Slashdot Mirror

$7995 single / $14995 dual
Check the prices yourself:
http://www.hp.com/workstations/products/itanium/ i2 000/summary.html
link

If you want to know more technical details about Linux on the Itanium Architecture, David and Stephane just released a book "IA-64 Linux Kernel: Design and Implementation". David was signing copies at HP's booth at LinuxWorld NY.

Compaq makes them, HP makes them, as do a number of companies that are traditionally associated with the manufacture of SBCs and PC-104 type equipment.

If memory serves, my former employer found that the Toshiba laptop drives worked the best, except for some spindown problems that should be resolved by now.

The average disk can sustain between 100-200 IOPs, while the average memory module can sustain about 10,000,000 IOPs (100ns latency). At $120/disk, this works out to $1.66/IOPs, and at $250/GB for memory, this works out to $0.00025/IOPs.

Google currently claims to index about 2G pages. If one assumes on average each page is 4KB, and that the inverted index takes half the space of the original text, then this means 4TB of index. 4TB of RAM at $250/GB is 4K memory modules for $1M. Assuming their motherboards can hold 2GB each, this means 2K machines at perhaps $120 each for another $250K. Now, those 4K memory modules on 2K motherboards can sustain something like 40G IOPs. $1M of disk is roughly 8K disks for 1.6M IOPs. In a real system, load is never evenly distributed so you are almost never able to approach the theoretical limit.

For more details on the (original) Google implementation, please see The anatomy of a large-scale hypertextual web search engine , by Sergey Brin and Larry Page.

From dim memory, to do a search, you need to:

• look up the word (or words) in a dictionary
  
• from the dictionary you get a pointer to the list of all word appearances. (Actually, Google keeps more than one list, and it only traverses as much of the list as it needs to.)
  
• lookup the document's page rank
  
• rank the hits
  
• lookup the document and generate the hit
  

Actually...this has nothing to do with the fact that people don't use Linux. I personally haven't had to recompile my kernel yet, and don't plan to in the near future. I don't consider myself stupid. If I ever need to do it, I'll be able to easily find the instructions online.

The reason why 95% of the world uses MS Windows is a) the fact that people have a great inertia in changing their habits, b) the fact that Microsoft has a quasi-monopoly on Office software (and they won't publish it for Linux) and c) their awesome marketing machine.

The truth is that, once properly setup (which nowadays is as simple as booting with the install disk and sitting back), a Linux computer is as easy to use as a Windows box. In some cases, easier. Don't overestimate's Windows simplicity: as a resident "computer specialist" for my friends and family, I have to say that Windows can be quite obfuscating to the average user sometimes. And let's not talk about the dreaded Registry - how user friendly is that?!

Linux is making inroads in business and high-end computing (read about the recent HP/Dreamworks announcement), it's only a matter of time before it begins to infiltrate the home desktop as well.

I sure am hoping that this is not the way their Linux commitment will be implemented...

It is possible they could employ the pricing scheme they currently use for the high end 'Superdome' servers.
- pay per forecast: pay for capacity based on planned usage
- capacity on demand: purchase excess capacity when activated
- pay per use: pay for additional capacity based on metered usage

In HP-UX, these are tools (PRM, Workload Manager) that allow process tracking and balancing.

It is possible they could employ the pricing scheme they currently use for the high end 'Superdome' servers.
- pay per forecast: pay for capacity based on planned usage
- capacity on demand: purchase excess capacity when activated
- pay per use: pay for additional capacity based on metered usage

In HP-UX, these are tools (PRM, Workload Manager) that allow process tracking and balancing.

It is possible they could employ the pricing scheme they currently use for the high end 'Superdome' servers.
- pay per forecast: pay for capacity based on planned usage
- capacity on demand: purchase excess capacity when activated
- pay per use: pay for additional capacity based on metered usage

In HP-UX, these are tools (PRM, Workload Manager) that allow process tracking and balancing.

