Slashdot Mirror

As someone else has mentioned, the ars system guides are excellent. They build several different types of system and explain the trade-offs they make very nicely.

I also happen to really like Dan Bernstein's advice, especially for a good *BSD desktop box. Like Ars, Dan does an excellent job explaining why he chose what he did.

The ars guides are usually almost current. DJB's is not as current. But look at them for the explanations, even if you want newer components. You can apply their advice to the in depth discussions of particular components you'll find at places like Tom's, HardOCP, AnandTech, etc.

Three other points I would add:

1. All the praise of Tom's Hardware Guide is absolutely true.

2. Analog sources can be good... flip through a few Computer Shopper magazines and the Consumer Reports Buyer's Guide before making significant purchases.

3. Before you spend a dime, run the numbers and figure out whether or not building it yourself is really worth it. Is there a config you want that Dell doesn't offer? How does price compare to an off-the-shelf solution? Would you prefer a single point of contact for repair issues or are you comfortable dealing with multiple vendors? Depending on what you need it to do, a DIY solution might very well be better, faster, and cheaper... just check first.

Also, just in case, this is solely my opinion and not necessarily the opinion of my employer.

At least temporarily? Smoke a big fat blunt. Pot effects your memory, and to some extent takes you off the "auto pilot" associations that you have formed to familiar stimuli. It can be helpful in giving one a fresh look at his assumptions, and also helps one notice features that he may not have payed attention to before.

Arstechnica's Nobel Intent section recently had an article titled Is cannabis good for your brain? , citing a new research study that says marijuana leads to neurogenesis in the hippocampus. This jives well with my experience smoking - I've thought for a while smoking roots roots one in nature. It brushes away some of the cultural veneer at least temporarily, and sometimes you notice things in this state you might have otherwised gotten used to judging more narrowly.

To me that reads as "people being trained to attach little black boxes of music to their computer, with the eventual intention of DRMing said boxes". If people are trained to attach arbitrary boxes to their computer to get music/films, the next step is to have those boxes "streaming" the audio/video straight to a Trusted Output Device [tm]. This probably wouldn't stop piracy, but it'd make backing up your media nigh-on impossible, since you'd no longer be able to copy directly.

This fits in well with plans to make Windows Vista only play DVDs at full quality using the aforementioned Trusted Output Devices [tm]

I dunno, but i'd donate 10,000 dollars to charifty if someone does make one

Yes, Apple did keep modifying their kernel and breaking stuff in the past. Now they have a consistent kernel system in 10.4 that will allow updates without breaking stuff. Read more about their kernel update system with KPIs

GOVERNMENT WHAT!

It's interesting that you name a Beatle in your example because they're exactly the reason Apple can't do this. Apple isn't allowed to enter the music business because of an agreement made with the Beatle's record label, Apple Corp. In exchange for being able to use the Apple name, they were forbidden to enter the music business. They've carefully tiptoed around by these restrictions by not using the apple name in any of their music sales (iTunes music store, not Apple music store). Apple Corp has filed suit, and rumor has it that there is a big settlement coming down the pipe

Now Apple Computer could just buy out Apple Corps or pay to end the settlement, but that would probably be a very expensive proposition, considering they own most of the Beatle's music. They're not nobodies in the music world.

Either way, I think your idea is a good one, as elliminating as many middlemen as possible is always best for everyone (except the middleman).

"If they want to raise the prices, it means that they are getting greedy." Doesn't sound like he's in favour to me. See the current Ars Technica article for the quote (http://arstechnica.com/news.ars/post/20051117-559 1.html) or google it for wider coverage, none of which suggests that Apple would even consider the idea.

Verizon is currently supplying 15mbps or faster internet in some areas, in addition to TV.
http://arstechnica.com/news.ars/post/20051014-5433 .html

Whoever gets their fibre network built first will have a headstart over the other. A few months ago, Cox (our cable company) bumped our dload speeds up to 5mbps from 3mbps, I was curious to why they did this. Later, I found out that 3mbps DSL is now available in our area. Who says there is no competition?

In the early '90s, the US congress decided they needed to regulate pricing on cable TV. This caused the cable companies to miss a rebuild cycle that would have pushed fiber closer to the home.

Yet another reason regulation is bad.

.....I bet most don't scratch up as bad as iPods do."

It seems the nano really isn't that fragile after all, and the scratch concern is also a running gag about people treating nanos as car keys.

