Slashdot Mirror

I was not aware of either the XPort or Rabbit options - at $40 to $60, those really open up some low-cost applications that are not in the range of $200-500 SBCs such as the Axis boards.

Is there anything similar for wireless 802.11, for less than a hundred bucks and with a power draw of less than 5W ? That is to say, a small board or chip with the functionality of the XPort or Rabbit, but in a wireless version? I know that AMD has the Alchemy boards, but my impression is that these are several hundred dollars. And you could always add a wireless PCI card to a Mini-Itx board, but that is at least $200, with power consumption in the range of 20-30W compared to the Xport, which draws less than 1 W.

If it's the same test they've got here, I can see why people got confused. I mean, they're trying to see if people can grok tech-talk, and they ask questions like:

Question 6: What is an MP3?
1. An audio compression technology that is part of the MPEG-1 and MPEG-2
specifications

2. A kind of magnetic tape originally designed for audio format now also used in computers to back up data

3. A box that allows you to watch television programs without commercials

Yes, one of those answers is technically the correct one, but if you're trying to judge the average person, instead of going into mpeg standards, etc, the correct answer should read "A type of file that contains music or other sound." If they had questions where the answers weren't more confusing than the acronyms, I'm sure they would have had a much higher success rate. In another question, they asked what WAP was. How many people (now that normal people are buying routers to sheir their connections) would know it as "Wireless Access Point" rather than "Wireless Application Protocol"? More? Less? It would have been more accurate to have both answers available, and then an "all of the above," and award half points to anyone who answered a or b.

Considering both the survey group and the results, I think people did quite well here. 75% of the people surveyed got 8 +/- 2 terms correct out of 11, btw, whereas random guessing would yield an average score of less than 4. Only 14% of the people in the survey actually got a 4 or below.

I know because I took the survey yesterday to check it out. Yep. got all 11 right, as I bet most /.'ers would. Although you have to "choose the best answer"; some of the choices are a bit misleading or slightly incomplete in their definitions. However, most of them are completely obvious if you have any idea of what the term actually means.

I think that the problem is an interesting reflection on the state of technology, and "technologists" themselves. For example, the test includes Megahertz, megapixel, download, web browser and Bluetooth--all good examples (IMO) of naming. "Bluetooth" may be debatable, but it's a distinct name for a distinct technology, and people who use technology should be aware of its capabilities. "Web browser" is another good name; unfortunately, Hollywood's and tech-illiterate journalists' insistence on "surfing the 'net" means that a good name is unknown by the public.

On the dark side of the naming spectrum, the tech industry has given us some gems such as SMS, DVR, MP3 and dot pitch (all from the quiz). SMS and DVR are good examples of trying to pick a generic name that didn't step on any copyright holders' toes, but didn't adequately describe the product either. But perhaps the public is too picky. They learned about VHS, so why can't they learn about DVR.

Dot pitch is a terrible misnomer but its roots are firmly entrenched in the display industry. Perhaps a better term would be "pixel density" or "image clarity," but then it's hard to associate a name like that with a value that gets better as it gets lower.

MP3 is understandable: no one is going to get a friendly, trademarkable name from a group of geeks writing cutting-edge software. But the trademark issue itself it one of the culprits. How many nice names could we have for computer components if the most descriptive words weren't already trademarked?

And finally, it's easy to point out to Houston that we have a problem. It's harder to realize what the problem's origins were and to appreciate the evolution of the computer industry in just fifty years. And it's most difficult to propose a workable solution and carry it through.

The survey can be found here

Question 1: Which of the following is a definition of Megahertz?
a. A data transfer technology that uses fiber optic cable to carry information
b. A unit of measurement equal to 1 million electrical cycles per second, commonly used to compare the clock speeds of microprocessors
c. A computer's random access memory equal to 1 million bytes

Question 2: Which of the following is a definition of Short Messaging Service (SMS)?
a. A messaging service that points out when an e-mail message was not delivered
b. The ability to send and receive text messages (words and or numbers) to and from cellular telephones
c. Service where the computer is installed, instead of having to bring the computer into a shop or ship the computer back to the manufacturer for repairs

