can you point us to any links that have actually TESTED your assertions of significant real world improvement in performance? specifically i'd like to see test results that demonstrate that real applications running on dual 2.4 GHz Intel procs is nearly equivalent to those same apps running on 4Ghz, as you claim. (of course taking into consideration your assumptions in the tests) .
Why is it in the "internet era", everyone seems to think there's always a magic "link" to any and all information?? Maybe it's born from the same thinking that everything should be free on the internet. Sorry, can't point you to a link - most benchmark attempts are published by magazines and they're not likely to running a high load datafeed/charting/analysis workload. However, some of us have actual hands on experience. So all I can tell you is what is obvious from having done about 20 years of internals development on a spectrum of OSes and having designed and integrated dozens of very large scale, high performance systems over the years. Take it or leave it - your choice. However, it's axiomatic that if nitro's workload is routinely running at 85% composite CPU utilization on a dual processor - that a single processor machine isn't going to run that same workload with the same throughput unless you jack up the processor speed comparably - it's not especially complex arithmetic. Average rules of thumb for CPU intensive application mixes (note, this of course does not apply to running a single, single threaded application): dual = 1.85-1.9x of a single quad = 3.6-3.8x of a single octo = 6.9-7.3x of a single Since multi-processor configs are more complex, it might be less expensive to buy a faster single processor config (if such a processor exists) - e.g., instead of using dual 1.5 Ghz processors, use a single 2.8-3 GHz processor - but if you needed four 2.4 GHz processors for your workload, you're not going to find a 9-10 GHz single processor anyway.
I had 5 applications running at the same time with a P3-800Mhz with 512Meg of ram and my CPU utilization maintained 20-40%. Then I added 5 more applications, browsing windows, a news feed, a chat page ... low intensity stuff. Well my CPU utilization rose a bit but it maintained a level of 35-60& utilization. I thought that maybe adding some extra ram memory might help so I added another 512Meg. Then I noticed that my computer was back down at the 20-40% range of CPU utilization. So there I was with a P3-800Mhz single processor system with 1 gig of ram with 8 to 10 applications running at the same time and my CPU utilization maintained a level of 20-40%. By the way I do run Windows 2000 as my operating system. I understand that there are some traders who have a special need for a dual processor but by and large most traders just don't need all of that horsepower. I say to the traders looking to buy or build a new machine ... take the extra money that you would have spent on a dual processor machine and take your wife out of town for a week. You'll get a better return on your money.
spreadem - Most computer users (not just traders) don't need dual processors. It depends on your workload and how CPU intensive your workload. Traders doing scans and loads of analytics on lots of symbols could burn a lot of CPU doing it. But for most trading applications it'll be unusual for the average traders to burn up an 800 MHz processor, let along a 2+ GHz one. Clearly in your case you've still got a lot of headroom on your PC. The extra memory you added probably helped reduce process working set flipping and paging overhead and helped reduce demand on your CPU after you added those extra apps (which are typically memory hogs and were probably forcing the OS to steal memory from other processes). Memory's cheap, so it's a good first step for those looking to improve their system performance (as long as they're using an NT derivative like W2K or XP - those using 9x or Me won't usually benefit). Next, they can make sure their disk is thoroughly defragged (fragmented disks tend to further degrade systems that are incurring paging overhead and apps that have to access the hard drive a lot). If more memory and unfragmented disks don't produce enough performance boost, then it's time to look for more horsepower (CPU if the job mix is CPU intensive or faster disks if the mix is disk intensive). But with cheap computers with up to 3 GHz P4s, only a handful of users will have workloads that will exhaust these machines. And if they have that kind of workload, they already know it and know what to do about it - it won't affect the "I'm trying to decide what kind of computer to get" crowd. Simple rule of thumb - if a person has to ask whether they should get (or whether they need) a dual processor, they don't need one and should save their money - or as you suggest, take their spouse on vacation.
The answer depends upon what applications you are running and wherther they even take advantage of more than one processor. For windows systems the way you determine the answers is by using the performance counters and detemining - for an exsiting system - where you can get improvements. The most common answer is to add RAM and a faster video card(s). We run several multi-processor systems under linux/unix and Windows. For a trading station you can really get by with older slower processors and more RAM and fast video cards. We only need dual (or more) processor systems for large database systems, and extremely complicated numerical calculations and transacting systems, all of which actually use extra processors if they are available. Things like data mining and pattern matching types of applications on large databases require this: a client side workstation that relies on things like external servers - news and data feeds, trade management, etc - typically uses only 30 - 70 percent of the processor, even on older intel processor models. ...Dont waste money by overbuying ...
WHAT A GUY!! HE IS FASTER THAN A SPEEDING BULLET! MORE POWERFUL THAN A LOCOMOTIVE! CAN LEAP TALL BUILDINGS WITH A SINGLE BOUND! (WHAT AN EGO!!) {{yawn}} yeah, whatever :-/