Heard a rumor that they may be considering support for IDE in something like this.

http://www.cooltown.hp.com/

Here is the open source codebase for some of it.
http://www.cooltown.hp.com/dev/

http://www.cooltown.hp.com/

Here is the open source codebase for some of it.
http://www.cooltown.hp.com/dev/

Fast forward to 2002. The company has scaled back their operations considerably. New market research data shows that there is almost nobody who would want to pay to live in a fully automated apartment. Hopeless companies no longer have stock valuations based more in ignorance than in profit potential. The Era of High Tech Toys has passed us by. I'm not sure what HP, "home of the earnings warning," is thinking, but something tells me that their cool new automated homes are not going to pave the way back to profitability.

~wally

Itanium is hardly vaporware:
IBM
SGI
HP
eBay

In a few years Itanium will be crushing PowerPC. Why am I so confident? Where do you think former DEC Alpha and PA-RISC engineers are working? Hint.

Look here, bottom of the page.

Hewlett-Packard Company and UCLA today announced they have received a U.S. patent for technology that could make it possible to build very complex logic chips -- simply and inexpensively -- at the molecular scale...
[In an earlier related experiment] researchers from the collaboration crossed wires the size of those used in today's computer chips and sandwiched them around a one-molecule thick layer of electrically switchable molecules called rotaxanes. Simple logic gates were then created electronically by downloading signals to molecules trapped between the crosswires...
Once a basic grid has been assembled, programming could be used to implement a very complex logic design by electronically setting the appropriate configuration switches in the molecular-scale structure...
The problem is that on a single large grid all the electrical signals would interfere with each other... The solution proposed by the patented invention is to cut the wires into smaller lengths by turning some "intersections" into insulators... The insulators are created by "cutter wires," which are chemically distinct from the others. A voltage difference between the cutter wire and the target wire creates the insulator.

Size does matter, yes, but the researchers involved covered the fault tolerance issue first before going ultra-small. See the Teramac project for details.

In a nutshell, the guys at HP labs have worked with a system made up of 864 faulty chips and found ways to detect and route around defects, even while the system operates and performs actual work. They anticipated back then that techniques such as theirs would be crucial for the operation of molecular computers.

The new work with actual molecular computers, especially in their first generation, drives home the point, because no two chips can be made identical. That's in the nature of the manufactoring process. Just Brownian motion will make precise and repeatable placement of gates and wires very hard, not to mention difficulties with steering the actual chemistry of the manufactoring process. What's needed is a change in how we think about chips. They now resemble biological systems, where everything is imperfect, but manages to function most of the time.

This project seems to be a follow on to the original Teramac project, in which they linked 864 faulty processors together to form a functional and powerful computer. See here.

The real breakthrough then was coping with the defects of the processors and making the whole thing function reliably. It can even detect new faults and route around them (literally). The authors of the paper, chief among them Phil Kuekes, stated back then that this was fundamental technology for eventual molecular computers, which by their very nature would be made of faulty parts.

Now the molecular chips are 'real', and as anticipated, no two of these nanochips are the same. We'll have to rethink our assumptions about machines, QA and such, and take a clue from biology where everything is less than perfect, but can funtion perfectly nonetheless.

This project seems to be a follow on to the original Teramac project, in which they linked 864 faulty processors together to form a functional and powerful computer. See here.

The real breakthrough then was coping with the defects of the processors and making the whole thing function reliably. It can even detect new faults and route around them (literally). The authors of the paper, chief among them Phil Kuekes, stated back then that this was fundamental technology for eventual molecular computers, which by their very nature would be made of faulty parts.

Now the molecular chips are 'real', and as anticipated, no two of these nanochips are the same. We'll have to rethink our assumptions about machines, QA and such, and take a clue from biology where everything is less than perfect, but can funtion perfectly nonetheless.

What's the alternative? Pay them $20 and hour and let them come and go as they please, or stop the line whenever they want to chat about their weekend? How willing are you to pay $500 for a printer that currently costs $125?

I knew it was only a matter of time until this albatross argument arrived. You are flatly out to lunch.

According to this articleMrs.Fiorina made $69.4 Million Dollars last year, further, according to this blurb at hp.com in 2000 hp had 88,000 employees.

So, 6,9400,000 / 88,000 == $788.63. Our kind friends in the article, working for HP's bottom line, "pull in around $1000" per month.

