plot speed up curve vs number of OpenMP threads - scalability?

Question

I am working on a C++ code which uses OpenMP threads. I have plotted the speedup curve versus the number of OpenMP threads and the theorical curve (if the code was able to be fully parallelized).

here is this plot :

enter image description here

From this picture, can we say this code is not scalable (from a point of view of parallelization) ? i.e the code is not twice more fast with 2 OpenMP threads, four more fast with 4 threads etc ... ?

Thanks

We can say the code doesn't scale. But that's slightly different from saying that it isn't scalable. — High Performance Mark, Oct 22 '14 at 18:23
yes the machine on which I run this code has 16 cores. @HighPerformance : what's the difference between "does not scale" and "is not scalable" ? — , Oct 22 '14 at 19:53
Alexey's answer captures most of the differences that I see between *not scaling* and *not scalable*. — High Performance Mark, Oct 22 '14 at 21:31

score 2 · Answer 1 · answered Oct 22 '14 at 20:05

For the code that barely achieves 2.5x speedup on 16 threads, it is fair to say that it does not scale. However "is not scalable" is often considered a stronger statement. The difference, as I understand it, is that "does not scale" typically refers to a particular implementation and does not imply inherent inability to scale; in other words, maybe you can make it scale if bottlenecks are eliminated. On the other hand, "is not scalable" usually means "you cannot make it scale, at least not without changing the core algorithm". Assuming such meaning, one cannot say "a problem/code/algorithm is not scalable" only looking at a chart.

On an additional note, it's not always reasonable to expect perfect scaling (2x with 2 threads, 4x with 4 threads, etc). A curve that is "close enough" to the ideal scaling might still be considered as showing good scalability; and what "close enough" means may depend on a number of factors. It can be useful to tell / think of parallel efficiency, and not speedup, when scalability is a question. For example, if parallel efficiency is 0.8 (or 80%) and does not drop when the number of threads increase, it could be considered a good scalability. Also, it's possible that some program scales well till a certain number of threads, but remains flat or even falls down if more resources are added.

plot speed up curve vs number of OpenMP threads - scalability?

1 Answers1