|
I have been using 2 processors at home in my main development machine since 1994. This was at first with dual 133 MHz Pentium but I upgraded at least 7 times and all but 1 were more than 1 core. The most expensive upgrade was dual Opteron 250s and 4GB registered of memory in 2005. That ran me over 1100 and the cheapest upgrade was a Quad core Q9550 which I got motherboard + cpu + 6GB of memory + new 650W 80+ power supply for $400 US on black Friday with the help of live.com 30% cash back. Anyways as a programmer I have been writing multi-threaded applications for at least 10 years.
John
modified on Monday, February 23, 2009 8:40 AM
|
|
|
|
|
With PLINQ everybody can do dual-core and more 
I work on WPF frontends and although they work with async operations all over the place, I can't really say that it is a true multi-core enabled application. The background work is still done on a single thread and I haven't optimized the code for more threads, except of course for the async calls to the backend.
|
|
|
|
|
I use a dual core W2k8 x64 box as my main development machine, and a dual core laptop for admin and mobile stuff. In addition - I run our build server (a dual core W2k3 box), and have another 3 desktop systems (one dual core; 2 single core) and a dual core laptop for testing.
To add to that I've a quad core Q9550 box "on the way" which I'm likely to use alongside the main dev box.
When we put them all into a grid all bets are off, of course. Our code analysis grid has something like 10 agents with up to 24 cores - when it's running full pelt it's rather fun to watch the progress bars zipping along and (hopefully) going green rather than yellow or red. 
|
|
|
|
|
When I am not at work or develop for a client of mine, I use a Commodore 128 to write small games or programs. Does that mean that I work on a dual-core computer? Hahaha!!!
|
|
|
|
|
Palavos wrote: When I am not at work or develop for a client of mine, I use a Commodore 128 to write small games or programs. Does that mean that I work on a dual-core computer?
That's 'hard-core' computing to me!. Two extra points if you use CP/M on the C=128
-=[ R ]=-
|
|
|
|
|
Rogelio Perea wrote: Two extra points if you use CP/M on the C=128
Back in the day I bought the manual and software and intended to use that but before I got there I replaced the commodore with a 486.
John
|
|
|
|
|
If I dump one of our Intellect 3.0 screen savers (2 files; scr & dll) on a box, I can drive it from my laptop as a "Voluntary Computing Node", together with all the rest, as one little itty bitty super computer. Otherwise, my lappie just has 2 cores.
|
|
|
|
|
I guess that would depend, at least partially, if that was the regular way you handled operations of that machine, or an occasional usage. Since I proved my theories for processing enough that my boss finally put in the requisition for a Tesla, this is how I use the machine, it is its purpose, and its intended and usual function. I am sure others will not appreciate my definition, but hey, it is just a poll. I am using nv280's until my Tesla comes in, still, that is its purpose, its design.
If you use a grid as your regular and everyday workhorse, my feeling is heck yeah, then you can use that as your core count.  but who am I but a crazy C/C++ programmer. 
modified on Monday, February 23, 2009 1:50 AM
|
|
|
|
|
One processor for Vista and its sniffing services and one for me 
Greetings from Germany
|
|
|
|
|
At work on linux I have the and use the ability to build with > 32 cores using a distcc or more recently icecream. This really speeds up building on slower machines. However with zippy quad cores this does not help much since the io becomes more of a bottleneck than the cpu speed.
http://distcc.samba.org/[^]
http://en.opensuse.org/Icecream[^]
John
|
|
|
|
|
I borrow 240 streaming processors from my nVidia... worse, I regularly borrow two sets of them. My work machine has 8 cores, I have access to 64 or more depending on if I activate a grid. Still, when I pull in the nVidia CPUs I can outdo the older 64 node super computer.
|
|
|
|
|
LOL I just knew there's be a "more than 100" answer from you. 
|
|
|
|
|
just wait until I get my 4 GPU Tesla... I am already doing fluid dynamics and physics calculations at speeds that exceed any super computer we have ever owned. And I only have one card at work, and two at home. When I get four?
|
|
|
|
|
I bet. Sounds like a fun rig - are you going to put a CB and go-faster stripes on it?
|
|
|
|
|
Anna-Jayne Metcalfe wrote: are you going to put a CB and go-faster stripes on it?
oh no... but I might have to calculate the RF communication distance of the CB through rough terrain as well as the ambient reflection of the racing stripes.... does that count?
|
|
|
|
|
I'm sure it does. 
|
|
|
|
|
The moment I saw the poll in the Insider, I *knew* you'd be boasting here 
Cheers,
Vıkram.
I've never ever worked anywhere where there has not been someone who given the choice I would not work with again. It's a job, you do your work, put up with the people you don't like, accept there are probably people there that don't like you a lot, and look forward to the weekends.
- Josh Gray.
|
|
|
|
|
That's not boasting... that is just "drowning my sorrows" with a Tesla. I find it interesting that the last two home machines have "embarassed" work into upgrading my machines at work. It is kind-of sad that it is remarkably that easy. My bosses like to have bragging rights on machines: origin 2000, CM5, quad single core, 64 node Enterprise Linux box, dual quads, etc. When an employee owns a computer faster than the company... they get a bigger computer.
Of course that means they don't have the R&D risk associated with new machines, they simpy one-up my designs directly. or try. The last one (dual quad core xeon, single nv280 is doing great, but design wise it is functioning in all respects save one, at half the speed of my home system. My RAIDs are 3 times faster, my memory bench twice as fast, IO almost twice as fast. They have 8 cores vs my 4 on the main chip, but even so, my 4 at 3.2ghz seem to outbench their 8 at 2.8ghz because of the slower BUS and memory. But when I demonstrate CUDA processing... when you can out process the sum total of all the standard CPUs in the building BEFORE you kick in the second card...
but... of course I am drowning sorrows this week.... so pass the Tesla to me... I'm ready for it.
|
|
|
|
|
Ah, you still have to pull in the results from NVidia into main RAM and then to CPU if you going to do anything other than weak C++ more like C-style mess CUDA compiler is.. have you measured the penalty there? It should be significant and I believe it should be a part of any benchmark or results (at least half-way
|
|
|
|
|
In a world were so many cores exist, we should be thinking seriously into developing more applications that take advantage of it._
|
|
|
|
|
that is why parallel coders exist.... and why other programmers scream that "thinking" in parallel (stretching their brain) is impossible.... one wants to grow, the other doesn't.
Now if only I could have a direct brain hookup.
|
|
|
|
|
I want one of those interfaces that Hamilton described, wired direct into the brain.....
Never underestimate the power of human stupidity
RAH
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
![Rose | [Rose]](https://www.codeproject.com/script/Forums/Images/rose.gif)