Question 3: Which of the following is a definition of WAP?
a. A global standard for developing applications over wireless communication networks
b. A company that provides wireless telecommunications services
c. Transmission of voice or other sound by means of electrical signals sent over wires or radio waves

Question 4: Which of the following is a definition of megapixel?
a. A crime committed using a computer or data stored on a computer
b. A presentation graphics program that enables you to produce attractive presentations
c. A term used in reference to the resolution of a graphics device such as a scanner, digital camera or monitor

Question 5: What is a Digital Video Recorder or DVR?
a. The same as a VCR/Video Cassette Recorder
b. A box that records and plays television programs
c. A box that makes DVDs

Question 6: What is an MP3?
a. An audio compression technology that is part of the MPEG-1 and MPEG-2 specifications
b. A kind of magnetic tape originally designed for audio format now also used in computers to back up data
c. A box that allows you to watch television programs without commercials

Question 7: What is a DPI?
a. A measure of the resolution of printers, scanners and monitors
b. A video production made with a desktop computer and home video equipment
c. A file that has been corrupted by a virus, or computer failure

Question 8: What does it mean to download?
a. To connect a computer to the Internet
b. To save a file on your computer from a remote computer
c. To send a computer file to someone else

Question 9: What is Dot Pitch?
a. A special type of television
b. A method for determining how sharp a displayed image can be
c. A company that provides individuals and companies access to the Internet

Question 10: What is a Web browser?
a. A person who likes to look at the Internet
b. A software program that allows you to view sites on the World Wide Web
c. A computer that stores World Wide Web files

Question 11: What is Bluetooth?
a. A product that can save many photographs in a small space
b. A way to connect products to each other without using wires
c. A program that searches the Internet for the lowest price available

Question 12: How much do you agree or disagree with the following statements? (Choices are "Strongly Agree", "Neutral", and "Strongly Disagree")
a. Technology words are made up just to sound interesting
b. Consumer electronics are more complicated than they need to be
c. Most product instruction manuals are not helpful
d. I wish to have things work and not spend time setting them up
e. I will try out a new technology even before I am sure I will really need it

Question 13: Have you used any of these products in the last three months? (Choose Yes or No)
a. Television
b. Digital Camera
c. Microwave Oven
d. Cell Phone
e. Videogame System
f. Internet Service
g. Home Computer
h. Digital Video Recorder (DVR)
i. DVD Player
j. Personal Digital Assistant (PDA)

The PDF of the survey can be found here.

From Page 4
"Because of objectives and
subject, paper surveys sent
by mail were used to avoid
built-in sample bias from
internet-based study"

From Page 6
Age mix
- 35% Age 55+
- 20% Age 45 to 54
- 21% Age 35 to 44
- 24% Age 34 and under

Gender blend
- 38% Male, 62% Female

It looks like the ended up with a bias in the sample anyway. 55% over 55 years old, 62% female... I think it was already understood that technology confuses them.

comparison table the Athlon XP has 3 full FPUs, the P4 has a full and a partial (I believe it only can do memory operations, not arithmatic).

Why no Opteron? They probably didn't have one. This is the most valid question you ask.

How? (you might ask)

If someone from NASA had sent an email to marketing@amd.com; basically asking*:

Howdy!
I work at NASA and do some testing of some new hardware, among it the new G5 Powermac.
Could i borrow a Opteron for some testing?

AMD would have sent it on the day.

*Or a phonecall to any of these numbers.

Disclaimer: I don't work for AMD or any other related companies

yeah - or compare it to this:
Dual Opteron fp benchmarks

x86ers would like it very much if 64bit wasn't relevant for the consumer, because they're not going to get it for a little while yet, but in truth, it really is huge.

Really?

"Yeah, I want some shiny new hardware, but I'd much rather get my 64 bits elsewhere. Yeah, the desktop version isn't available yet, but I'd take a workstation over a desktop any day of the week."

Oh? Personally, I'd much prefer an IBM-made 64-bit CPU to something out of AMD.

I know which of those two companies have more experience in designing and fabricating 64-bit chips, and it's sure as hell not AMD...

if nothing else, it's going to be 64 bit. OF COURSE you're going to have to pay for it.

