Slashdot Mirror
Cooling Down Hot Processors
DonnaMai writes "Face it: the only scorching hot thing you want with a chip is salsa. Any other overheating is potentially counterproductive, and can be downright damaging to the microprocessor -- or other components. This article uncovers potential ways to chill the chips."
I don't know about you, but I like my salsa cold
Because nothing says "fiesta!" quite like third-degree burns on the roof of your mouth...
Obliteracy: Words with explosions
To maximize my ROI i use my p4 as a hotplate/Pizza Warmer when I'm not surfing the web.
So Long and Thanks for all the Fish.
When I was a kid we had to cool our chips by using our little brothers as a heatsink.
What we really need is a spare, low-power, mimimal processor without all the fancy extensions that you can switch to when you're just, say, reading a webpage or email, or such.. you could integrate this right into the motherboard and completely shut down your processor when you're not using it for real stuff. IMHO... maybe an engineer will give me a reason this is unreasonable.
Why not make something for laptops so i don't get hurt from having my computer on the lap. (there was something about the heat hurting your sperm or something)
Its the chip that is hot here, so your salsa analogy does not work very good.
The easiest way to keep it cool to not run Intel.
We used to build a little dam around the processor with putty, fill up the reservoir with freeze-spray, and drink margaritas while the whole shebang evaporated noisily.
No fancy metal heat sinks for us...andd we liked it!
really...as a consumer..who gives a crap how hot it gets? Is it fast? Does it work? those are the questions I ask. Face it, if it were actually something that normal(read non-/. type) people cared about it, then it would have been solved.
It must have been just last night my GF was saying I really need a water cooler for the pc, it's so hot. Not!
Joshua Fruhlinger (pdwe@jfruh.com) Editor and Writer 02 Feb 2005
Face it: the only scorching hot thing you want with a chip is salsa. Any other overheating is potentially counterproductive, and can be downright damaging to the microprocessor -- or other components. In this Power Architecture challenge, developers warm up to the idea of how to cool down the hotter processors. From the weird to the wonderful, readers uncover potential ways to chill the chips. Somewhere, deep inside your computer is the tiny slab of silicon that makes it go. That slab in turn is built out of millions -- perhaps hundreds of millions -- of transistors. Every time one of those transistors changes state, it leaks a tiny amount of electricity; in turn, that electricity produces heat. And that heat, accumulated over millions of transistors changing state thousands of times per second, may potentially threaten your fertility (see Resources).
Dr. Claes-Goran Ostenson saw this first hand when he concluded that one of his patients had been using a laptop in the way that its name implied, became engrossed in his work, and didn't notice the burning sensation in his lap, and thus became the first victim of what has come to be known as "lapburn." Ostenson felt the incident warranted exposure in the world of medical science, so he wrote a letter to the Lancet in 2002.
It stirred a mild amount of controversy, with commentors coming down on predictable sides. Laptop manufacturers were skeptical, while spokespersons for companies that produce chip-cooling paraphenalia looked serious and nodded sagely, implying that your lap could be next. Worries about "lapburn" spawned a whole industry of fan-based gadgets that plugged into the bottom of laptops, sometimes rendering the laptops' portability features pointless in the process. But the situation did highlight one important fact: Chips are hot.
And that's meant not in a market-ese, "everybody's-gotta-have-one" kind of way, but in a very literal and skin-scorching way.
The winner The First Law of Thermodynamics states essentially that energy -- including heat -- can not be created or destroyed. And if you think the punishment is stiff when you break municipal, state, or federal law, just try monkeying around with thermodynamic law! Also, physicists such as Frenchman Nicolas Leonard Sadi Carnot, as far back as the 19th century, recognized that heat tends to move from hot objects to cooler objects. These two rules circumscribe the work of every engineer and tinkerer who has attempted to cool down microprocessors. Once a chip has generated heat, that heat cannot simply be eliminated or suppressed: It must be inevitably moved from the superheated chip to something cooler. Problems arise when those cooler objects are the sorts of things that react badly to steady influxes of heat, such as other components inside the computer case, or a Swede's lap.
