Updates in 2022.1.1

General

  • Filtering kernel launches or profile results based on NVTX domains/ranges now takes registered strings in the payload field into account, if the range name is empty.

  • Added support for the suffix .max_rate for ratio metrics.

Resolved Issues

  • Fixed a crash during the disassembly of the kernel’s SASS code for the Source page.

  • Fixed a crash on exit of the NVIDIA Nsight Compute UI.

  • Fixed a hang during profiling when CPU call stack collection is enabled.

  • Fixed missing to flush UVM buffers before taking memory checkpoints during Range Replay.

  • Fixed tracking of memory during Range Replay, if the CUDA context has any device mapped memory allocations.

  • Fixed the maximum available shared memory sizes in the Occupancy Calculator for NVIDIA Ampere GPUs.

  • Fixed that the shared memory usage of the kernel is incorrectly initialized when opening the Occupancy Calculator from a profile report.