Core i7-3930K vs Xeon E5-2630 For Long-duration Financial Calculations

Quote from scriabinop23:

Sounds like you could do the entire process from within matlab (excel not necessary) and dramatically speed things up with the parallel computing toolbox from within matlab (enabling you to use parfor loops etc).

having your data on a SQL server (on a local SSD drive or array of SSDs) instead of from within excel would be a big improvement for you as well. And matlab is great for querying SQL... [you could do SQL express 2012 free edition even]

I'd worry more about disk/etc than processor here....

yes thank you for the suggestion on how to speed this up - right now I am setup with Excel doing he model and Matlab the charts.....could be much faster with c++ for sure....do not have time to transform all the models there right now...maybe later....
 
Quote from Mr_You:

Yes I'll also add that if you consider moving away from Excel that you might look into R and RStudio. They're my preferred tool for analyzing trading results saved in csv format.

RStudio has a web interface option will allows you to easily run it from a Linux server.

yes thank you...but I am limited in time right now.....will stick with excel for now....maybe later...how long do you think ti mitgh take to transform a 300 mb excel model file with around 500,000 cells with formulas?
 
Quote from braincell:

I have 2600K, 2700K and 3930K CPUs, all running 24/7 for months. For stability you need a good motherboard and PSU, as well as memory. So far I've found that in my case the 2700K is outperforming the 3930K. This is because of the kinds of instructions that the compiled software is using are more suitable for the 2700K. There are differenes in what compiler was used and what kind of processing it, how parallel etc, so it's not such a straight answer as to what is the best. Also, if you use 32bit applications on a 64bit system and the software is using many Windows API calls, the 64bit system will be slower than if you installed 32bit Windows on it. As far as stability is concerned, you can create a 99.9999% stable top notch rig with a 2700K for ~$1200 if you know where to shop and you build your own PC. Don't worry about stability of the CPU, you should worry about how reliable your software is to automate the usage of Excel which imo will be your biggest problem. It is slow, and you can probably get 20 times the performance with some custom bit of C# software. Just my 2c.
7

yes thank you for pointing me in the direciotnof the excel...yes I knwo it has some issues that I will need ot del with the fastest and most stable machine as possible.....do you thinkt hat XEON E3 1275 V2 with 4 cores at 3,5 ghZ CAN PULL OF 4 VIRTUAL MACHINES EACH RUNNING EXCEL 2007 AND MATLAB?
 
Quote from dima777:

do you thinkt hat XEON E3 1275 V2 with 4 cores at 3,5 ghZ CAN PULL OF 4 VIRTUAL MACHINES EACH RUNNING EXCEL 2007 AND MATLAB?

Why would you run 4 VMs? You should be able to use each of the 4 cores running 4 instances on a single machine. You'd just have to figure out the details. The VM might slow you down also, and you might need more memory. I'm sure there's a way to not use VMs if you put your mind to it, but I'd have to know the details. To answer your question, yes, it can pull it off, if you do it properly.
 
Quote from dima777:

yes thank you...but I am limited in time right now.....will stick with excel for now....maybe later...how long do you think ti mitgh take to transform a 300 mb excel model file with around 500,000 cells with formulas?

I'm not sure. I imagine if you exported the file to csv that you could find out in a few hours. R / RStudio is pretty easy to install and use.

Here is a very basic R/RStudio quickstart guide in the works.
 
Quote from braincell:

Why would you run 4 VMs? You should be able to use each of the 4 cores running 4 instances on a single machine. You'd just have to figure out the details. The VM might slow you down also, and you might need more memory. I'm sure there's a way to not use VMs if you put your mind to it, but I'd have to know the details. To answer your question, yes, it can pull it off, if you do it properly.

thank you for your reply...I need 4 VMs to each analyse its own time frame of the 50 currency pairs....the analysis will be performed identically for each time frame of the 50 currency pairs....so to analyse it all in parallel I am thinking of breaking the whole pipeline into 4 parallel sub pipelines each working on its own time-frame....what do you think?
 
Quote from halfwaythere:

2500k here...

hardly ever go above 50% utilization w/ 8 monitors

beast system though.

do yourself a favor and get a SSD while you're at it.

yes thanks...I will surely get the SSD....HAVE YOU HEARD OF THE RAMDISK? it appears to beat the SSD in some ways?
 
Quote from Runningbear:

Im with the other posters here. Excel is your weak link, not the hardware. Do it all in Matlab.

thank you for your reply.....I will think more about adding the VMS - with excel 2003 each running in one WinXP VM - this can be really fast to parallelize....I will combine the analytics from the separate VMS in the host machine.....the individual analysis could be done in excel 2003 but aggregating analysis and post-production woudl be done in excel 2010 which allows much more than the 2 gb of memory...software errors are likely but mos dependent on excel and matlab and vmware...I will test this setup and if it is suitable for daily work will stick with it - if no - will do all in sequence on the host machine...I am stuck with excel for now as taking it to an executable code would add a year to the project....do you think EXCEL 2010 on 4 cores will run faster than EXCEL 2003 on one core?
 
Back
Top