Since not many of you (or, frankly, none of you) wrote about how to actually reduce the amount of heat coming from a chip, this article focuses instead on cooling systems. Faithful reader Daniel Griffin did define the problem succinctly, however, and thus walks off with this month's grand prize of a developerWorks t-shirt. He points out that just "cooling a small area immediately above the processor" is fruitless; it's better "to move the heat away from the die than to deal with it." It's that struggle -- getting the heat away from the delicate, but hot, innards of your PC -- that has defined the cooling battle for the past decade.
Astute readers will also note that Daniel's was the only entry this month. Come on, where's the competition? Your entries are the only thing between my box seats and "balcony rear" at the opera! Won't someone please think of the columnist?
So this time, instead of your entries, this space is devoted to the history of the chip-cooling process. This is my treat to you, but don't forget t
DAMN YOU OCTODOG! DAMN YOU TO HELL!
Best way to cool your processor is to move to Canada. Hands down.
a block of frozen CO2 on top of your pc and your problems will be solved.
Granted, you'll have to have a tank of O2 nearby, wear a mask and have on thick gloves but hey, you can't have everything.
We will bankrupt ourselves in the vain search for absolute security. -- Dwight D. Eisenhower
Ice cubes work well.
They don't last very long, though.
Perhaps we should be working on a better ice cube!
"Rocky Rococo, at your cervix!"
Oh. You mean Crisps? Or Nachos or something? I don't speak American, you insensitive clod!
Oh. You mean integrated circuits? I DO like the idea of the CPU sticking out of the top of the case, like a muscle car's engine!
----
Imagine a beowulf cluster of fans!
Dr. Trevor Mudge (U. Michigan) came to give a lecture at my University last year. He had an interesting proposal which I suspect is probably going to end up being used in nearly every architecture. The energy usage of a procesor is proportion to the square of the voltage - so dropping it as much as possible is desirable. The only problem is that once you get too close, you start getting bit level errors. He proposes to use a shadow register to keep track of values as they pass through and detect bit errors automatically, and route around them. If run at the optimal voltage (1.4 volts) a razored process will see a dramatic drop in energy consumption with a virtually-nonexistant hit to processing power.
To make laws that man cannot, and will not obey, serves to bring all law into contempt.
--E.C. Stanton
As reported on /. a while back. "Record Attempt: The 5 GHz Project"
Tell the truth and you won't have so much to remember.
The funkiest solution I ever heard of was submerging the entire motherboard in Mineral Oil and using some aquarium filters. Have wires running out of the soup to the hard drive, floppy and the rest and you're good to go.
I'm told it was fun to watch as the mineral oil went through the filter and was cooled by the process of falling through the air.
Don't know how long it ran before a technical problem though.
It WAS something a coworker told me a college friend had told him about.
"Live Free or Die." Don't like it? Then keep out of the USA
Why not put it in a dry freezer. That should keep it nice and cool. Ice cream helps to cool off those hot chips.
I don't know what the problem is, I like hot chi... oh wait, you're talking about chips, nevermind...
hack a day
You need a marketing person to tell you why a slow, cool processor is unreasonable!
Paul "Say no to feeping creaturism"
There are many, many ICs that run happily for years at high operating temperatures (Blaupunkt's Digiceiver digital RF processor being one I'm familiar with).
Saying this, I do run a 12" G4 PowerBook and can appreciate the delights of a 20degC chip...
The Slashdot Paradox: "100% Overrated"
a liquid cooling system that is also a conversation piece http://nobispro.com/aquatank/?
How do I cool processors? Simple: I underclock them. Even a 10-20% less MHzs is usually enough to get rid of a noisy fan, i.e. the most stupid idea in the history of personal computers. Most of today's computers are I/O-bound anyway (Moore's law) so there is no performance loss whatsoever. Seems like an obvious solution.
