I can see a roofline using nsight compute, but what can I do when I see this?
What does it indicate? The program is compute bound ? So I should optimize my compute or what?
Really confused about this, Thank you!
Take a look at this blog that has some detailed information on what the roofline analysis is and how it can be used in Nsight Compute Accelerating HPC Applications with NVIDIA Nsight Compute Roofline Analysis | NVIDIA Technical Blog
I’ll try that, thank you.