For all the "wealth" created by HP, a single person, the CEO earns 75% of a month salary for EVERY EMPLOYEE* .

What is it that Carly Fiorina does that affords her such phenomenal wealth and security? Why is she afforded the kind of kingly existence of comfort and un-imaginable security while those who MAKE THE WEALTH are forced to earn a pittance with zero security. Remember, it is not only the low wages that people have to contend with but the risk of being instantly unemployed without provocation.

I cannot fully explain the rage I feel at this situation, it exists all around us (and the world) -- this is the reality of Capitalism -- left unchanged it is guaranteed to get worse.

The world is in an uncomfortable place at the moment, out of control and heading in the absolutely wrong direction.. and most people of conscience recognize change is necessary. Sweeping, fundamental changes to the economic systems we employ.

Without a democratic solution to economic problems, (economically) powerless people will eventually revolt. It is not a debate of *if* but when, history has proven this -- and we are destined to allow it to repeat. Sad, very very sad.

Interesting Reading: The history of all hitherto existing society is the history of class struggles.

So, explain now, what does paying equitable salary have to do with the choice you mentioned? It is simply a non-issue.

*i recognize that temps are not included in the 88k number, and therefore would be a smaller portion of Mrs.Fiorina's salary... but it really has no bearing on the concept.

Also, im not surprised at the complete lack of understanding of the reality of this situation displayed in this forum. People have been so overwhelmed by the rhetoric and dogma of Capitalism, Freedom and America that they are absolutely blind to the massive problems with the present system -- and our ability to build a better alternative for everyone.

This has been floating around on other tech lists for a while. There is a descent article on HP's site about the technology and their envisioned application here.

This has been floating around on other tech lists for a while. There is a descent article on HP's site about the technology and their envisioned application here.

This has been floating around on other tech lists for a while. There is a descent article on HP's site about the technology and their envisioned application here.

The Jornada 52x and the 54x use the Hitachi SH3 processor (as stated here) and not the StrongARM processor which is the one that you linked you. The link to the NetBSD/hpcsh port is http://www.netbsd.org/Ports/hpcsh/. I'm not sure if that port supports the 52x nor the 54x or not... if it does, then I might have a use for my unused 545 ;-)

actually, HP has been doing this for awhile with their eVectra line of PC's (now known as e-pc's)

Granted, they aren't the cheapest or most expandable, nor do they conform to a "standard" of any sort, but for outta the box smallness, these are pretty good if you don't need to crank out Q3 or RtCW on it...

actually, HP has been doing this for awhile with their eVectra line of PC's (now known as e-pc's)

Granted, they aren't the cheapest or most expandable, nor do they conform to a "standard" of any sort, but for outta the box smallness, these are pretty good if you don't need to crank out Q3 or RtCW on it...

Your sitting around all day doesn't qualify you for anything. And your post here shows that you don't know what you speak of. .NET Server (and that is what the family is called; there are four different versions in the family) is not the same thing as Windows XP 64-bit Edition. Windows XP 64-bit Edition has already been released--it is not in beta, and you can buy workstations that are bundled with it.

The Register is incorrect. HP-UX 11i was developed to run on Itanium so that they can install Unix or NT on the same hardware. Future versions will also be developed.

Read this article for specifics.

• Complexity and Flexibility: The more complex a product is, the more flexible it can be. SubDomain is less complex to manage than SELinux, but offers more flexibility than HP-LX.
• Price: SELinux is free, Immunix Systems are $90 each, and HP-LX is $3000 each.

• StackGuard: resists most buffer overflow attacks.
• FormatGuard: resists most printf format bug attacks.

Bruce

Yes and no. They have to release the source to the people to whom the product is distributed. However, they don't have to make it publically available. The catch is that the people who receive the source can also redistribute it at will. As someone else pointed out, the source is available here.

I expect, however, that HP has some proprietary stuff that's included in non-GPLd binaries.

...here.

b&

Your desktop PC in 2004: Two years from now, your desktop system will be slimmer and trimmer. Flat-panel screens will replace bulky CRTs, and rewritable-DVD drives and fast graphics subsystems will turn your PC into a movie lover's dream.

