Slashdot Mirror
Pentium 4 Overclocked to 7.1GHz, Sets World Record
Netmonger writes "This Japanese guy
overclocked a Pentium 4 to 7.132GHz!! The system managed to calculate pi to 1 million decimal places in 18.516 seconds, setting the world's record." The article notes that a Pentium 4 had been overclocked faster earlier this year, but at that speed it was not possible for the machine to function beyond BIOS. Of course, they'd yet to try diverting power from the dilthium crystal reactor to the deflector array.
How long can the machine last at that sort of overclocking? How much experience have others had with lifetimes of chips once you overclock them by a lot.
http://use.perl.org
That's because it's limited by how fast your hard drive is, not how fast your processor is.
Or did you think all of the data was stored in your L2 cache?
...even at 7Ghz is still can't game any faster than a two year old Athlon 64 3200+... Why do games hate intel anyway?
My question is this. Tom's Hardware put a P4 under liquid nitrogen a while ago, put the northbridge chipset under a phase change compressor, and replaced the motherboard power converter in order to supply enough power to the chips, and they were only able to achieve 5.25GHz max. What did this japanese guy do different that gained him another 2.5 GHz? Is it entirely a result of using newer chips with new manufacturing technologies like Silicon-On-Insulator (SOI)? Or did this japan guy do something that Tom's didn't?
You want that render to finish before lunch? Just slide in a brick of dry ice and watch the steam come out the sides as your motherboard's temperature sensor gives the go-ahead to crank the clock up to 7 GHz.
Even though they've made clockspeed less relevant, I'd kinda like to see this sort of extreme overclocking on AMD.
Or does it already exist?
All I know is I see all these liquid nitrogen P4s and think "wtf...where's amd?"
Ah! Witness the emergence of a new Slashdot catchphrase.
"I'm not impatient. I just hate waiting." - My Dad
Comment taken from the website:
"18.516 must be wrong. My athlon 2400+ did
1 million places of PI using FASTPI in 4.4 secs.
Maybe the number should read 1.8516 secs.
That would be more in line with factors of
speed differences between my 2400 and
the P4 system."
Calculating pi is a series of mathematical operations where you can't do the next one without the prior because you need the remainders.
That's not entirely true. There exists a digit-extraction algorithm for computing pi starting at the nth digit, without the need to compute any other digits. The only catch is that it only works on base 16.
And the knowledge that they fear is a weapon to be used against them...
My Powerbook G4 using Mathematica can compute Pi to 1000000 places in about 19 seconds. How can this be any kind of record, or anything to write home about.
Since mathematica's performance for this algorithm is directly related to clock speed, I'd expect to see something like 3 seconds for that clock speed, and even faster for optimised code
To be fair, the grandparent do have a point.
If the clock period is less than the propagation delay of the transistors in the processor, the processor will not meet its critical deadlines, and the results will be unstable.
However.
If that was the case, I doubt it would be able to run much at all, let alone an operating system.
REALLY FUNNY considering we just had the anniversary of Hiroshima and Nagasaki in Japan. Perhaps you want to joke about the Jewish holocaust or the slaughter of the Native American indians.
If you looks closely at the first screenshot, you will see that the system tempeture is 242 degrees Celcius (468 Fahrenheit).
Cooling and power requirements aren't the only issue, since at those types of frequencies you are likely to be interfering with radio frequencies, unless you have really good shielding.
The real future is asynchronous CPUs, that are actually clockless. They generate much less heat and consume much less power. The only reason that they aren't replacing the current batch of chips fast, is that all chip design and testing processes are built around clocked CPUs.
A few articles on the subject:
- Will Self-timed Asynchronous Logic Rescue CPU Design?
- Computer Chips Without Clocks
Jumpstart the tartan drive.
I believe that since version 7, you don't need to do this since it does start up faster (I think it loads plugins on demand or something). It still works kind of sluggish though!
It does prove that propagation delays within the P4 have enough margin to go well beyond 4GHz. Trace propagation delays do not change much from -200C to +100C but CMOS transistors' and copper traces' conductivities do improve quite a bit.
So the devil's in the transistors and trace losses. I wonder how this will pan out at 65nm... smaller transistors are potentially faster but they have to be large enough to drive the nets and the loads these nets represent scale less than linearly with process technology. Static power is also likely to increase substantially.
I would not be surprised if phase-change cooling became common within the next 10 years, along with CPUs designed and manufactured specifically to run in sub-zero environments for the mid/high-end. I am having a hard time imagining progress much beyond 65nm (maybe 45nm) without phase-change: leakage, conduction losses, thermal noise and other temperature-dependent parameters will be major show-stoppers. Getting closer to atomic transistors is trimming noise and leakage tolerances.
Well, someone could be even more "crazy stupider" and repeat the experiment using either liquid helium (much more expensive than nitrogen) or hydrogen (kinda flammable/explosive)... they could probably reach 8.5GHz this way.
While Fabrice is a respectable person, he did not invent this formula. One of the most responsible persons for this discover is called Plouffe. The complete formula name is the Bailey-Borwein-Plouffe and the most interesting way is how they did "discover" it : Mathematica did with input from them and it was a surprise for them when it spitted out the formula.
p %3A//www.lacim.uqam.ca/~plouffe/articles/Miraculou s.pdf&ei=XFL-QuroJY7QQe6vkYUC
http://www.google.fr/url?sa=t&ct=res&cd=1&url=htt
The other reason the bomb was used is the usual simple one: Because the US military had it. They had a new toy and were happy to still have a reason to use it.
And BTW: Nagasaki was an "accident". Well, sort of. The sky wasn't clear and the bombers couldn't see groung zero clearly and had strikt orders not to drop in that case. But the pilot couldn't open a valve on a fuel tank on the bomber, so they still had to drop the heavy bomb in order to make it back to base.
We suffer more in our imagination than in reality. - Seneca