Here's a Dell story you don't see too often

[Rob Stow]

Error: Incompatible Browser Detected

We're Sorry! This Performance Portal site requires Microsoft Internet
Explorer 5.0 or later (IE 5.5 or later recommended). You can obtain the
latest version of IE from the Microsoft Internet Explorer web site.

Note: For a complete list of system requirements, please see our
Performance Portal product information page.

If they can't even do a decent job with their web site,
how the heck is anybody supposed to believe they have
successfully tackled the more difficult job of creating
a valid benchmarking app ?

 

[The little lost angel]

If they can't even do a decent job with their web site,
how the heck is anybody supposed to believe they have
successfully tackled the more difficult job of creating
a valid benchmarking app ?

Might not be their fault... they used FrontPage... a software company
used to deliberately make their apps break when ran on a rival
operating system back in the DOS days you know pPP

--
L.Angel: I'm looking for web design work.
If you need basic to med complexity webpages at affordable rates, email me
Standard HTML, SHTML, MySQL + PHP or ASP, Javascript.
If you really want, FrontPage & DreamWeaver too.
But keep in mind you pay extra bandwidth for their bloated code

 

[Rob Stow]

Might not be their fault... they used FrontPage... a software company
used to deliberately make their apps break when ran on a rival
operating system back in the DOS days you know pPP

They're dumb enough to use FrontPage but we are
supposed to trust them to be smart enough to make
a valid benchmarking app ? "Does not compute."

 

[Yousuf Khan]

Your key claim (I believe) is that the benchmark software is a
subterfuge by way of giving scheduling attention to the jobs on the
hyperthreaded system but not on the Opteron system. That's an
interesting theory, and it may well be correct, but your analysis
rests on assumptions about the actual benchmark and about scheduling
behavior that I don't know how to check.

To play my own devil's advocate, I'll list what we do know about the
benchmark, and what we are conjecturing. We _know_ that the benchmark is
Hyperthreading aware, we know that it runs one real-world application
thread, and multiple synthetic load-generating threads, and that the
synthetic threads are disposable (i.e. their results are not saved or
measured). What we are _conjecturing_ is that the benchmark is using its
Hyperthreading awareness to create an unfair multitasking priority advantage
for the benchmarked application -- we don't know this for sure; for all we
know, this benchmark doesn't make use of any of its Hyperthreading knowledge
(i.e. complete innocence), to create an unfair testing situation.

The conjecture is based upon the fact that it's easy to detect
Hyperthreading and to optimize for it. Detecting Hyperthreading can be done
completely in user-space, it doesn't require any privileged instructions,
simply a couple of CPUID instructions and you're done. During bootup, Intel
has specified that all physical processors will be enumerated first, and all
virtual processors will be enumerated last. So it's easy to figure out which
processors are real and which ones are virtual. Most OS'es have some kind of
functionality to allow applications to specify which processors they want
their threads to start up on.

Since this was a dual-processor vs. dual-processor shootout, the non-HT CPU
will appear simply as two CPUs, whereas the HT CPU will appear as 4 CPUs.
CPUID will tell you automatically how many are real and how many are virtual
and which ones they are.

One can always, at least in theory, arrange job priorities so that
background jobs interfere minimally with foreground jobs. Without any
constraint on how the background jobs are hog-tied, you could probably
get any result you wanted...if indeed you are fiddling with scheduling
priorities.

Yeah, obviously they didn't want to appear to be fiddling with Windows' own
scheduling priorities that would be too obviously unfair, so they worked
around Windows' scheduling priorities with the HT loophole. Since each
logical processor appears to have its own separate run queue in Windows,
they didn't actually modify any of the run queue priorities, they just
distributed the workloads strategically, putting their most important
threads on less busy logical processors. That way they can claim that all of
the individual run queues were unchanged, which is true, but they have twice
as many run queues to choose from.

In an actual multitasking environment, with real work being done both in the
foreground and background, the applications will get distributed out to the
run queues in a roundrobin-fashion. Therefore even with twice the run
queues, an HT processor will have more or less evenly loaded run queues, no
different than the case on a non-HT processor.

csaresearch.com has a skewed view of things resulting from a desire to
sell advertising? The "Seeing double?" stuff right on the web page
you linked to is probably a better clue than Randall Kennedy's c.v.

Perhaps, it is a better clue. But I thought the fact he himself says he
worked for an Intel marketing department was also a pretty good clue.

Someone is influenced by his "strong recommendations" despite an
apparent conflict of interest? Caveat emptor.

It's hard to say how much people are going to be influenced by this, since
this article barely published any of the benchmarks that they said they ran.

Yousuf Khan

 

[Neil Maxwell]

Who are the readers of Infoworld? Whether the data reflect reality or
not, I'm sure they've got data to show that their readers are serious
prospective enterprise buyers.

Back in the old days, Infoworld was partly a pretty hard-tech
publication, with video card and MB comparisons and such. Some time
back, maybe a decade ago, they started focusing more on the
"enterprise computing" arena, eschewing the nuts'n'bolts for
high-level coverage. Eventually, this became their entire focus.