You are, I assume, referring to the same "Japanese" electronics arm that is behind Blu-ray DRM?

Judging by the tricks Sony is developing for consumer electronics, I'd assume their "engineering-led" arm is saying "Hell yeah, BMG, lead the way!"

By skimping on cache and using chips with no branching predictor, PS3 and 360 are "getting rid of the whole hardware capability. It won't be harder to implement a feature, it will be impossible."

From current rumored specs and Nintendo's gameplay-over-graphics mentality, Revolution will likely have some combination of a larger CPU cache, a 970-based CPU (instead of the PPE used in the PS3 and 360), and an Ageia physics processor.

None of these would improve streaming media performance (the main focus of the competitors' hardware), but any of these would make the Revolution the most powerful console on the block for branching-intensive code; code for things like AI, physics, and game-control code.

That said, 360 and PS3 will dominate in the streaming media applications they're designed for; likely enough to match or surpass the Revolution's graphics at the much higher resolutions required for HD support.

Sources:
PPE's poor branching performance
Advantages of large cache or 970-based CPU
Revolution Ageia rumor

By skimping on cache and using chips with no branching predictor, PS3 and 360 are "getting rid of the whole hardware capability. It won't be harder to implement a feature, it will be impossible."

From current rumored specs and Nintendo's gameplay-over-graphics mentality, Revolution will likely have some combination of a larger CPU cache, a 970-based CPU (instead of the PPE used in the PS3 and 360), and an Ageia physics processor.

None of these would improve streaming media performance (the main focus of the competitors' hardware), but any of these would make the Revolution the most powerful console on the block for branching-intensive code; code for things like AI, physics, and game-control code.

That said, 360 and PS3 will dominate in the streaming media applications they're designed for; likely enough to match or surpass the Revolution's graphics at the much higher resolutions required for HD support.

Sources:
PPE's poor branching performance
Advantages of large cache or 970-based CPU
Revolution Ageia rumor

By skimping on cache and using chips with no branching predictor, PS3 and 360 are "getting rid of the whole hardware capability. It won't be harder to implement a feature, it will be impossible."

From current rumored specs and Nintendo's gameplay-over-graphics mentality, Revolution will likely have some combination of a larger CPU cache, a 970-based CPU (instead of the PPE used in the PS3 and 360), and an Ageia physics processor.

None of these would improve streaming media performance (the main focus of the competitors' hardware), but any of these would make the Revolution the most powerful console on the block for branching-intensive code; code for things like AI, physics, and game-control code.

That said, 360 and PS3 will dominate in the streaming media applications they're designed for; likely enough to match or surpass the Revolution's graphics at the much higher resolutions required for HD support.

Sources:
PPE's poor branching performance
Advantages of large cache or 970-based CPU
Revolution Ageia rumor

That's a slippery slope if I've ever heard one.

If you want a rundown on the hardware here ya go (link lifted from a previous slashdot post).

The reduced price is of course justified as mentioned above, you're not getting nearly as much hardware for the buck as the revolution is sans: Hardive, 802.11g, HDTV input, CPU clock. However the interesting thing to note as the article points out is the speculative large(r) size of L2 cache. I don't feel like quoting it so have a read yourself and take notes on how "less features" does not correlate to "poor quality".

Ars Technica had a good piece related to this. Very briefly, they point out that most titles are written to be cross-platform, thus erasing a lot of the relative hardware benefits of each platform.

http://arstechnica.com/articles/paedia/hardware/cr ossplatform.ars

I think Nintendo is on to a winner; we'll see if the execution is as good as their ideas.

I buy CDs if I want to support the artist, though not before some background checking on the album. I think it's fairly obvious that allofmp3.com does not share profits with the artist, particularly since the RIAA tried to get them shut down. So if I think an artist has enough talent to deserve my support, and if I have no reason to beleive there is any sketchy software on the CD (ie if it has the Compact Disc label on it), and I am relatively confident that buying an album won't support the RIAA, then yes, I'll buy a CD. (And I can't back this up with anything more that a serach for sony on RIAA radar, but i'd say chances are the last two "if"s pretty much coincide other). That being said, I'm still spreading the word about allofmp3.com to anyone I know.

The scariest bit of this story, IMO, is that Sony is doing this. The same Sony that's pushing the BluRay disc format. The same format that has no required end-user protections. Imagine if the BluRay drivers themselves were essentially rootkits. HD DVD sounds better and better, if even for the fact that its not a Sony product.