Sincerely,
Pan Tarhei Hosé, PhD.
"Homo sum et cogito ergo odi profanum vulgus et libido."
There was nothing new or innovative in the article, and it had the depth of Paris Hilton as far as actual real world cooling suggestions.
/. I forgot for a moment...
There are a ton of different solutions out there both onchip and off including aircooling via different heatsink designs, watercooling, peltier cooling, and self contained refrigeration units.
This article barely scraped the surface of anything useful or interesting related to cooling.
Oh wait, this is
When I first got my Prescott chip, it ran *way* too hot. Realized that the stock thermal pad was just acting as insulation, so I scraped it off and replaced it with Ceramique. It still ran warm, so I superglued a piece of 3" PVC pipe to my case fan. Now air blows right onto the processor area, and the CPU temps are great. I highly recommend the ducting. Cheap, easy, and oh-so-geeky.
Call me a curmudgeon, but it seems like most of the heat is created by wasted cpu cycles. Eye candy is nice, but at 200 million computers in the U.S. alone, each Watt saved represents about $31 million in annual energy costs (assuming 40 hrs/wk, @ $0.074/kWHr. Reducing power consumption by 10 W would pay for a lot of good beer to fuel software development for more efficient software.
Two wrongs don't make a right, but three lefts do.
The best solution is to install something like NetNanny to filter out porn sites. Even the slowest and oldest cpu in the world can't help but heat up when natportmanhotgrits.jpg is being processed.
I Am My Own Worst Enemy
First we have "Fans Attempting to Pay for Enterprise," and now they're "Cooling Down Hot Processors."
Is there anything that these devices can't do?
...but would increasing the size of the actual chip help any? Like a vented, flow-through design. The actual chip is about the size of a fingernail, i know, but if we increased it to the size of the whole plastic skirt around it (that which has all the pins) wouldn't that help heat dissipation?
I haven't taken any measurements, but i'm willing to bet that the skirting around that wouldn't be much bigger- we've got more length on all sides, so we don't have to go as deep.
However, i don't design microprocessors, and don't know anything about electronics, so i'm betting there's something i'm missing out- i.e. the impedance or capacitance effects of increasing the microscopic traces. I would assume someone has thought of this once before, but with all the rush to make stuff smaller and smaller, can it be overlooked?
It's not like we don't have any spare room in a PC case, y'know...
do() || do_not();
apt-get install athcool
The old Lie: Dulce et decorum est Pro patria mori
this subject is so hot I won't even touch it with a 10-foot pole...
i just stick mine in a tub of cold water. but for some reason it stops running after that. still trying to figure out why.
Color this mechanical engineer disappointed.
Software piracy is victimless theft.
This is so lame, I think I should post it AC...
... but...
The roof, the roof, the roof is on fire!
(Or, for the Futurama fan in you, and me, Nixon: "The loot, the loot, the loot is on fire!")
Maybe the mighty IBM can withstand one?
The air surrounding the chip does not conduct heat efficiently. Therefore only the area in direct contact with the heatsink and/or cooling mechanism will drain heat from the chip.
My invention is this: encase the chip in a liquid or (better) a solid that does not conduct electricity but is an excellent heat conductor. Alternatively, wrap the chip in a thin layer of insulating material and then encase the rest in a metal brick. The idea is to provide a large solid primary heat sink.
The primary heat sink should have a highly convoluted surface as to maximise its area.
A secondary heatsink (coolant, fan, etc.) will move heat still further away.
Ideally the heat produced in this way would be used to drive useful processes, such as espresso production.
Sig for sale or rent. One previous user. Inquire within.
No big advancements brought out in this article.
My AMD64 3400+ never goes about 100F with my hyper 6 by coolermaster. Granted it's got an 80mm fan but it's quieter than most power supplies. From there you can underclock and turn the fan down to where it's nearly silent while maintaining a good temp.