I believe their current target readership is more along the line of
middle-to-upper IT managers, with lots less emphasis on technical
integrity and more emphasis on systems, support, and marketing trends,
but I haven't read them much for the last 5 years.

 

[Neil Maxwell]

Here's another article that basically puts the blame for Intel's (and
therefore Dell's) uncompetiveness squarely on the shoulders of Intel, from
the following article:

http://www.chinadaily.com.cn/english/doc/2004-08/17/content_366242.htm

I haven't seen any articles with any data regarding what the
configurations of these competing systems are. That is, which AMD
chips are Lenovo putting in their bottom-end boxes vs. which Intel
chips are Dell putting in their China-targetted bottom-tier PCs? This
would tell you how much of a price impact the actual CPU has on the
final system. Of course, even $20 is a fair bit of margin on a $360
PC.

The article did note that Lenovo has been losing money, and is
attempting to narrow losses by focusing on core businesses. It sounds
to me like they're emphasizing market share over profits, which is a
strategy Dell has never been too fond of. Dell's China growth
estimate is still pretty hefty, and they may have decided to focus on
the middle range where there are still some profits to be had. Time
will tell which is the right approach for the China market.

 

[chrisv]

Might not be their fault... they used FrontPage... a software company
used to deliberately make their apps break when ran on a rival
operating system back in the DOS days you know pPP

If they endorsed, paid for, or are in any other way associated with a
Web site that only works if you're using monopoly crapware, yes, it is
their fault.

 

[Yousuf Khan]

I haven't seen any articles with any data regarding what the
configurations of these competing systems are. That is, which AMD
chips are Lenovo putting in their bottom-end boxes vs. which Intel
chips are Dell putting in their China-targetted bottom-tier PCs? This
would tell you how much of a price impact the actual CPU has on the
final system. Of course, even $20 is a fair bit of margin on a $360
PC.

I thought they mentioned that they were using Semprons here. I could be
wrong, a lot of other news stories floating around, can't keep them all
straight in my head.

The article did note that Lenovo has been losing money, and is
attempting to narrow losses by focusing on core businesses. It sounds
to me like they're emphasizing market share over profits, which is a
strategy Dell has never been too fond of. Dell's China growth
estimate is still pretty hefty, and they may have decided to focus on
the middle range where there are still some profits to be had. Time
will tell which is the right approach for the China market.

I don't think Dell has had any problems with using loss-leader economics in
the past. Bring people in with products that are so cheap that they lose
money on them, and hopefully they'll buy some other things that will make up
for the loss.

I doubt that the Lenovo model is any different than that. Of course, it
might have gotten to the point in China that all products are now
loss-leaders (meaning companies are now producing losses overall). But Dell
is remaining in the higher-end Chinese markets, like business PCs, etc. So
if Dell is hanging around for those markets, then perhaps profits are still
to be had there. That means that probably the locals, Lenovo and Founder,
are probably still making profits in those markets too.

The locals want to sell loss-leaders so that they can establish a product
identity with their customers for the future. If they buy a cheap PC today,
they'll buy an expensive PC tomorrow.

Yousuf Khan

 

[The little lost angel]

They're dumb enough to use FrontPage but we are
supposed to trust them to be smart enough to make
a valid benchmarking app ? "Does not compute."

Well, even though I personally am biased against people who uses
FrontPage, a lot of people does simply because they don't know any
better or can't be bothered to learn anything else. Don't forget,
often the web developer isn't a permanent staff of the company, it's
usually a contract job. So there may be no relation between the
capabilities of the web designer and the company itself.



--
L.Angel: I'm looking for web design work.
If you need basic to med complexity webpages at affordable rates, email me
Standard HTML, SHTML, MySQL + PHP or ASP, Javascript.
If you really want, FrontPage & DreamWeaver too.
But keep in mind you pay extra bandwidth for their bloated code

 

[Ed]

The locals want to sell loss-leaders so that they can establish a product
identity with their customers for the future. If they buy a cheap PC today,
they'll buy an expensive PC tomorrow.

and that expensive PC will probably have a different brand name inside
and out (Dell/Intel). ;p

Ed

 

[Yousuf Khan]

and that expensive PC will probably have a different brand name inside
and out (Dell/Intel). ;p

Maybe, that future PC might have an Intel inside it, but I don't think it'll
be a Dell. The locals are trying to build brand loyalty to themselves with
these loss-leaders.

Anyways, the really high-end PCs are now Athlon 64-based. Pentium 4 PCs are
now mid-range.

Yousuf Khan

 

[Yousuf Khan]

Error: Incompatible Browser Detected

We're Sorry! This Performance Portal site requires Microsoft
Internet Explorer 5.0 or later (IE 5.5 or later recommended). You
can obtain the latest version of IE from the Microsoft Internet
Explorer web site.

Note: For a complete list of system requirements, please see our
Performance Portal product information page.

So which browser did it die on, Mozilla or Opera?

Yousuf Khan

 

[Rob Stow]

So which browser did it die on, Mozilla or Opera?

