Why does the performance of my #pragma-unrolled loop degrade if the trip count is not constant?

loops cuda unroll
small_potato picture small_potato · Mar 31, 2011 · Viewed 9.4k times · Source

I have following code using loop unrolling:

#pragma unroll
for (int i=0;i<n;i++)
{
    ....
}

here if n is a defined constant, everything works fine. However, if n is a variable, performance dramatically reduced. I noticed roughly 3 times the instructions are issued and executed. I guess I am looking for a way to do loop unrolling at run time, may be that's just not feasible.

Answer

talonmies picture talonmies · Mar 31, 2011

CUDA is a compiled language. Loop unrolling is a compiler optimization. Runtime loop unrolling would imply some sort of runtime interpreter or dynamic code generation. That clearly can't happen.

It would make sense that the unrolled case executes as many or more instructions than the naïve loop, because the compiler will replace the loop with repetitions of the loop contents. If the unrolled case executes less instructions, that would imply that the compiler is pre-calculating some or all of the loop contents and replacing code with a constant result.

It all depends on what is contained in the loop.

Related questions

For-each over an array in JavaScript

How can I loop through all the entries in an array using JavaScript? I thought it was something like this: forEach(instance in theArray) Where theArray is my array, but this seems to be incorrect.

Read More
Loop through an array in JavaScript

In Java you can use a for loop to traverse objects in an array as follows: String[] myStringArray = {"Hello", "World"}; for (String s : myStringArray) { // Do something } Can you do the same in JavaScript?

Read More
Iterate through a HashMap

What's the best way to iterate over the items in a HashMap?

Read More