Intel have, in fact, been pulling the blinds over our eyes with the Pentium 4 series - particularly the infamous Prescott infernace. An entire industry exists in cooling down CPUs to the point that there's more reviews of silly cooling contraptions and water cooling kits on the web than there are the bits in PCs that do useful stuff.
Why the Intel blinds? Because the Pentium M manages to be just as fast and frequently faster - when given a fair trial on a desktop board - as the latest and greatest Pentium 4s. What's more, the chips cost less and they use a fraction as much power.
One wonders what tricks Intel will use to bump the heat up on the new 800 series (basically just two Pentium Ms on a chip) to safeguard the enthusiast cooling industry?
I'm sure they'll think of something.
How to fry an egg on an XP
From today's Raleigh, NC News and Observer: http://www.newsobserver.com/business/story/2100089 p-8480000c.html
At the bottom of TFA was a request for proposals for something for April Fool's day.
Anyway, my favorite solution is the heat pipe. They act like a thermal superconductor but they are sensitive to orientation ie. 'up' has to be up or else. With a heat pipe, you could move the cooling surface to the back of the lcd. It would work great unless you tried to use it upside down.
If I wanted a computer to run for ever in a harsh environment, I would seriously consider dunking everything but the drives in a tank of transformer oil.
Water has the highest specific heat available, and therefore will
be the most effective means available for transferring heat.
If the coolant will reach temperatures above the boiling point of water,
then propylene glycol would be a better choice, because its boiling point is _much_ higher.
IMO, the surface area of the case can be used to advantage, if coolant is circulated
through passages which are either in the case or attached to it.
Comment removed based on user account deletion
The shadow registers run in parallel with the computation logic and do not add anythign to the total path length, which means there's no loss of speed.
To make laws that man cannot, and will not obey, serves to bring all law into contempt.
--E.C. Stanton
That's what the sleep Button is for.
I use it pretty often on my Mac. For some reason, on my parents PC it doesn't seem to work reliably as they do on their PC laptops.
I know this has been done before, but it's not something you see very often. The basic premise is: Pure water doesn't conduct electricity! So, use a modified fish tank (make sure it and your computer are squeaky clean), and fill it with distilled water. Then submerge your squeaky clean computer into the squeaky clean water contained in the squeaky clean fish tank. Blam! Instant kick-ass cooling. Convection currents alone will help to cool all hot parts, but you could easily add a water pump to create forced currents.
What you reap is what you sow
As of yet there has been no punishment, since there has been no crime. Presumably if someone did break it, their punishment would be a nobel prize though.
Am I the only one that gets irritated by these kind of articles?
Comment removed based on user account deletion
From the Slashdot summary
and from the first paragraph of the article itselfAside from the removal of one sentence and a slight re-wording of the last, this is word for word the introduction to the article. If you were to submit this in a paper for a college (or even high school!) class, you'd be a good candidate for a plagiarism investigation.
Once again, Slashdot editors, there's a very simple way to deal with this -- change the author attribution. Rather than saying, "DonnaMai writes ...", use "DonnaMai quotes ..." or "DonnaMai poorly paraphrases ...". By properly citing the summary as a quotation or paraphrasing* of the article, you would avoid the impression of plagiarism.
* Yes, paraphrasing is allowed by fair use. In fact, if you're going to summarize an article, you want to paraphrase. However, paraphrasing is not, "Copy a sentence with a changed word here, drop a sentence there." You need to write a summarization in your own words, not take the article's words and (poorly) "massage" them so that they're not 100% identical (90% identical is still a problem).
(S(SKK)(SKK))(S(SKK)(SKK))
What's needed are breakthrough in material science. Carbon nanotube heatsinks, on die peltiers, diamond based semiconductors. If engineers make these technologies work, in the future we might not be worrying about heat anymore but other barriers to performance. Such as software design and storage I/O.
