Can't execute kernel function in CUDA

Question

1.00/5 (1 vote)

See more:

Hello,

I have several kernel functions in my program. Some kernel functions do execute, but some others do not. Can't get what is the problem. The program upon compilation do not give any error, neither compilation error nor any runtime error. Please help.

One kernel function is in a nested loop, like below:

C++

for(init; condition; re-initialization)
{
     ----;
     ----;
     ----;
    for(init; condition; re-initialization)
    {
       Kernel1<<<blocks, threads>>>(arguments);
    }
}

Kernel2<<<blocks, threads>>>(arguments);
----;
----;
----;
Kernel3<<<blocks, threads>>>(arguments);

If I put the kernel function, Kernel1, inside the nested loop as shown above, the rest of the kernel functions also execute, but if I put this kernel function outside the loop, since the kernel function should not be put inside any loop, the rest do not get executed at all.

Will it help in understanding? Once again, thanks in advance.

Posted 6-Nov-14 1:40am

SanjaySMK

Updated 10-Nov-14 21:11pm

Suraj Sahoo | Coding Passion

v6

Add a Solution

Comments

Richard MacCutchan 6-Nov-14 8:49am

How can we help when we have no idea how your code works? Please edit your question and show the parts of your code that does not work, and explain exactly what happens.

KarstenK 6-Nov-14 14:15pm

I guess that the declaration of these functions have subtile bugs. but without code it is only guessing ...

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)

Joren Heit · Accepted Answer · 2014-11-26T22:35:00

Often when this happens, it is due to your kernel launch parameters. When debugging, print these values to check if they are within the bounds of your hardware.

A second way of debugging is by using the cudaGetLastError() function (documentation). It returns a cudaError_t, which you can pass to cudaGetErrorString() (documentation).

E.g.

C++

cout << "Blocks: " << blocks << ", Threads: " << threads << '\n';
kernel<<< blocks, threads >>>(params);
cout << "Error: " << cudaGetErrorString(cudaGetLastError()) << '\n';