...the Cell processor is an upcoming PowerPC variant that will be used in the PlayStation 3. It's great at DSP but terrible at branch prediction, and would not make a very good Mac. If you want to know full tech specs, Hannibal is da man.

I don't know whether to laugh or cry at Apple/Jobs lastest attempt to monopolize. Maube this time even the Apple devotess/apologists will sit up and notice. What has Apple actually contributed to the invention of the desktop computer? Almost everything that makes an Apple/Jobs computer - has been taken from others - at no cost to Apple/Jobs - and is based on the inventiveness and the sweat/work of others. OS X's Darwin is based on FreeBSD. Check out the Free BSD site http://www.freebsd.org/doc/en_US.ISO8859-1/article s/contributors/index.html and you'll see that Apple/Jobs neither contributed money or staff to the development of FreeBSD. In a similar fashion the GUI, the mouse, ICONS all came from Douglas Englebart in the early 60s and in the following years at Xerox. Check out http://arstechnica.com/articles/paedia/gui.ars "The combination of Smalltalk and the Alto was essentially a modern personal computer with a very similar graphical user interface to the ones we use today. Altos had networking and could send e-mail to and receive it from one another, and seemed ideal for an office environment. Many of the PARC team wanted Xerox to market the new, cost-reduced Alto III as a commercial product (the original Alto was never available for sale) but Xerox management declined."

"Most people, I think, don't even know what a rootkit is, so why should they care about it," he asked? "The software is designed to protect our CDs from unauthorized copying, ripping."

Gavin Carter: Oblivion will absolutely benefit from a multi-processor or multi-core PC architecture. These improvements have largely been driven by our optimizations for the Xbox 360 hardware. We have built a dynamic thread management system that manages processor load by our specific direction and by priorities. Portions of physics, AI, loading, audio, and rendering tasks can all be moved to different threads to keep the overall load balanced. The net result for the end user is a smoother experience.

I think there are some interesting bits in this response. "We have built a dynamic thread management system" really caught my attention. I have read a number of recent articles [ 1, 2 ]talking about the need for multithread programming, and the difficulty of doing it. It seems to me that the ES4 team has not only embraced the idea of threading, but done so in what I think is a very logical manner.

What I envision of a dynamic thread management system from the quote above seems to be what is needed in the next generation of applications. With clock speed giving way to more cores speed increases will need to come from running tasks in parallel. For a number of reasons that I will not go into here, threading by hand can is difficult to do safely, and in many cases ends up being premature optimization. On the other hand leaving threading to a compiler or even worse the CPU circuitry itself has been seen to be fairly ineffective. The human who writes an application is probably the one most qualified to find parallelism, but may not be the best one to implement it at the thread level.

I envision that this system has allowed the different groups involved to create their distinct tasks and rules that govern how the tasks interact, but instead of trying to hand code that interaction, they have designed a system that does the dirty work of translating task interaction into thread logic for them. Additionally, this seems to be done on the fly so a system like the XBOX360 with 3 PPE cores can execute differently then a new PC with a multi core an AMD or INTEL cpu. It also would seem to allow program to adapt to the loads finds itself under.

I for one would really like to hear more about the way this thing functions. In a post to one of the articles I referenced, I asked about the availability of programming paradigms that would abstract the concept of threads much as many languages now abstract the concept of memory allocation with "Garbage Collection." I didn't get much of a response. I'm hoping some Slashdot reader can fill me in on what is know about thread management systems.

References:

• Wikipedia Entry: Threads
• Ars Technica Article: Introduction to Multithreading, Superthreading and Hyperthreading
• A threads FAQ from comp.programming.threads

Gavin Carter: Oblivion will absolutely benefit from a multi-processor or multi-core PC architecture. These improvements have largely been driven by our optimizations for the Xbox 360 hardware. We have built a dynamic thread management system that manages processor load by our specific direction and by priorities. Portions of physics, AI, loading, audio, and rendering tasks can all be moved to different threads to keep the overall load balanced. The net result for the end user is a smoother experience.

I think there are some interesting bits in this response. "We have built a dynamic thread management system" really caught my attention. I have read a number of recent articles [ 1, 2 ]talking about the need for multithread programming, and the difficulty of doing it. It seems to me that the ES4 team has not only embraced the idea of threading, but done so in what I think is a very logical manner.