If you're going to push a fundamental formula onto us unwashed masses, first make sure you haven't fundamentally forgotten it, OK?
P=I*V.
Not to get into a clock-waving contest (excuse my pun), I'm running a Prescott 2.4GHz chip on a microATX board inside a gutted Mac Classic with one 8mm fan in the side, one 12mm fan out the back, and it runs at an average 96F. Just my two cents.
When I clicked on the link in the article expecting to see some fried eggs and instead there was this.
I WILL NEVER USE A LAPTOP AGAIN
Bloat is there because it's cheaper to buy a new PC than to buy unbloated software.
-- Too lazy to get a lower UID.
Use your hot CPU to cut breakfast :)
t ml/
http://www.phys.ncku.edu.tw/~htsu/humor/fry_egg.h
just because 90degC is hot to us meatbags, doesn't mean that it's dangerous to have ICs who run at this temp...many ICs run happily for years
You use "who" to refer to chips rather than "which" or "that", and describe high-temp chips as "happy" with their lot in life. Actual for-real people meanwhile, are merely "meatbags". I didn't even need to read your last sentence to know you are a Mac user.
Actually, I have dual processors. Each processor has a heat sink and a fan on the heat sink, but most importantly, my enclusure is WTX form factor which allows the motherboard to be mounted upside down... keeping the CPUs away from the heat generated by the power supply and hard drives.
The dudes and Overleap are more concerned with the effects of sustained heat on the motherboard, particularly the capacitors which reduces significantly the functional life of the circuitry. They figures they use estimate that today's current crop of CPUs generate enough heat to reduce the life of the motherboard by half or to about 3 years on average. So regardless of what is happening to the operational performance of the unit from too much heat, what's true is that come hell or high water your machine will die in about 3 years.
Considering a I just took a 11 year old PC out of service on my home network I consider this a very big downer.
In fact with the way that companies like Dell do their financing you will probably wind up paying a lease on a machine that doesn't last as long as the term of the lease. And that is great big fat downer.
Use an older, cool laptop to do everything you do daily and enjoy the instant-on/off. use cpufreqd, apmiser, and even something like the gnome cpufreq applet to control speed use.
Save the superhot machine for your gaming, if you still play games. It's soooo much quieter and cooler in my office since I switched to notebooks.
99% of the suggestions are variations in heat transfer... moving the thermal energy from the chip into a heat sink, and then into the surrounding air.
The other method is to come up with an endothermic process, one which absorbs the heat and transforms the thermal energy into a different kind of energy.
A simple example is to boil a liquid such as water or alcohol. The thermal energy is absorbed by the heat of evaporation of the liquid, and the vapors exit the case. Or, this could be used in a closed loop system, such as a Carnot cycle to actually use the waste heat to generate electricity.
Another example would be some kind of chemical reaction that absorbs heat.
Primer at www.silentpcreview.com
std. disclaimer: i am just a fan. ba dum bum.
When I was a kid, we only had one Darth.
What we really need is a radiator.
"Me ol' compy's leaking coolant again!"
It could even be fanned by your very own flatulence, and you could say you have a gas-powered cooling system.
Okay, well, it was just a thought....
http://augustwestproducts.i8.com
Am I the only person that sees absolutely nothing in the article about CPU cooling? All I saw was a bunch of crap about April Fool's and a huge amount of "Resource" links that had little to do with cooling, either. If you anyone came here is interested in cooling, then check out vaporizers, cascade phase-change systems, and take a look at stirling engine technology. Carbon nanotubes and diamonds are in the future. I suggest starting at http://www.akiba-pc.com and checking out their article on cascade systems to begin.
http://www.kernel.org/pub/linux/utils/kernel/cpufr eq/cpufreq.html
CPUfreq works very well both on my Dell Inspiron 8600 (Pentium M, 1.8GHz) and my desktop machine (Pentium 4, 3.0EGHz).