Considering that other OS platforms, such as Linux and FreeBSD have been 64 bit clean for several years, why should the bump up to 64 bits be different for Apple? As it's been known for some time that the future of desktop/workstation computing is in 64 bit procs, I think programming in portability should be something that Apple should have been doing for years, so that introducing a 64 bit proc just means compiling resource-intensive portions of the operating environment, such as the kernel and the GUI.

unless of course you want to buy some shiny new hardware. (you know you want to)

Granted. However the point I was trying to make stands. The minor differences between the Opteron and the OpteronSX(AMD64) will be primarily cosmetic and not architectural.
See FAQ from AMD

Q: What are the differences between the AMD Athlon 64 and AMD Opteron processors?

A: The upcoming AMD Opteron and AMD Athlon 64 processors are designed for different markets. For the server/workstation market, the AMD Opteron processor will undergo more stringent validation and reliability testing. Another difference will be in the number of HyperTransport links embedded on the chip. The AMD Athlon 64 processor will contain one HyperTransport link offering 6.4 GB/s data transfer while the AMD Opteron processor will offer three links. The processors will also contain different amounts of cache.

Unfortunately, Taco et al have drank the Jobs Kool-Aide and have become little more than a drooling fanboy WRT Apple's hardware. Thus, they ignore apple's many shortcomings, including price, compatibility, their obnoxious hardware design, etc. As Apple is the last computer maker to head into the modern era with a 64 bit processor -- something other makers have had for months, if not years -- they're trying to generate hype for themselves and other fanboys so they can keep saying to themselves that the money they spent on the crapware from cupertino was somehow worth it.

It's very difficult to make money on software in the Beowulf arena because, duh, it's FREE! You have to make your money on hardware and integration of the hardware and software. Seems that there'll be lots of overhead with all of the developers now on hand at Penguin. Maybe this is why the CEO of Penguin, Marty Sayer, left 2 years ago and is now a VP at AMD.

In addition, for the most part Clustermatic does the same thing and is setup the exact same as a Scyld distribution, granted Scyld does add some neat things of their own. Although Scyld actually has turned a profit here of late, don't get me wrong, I like Becker but I really don't see this one working out in the long run.

Huh? Out of date? In what way? I think you might have been tricked into following the Megahertz Myth. Or maybe you just didn't notice USB, firewire, etc on every mac long before PCs. Most popular technologies were popular on macs before PCs and this doesn't look like it will change any time soon..

Also, if Apple did release OS X for PC I doubt they'd put in any "draconian anti-piracy copy protection crap", these are the people who brought us the "Rip, Burn, Enjoy" ads.

Intel P4 3.0 costs $417 US. AMD 3200+ costs $464 US.

Everything that is present in each of the L1 caches is also present in the L2 cache.

Not on the AMD, which has an exclusive cache.

So it's the MS-DOS and application executing completely on chip. Someone post benchmarks please. ;-)

AMD Athlon Processor Model 6 Revision Guide
AMD Athlon Processor Model 8 Revision Guide

Itanium based computers can cost about $20000 [...]

AMD Athlon Processor Model 6 Revision Guide
AMD Athlon Processor Model 8 Revision Guide

Itanium based computers can cost about $20000 [...]

...that's why Itanium is not yet in the mass-market. Regardless of the flaws. It's also why my first 64-bit CPU is likely to be an AMD.

I mean, come on. I want 64-bit a lot. An awful lot. I even wanted a redesigned instruction set - something I was please to see Intel had the balls to do with Itanium. The old IA-32 has a lot of baggage and bad design choices. But for crying out loud - $7000 for a single chip?

I kid you not about the $7000 price tag for a single CPU - Itanium 2 is literally 10 times more expensive than AMD's 64-bit Opteron.

This is why, as a life-long fan of Intel, am planning on defecting to AMD with my next machine purchase. To anyone else buying a new machine in the next 6 months: it makes absolutely no sense to get a 32-bit system when vastly more capable and future-proof 64-bit ones can be had for almost the same price as the old 32-bit ones.

This time next year, I reckon that Intel will be steadily loosing market share to new system purchases because of their exhorbitant prices and their complete failure to provide a capable 64-bit platform in the same price range as AMD. Intel haven't even announced a consumer 64-bit chip. AMD's announced six - 2 Opterons, 4 Athlon 64's).

