Known Issues

• Kernels launched from a subprocess which is created within the annotated region will not be profiled.

• Kernels launched from a different thread to that which creates the annotated region will not be profiled. nsight.annotate marks the region with a thread-local NVTX push/pop range, so kernels launched from any other thread fall outside the range that ncu targets.

• For the @nsight.analyze.kernel’s replay_mode="range" option, only a subset of CUDA APIs are supported within the annotated range. If an unsupported API call is detected, an error will be reported. For details on supported APIs, refer to the NVIDIA Nsight Compute Profiling Guide. In such cases, you can either switch to replay_mode="kernel" or modify the code to exclude the unsupported API from the annotated range.

• Nested annotations (using nsight.annotate within another nsight.annotate context) are not supported. nsight-python errors out when nested annotations are used.

• *args and **kwargs in decorated function signatures are tolerated but ignored — they will always be empty and will not appear in the profiling output.

• Calling @nsight.analyze.kernel-decorated functions from multiple threads is not supported, whether the threads run sequentially or concurrently.