Jump to content

Welcome to the new Traders Laboratory! Please bear with us as we finish the migration over the next few days. If you find any issues, want to leave feedback, get in touch with us, or offer suggestions please post to the Support forum here.

  • Welcome Guests

    Welcome. You are currently viewing the forum as a guest which does not give you access to all the great features at Traders Laboratory such as interacting with members, access to all forums, downloading attachments, and eligibility to win free giveaways. Registration is fast, simple and absolutely free. Create a FREE Traders Laboratory account here.

TheNegotiator

Massively Parallel Processing

Recommended Posts

Does anyone know CUDA or CUDA.net? Is anyone integrating it in any way? Are there any good alternatives to it? I think there is ATI Stream maybe.

 

but the market is a sequential event...

Share this post


Link to post
Share on other sites

A single market in real-time is a sequential event yes. What about if you were interested in processing real-time data of all the stocks in the S&P 500 for example? How much quicker might you be able to run backtesting and optimisations if you are clever about how you use the programming? I know that cuda is used already by various financial companies. Why should it be their edge though when all we have to do is pop a couple of gpu's in sli into our own pc's? Not that you could compete at the same level, just on the same playing field.

Share this post


Link to post
Share on other sites
A single market in real-time is a sequential event yes. What about if you were interested in processing real-time data of all the stocks in the S&P 500 for example? How much quicker might you be able to run backtesting and optimisations if you are clever about how you use the programming? I know that cuda is used already by various financial companies. Why should it be their edge though when all we have to do is pop a couple of gpu's in sli into our own pc's? Not that you could compete at the same level, just on the same playing field.

 

backtest is still a sequential event

 

you can use genetic algorithm to simulate optimization,

that speeds up processing without added hardware.

 

 

ps. CUDA is good for vector processing (Look up Google)... ok to make 3D financial models, but not sequential events like trading.

 

One famous charting software (which should remain nameless) had to turn off multi-core CPU and multi-thread processing, because of problem with data integrity. This should give you an idea the practical application of massively parallel processing.

Share this post


Link to post
Share on other sites

Hmm. Interesting. It seems to not be of huge benefit right now. If you were backtesting/optimising, could the time period you were analysing not be broken up into many constituent parts, tested and then reformed to give an output?

 

I am sure there are applications for this, perhaps at a later date as the technology evolves.

Share this post


Link to post
Share on other sites
Hmm. Interesting. It seems to not be of huge benefit right now. If you were backtesting/optimising, could the time period you were analysing not be broken up into many constituent parts, tested and then reformed to give an output?

 

I am sure there are applications for this, perhaps at a later date as the technology evolves.

 

the basic fact is.... you have to buy before you can exit long -- that is an sequential event.

You cannot chop up a sequential event and process the exit long before a buy is executed.

 

 

furthermore, most of the trading logics require something like this:

if price is larger than 50 SMA ... then buy...

if number of loss trades today is smaller than "max_allowed_loss_trade"... then proceed...

 

 

that 50 SMA is a sequential event that must go back 50 bars... you cannot chop up this event for parallel processing.

 

same goes for any conditional decisions that looks back in time.

 

 

Hope these examples helps.

Share this post


Link to post
Share on other sites

Hello guys,

 

I was considering learning CUDA for making a backtester of my own making faster, but the problem with GPGPU is that these technologies are greatly hindered by the RAM -> GPU bandwidth. Hence it is benefitial for backtests where a large part of RAM is moved onto the graphics card once, from where the GPUs can perform the whole backtest. However, with today's cards having at max 3GBs of memory, you can't possibly hold more than 1.5 year of tick data for some less liquid instruments (say TF).

 

Backtesting is a sequential event, however not in the sense discussed here. The fact that SMA50 needs to look back 50 periods is valid, however once you precompute the the indicator for the whole investigated period, you can have each core investigate a different period of the market (searching for entries). The same can be applied for exits. However, it is the synchronization of entries and exits on patterns/SL/PT that cannot be done in parallel. So, in my view, GPGPU in backtesting if worth it only if you have enormously complicated entry patterns that take a lot of time to evaluate, where having 3000 cores evaluating entries at every tick is what makes the backtest fast. In any other setup, the power of GPGPU can't be used for quicker backtesting in my view.

Share this post


Link to post
Share on other sites
Hello guys,

.... However, it is the synchronization of entries and exits on patterns/SL/PT that cannot be done in parallel. ....

 

.......... LOL ..........

 

there is a genius in every clown.

Share this post


Link to post
Share on other sites
the basic fact is.... you have to buy before you can exit long -- that is an sequential event.

You cannot chop up a sequential event and process the exit long before a buy is executed.

 

 

furthermore, most of the trading logics require something like this:

if price is larger than 50 SMA ... then buy...

if number of loss trades today is smaller than "max_allowed_loss_trade"... then proceed...

 

 

that 50 SMA is a sequential event that must go back 50 bars... you cannot chop up this event for parallel processing.

 

same goes for any conditional decisions that looks back in time.

 

 

Hope these examples helps.

 

Unless you are executing the same process for many tickers ;-) From simple view of the world and our actions to it - yes it is not really possible to do stuff in parallel. But when you move a bit into what is really going on - you'll find a lot of things for parallel computing ;)

 

Anyway back to topic - CUDA is usually about heavy C programs. If your are able to do that - than try first to write backtest for your data on your CPU in C... maybe you will find the performance sufficient.... / like me, I was planning to the same. Then I found that by using optimized libraries and 4 CPU cores my speed up was :haha: 250x

Share this post


Link to post
Share on other sites
...Then I found that by using optimized libraries and 4 CPU cores my speed up was :haha: 250x

 

Hello andro, just ouf ot curiosity, what libraries do you use?