I'm desperately hoping that AMD and Microsoft's marketing machines ramp up to push 64-bit - the sooner the better to punish Intel for not being more pro-active in the marketplace.

If you follow the article's link to AMD's website from the article, you see that the CPU supports Linux; so it shouldn't take long.

Questions that I have. On AMD's page, they say that power usage is given in mW for the chip at 333, 400, and 500 MHz are 400, 700, and 1.2. Do they mean 1.2 watts (and hence 1200 mW) or does it actually use 1.2 mW? (I know that it's 1.2 W, but I wish it was 1.2 mW!) More seriously though, why aren't we seeing these chips in more things, like say mini-ITX boards? Of course, I'm not a chip and board designer; so this could be senseless dribble.

...all still bitter that the 64-bit processor is still close to vapor.

Allow me to speculate.

Barton (Model 10) comes in three flavors: 3000+ (2.167 GHz), 2800+ (2.083 GHz) and 2500+ (1.83 GHz). All other things equal, the 3200+ should run at 2.25 GHz, same as the 2800+ Thoroughbred (Model 8).

However, if AMD were to increase the FSB speed, you can expect the CPU frequency to be slightly lower. I would guess between 2.083 and 2.167 Ghz.

AMD keeps a definitive list up to date.

The heat sink makes contact with the top surface of the processor package utilizing the thermal interface material between the processor lid and the heat sink. AMD recommends using a high-performance grease such as those listed in Table 6. AMD does not recommend using phase-change materials between the heat sink and the processor. Phase-change materials develop high adhesion forces between the heat sink and processor when the material is in the solid phase. This strong adhesive force may cause the processor to stick to the heat sink. During heat sink removal, this strong adhesive force may cause the processor to be removed from the socket while it is locked, and this action can result in damage to the socket or to the processor pins.

What does the German economy have to do with anything? Just because AMD has a fab there doesn't mean that they are based there. Seems like the German economy being down would let them hire workers cheaper for the Fab 30 in Dresden.

What does the German economy have to do with anything? Just because AMD has a fab there doesn't mean that they are based there. Seems like the German economy being down would let them hire workers cheaper for the Fab 30 in Dresden.

"Sucks to be you if you buy a defective AMD CPU and put a Zalman on it for the first boot"

AMD Athlon XP(TM) Processor Thermal Solutions

When selecting a thermal solution for your system, please refer to the following listing of heatsinks evaluated and recommended by AMD for use with AMD Athlon XP(TM) processors. Note, the following heatsinks are recommended for maintaining the specified Maximum die temperature requirement. In addition, this selection is not intended to be a comprehensive listing of all heatsinks that support AMD processors.

From the article:
"using a heatsink other than the stock heatsink on a retail chip also voids the warranty."

So if you pay the $10-15 extra for the retail instead of OEM, they expect you to use the hs/fan that comes with it.

The announced Opteron parts do not have dual DDR memory channels

I don't know where this crap is coming from. Certainly not from the document referenced in the parent post.

A DIMM is 64-bits wide. The Opteron has a 128-bit wide memory bus, which means you need to use pairs of DIMMS much like the older P4's with Rambus memory.

There are plenty of pins for this in the 940 package. The block diagram on page 11 of the the data sheet even shows the 128 MEMDATA pins.

The memory controller is configurable to support a 64-bit memory bus (probably for desktop or mobile versions of the part), but in all the systems I've used you can't even boot with an odd number of DIMMS.

Now you can decide for yourself if a 128-bit wide DDR bus is "dual channel" or not. I'm not going to argue semantics. I am, however, going to do the math and tell you that the Opteron paired with DDR333 provides 128*333/8 = 5328 MB/s of some seriously low-latency bandwidth. Oh yea and it scales with the number of processors too.

DISCLAIMER: I work at AMD but I am not speaking on behalf of the company.

The announced Opteron parts do not have dual DDR memory channels

I don't know where this crap is coming from. Certainly not from the document referenced in the parent post.

A DIMM is 64-bits wide. The Opteron has a 128-bit wide memory bus, which means you need to use pairs of DIMMS much like the older P4's with Rambus memory.

