Hi All, I am not much impressed with the uncritical hype in this thread about hyperthreading. Although the latest P4 technology is indeed faster than any earlier Intel product, much doubt has been expressed about the true contribution of hyperthreading. I pointed this out in an earlier post. Whereas I could definitely see decent load sharing in my older multiprocessor systems, not much benefit seemed to show up in my current single processor P4 with hyperthreading enabled. I had observed this for more than 6 months now and decided to google around a bit. I did not encouter much of the uncritical "yeah yeah hype" of this current ET thread. In fact several articles point out that turning hyperthreading off may actually speedup things: http://www.newsfactor.com/perl/story/21119.html What is quite relevant for serious scientific kind of computation is that especially floating point operations don't seem to benefit at all. The article points out that in fact only a single floating point processor is available. This would make it definitely worthwile to go for true multiprocessor solutions. (nitro keep on going!). This less or more confirms what I seemed to have found out. P4: better speed? - by all means. Due to hyperthreading? - doubtful, lots of hype certain. P.S. My experience is based on the 2.8GHz of 6 months back. Could Intel have improved/corrected something in the latest 3.2GHz? Be good, nononsense
This is what I thought. Suppose there are two CPU intensive applications running. Without HT, each should get 50% CPU time; with HT, each is supposed to get 100% CPU time of one processor. If the above theory is not right, could you explain?
OK guys - a question for the average schmuck. Right now I'm running a 2-year old AMD XP 1700+ with 1GB DDR RAM, 3 screens with a 20-chart realtime Metastock layout and IB. During the market I am pegged at close to 100% and the computer drags a bit - the curser is a bit jumpy, etc. Will hyperthreading alleviate that or is it just more merkating BS from INTC? I know software has to be written to take advantage of dual processors but what about a single processor hyperthreaded? Also does XP Home support hyperhreaded processors - I know it doesn't support duals. It's not the expense or the building of the hardware that makes me reluctant to change over - it's the work of reinstalling/configuring the apps and win itself. What a nightmare. Thanks for your help --
XP home does support hyperthreading. But the majority of the speed improvement you will see is from the huge boost in overall performance, not the hyperthreading. If you are "near" 100% pegged all the time, and "just" getting sluggish under peak loads, then you will be running fast and smooth as silk on a new processor. peace axeman
Some bundled applications are "hyperthreaded" applications, but the OS ( to my knowledge ) is not. In otherwords, Windows XP is capable of running your hyperthreading applications, and knows how to do it, but doesn't need to do it for itself. Reallly, all an OS is for is for making calls to hardware.
Hi All, The thread of hyperthreading contained a lot of sentimental testimonials by naive "believers". I just came accross an url with very extensive results on testing, this under the latest Linux 2.6 kernel: http://www.2cpu.com/articles/41_1.html These tests clearly show the shining superiority of true ( physical) multiprocessor solutions. Interesting is also that the Prescott, recently discussed at ET, seems to perform somewhat better with hype on. A point also of interest for traders is the very severe degradation introduced by hyperthreading in the case of database performance testing. Obviously, the hyperthreading question is not one that can be answered with any simplistic approach. As for myself, I run my P4's with hyperthreading turned off. Be good, nononsense
I built a P4 2.8 HT system w/ 1GB DDR400 for my mother and found that, yes, it is totally fast. However, it cost $2,000 in parts and I really think that an AMD based machine can save you a lot of money without sacraficing much performance. Right now it seems that the Althon 2500+ is a killer deal. Check out newegg.com -- they sell it for like $89. You can overclock the heck out of it with a decent CPU fan. My 2500+ system, with 1GB DDR400, suits my needs quite well. I throw a lot at it with my trading software, chat rooms, real time AV, et cetera. Never had a glitch. Paid under $800 for the parts. If you're totally into max speed and power, I've tested AMD's 64 bit processors and can tell you that they are noticeably faster than Intel's P4 EE HT. Noticeable cheaper as well. So what's all the hype about P4's?!?!?!?!?!
Billy Bob made billions on selling the same operating systems for pc's with just minor changes to the previous versions.... don't blame INTC for doing a similar thing with changing the speed and features of each processor just slightly and selling and marketing the daylights out of it. hey, why get today's 23.8Ghz when you can get tomorrows' 24.9 Ghz processor based system? huh?
Have to agree with above post re AMD vs P4. I have both. Couple months ago I built a P4 3.0 with 1G ram. This week I had my local shop build a Athlon 2500 with 512 ram (there were about $75 higher than just parts from Newegg). I swear the AMD is as fast if not faster, or so it seems. About $350 dif in price and the new AMD is much quiter too. This is my first AMD machine. Very satisfied. PS Alot of useful info here.......... http://www6.tomshardware.com/cpu/index.html