We are proud to announce the final release of NVIDIA Parallel Nsight™ 2.1. This release adds a number of new features to enhance debugging and profiling capabilities, including support for the new CUDA Toolkit 4.1 available here.

(login required)

To download Parallel Nsight 2.1, you must be signed up for the Parallel Nsight Registered Developer Program. Signing up and access is free of charge. Please follow the instructions here for more information.

Parallel Nsight 2.1 requires NVIDIA Display Driver Release 286.16 or newer, available on the same download site.

  • New Frame Timings page allows DirectX developers to get to the exact measured draw call timings in isolation or in concurrent execution of the GPU.
  • Traced workloads can now navigate the dependencies and call stack to allow the developer to follow through GPU workloads, corresponding API calls and host code that was the cause of the activity.
  • The new CUDA information tool window gives detailed information about the state of CUDA launches in the user’s application. Users can filter and find detailed information about exceptions, asserts, breakpoints, MMU faults, and easily switch to a specific warp of interest to debug problems.
  • CUDA warp watch visualizes variables and expressions across an entire CUDA warp.
  • CUDA profiler now analyzes kernel memory activities, execution stalls and instruction throughput.
  • Multiple bug fixes and stability improvements

For a complete list of the new exciting 2.1 features, go here.

All current and future releases of Parallel Nsight will be distributed from the new Parallel Nsight Registered Developer Program (login required).