And DVD and CD so fscked up with copy protection that you can't use any of it on your PC

CPU and RAM: 4- to 5-GHz microprocessor with 512MB of DDR memory and a 600-MHz system bus

Try more memory, 512 isn't that uncommon in off the shelf computers today. And as for CPU, how about mentioning 64 bits, like the Hammer, instead of yammering on about that ancient Pentium 4

Hard disk: From 300GB to 400GB on a Serial ATA bus

And no backup technology even close, so you'll have to have RAID standard or risk losing all those pr0n videos. Rather have SCSI, too.

Removable storage: Rewritable DVD and -- yes -- the unsinkable 1.44MB floppy

DVD+RW or something else, perferably without some built in copy protection lock, like HP's unit has.

Internet connection: Cable or DSL broadband if you're lucky; 56-kbps modem if not

If there's ANY left and IF they provide in a reasonably open service format and IF it doesn't cost $100/mo so they're profitable.

Video: 3D graphics card with 128MB of video RAM

And still able to play NetHack? :)

Display: 18- to 21-inch flat-panel LCD screen capable of 1600 by 1200 resolution

And weighs less than 20 lbs and lasts longer than 30 minutes on battery? I'd be happy with inexpensive 17", thanks.

Ports: USB 2.0 and IEEE 1394

Input devices: Wireless (Bluetooth) mouse and keyboard

What? Now Eye-mouse or Gyromouse?

Operating system: Some version of Windows (you expected Linux, perhaps?)

Some version of Linux (you expected Windows, perhaps?)

Other: An 802.11b wireless network designed for users with more than one PC

Or a more up to date version of 802.11, but why not network it to more than just PC's, or did the future vision 15 watt bulb start to grow dim?

Price: $1,500 to $2,000

Well, ok, but only because the $900 model has that crappy P4 in it.

From the release summary:

"We are not planning any product updates to Ximian GNOME 1.2. During 2002, we plan to release Ximian GNOME 1.4 for HP-UX, with limited support available from HP."

Here's an embedded link for those who don't care to futz with cut-n-paste.

Honnestly it would be a really good thing for Linux.

If it was that way, I think that Dell, Compaq, HP, and others would sell more Linux-powered PCs (cheaper price), so people would buy more, and probably learn to like Linux as a "really good OS which will help working, playing, learning" --- better than the usual "black screen with command prompt designed by geeks for geeks" :).

WTF are they waiting for ? :)

So I went though all the domains, and noticed that only z.com seems to be a functioning website (redirects to Nissan's website.)

Since you also mentioned two-letter domain names in your post as being verboten, what about Hewlett-Packard or Texas Instruments? (You need the "www." in front of them, though, to access their websites. General Motors, OTOH, works without the "www.")

There is more information from the (non-slashdotted) Intel site. The thing at the side of the monitor is indeed a CD player (CD writer, even).

For comparison, look at the Concept PC 2000 (also known as "deep forest") from HP and Intel sites. Both designs feature a small case. The most advanced feature of the 2000 design is that the side of the case has a translucent panel so that you can use the PC as a picture frame (for those who don't have enough room for their pr0n). But the lack of PCI slots seems like a pretty big limitation (if USB were faster and had more peripherals, maybe that wouldn't be such a big deal and I suppose for many uses it still isn't a big deal, but I'm not sure I'm quite willing to consign PCI to the "legacy" category yet).

HP doesn't really even deserve their name anymore. Hewlett and Packard are both dead. All the cool scientific goodies have been spun off into Agilent. HP just killed off ACO after insulting their loyal user community with the 49G. And Carly Fiorina (can you look at her picture and honestly say that she doesn't look like a vulture?) is gleefully turning the remnants of HP into yet another Microsoft whore.

Their printers are the only tolerable product they're still producing, and I hear Epson is rapidly catching up. I have had the worst luck with HP's computer systems, both with the Kayak (their "high-end workstation" that I used at a previous job) and with various Pavilions that I have tried to fix/upgrade for people (oh, and their tech support is useless; try calling and asking what Ethernet card they have inside: "oh, that would be a `10/100' card, sir").