Yousuf Khan

It doesn't work with either the latest Mozilla or Mozilla
Firebird. I also talked to someone I know who has a Sparc III
system running Solaris and Linux - he can't view it with any
of his browsers. For me, not using crapware like IE
is my choice - he has no such option at all.

No idea about Opera.

 

[Adam Warner]

Hi Yousuf Khan,

So which browser did it die on, Mozilla or Opera?

Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.7.2) Gecko/20040810 Debian/1.7.2-2

Konqueror has a friendly feature to set a custom user agent string that
matches, say, MSIE in order to gain access to poorly designed websites.

$ whois csaresearch.com
....Administrative Contact:
Kennedy, Randall ...

Regards,
Adam

 

[Yousuf Khan]

Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.7.2) Gecko/20040810
Debian/1.7.2-2

Konqueror has a friendly feature to set a custom user agent string
that matches, say, MSIE in order to gain access to poorly designed
websites.

So did Konquerer work with this page? Opera has a similar feature.

However, recently some pages on my ISP homepage became even a little
unfriendly to Opera, though it works with Mozilla.

Yousuf Khan

 

[Adam Warner]

Hi Yousuf Khan,

So did Konquerer work with this page? Opera has a similar feature.

Yes, after reconfiguring it to send a MSIE 6.0/Windows XP user agent
string to the domain's web server. It rendered 100% correctly.

However, recently some pages on my ISP homepage became even a little
unfriendly to Opera, though it works with Mozilla.

It has probably been years since I've struck a MSIE mandatory website.
They're rather uncommon. Flash content is common but I just ignore any
sites that enforce it for navigation. I'd say the web is more platform
neutral than ever.

It's great news that AOL have just released Netscape 7.2. I've found a
known corporate brand can help break down the resistance of some users to
upgrade.

I've never used Opera. It's good to see the company coming out against
software patents in Europe, especially by undermining Nokia's pro-software
patent stance as the supplier of browser software in their mobile phones.
That takes guts.

Regards,
Adam

 

[Tony Hill]

Hi Tony Hill,

You make a great point, thanks Tony. But why would a savvy consumer choose
an Intel _Celeron_ over most AMD CPU choices?

I'd buy a Celeron + i865 combo over some piece an AMD CPU stuck in a
POS VIA KM266 setup any day. There's much more too it than just the
processor, and Dell is able to sell fairly high-end platforms for VERY
cheap prices.

Doesn't Dell need to hope
that Intel's marketing is so strong in China that consumers will choose
the Intel brand even if computers are priced the same? If Dell cannot rely
upon this perception it cannot compete. Period.

Not so much that they can't compete, just that they'll have to compete
on features instead of just brand-name. However Dell is capable of
doing that.

Even if it starts selling
"naked PCs". What happens if 64-bit computing becomes a checklist point?

Presumably at that stage Intel will have a 64-bit desktop processor.

Or gamers find out that an AMD Athlon64 3000+ beat a P4 3.2GHz _Extreme
Edition_ running Doom 3?

That isn't going to mean much of anything to the consumers in
question, many of whom can't even think about affording either one.
It's all well and good that the Athlon64 3000+ is fast, but when
you're choice is an AMD Sempron 2400+ or a Celeron 2.4GHz, that point
is kind of moot.

Intel has to provide Dell with suitable priceerformance options so it
can compete effectively. Whether this is already hurting Dell is debatable.

Given Dell's recent history (ie the last 5 years) of making FAR more
profit than any of their competitors, I'd say that no, it's not
hurting Dell much at all.

 

[Tony Hill]

Robert Myers wrote:
Actually the problem with the Infoworld article is that it's not even really
a true test of multitasking performance. If you read the article, and then
do some checking up on the tools used, it's very shady. First of all, the
benchmarking application is described on the company's website here:

Yup, some VERY shady deals going on here, especially considering that
the author of the article is also the guy selling the benchmark and is
also a paid consultant for companies trying to demonstrate the
performance of their systems

Having read through the article it *STRONGLY* reminds me of all those
Microsoft-funded "studies" that clearly demonstrate Windows has a
lower cost of ownership than <insert any other OS here>.

Somebody is definitely getting paid here to show a particular result,
regardless of whether that result corresponds to reality or not.

 

[Tony Hill]

Error: Incompatible Browser Detected

We're Sorry! This Performance Portal site requires Microsoft Internet
Explorer 5.0 or later (IE 5.5 or later recommended). You can obtain the
latest version of IE from the Microsoft Internet Explorer web site.

Note: For a complete list of system requirements, please see our
Performance Portal product information page.

If you're using Mozilla Firefox the useragentswitch extension does a
nice job of bypassing this stupidity. Not surprisingly everything
displays perfectly using non-IE browsers (with the exception of his
rather pointless "demo", which is in ASP).'

 

[Rob Stow]

If you're using Mozilla Firefox the useragentswitch extension does a
nice job of bypassing this stupidity. Not surprisingly everything
displays perfectly using non-IE browsers (with the exception of his
rather pointless "demo", which is in ASP).'

The problem with browser spoofing like that is that it
lets the web developer get away with his stupidity.
In the long run I think you are far better served by
requiring the developers to do a good job instead of
looking for work-arounds on your end when they screw up.