PyTorch Developer Mailing List
Using Nsight Systems to profile GPU workload
hardware-backends
NVIDIA CUDA
pyotr777
May 16, 2022, 6:56am
6
If I build PyTorch from sources, then there is cuDNN info in nsys traces.
show post in topic
Related topics
Topic
Replies
Views
Activity
How profiling Pytorch Using Nsight Compute?
NVIDIA CUDA
2
403
October 16, 2024
[RFC] Performance profiling at scale with detailed NVTX annotations
compiler
0
337
July 10, 2024
Depthwise conv2d: An NNC Case Study
compiler
0
1428
April 7, 2021
GPU Overheads and Fused Strassen
performance
0
2179
February 13, 2021
Anomalous time gaps observed when using CUDA kernels in PyTorch
1
165
August 5, 2024