HP has a training program wherein you can get significant discounts on their products if you take online classes. I guess the idea is that retailers will be more eager to sell HP if they have 1) gotten free stuff from HP, and 2) know lots about HP products. Well, the HP PhotoSmart 612 which I got at a nice discount is of horrible quality. The camera design itself is actually pretty decent, but I had to go through 5 cameras before I found 1 without significant CCD defects. What I can tell you from my extensive HP training is this: Don't buy HP, kids. They suck.

(As an electronic music lover)
I'd have to say the DJ is over-rated as hell.
You can scream all you want about the subtleties of reacting to a crowd, but frankly, thats not music-making. Its still playing other peoples songs and taking credit for them. But I digress.

This link provides background including the paper published concerning the first version of the software (no heartrate - beatmatching, just electronic deejaying)

Here is the official announcement from HP.

• By default, tinydns does not hand out referrals to questions it is asked about zones it does not control. I believe that this violates the spirt of the RFCs, if not the letter.
• By default, tinydns does not support the use of TCP at all. This most definitely violates the spirt of the RFCs, as well as the letter (if a DNS query via UDP results in truncation, you're supposed to re-do the query using TCP instead).
  Indeed, if you want to support TCP under tinydns, you have to configure an optional program called "axfrdns", which was intended to handle zone transfers, but also happens to share the same database as tinydns, and can handle generic TCP queries.
• The suggested method for copying contents of DNS zones is rsync, scp, or other remote copy tools. The DNS standard method of zone transfers (query type "axfr") is only supported as an additional, disrecommended method.
  The problem is that if you make a mistake and munge the database and then rsync or rcp that to the backup servers, you're totally hosed. Contrariwise, if you use the standard zone transfer mechanism, then the zone transfer should fail if the master is munged, and the slaves should keep a good working copy for a while and give you time to notice that the master is munged and needs to be fixed.
• Without a patch from a third party, tinydns does not listen to more than one IP address. If you have a multi-homed server, you have to apply a patch from someone other than they author, before you can get it to listen on more than one address/interface.
• Without a patch from a third party, tinydns does not support the standard "NOTIFY" protocol of informing secondary nameservers that the zone has been updated, and that they need to check the SOA serial number and download a new copy (if they don't already have it).
• Without a third party patch, tinydns does not support standard SRV records (which are intended to ultimately replace MX records, as well as perform similar functions for services other than mail).
• Like tinydns, dnscache will not bind to more than one IP address without a third party patch.
• Because they are separate programs, you can't have both tinydns and dnscache listening to the same IP address(es) on the same server.
  While this is not the recommended mode of configuration, some sites don't have the luxury of having separate authoritative-only and caching/recursive-only server(s), and need to mix them both on one machine (or set of machines). With the BIND 9 "view" mechanism, this is relatively easy to do. With djbdns, this is impossible.
• There aren't even any patches that can get djbdns to implement TSIG, Dynamic DNS, or DNSSEC, nor are they ever likely to be created (my understanding is that the author is strongly opposed to them).
  Unfortunately, as time goes on and more and more people are doing things like IPv6, VPNs based on IPSec, or people just care about being able to cryptographically prove that their servers are handing out the only correct information and that the clients are able to cryptographically verify this fact (think: electronic banking), these kinds of features are going to become ever more commonplace.
  Note that, with the advent of BIND 9, you can create a caching-only server that will validate cryptographically signed records, and all clients can benefit even if they do not themselves implement any of the new DNSSEC features.
• There are a number of things that djbdns does which I believe to be outright bugs. However, the author of this package simply refuses to accept that his code could be anything less than 100% perfect, and while he claims to have a "bounty" that he will pay for any bug that is found, in reality he is the one that gets to define what he accepts as a "bug", and has repeatedly demonstrated a tendancy to openly refuse to accept some purported bug, but then to quietly fix the code with future releases.
  So, let's look at some of these bugs:
  • When an IQUERY is sent to a djbdns server, it will respond with opcode set to QUERY. (it should simply copy the opcode, not make something up).
  • DNSCACHE (the caching server) does not respond to queries with the RD bit clear in the query. (Instead of simply answering from cache without recursing the dns-tree).
• One argument frequently used to support the use of djbdns over BIND is performance. Upon further investigation, this claim simply does not hold water.
  Benchmarks published by Rick Jones have clearly shown that BIND can scale up to at least 12,000 DNS queries per second, and there is every indication that BIND 9.2 will be able to go considerably higher. The best benchmarks available for tinydns indicate that it can handle at least 500 queries per second, but that is the highest number reported. Other people on the bind-users mailing list have indicated that they have performed their own (as yet unpublished) benchmarks of tinydns, and that it had notable performance problems that BIND did not suffer.
  The best published benchmarks from the author for dnscache report a query handling rate of less than one million records over a 4.5 hour period of time, which works out to an average of less than sixty-two queries per second. Even if you look at numbers of queries per CPU second, the best numbers they can provide are 13.7 million queries over a four week period of time with 128 minutes of CPU time used (an average of slightly less than 1784 queries per CPU second).
  Compare this with the requirement from RFC 2010 "Operational Criteriafor Root Name Servers" (since obsoleted by RFC 2870 "Root Name Server Operational Requirements") is that the machine and software in question be able to handle at least 2000 queries per second, and be scalable to levels higher than that. Indeed, recent reports have indicated that a.root-servers.net (considered by many to be the "primary" root nameserver) is currently handling around 12,000 DNS queries per second at peak.
  Preliminary benchmarks published on the bind-users mailing list have indicated that, on the same hardware, there is little or no performance benefit to using dnscache as opposed to BIND 9.1.2, and when these tests are re-run with BIND 9.2, I'm sure that it will come out even faster.
• Unfortunately, a lot of the reasons the author gives for running djbdns instead of BIND are related to problems in older versions of BIND which have been fixed or are largely non-issues in later releases of BIND 9.
  For example, he makes a big point of tinydns being better than BIND, because while the process is starting up, it still answers queries. While previous versions of BIND would not answer queries during startup, this is no longer a problem with BIND 9.
  Dan also makes a great deal of the fact that the djbdns tools run as a user other than root, and in chroot() environments. While the "monolithic setuid root" situation was an issue with older versions of BIND, even more recent releases of BIND 8 could be easily run as a non-priviledged user in a chroot() environment, and this is the preferred method of running BIND 9.
  Contrariwise, one of the legitimate big complaints about older versions of BIND is that they implemented zone transfers in a separate program. If the database was large, then the fork()/exec() overhead was large, and the system could seriously thrash itself to death as it copied all those pages (for systems without copy-on-write), only to immediately throw them away again when it fired up the named-xfer program. With BIND 9, this problem is solved by having a separate thread inside the server handling zone transfers, and no fork()/exec() is done. However, tinydns/axfrdns goes back to the fork()/exec() model that was so greatly despised.