Share this post


Link to post
Share on other sites
Hello andro, just ouf ot curiosity, what libraries do you use?

 

Python and Numpy, for code overfilled with "if"s Cython.

 

And just to be precise I'm talking about code "vectorization" and "parallelization". But the same applies to CUDA.

Share this post


Link to post
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.


  • Topics

  • Posts

    • Be careful who you blame.   I can tell you one thing for sure.   Effective traders don’t blame others when things start to go wrong.   You can hang onto your tendency to play the victim, or the martyr… but if you want to achieve in trading, you have to be prepared to take responsibility.   People assign reasons to outcomes, whether based on internal or external factors.   When traders face losses, it's common for them to blame bad luck, poor advice, or other external factors, rather than reflecting on their own personal attributes like arrogance, fear, or greed.   This is a challenging lesson to grasp in your trading journey, but one that holds immense value.   This is called attribution theory. Taking responsibility for your actions is the key to improving your trading skills. Pause and ask yourself - What role did I play in my financial decisions?   After all, you were the one who listened to that source, and decided to act on that trade based on the rumour. Attributing results solely to external circumstances is what is known as having an ‘external locus of control’.   It's a concept coined by psychologist Julian Rotter in 1954. A trader with an external locus of control might say, "I made a profit because the markets are currently favourable."   Instead, strive to develop an "internal locus of control" and take ownership of your actions.   Assume that all trading results are within your realm of responsibility and actively seek ways to improve your own behaviour.   This is the fastest route to enhancing your trading abilities. A trader with an internal locus of control might proudly state, "My equity curve is rising because I am a disciplined trader who faithfully follows my trading plan." Author: Louise Bedford Source: https://www.tradinggame.com.au/
    • SELF IMPROVEMENT.   The whole self-help industry began when Dale Carnegie published How to Win Friends and Influence People in 1936. Then came other classics like Think And Grow Rich by Napoleon Hill, Awaken the Giant Within by Tony Robbins toward the end of the century.   Today, teaching people how to improve themselves is a business. A pure ruthless business where some people sell utter bullshit.   There are broke Instagrammers and YouTubers with literally no solid background teaching men how to be attractive to women, how to begin a start-up, how to become successful — most of these guys speaking nothing more than hollow motivational words and cliche stuff. They waste your time. Some of these people who present themselves as hugely successful also give talks and write books.   There are so many books on financial advice, self-improvement, love, etc and some people actually try to read them. They are a waste of time, mostly.   When you start reading a dozen books on finance you realize that they all say the same stuff.   You are not going to live forever in the learning phase. Don't procrastinate by reading bull-shit or the same good knowledge in 10 books. What we ought to do is choose wisely.   Yes. A good book can change your life, given you do what it asks you to do.   All the books I have named up to now are worthy of reading. Tim Ferriss, Simon Sinek, Robert Greene — these guys are worthy of reading. These guys teach what others don't. Their books are unique and actually, come from relevant and successful people.   When Richard Branson writes a book about entrepreneurship, go read it. Every line in that book is said by one of the greatest entrepreneurs of our time.   When a Chinese millionaire( he claims to be) Youtuber who releases a video titled “Why reading books keeps you broke” and a year later another one “My recommendation of books for grand success” you should be wise to tell him to jump from Victoria Falls.   These self-improvement gurus sell you delusions.   They say they have those little tricks that only they know that if you use, everything in your life will be perfect. Those little tricks. We are just “making of a to-do-list before sleeping” away from becoming the next Bill Gates.   There are no little tricks.   There is no success-mantra.   Self-improvement is a trap for 99% of the people. You can't do that unless you are very, very strong.   If you are looking for easy ways, you will only keep wasting your time forgetting that your time on this planet is limited, as alive humans that is.   Also, I feel that people who claim to read like a book a day or promote it are idiots. You retain nothing. When you do read a good book, you read slow, sometimes a whole paragraph, again and again, dwelling on it, trying to internalize its knowledge. You try to understand. You think. It takes time.   It's better to read a good book 10 times than 1000 stupid ones.   So be choosy. Read from the guys who actually know something, not some wannabe ‘influencers’.   Edit: Think And Grow Rich was written as a result of a project assigned to Napoleon Hill by Andrew Carnegie(the 2nd richest man in recent history). He was asked to study the most successful people on the planet and document which characteristics made them great. He did extensive work in studying hundreds of the most successful people of that time. The result was that little book.   Nowadays some people just study Instagram algorithms and think of themselves as a Dale Carnegie or Anthony Robbins. By Nupur Nishant, Quora Profits from free accurate cryptos signals: https://www.predictmag.com/    
    • there is no avoiding loses to be honest, its just how the market is. you win some and hopefully more, but u do lose some. 
    • $CSCO Cisco Systems stock, nice top of range breakout, from Stocks to Watch at https://stockconsultant.com/?CSCOSEPN Septerna stock watch for a bottom breakout, good upside price gap
    • $CSCO Cisco Systems stock, nice top of range breakout, from Stocks to Watch at https://stockconsultant.com/?CSCOSEPN Septerna stock watch for a bottom breakout, good upside price gap
×
×
  • Create New...

Important Information

By using this site, you agree to our Terms of Use.