can we learn from =
evaluating the performance of Photoshop on Windows and the Gimp on =
Linux? Damn little, I reckon.=20
For that matter, what can we learn from running Netscape, StarOffice and =
the Gimp on both? It's entirely possible that these applications could =
have performance issues on a given OS which would skew the results.=20
I'll certainly try a number of tests like that during the weekend. This =
way, I hope, a single performance oddity won't cause too much =
distortion.=20
It's also worthwhile trying to match a system with an OS. For insight we =
can look at some of the everyday tasks common to both OS's, and compare =
them on different systems. I've taken a few common-sense measurements on =
both SuSE and Win-XP with the Intel 850/Northwood combo, but these won't =
have meaning until I repeat them on a different system and see where =
they differ.=20
Which I'll do, early next week. =C2=AE=20
------=_NextPart_000_0005_01C1A0A6.893EBCD0
Content-Type: text/html;
charset="utf-8"
Content-Transfer-Encoding: quoted-printable
=EF=BB=BF<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META http-equiv=3DContent-Type content=3D"text/html; charset=3Dutf-8">
<META content=3D"MSHTML 6.00.2712.300" name=3DGENERATOR>
<STYLE></STYLE>
</HEAD>
<BODY bgColor=3D#ffffff>
<DIV><FONT face=3DArial color=3D#0000ff size=3D2>
<DIV class=3Dstoryhead>Linux Quake3 rocks Win-XP Quake3 on new P4</DIV>
<DIV class=3Dstorybyline>By <A=20
href=3D"mailto:[EMAIL PROTECTED]">Thomas C Greene in=20
Washington</A></DIV>
<DIV class=3Dindexposted>Posted: 18/01/2002 at 12:58 GMT</DIV>
<DIV class=3Dindexposted><A=20
href=3D"http://www.theregister.co.uk/content/4/23735.html";>http://www.the=
register.co.uk/content/4/23735.html</A></DIV><BR>
<DIV class=3Dstorybody>The new Northwood 2.2gHz 0.13-micron P4, as I <A=20
href=3D"http://www.theregister.co.uk/content/4/23693.html"; =
target=3Dnew>mentioned=20
earlier</A>, seems made for Windows-XP. It's got special chipset =
drivers; it's=20
got an 'application accelerator'; it's got Rambus working overtime. =
<BR><BR>For=20
Linux it's got nothing special to offer -- no accelerators or drivers. =
Just 2.2=20
in clock speed and a memory controller that exploits RDRAM nicely, which =
is=20
definitely nothing to sneeze at. But it's got that on Windows as well.=20
<BR><BR>So imagine my surprise when I benchmarked it with the only test =
I know=20
that crosses the great divide between Linux and Windows -- the Quake-3 =
FPS=20
benchmark -- and found that the performance of this Windows-loving kit =
was=20
considerably better on Linux, at least in that context. <BR><BR>A brief =
re-cap=20
of the hardware: <BR><BR>One Intel D850MVSE mobo with Northwood P4; 512M =
PC800=20
RDRAM; two Maxtor D740X 20G ATA-133 drives on the mobo's onboard ATA-100 =
controller, one booting Win-XP Pro on FAT and one booting SuSE 7.3 Pro =
on=20
ReiserFS and both installed clean and subsequently patched; and a 64M =
DDR=20
GeForce AGP4. <BR><BR>The Windows drive is patched with whatever the MS=20
auto-update cloak-and-dagger process does to it. The Linux drive is =
patched to=20
kernel 2.4.17. The video and OpenGL drivers for both OS's were upgraded =
with the=20
most recent files from Nvidia's Web site. <BR><BR>On the Windows drive I =
installed all the Intel chipset drivers and the Application Accelerator. =
The=20
Linux kernel is reasonably optimized for the HDD and the P4, but with =
APIC=20
disabled, as it just won't run on the 850 mobo otherwise. <BR><BR>But =
that's=20
hardly a problem. <BR><BR>Both operating systems, obviously, had to be =
running=20
at the same level of display detail, and the limitations of XFree86 =
pretty well=20
determined that for me. Both desktops were set at 16-bit color depth, =
and in=20
both cases Quake was set with the following display options for the =
first series=20
of runs: <BR><BR>Mode: 1024x786 <BR>Color depth: 16-bit <BR>Lighting: =
lightmap=20
<BR>Geometric detail: high <BR>Texture Detail: maximum <BR>Texture =
quality:=20
16-bit <BR>Filter: trilinear <BR><BR>It seems a bit skimpy, but rich =
detail=20
takes more from the graphics accelerator whereas less detail gives us a =
better=20
look at the CPU, chipset and system memory. <BR><BR>Win-XP returned an =
average=20
of 72.7 FPS, which is worse than I'd expect from a P3 800 on '98 with =
about 128M=20
RAM, or a 486DX 100 on Win 3.1 with about 16M RAM. (You see the pattern=20
here....) <BR><BR>Linux returned an average of 80.2 FPS, which is =
significantly=20
better, though hardly brilliant. But let's keep in mind that the system =
I'm=20
using here is virtually Linux-hostile. The next one won't be. =
<BR><BR>With even=20
less detail, further reducing dependency on the graphics card, we got =
better=20
numbers from the CPU. The breakdown was similar, though Windows narrowed =
the gap=20
a bit. <BR><BR>Mode: 640x480 <BR>Color depth: 16-bit <BR>Lighting: =
vertex=20
<BR>Geometric detail: low <BR>Texture Detail: minimum <BR>Texture =
quality:=20
16-bit <BR>Filter: bilinear <BR><BR>This gave us averages of 272.2 FPS =
on=20
Windows and 304.7 on Linux. <BR><BR>We can infer that Win-XP is so =
greedy for=20
system resources that even the most potent (and most expensive) CPU on =
the=20
market, coupled with a hefty chunk of very fast RDRAM (also very =
expensive),=20
only suffices to make it work nicely. <BR><BR><B>Other =
considerations</B>=20
<BR>It's quite difficult to compare the performance of a given system on =
both=20
Linux and Windows. The Quake benchmark is a rare exception, but =
basically it's=20
apples and oranges. For example, what can we learn from evaluating the=20
performance of Photoshop on Windows and the Gimp on Linux? Damn little, =
I=20
reckon. <BR><BR>For that matter, what can we learn from running =
Netscape,=20
StarOffice and the Gimp on both? It's entirely possible that these =
applications=20
could have performance issues on a given OS which would skew the =
results.=20
<BR><BR>I'll certainly try a number of tests like that during the =
weekend. This=20
way, I hope, a single performance oddity won't cause too much =
distortion.=20
<BR><BR>It's also worthwhile trying to match a system with an OS. For =
insight we=20
can look at some of the everyday tasks common to both OS's, and compare =
them on=20
different systems. I've taken a few common-sense measurements on both =
SuSE and=20
Win-XP with the Intel 850/Northwood combo, but these won't have meaning =
until I=20
repeat them on a different system and see where they differ. =
<BR><BR>Which I'll=20
do, early next week. =C2=AE </DIV>
<DIV class=3Dstorybody><BR> </DIV></FONT></DIV></BODY></HTML>
------=_NextPart_000_0005_01C1A0A6.893EBCD0--
================================================
BRLUG - The Baton Rouge Linux User Group
Visit http://www.brlug.net for more information.
Send email to [EMAIL PROTECTED] to change
your subscription information.
================================================