Suffice it to say that there is absolutely nothing that djbdns does that I believe can't be done at least as well (or considerably better) with BIND, and there are no security benefits it provides that cannot be provided at least as well (or much better) by a proper installation of a modern version of BIND.

I believe in the "security through diversity" scheme as much as anyone, but I'd take root nameservers running a program written in Bourne shell over djbdns. Hell, I'd rather fall back to using HOSTS.TXT than use djbdns.

Unfortunately, the other alternative of DENTS is also unsuitable for use as a production nameserver.

Show me something that is sufficiently better than BIND (and open source), and I'm sure that everyone will quickly gravitate towards it. Until then, BIND is the best we've got.

SCSI is dead.

For most consumer and single-user environments, IDE is plenty fast enough. Even in the small server market, IDE is adequate.

SCSI won't be around as a serious disk option for much longer, I suspect.

(The storage I use at home is a mix of IDE and SCSI. The x86 boxen got IDE because it was cheap (though the 100GB Western Digital I bought recently is now in a FireWire case so I can schlep it between home and work). The Apples (a IIGS and a Mac Quadra 610) got SCSI because it's what they expect. I'll be building a "new" server soon with a pair of P!!!-500s that was given to me...the motherboard I bought for them has onboard UW SCSI, so I might snag a Barracuda or three from the local used-parts place and see how Linux runs on SMP.)

Not to mention that USB has killed SCSI for things like scanners.