There are plenty of pins for this in the 940 package. The block diagram on page 11 of the the data sheet even shows the 128 MEMDATA pins.

The memory controller is configurable to support a 64-bit memory bus (probably for desktop or mobile versions of the part), but in all the systems I've used you can't even boot with an odd number of DIMMS.

Now you can decide for yourself if a 128-bit wide DDR bus is "dual channel" or not. I'm not going to argue semantics. I am, however, going to do the math and tell you that the Opteron paired with DDR333 provides 128*333/8 = 5328 MB/s of some seriously low-latency bandwidth. Oh yea and it scales with the number of processors too.

DISCLAIMER: I work at AMD but I am not speaking on behalf of the company.

Untrue. Linux can do 32 GB; at work I test and benchmark this stuff (for example see here and here). Linux can also probably do 64 GB, though we haven't tested this because we don't have enough memory slots on our development platforms.

Untrue. Linux can do 32 GB; at work I test and benchmark this stuff (for example see here and here). Linux can also probably do 64 GB, though we haven't tested this because we don't have enough memory slots on our development platforms.

Untrue. Linux can do 32 GB; at work I test and benchmark this stuff (for example see here and here). Linux can also probably do 64 GB, though we haven't tested this because we don't have enough memory slots on our development platforms.

The dual Xeon has 512 MB RAM.
The dual Opteron has 2 GB RAM.

Maybe I'm just blind, but I can't seem to find these figures. According to the Config page for the 2x Xeon, it shows 8x512MB, same amount as the 2x Opteron.

Granted the 4xXeon also has the same amount of memory, whereas the 4xOpteron has 16x512MB, but that's cos the poor little(!) 32-bit Xeon can't address past 4GB of RAM anyway...

If i'm smoking crack, and you guys are looking at some different numbers, please let me know.

The dual Xeon has 512 MB RAM.
The dual Opteron has 2 GB RAM.

Maybe I'm just blind, but I can't seem to find these figures. According to the Config page for the 2x Xeon, it shows 8x512MB, same amount as the 2x Opteron.

Granted the 4xXeon also has the same amount of memory, whereas the 4xOpteron has 16x512MB, but that's cos the poor little(!) 32-bit Xeon can't address past 4GB of RAM anyway...

If i'm smoking crack, and you guys are looking at some different numbers, please let me know.

The Opteron will be available in a desktop version. The Xeon is not, and will not be.

How so? The Opteron is to the Athlon64 ("the desktop version") as the current-generation Xeon is to the Pentium 4. In fact, the Pentium 4 is much closer to the Xeon than the Athlon64 is to the Opteron.

Tom didn't enable the second memory channel

The Athlon64 will not have a second memory channel regardless...

or use DDR400

Can't blame him for that. AMD does not officially support DDR400.

From the first page of AMD's technical datasheet released today:

Target CPU core power: 80.6W
Target maximum thermal power: 84.7W

I wish it was only 40 watts! Where did you find this number - was it an actual measurement? If so, was it at 100% cpu load, idle, or midway?

I thought this was a little low (esp. compared to my athlons), and didn't actually look it up until I ran across this EETimes article that claims 89 Watts for the AMD64 240.

the 800mhz bus Opteron

The Opteron has an integrated memory controller. Therefore, its "Front Side Bus" runs at the same speed as the actual processor.

Proof: With the memory controller integrated onto the AMD Opteron processor, the front side bus (interface to memory) runs at the speed of the processor

Apparently the IBM xSeries 360 runs at 2.0 Hertz.

[...] the Opteron supports DDR400, but Tom used DDR333 [...]

The Xeon's have a 533 MHz FSB, while Opteron is running at 333 MHz FSB (Technically the P4/Xeon is 133 MHz quad pumped and the Opteron is 166 MHz double pumped).

The memory controller on the chip means that Opteron will have a much lower latency... it doesn't give it any bandwidth bonuses. AMD's own faq says that there's not really any such thing as an FSB with the Opteron, but that's mostly indirection. The reality is that it's still 166 Mhz... the FAQ could be (deeply) misread that the memory controller operates at 1.6 GHz (or whatever the speed of that particular Opteron is), which would be wrong.

Check the Spec benchmarks here.