Using CPUfreq is a good way of lowering CPU temperature when all of the CPU's power is not required (like when using the computer just to listen to music, etc).
From my experience, heat is indeed a killer, but more often than not, the heat and the subsequent damage done is a secondary effect of not keeping computer equipment in a clean environment. When dust accumulates in the PC, this affects the components and causes heat build-up. I'd say a bigger problem involves people not keeping the area around their PC clean. The way I figure, if you own a cat and the thing is always near the computer, subtract a year right off the bat.
Hotness is all about Intel's branding....
Did you hear about the new hotness? Intel Pentium, SCORCHING PERFORMANCE! ssssssssss!
Stick a Prescott on a long stick and apply that scortching brand on the rear end of any Longhorn cattle, and you've got yourself a stampede of sales, yeeeee-haw!
You see? You see? Your stupid minds! Stupid! Stupid!
Beer.
Thanks, I needed some validation of my self-image!
in case you didnt read the article, the option I liked the best was
using liquid nitrogen for supercooling
http://www6.tomshardware.com/cpu/20031230/
I've never heard of such a thing, but I cracked open the case and sure enough there was a fan attached to my processor. That must be used to cool it down. I've just had a great idea! Wish some extra cooling, I may be able to increase the clock speed of my processor! I think I just invented a new thing, maybe I should patent it. What should I call it? Since I'm going "Over" the normal "Clock" speed of my processor, I think I'll call it "clock-overing"! I'll try to clock-over my processor tonight and if it works, I'll be in the money!
I can't believe nobody has said this yet, but the absolute FIRST thing you should do if your system is running over-hot is check the airflow and direction of all of your fans.
Most ATX cases like to have a fan blowing in the front, and other fans blowing out the back, check your case documentation. If one of your fans isn't working well, or is actually facing the wrong way, the entire airflow scheme goes straight to hell. I've seen this happen several times, but now that cooling is so critical incorrect fan placement is often a show-stopper.
Today's story? My buddy builds a new system with a new P4 3.4HT. It exhibits classic signs of overheating-- the fan sounds like a 747 taking off all the time, odd beeping, memory errors, and when his brother who actually built it for him runs 3DMark, it scores something like 40% of what it should have on CPU. Everest says it's running at >80C. Much freaking out is done, and they order a hardcore Thermaltake fan to replace the standard/weak one that came bundled with the processor. That comes, and it helps somewhat, so the processor isn't stepping itself down to non-melting temperatures, hanging at 65-70C full-performance. Memory errors still a bit of an issue.
So I come over to look at it. Dumbass neighbor (Best Buy Geek Squad employee/Frat Boy) had put the front fan on facing backward while assisting with the assembly, so the front 80mm case fan was blowing OUT of the case.
I unscrewed the fan, flipped it around, and two minutes later the computer was playing Far Cry and humming along at 40C, by far the quietest computer in the room.
Moral of the story? If you have a misplaced or broken fan, your cooling power drops massively. It pays to actually look at your case documentation now. Oh, and buy Antec.
"We have to go forth and crush every world view that doesn't believe in tolerance and free speech." - David Brin
...are usually facing in the wrong direction... they should be blowing in the case (except the one in the PSU)... there are two advantages : you get a cooler PC and a more silent PC (this was btw. implemented in some DEC cases).
...and use good silent fans (f.x. Papst)... they move lot of air without the noise...
IBM Developer Works staff writing guidelines:
(For internal distribution only).
1. Chose topic for writing that is common knowledge in the computing community that you yourself know very little about.
2. Do research on topic by asking your neighbors about it. Then ask people from the local coffee shop. Include this process in your article.
3. Ask other editors about the topic. Print their way off responses without actually showing an understanding of them.
4. Always include buzz words like "nanotechnology" in your articles to show you're on the bleeding edge. Also include references to pop-culture like "The Daily Show" to show you're hip. You may want to tell people you lived near the Berlin Wall in your by-line to show how cool you are.