(FWIW, I have lots of stuff that plugs in through serial, parallel, or SCSI. I even have a device now that uses FireWire (a hard drive, and I'd strongly consider a DV camcorder over VHS-C or 8mm, if I needed one). I've never bought anything that used USB, though...already had a nice SCSI scanner, SCSI Zip, various AT/serial/PS/2 keyboards and mice, etc.)

Check out this product from hp.

Amongst its other features, it also provides an auditing subsystem, so you can audit pretty anything going on in the system. You can then use a filter to produce either plain text or xml reports.

It has lots of other nifty features too - compartments, with kernel-level access control that goes beyond chmod.It makes it easy to run Internet services in a chrooted environment, with tightly controlled access limiting damage if one app were to be compromised.

(Yes I do work for HP, but not for the ISSL division. The thoughts above are my own, not HP'S)

- Lindsay

Ah, but They do make a palmtop.

Anyone out there have one of the SlimDevices?
There was a buzz when it was mentioned earlier. But I haven't heard from anyone that bought one since.

I rather like the idea of streaming from a computer over ethernet better than the HP solution of having the HD fixed in the device.

For one thing, I have much more storage on the computer. Most of my interacting with the MP3 files will be done on the computer anyway, and I already have a CD-R on it. I would suspect that I have greater control over playlists and the like from a computer than the HP device.

Then there is the issue of DRM which I have more control over on my computer. As this is a consumer device, I presume they expect that most people will rip their files in the device's CD-RW drive (although it includes a NIC for HomePNA, most consumers are the 12:00-blinking-set and may not even bother with that) at which time the file can be marked.

In fact, the only thing the HP device seems to do that one of the other products won't is act kinda like a WebTV for internet music (although the only connection is through a v.90 modem. *ICK!*).

That said, can I get a bit more input on the RioReceiver, the Auditron, and especially the SlimDevices from people that have them?

is the fact that Amazon credited HP with guiding them through this transition into open source software. Granted HP is on the open source bandwagon but it is great to see them following through on it.

Do you think Amazon is running Debian?

The official HP presentation on the PA-8800 is
available as a PDF from http://www.cpus.hp.com/technical_references/mpf_20 01.pdf.

Y.

HP actually found that some code actually ran faster in their PA-RISC emulator for PA-RISC than on the bare hardware! Perhapse HP was using the equivalent of gcc -O instead of gcc -O2 in their trials, thus giving more room for dynamic optimizations, but they got good results for an early project. Dynamic code optimization still looks promising. HP is working on a product utilizing quick-and-dirty PA-RISC to IA-64 translation and dynamic code optimization to ease the transition from PA-RISC to IA-64.

The HP Dynamo project has some good arguments about why dynamic optimizations might be becomming increasingly usefull. Basically, HP was researching emmulation, so they wrote a PA-RISC emulator to run on PA-RISC and put in some dynamic code optimization to increase performance of commonly run code. There's the old rule of thumb that 80% of your CPU time is spent on 20% of the code, so they concentrate expensive optimizations on the commonly run code, after on-the fly profiling indicates which areas should be optimized. It's like having a -O4 option for gcc and only using it on the code that gets run alot, in order to avoid all the bloat associated with gcc -O3.

Personally, I'd love to see AMD or Intell throw away hardware emulation of the ancient x86 instruction set. The greatly restricted number of registers causes the compilers to really hide the inherent parallelism in the source code. A lot of chip realestate is wasted in extracting the parallelism back out of the binaries. It's not as bad as the stack-based JVM, but the x86 instruction set is pretty bad about expressing parallelism in the source code. I think software emulation of legacy apps is where it's at. If Intel or AMD released an x86 emulator for thier new chipsets and got Microsoft to go along with the idea of software emulation of x86, then we'd see native apps running much more efficiently. It's my understanding that IA-64 kind-of does this with an x86 emulation mode. However, I think that chip realestate would be better spent on thins to speed up native code.

If I'm not mistaken, Win95 even had partial virtual DOS machines for each DOS executable. It's not too much more of a leap to emulate the ancient instruction set after you're emulating the ancient OS. Transmetta wants the flexability to completely redesign the native instruction set for each release, and that's understandable. However, it would be nice to move on to compiling into something that better expresses inherent parallelism in the source code.