Originally published at: https://developer.nvidia.com/blog/sc20-demos-new-nsight-systems-and-nsight-compute-demos/
NVIDIA Nsight Compute: Roofline and NVIDIA Ampere GPU Architecture Analysis This demo shows the latest CUDA kernel analysis capabilities in NVIDIA Nsight Compute, including the popular Roofline Analysis Method and a new feature for the NVIDIA Ampere GPU Architecture. Specifically, we’ll demonstrate profiling the hardware-supported asynchronous data copy feature, which can boost the performance of…