5. Inflate your article as much as possible. While you could say what you need to say in 2 or 3 paragraphs, include all sorts of extraneous information so it looks like you are a real writer.
***
The Internet is generally stupid
Are you suggesting that I pour salsa into my computer... again?
For real. Why does all my hardware have to be obsolete just so I can use a single new piece of hardware?
Anyone here remember when the liquid based off of novec 1238 appeared called sapphire. A post for it was issued way back when: http://science.slashdot.org/article.pl?sid=04/04/1 4/1621235&tid=126&tid=14
Anway, on the topic of cooling, total submersion of the cpu and motherboard within this man made liquid was thought of. With the right equipment, I'm sure it wouldn't be a bad idea, and if someone could get ahold of it, I'm sure they'd want to hack one out first before the corporations got ahold of the idea..
Just a thought on how you could seriously cool your computer.
I recall reading and article (with pictures) where a guy who had been water-cooling his CPU using a radiator and an in-window air conditioner.
To cut down on noise, he ran a 60-foot copper pipe out of his office, along his garage floor and back into his office. He filled it with gallons of water and had a pump recirculate the whole business over his CPU.
I thought that was a wcky idea, until I saw the movie of the liquid nitrogen 5 GHz overclock at Tom's hardware.
.. pa-ra-bo-la, pa-ra-bo-la, 2 pi R, 2 pi R, where's your latus rectum, where's your latus rectum, 2 pi R
All ya gotta do is let my ex-wife stand next to your computer and I guarantee nothing will get hot. She's colder than liquid nitrogen.
http://gtresearchnews.gatech.edu/newsrelease/synje ts.htm
This new technology seems to be promising.
No one wrote in to the article to say why either
"Since not many of you (or, frankly, none of you) wrote about how to actually reduce the amount of heat coming from a chip..."
There's electric involved in a small space... and that's abuot as far as my knowledge goes.
- dentritic (tree) heatsinks
I think a big problem will/is the ratio of having physical space in the core for cooling of some sort verses the slow down that that space creates.
Because the human brain also creates heat and ditto for others I feel the problem will remain until quantum efforts. Overclockers feel that this seems to be a sorely overlooked part of increasing speed on the CPU makers part -
why isn't CPU design heading toward cooling as it gets harder to increase CPU speeds?
Here's a mind bender; what if the actual design of the CPU was made such that it's very design has a piezo effect... would be harder than C++ Code obfustication to design I guess.
A blog I run for the wealth
How very American of you....
Me? I want fish with my chips.
The Wind-Tunnel PC
When the article summary is the same as the first paragraph of the linked article, this is called PLAGIARISM.
You shouldn't allow this to happen, as it lowers Slashdot's creditibilty. Hopefully you can find the time to check for plagiarism right after performing a thorough dupe che...ohh nevermind...
...that don't stall when IO is blocked. Opera and Microsoft Word are two notorious criminals in this regard. I assume Opera is constantly writing to disk due to its "restore-on-crash" fucntion, Word with auto-save... which in itself, is fine.
But when doing heavy IO (e.g. a BT download), they are unusable. Then I use Firefox and Textpad. Just put that damn disk IO on a separate thread and let it go off to limbo. I've done that myself, for crying out loud. It doesn't take a genious. I repeat, the GUI thread should never ever be doing disk IO.
Kjella
Live today, because you never know what tomorrow brings
a rackmount server in a full rack has bugger-all coolling surface: take a modern 1U server like an HP DL360. stuff it in a populated rack and there's 1U of space at the front, and 90% of that is taken up with floppy, CD, and hard disks. at the rear, there's 1U of space, and 90% of that is taken up with I/O ports.
Is there such a miracle fluid?
Is there an epoxy sufficiently heat resistant, etc so I could make a prototype?
Should I put grooves in the bottom of the HS to increase surface area and to enhance flow characteristics?
Lost in space at an early age. Survived the vacuum. Now rebuilding castle in air.