It is possible to make a new opencl command to generate reductions?

Question

0.00/5 (No votes)

See more:

To obtain data resume from results like following code:

int k = get_global_id(0);
double result=d[k]*d[k];

It must be used reductions that is very difficult to perform and reduces the code cleariness as said in following link:
http://developer.amd.com/resources/articles-whitepapers/opencl-optimization-case-study-simple-reductions/"]http://developer.amd.com/resources/articles-whitepapers/opencl-optimization-case-study-simple-reductions

So it would be an advantage that the opencl had a command to do it (also over kuda)

What I have tried:

This is the smaller working code I made to make reductions:

if (k==0)
{
    int size=HEIGHT;
    while(size>1)
    {
        barrier(CLK_GLOBAL_MEM_FENCE ); //to give time to all rms[k] of the level be filled
        rms[size]=0.0f;size=(1+size)/2;
        rms[k]+=rms[k+size];
    }
}
barrier(CLK_GLOBAL_MEM_FENCE ); //to give time to all rms[k] be filled
media=rms[0]/(float) WIDTH/(float) HEIGHT;

Posted 31-Aug-17 0:50am

Javier Luis Lopez

Updated 31-Aug-17 0:52am

Richard MacCutchan

Add a Solution

1 solution

Add a Solution

Add your solution here

Treat my content as plain text, not as HTML

Preview 0

…

Existing Members

Sign in to your account

...or Join us

Download, Vote, Comment, Publish.

Your Email
Password
Forgot your password?

Your Email
This email is in use. Do you need your password?
Optional Password

I have read and agree to the Terms of Service and Privacy Policy
Please subscribe me to the CodeProject newsletters

When answering a question please:

Read the question carefully.
Understand that English isn't everyone's first language so be lenient of bad spelling and grammar.
If a question is poorly phrased then either ask for clarification, ignore it, or edit the question and fix the problem. Insults are not welcome.
Don't tell someone to read the manual. Chances are they have and don't get it. Provide an answer or move on to the next question.

Let's work to help developers, not make them feel stupid.

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

tugrulGtx · Answer 1 · 2019-02-10T04:30:00

OpenCL 2.0 already has reductions for thread groups.

C++

work_group_reduce_add()

this command adds all participant threads' elements into single value and broadcasts it to all participant threads.

Its execution time will be comparable to an optimized custom algorithm so it can get automatically upgraded for speed, depending on the hardware vendor's implementation of these functions.

You can say "just workgroup scope is not enough" but whole thing about OpenCL and CUDA is breaking a work into smaller pieces and computing them in parallel. You could use these functions to compute a global sum reduction with good enough performance.