What I envision of a dynamic thread management system from the quote above seems to be what is needed in the next generation of applications. With clock speed giving way to more cores speed increases will need to come from running tasks in parallel. For a number of reasons that I will not go into here, threading by hand can is difficult to do safely, and in many cases ends up being premature optimization. On the other hand leaving threading to a compiler or even worse the CPU circuitry itself has been seen to be fairly ineffective. The human who writes an application is probably the one most qualified to find parallelism, but may not be the best one to implement it at the thread level.

I envision that this system has allowed the different groups involved to create their distinct tasks and rules that govern how the tasks interact, but instead of trying to hand code that interaction, they have designed a system that does the dirty work of translating task interaction into thread logic for them. Additionally, this seems to be done on the fly so a system like the XBOX360 with 3 PPE cores can execute differently then a new PC with a multi core an AMD or INTEL cpu. It also would seem to allow program to adapt to the loads finds itself under.

I for one would really like to hear more about the way this thing functions. In a post to one of the articles I referenced, I asked about the availability of programming paradigms that would abstract the concept of threads much as many languages now abstract the concept of memory allocation with "Garbage Collection." I didn't get much of a response. I'm hoping some Slashdot reader can fill me in on what is know about thread management systems.

References:

• Wikipedia Entry: Threads
• Ars Technica Article: Introduction to Multithreading, Superthreading and Hyperthreading
• A threads FAQ from comp.programming.threads

Gavin Carter: Oblivion will absolutely benefit from a multi-processor or multi-core PC architecture. These improvements have largely been driven by our optimizations for the Xbox 360 hardware. We have built a dynamic thread management system that manages processor load by our specific direction and by priorities. Portions of physics, AI, loading, audio, and rendering tasks can all be moved to different threads to keep the overall load balanced. The net result for the end user is a smoother experience.

I think there are some interesting bits in this response. "We have built a dynamic thread management system" really caught my attention. I have read a number of recent articles [ 1, 2 ]talking about the need for multithread programming, and the difficulty of doing it. It seems to me that the ES4 team has not only embraced the idea of threading, but done so in what I think is a very logical manner.

What I envision of a dynamic thread management system from the quote above seems to be what is needed in the next generation of applications. With clock speed giving way to more cores speed increases will need to come from running tasks in parallel. For a number of reasons that I will not go into here, threading by hand can is difficult to do safely, and in many cases ends up being premature optimization. On the other hand leaving threading to a compiler or even worse the CPU circuitry itself has been seen to be fairly ineffective. The human who writes an application is probably the one most qualified to find parallelism, but may not be the best one to implement it at the thread level.

I envision that this system has allowed the different groups involved to create their distinct tasks and rules that govern how the tasks interact, but instead of trying to hand code that interaction, they have designed a system that does the dirty work of translating task interaction into thread logic for them. Additionally, this seems to be done on the fly so a system like the XBOX360 with 3 PPE cores can execute differently then a new PC with a multi core an AMD or INTEL cpu. It also would seem to allow program to adapt to the loads finds itself under.

I for one would really like to hear more about the way this thing functions. In a post to one of the articles I referenced, I asked about the availability of programming paradigms that would abstract the concept of threads much as many languages now abstract the concept of memory allocation with "Garbage Collection." I didn't get much of a response. I'm hoping some Slashdot reader can fill me in on what is know about thread management systems.

References:

• Wikipedia Entry: Threads
• Ars Technica Article: Introduction to Multithreading, Superthreading and Hyperthreading
• A threads FAQ from comp.programming.threads

Reference here: The first generation Aluminium 12" Powerbooks did not have this feature, although it was added later. I have an 867MHz 12" Powerbook, ergo I do not have this feature. So RTFM right back at you and fuck the moron who modded me flamebait.

This is a legitimate question I have. Why not support a system like Apple introduced with their kernel in OS 10.4? When it comes to operating systems, I am just a user. I don't hack on them. So, I could be missing something in the whole "the drivers must be open source so that they can be included in the kernel and updated along with it" thing. I would like a clear explanation why doing things the current way is better than implementing a new system that supports binary drivers in a clean way.

If you are not familiar with the "KPI" thing, here is a short summary from http://arstechnica.com/reviews/os/macosx-10.4.ars/ 4. I think it is a rather neat solution:

"With Tiger, Apple is finally ready to put some kernel interface stakes in the ground. For the first time, there are stable, officially supported kernel programming interfaces (KPIs). Even better, there's an interface versioning mechanism and migration policy in place that will ensure that the pre-Tiger situation never happens again.

