Welcome to NexusFi: the best trading community on the planet, with over 150,000 members Sign Up Now for Free
Genuine reviews from real traders, not fake reviews from stealth vendors
Quality education from leading professional traders
We are a friendly, helpful, and positive community
We do not tolerate rude behavior, trolling, or vendors advertising in posts
We are here to help, just let us know what you need
You'll need to register in order to view the content of the threads and start contributing to our community. It's free for basic access, or support us by becoming an Elite Member -- see if you qualify for a discount below.
-- Big Mike, Site Administrator
(If you already have an account, login at the top of the page)
If you are a "computer guy", you know that CUDA is likely "the way of the future". GPU's are so much more powerful at number crunching than CPU's it is mind numbing. CUDA allows applications to use the GPU for math computations instead of drawing video games, which is directly relevant to financial applications like backtest optimization.
If you are a fan of this idea, please vote up the CUDA idea even though on MultiCharts forum, I'd like them to reconsider their option to not implement it.
The first main stream trading application released with this support will have a clear advantage over other platforms. A couple of top of the line GPU's can be purchased for under $1,000. CUDA can deliver around 5-20x the performance boost over just a high-end CPU alone.
This image is out of date, todays high end GPU's are even faster.
I don't know much about MultiCharts, but to benefit from CUDA performance, the IO of moving data to and from the GPU card needs to be eliminated (very slow operation compared to processing time). So data needs to be moved to the card, processed and the results returned to the CPU bus.
There needs to be some parallel computations that are possible as well, so it can't be a sequential time series only being processed. But if there are inner loops or double inner loops it is likely CUDA will dramatically improve the execution.