SpecFP_rate, 2CPUs:
Itanium2 1GHz: 30.7
Opteron 1.8GHz: 26.7

SpecFP_rate, 4CPUs:
Itanium2 1GHz: 49.3
Opteron 1.8GHz: 49.2

Here we see the beauty of AMDs integrated memory contoller. Despite that 1GHz Itanium2 is a $4000 chip and has 3MB of cache, doubling the number of CPUs increase performance only by 60% because Itanium2 uses shared bus.

Opteron gets impressive 84% improvement because
memory bandwidth increases as more CPUs are added.

In SpecInt Opteron is much more faster than more expensive Itanium2.

You mean this one coming out next week?

You could try this page, and if they move it the steps are:

- amd.com
- Technical Resources link at top
- Technical Documentation at top left
- AMD Athlon(tm) XP Tech Docs

System makers can brand executables, but it is more common for them to use oeminfo.ini. If the General tab under system properties doesn't have a "Computer:" heading and does have a "Manufactured and Supported by:" heading, manufacturers logo or Support Information button, then your system has been branded by the OEM. If you have an oem system then it is about 99% certain that when it was branded, the cpu model ( 1700+ ) was created during.

So, which company made your computer system? I don't have to ask if you built it yourself. We wouldn't be having this discussion if you had.

Some well respected software that won't/can't tell you your sold-as-speed, Sandra 2003, wcpuid, CPU-Z and the Linux kernel.

I have built thousands of systems from scratch and generally know what I am speaking about, but have been wrong before and will be wrong again. I have kept a civil tongue while you made snide remarks like "What's your next brilliant theory?". I have provided detailed information, you quoted WinXP as an unquestionable resource. Check the Forums at overclockers.com, one of the many places on the web to get good info and meet strange new people. BTW, with watercooling, my AthlonXP 1700+ DLT3C (1.5v) chip will run 2.55GHz and pass the prime95 torture test.

Have a great Palm Sunday.

Check out the FAQ here. Basically it's a little PC with nothing but USB ports, built-on VGA and LAN, and a power button, released in the K6-400 heyday. This was a response to the first iMacs. I bought one for $50 a couple of months ago, thinking I might make a nice little linux router and file server out of it.

That's when I found out that "legacy free" meant "software emulation requiring WinDrivers." I still haven't managed to get the goddamned thing to recognize the built-in LAN unless I put Windows on it and hunt down the drivers for a product that AMD would rather not admit it ever put out.

Screw legacy-free. I only realized after purchasing it that even if I'd managed to get this little bitch to work, I'd still have to sacrifice running my printer server off of it because it has no parallel port. If legacy-free means "replace all your hardware and peripherals" then I don't want any part of it, thanks.
GMFTatsujin

AMD has a nice flash presentation on how conventional, MLC, and Mirrorbit flash works. It's actually an presentation for their MirrorBit flash technology, but it has a good description of the basics.

It means the flash memory hardware will eventually die. The usual number heard is one million writes, or more.

That should last years- and in a few years, CompactFlash cards will be cheap anyway, so who cares? (As long as it's not built into your PDA- but a PDA will be obselete in 4 years as well)

Note that most flash chips contain a little software for "wear leveling" to ensure that those million writes don't happen at all the same place, burning a tiny "hole" in the media while the rest is left unused. Even if you repeatedly load/save the same file, it will try to spread the changes out all over the memory, reducing excessive wear.

In short, ordinary consumers don't need to worry about the fact that flash memory will someday wear out- nobody uses it for persistent storage anyhow, right?

However- people who install custom-built aftermarket software do need to keep this in mind. If you accidently get a file-system driver which disables wear leveling, or you do something like using flash memory as RAM (which a program can edit thousands of times per second), then theoretically, you could be reducing the lifetime of your machine.

lots of others too

Its amazing what you can find when you actually look for it, rather than run at the mouth

Fujitsu

I've been working with the AMD Alchemy family chips. In our particular situation, it ran faster, used less power, and was priced much lower than the XScale chips that we considered.

It is a wonderful little piece of silicon with lots of integrated peripherals, low power, and great performance. It is built around a MIPS architecture processor core.

Linux-MIPS runs great on this chip.

Check them out.