From Tiger forward, kernel extensions will link against KPIs, rather than directly against the kernel. The KPIs have been broken down into smaller modules, so kexts can link against only the interfaces that they actually need to use.

Each KPI has a well-defined life cycle made up of the following stages.

        * Supported - The KPI is source and binary compatible from release to release.
        * Deprecated - The interface may be removed in the following major release. Compiler warnings are generated on use.
        * Obsolete - It's no longer possible to build new kernel extensions using this KPI, but binary compatibility for existing kexts that use this KPI is still assured.
        * Unsupported - Kexts using this KPI will no longer work, period.

The most significant part of this new system is that the kernel itself can and will change behind the scenes. KPIs will descend towards the "unsupported" end of the life cycle only as kernel changes absolutely demand.

Best of all, multiple versions of a KPI can coexist on the same system. This allows a KPI to move forward with new abilities and a changed interface without breaking kernel extensions that link to the older version of the KPI. The expectation is that the kernel can undergo a heck of a lot of changes while still supporting all of the KPIs."

But there are other ones, I'm sure, that caused loss of life. I just can't think of any.

True, and Microsoft seem to be siding with people who rip and stream content as a way to compete with Sony.

http://arstechnica.com/news.ars/post/20051017-5445 .html

Ars Technica did an interesting roundup of some wireless desktop devices back in August. If you're interested in this new model, you might want to have a look at their roundup, too.

AFAIK Monad is actually, as far as interfacing with the OS it's applicable to, more useful than several of the currently popular *nix shell scripting languages... for reference see this LONG article.

ridiculously false eh. Care to back up your claims? (Before you spout off about the gospels, and the whole new testament being corrupted or made up etc, you might like to check out this thread) Once you've done that please explain how you can start a new religion based upon miraculous events within days of the death of your its founder, while there are still many thousands of eyewitnesses around to disprove your claims. Finally please explain why people would be willing to die for something they knew to be false. I await your answer with eager anticipation.

Well, to be fair, there aren't that many PowerPC based PCs. In the server and embedded market there are quite a few PPC based machines, though. In this market, you can definitely find PPC machines with HT. For instance, Momentum boards have HT.

why? because apple engineered and designed the silicon, had the boards fabed for them

Apple designed an ASIC for their own use, but they could have also used IBM chips.

ibm has shifted over to being a video game console cpu maker

Yes, they do make the Cell, Xenon, and Broadway processors, but saying that they have shifted their core business is a bit disingenuous. One of the things IBM does is make custom chipsets for whoever is willing to pay for it. Furthermore, IBM makes a lot of chips for many different applications, and both Apple and the video game market are a small fraction of their output. I'll give you another example: Hitachi also makes custom CPUs for video game consoles, but no one is claiming that Hitachi's core business is video game consoles.

they hardly care about apple's business, and as such aren't focusing on the design work apple needs done to stay in the game. intel was willing to make a sweet deal, and amd would have had the same production volume issues that ibm was having. since intel has the fab capacity

Ars Technica has a good article on pretty much exactly what you said.

http://arstechnica.com/columns/linux/linux-2005090 7.ars

Let's not forget the software!

I'm going to sound really lazy now, but someone -- maybe ArsTechnica -- ran an article on the iLife stuff you get with your Mac and tried to find free alternatives for the PC.

The upshot is, there simply aren't any free alternatives that come anywhere near what you get with iLife.

If memory serves me correctly, the guys had to fork out a little over $800 to get their hands on the equivalent commercial software...

Of course Apple's not going to build DVD ripping into iTunes. That would get them into a huge amount of legal trouble. You can still do it yourself, though, using third-party applications such as Handbrake that can rip the video from the DVD and encode it in h.264 for you.

For converting existing videos to a compatible format, Apple does provide that functionality in Quicktime Pro, but that costs $30 USD. I'm sure a google search will bring up many free video converters.

You also might be interested in reading the guide to creating video for iPods at Ars Technica.

I agree totally with regards to the video Airport Express. I'm guessing they're just going to wait a little to let the video thing expand a little more, then Steve will announce this at a future Apple event. Wireless video out + Front Row + Mac Mini would be an awesome move for Apple.

Ars has better coverage.

It's a bit confusing, but as I understand things, this is the story: Eolas were awarded big damages against Microsoft based on their browser plugin patent. This patent was overturned in March 2004, which means Microsoft no longer had to pay those damages. Micosoft's appeal to SCOTUS was against those damages that it doesn't have to pay any more. So, I imagine the SCOTUS were like "WTF?" when they declined to hear the case.

Microsoft's not totally insane, though, because the patent has been reinstated, so MS and Eolas will be going back to court, and MS might lose again and have to pay money again. So they were looking for a precedent to keep a lid on those damages which they might get.

you'd be right, if the Revolution wasn't very much up to the task of producing visuals comparable to Xbox360 and PS3. you might want to read Hannibal's Analysis of the Revolution specs that were leaked.

WindowServer is responsible for handling moving windows, drawing the frames of windows, hidding and unhiding them and the like. It doesn't handle the desktop and drawing the items on it, Finder does that.

Yes and no. WindowServer, or to be more specific, the Quartz Compositor (itself a part of the WindowServer process) is also responsible for compositing all the windows into one image to send to your graphics card. While the Finder draws the items that reside on the desktop, it sends them to WindowServer to composite the images of each item onto the desktop. one. item. at. a time.*

By having 300 items on the desktop, WindowServer now has 300 MORE things to composite (yes, even if it most of them are covered by a fully opaque window) it's going to start using more CPU time.

*With Quartz Extreme, and Quartz 2D Extreme, some (but not all!) of this work is pushed onto the graphics card. It still takes CPU horsepower to put the data into a graphics card friendly format. [details]

There is another article in Ars Technical (http://arstechnica.com/news.ars/post/20051031-550 3.html) that says:

Users will also be able to copy music purchased via the store to their PCs and burn it to CD. In addition, they will be able to load 16-32MB of their own music on to the new phones if they choose.

I *assume* the 16-32MB *limit* is because that is the size of the bundled cards. So it looks like you CAN put music you already own into your phone. And if you did put in a 1GB card you can have a pretty decent portable music player that is also a phone. I think that makes this a much more significant announcement. I'm surprised they don't play that angle up more. Seems to me that Sprint has 2 distinct advantages over the iTunes phone: no 100 song limit and the ability (if you want) to buy a song instantly over-the-air.

Rambus hasn't been playing by the rules either. They've been penalized for destroying documents, http://arstechnica.com/news.ars/post/20050302-4664 .html and are suing Samsung immediately after revoking their liscence. http://news.zdnet.com/2100-9584_22-5734443.html It seems as if the entire industry is corrupt.

Posted by MightySpoon:

Quote:why has apple dropped the development of Q2DX in tiger?

To avoid potential lawsuits from Vanilla Ice.

(Say Quartz Two Dee Extreme out loud and then try not to shoot yourself in your face. You can't do it.)

Posted by MightySpoon:

Quote:why has apple dropped the development of Q2DX in tiger?

To avoid potential lawsuits from Vanilla Ice.

(Say Quartz Two Dee Extreme out loud and then try not to shoot yourself in your face. You can't do it.)

There was good article on Ars Technica as well, going into a fair amount of technical detail into why Valve's HDR implementation is interesting, and why it took so long (and so many attempts) to create.

I'm still waiting for the updated Source SDK so I can build maps using HDR - it's something I'm really looking forwards to. Eat your heart out, darkness-obsessed Doom 3 and friends! ;-)

Disables Quartz 2D Extreme--Quartz 2D Extreme is not a supported feature in Tiger, and re-enabling it may lead to video redraw issues or kernel panics.

http://arstechnica.com/reviews/hardware/thinkpad-x 41.ars

I'm not sure why suddenly all these companies are doing reviews on the x41 tablet pc. It's been out for quite some time.

I think I liked Ars Technica's unreview of the X41 that they ran last week better. From the review: "You have to admire the tenacity of the guy who fought to keep the IR port on the X41. Does anybody own devices with IR ports anymore? I dug a four year-old PalmPilot out of the garage and tried to link up, but I think a dust mite fell between the respective IR ports, either that or the Earth was rotating and the movement caused interference." Comedy (precious metal)!

The HP Dynamo project is probably what you are refering to. It was done on PA-RISC, not MIPS. The performance increases of running native code (ie C/C++) inside a VM was in the order of 20-30%. A quick google brought up the Ars Technica article on it, but there's plenty more.

Lenovo Thinkpad x41 Unreview
http://arstechnica.com/reviews/hardware/thinkpad-x 41.ars

-theGreater.

Lenovo Thinkpad x41 Unreview
http://arstechnica.com/reviews/hardware/thinkpad-x 41.ars

-theGreater.