Release Notes

See the latest features and updates for this version of NVIDIA Nsight Visual Studio Code Edition.

1. Release Notes 2023.2

While you may already have the prerequisite software on your host and target machines, this release recommends the following versions for a qualified experience:

  • IDE Host : Microsoft Visual Studio Code 1.77.0 (and later)

  • Toolkit :

    • Workstation/L4T : NVIDIA CUDA Toolkit 12.1 Update 1 (and later)

    • DriveOS (QNX) : NVIDIA DriveOS 6.0.6.0 (and later)

  • Driver : NVIDIA 530.30.02 (and later)

1.1. New in NVIDIA Nsight Visual Studio Code Edition 2023.2

  • New Features

    • Added support for remote debugging (via cuda-gdbserver) an application running on L4T.

    • Added support for remote debugging (via cuda-gdbserver) an application running on QNX.

    • Added five autostart tasks which help users easily set up and instantiate remote debugging sessions on L4T and QNX platforms.

  • General Enhancements

    • Added the ability to set a SOLibSearchPath for the debugging session.

    • Added the ability to set environment variables before the cuda-gdb (or cuda-qnx-gdb) is launched.

  • CUDA Debugger
    • See cuda-gdb release notes in the NVIDIA CUDA Toolkit 12.1 Update 1.

2. Release Notes 2023.1

While you may already have the prerequisite software on your host and target machines, this release recommends the following versions for a qualified experience:

  • IDE Host : Microsoft Visual Studio Code 1.75.0 (and later)

  • Toolkit : NVIDIA CUDA Toolkit 12.0 Update 1 (and later)

  • Driver : NVIDIA 525.85.12 (and later)

2.1. New in NVIDIA Nsight Visual Studio Code Edition 2023.1

  • Important Fixes

    • Fixed an issue where Nsight VSCode Edition was not able to set breakpoints and debug in delayed module load scenarios (for example, in CUDA Driver API applications).

    • Added additional logging to Nsight Visual Studio Code edition.

    • Fixed a bug where Nsight Visual Studio Code Edition attempted to read ptrace_scope on systems where it was not present.

  • CUDA Debugger
    • See cuda-gdb release notes in the NVIDIA CUDA Toolkit 12.0 Update 1.

3. Release Notes 2022.2

While you may already have the prerequisite software on your host and target machines, this release recommends the following versions for a qualified experience:

  • IDE Host : Microsoft Visual Studio Code 1.70.0 (and later)

  • Toolkit : NVIDIA CUDA Toolkit 11.7 Update 1 (and later)

  • Driver : NVIDIA 515.65.01 (and later)

3.1. New in NVIDIA Nsight Visual Studio Code Edition 2022.2

  • General Enhancements

    • A fix for truncated process names during attach.

    • Support for when PIDs for attach are entered as a string.

    • New warnings for when cuda-gdb is not found in the path.

    • Improvements to the user experience when stepping out of functions during debugging.

    • Various bug fixes and performance improvements.

  • CUDA Debugger
    • See cuda-gdb release notes in the NVIDIA CUDA Toolkit 11.7 Update 1.

4. Release Notes 2022.1

While you may already have the prerequisite software on your host and target machines, this release recommends the following versions for a qualified experience:

  • IDE Host : Microsoft Visual Studio Code 1.65.0 (and later)

  • Toolkit : NVIDIA CUDA Toolkit 11.6 Update 2 (and later)

  • Driver : NVIDIA 510.47.03 (and later)

4.1. New in NVIDIA Nsight Visual Studio Code Edition 2022.1

  • General

    • Attach to a running CUDA process

      It is now possible to attach to a CUDA application that is already running. It is also possible to detach from the application before letting it run to completion. When attached, all the usual features of the debugger are available to the user, as if the application had been launched from the debugger. This feature is also supported with applications using Dynamic Parallelism.

    • Additional Launch Settings

      • envFile

        Path to a file containing environment variables to set for the debuggee process. Each line is formatted as either:
        • KEY=VALUE
        • unset KEY
        with the latter form used to unset the environment variable.

      • InitCommands

        Provide an array of cuda-gdb commands to run before debugging is started.

      • stopAtEntry

        If true, the debugger should stop at the entry points of the debuggee.

      • cwd

        Set current working directory for debuggee.

    • Security Updates

      We've updated the vscode npm packages to the latest versions to address known vulnerabilities.

  • CUDA Debugger
    • See cuda-gdb release notes in the NVIDIA CUDA Toolkit 11.6 Update 2.

5. Release Notes 2021.1

While you may already have the prerequisite software on your host and target machines, this release recommends the following versions for a qualified experience:

  • IDE Host : Microsoft Visual Studio Code 1.56.0 (and later)

  • Toolkit : NVIDIA CUDA Toolkit 11.3 (and later)

  • Driver : NVIDIA 465.19.01 (and later)

5.1. Introducing NVIDIA Nsight Visual Studio Code Edition 2021.1

We would like to introduce our newest developer tool for CUDA kernel debugging, NVIDIA Nsight™ Visual Studio Code Edition. NVIDIA Nsight™ Visual Studio Code Edition (VSCE) is an application development environment for heterogeneous platforms that brings CUDA® development for GPUs into Microsoft Visual Studio Code. NVIDIA Nsight™ VSCE enables you to build and debug GPU kernels and native CPU code as well as inspect the state of the GPU and memory.

  • Overview

    Benefits

    • Higher Productivity

      Using smart CUDA auto-code completion features improves the overall development experience and allows users to save time and effort when writing code.

    • Interactivity

      Debugging with Nsight Visual Studio Code Edition provides diverse benefits, including code formatting, easy navigation through source code, displaying and interacting with different source files, building executables, and testing.

    • Remote Development Support

      Nsight Visual Studio Code Edition allows developers to implement CUDA code in various cluster environments such as Virtual Machines or remote Docker containers. It also supports code development for Linux systems via the Remote – WSL extension.

    • Free

      As with other Nsight tools from NVIDIA, Nsight Visual Studio Code Edition is offered free of charge. We love it when your code works better and is delivered sooner. Enjoy!

    Key Features

    • CUDA Syntax Highlighting for Code Development and Debugging

      Edit code productively with syntax highlighting and IntelliSense for CUDA code. Auto-completion, go to definition, find references, rename symbols, and more all seamlessly work for kernel functions the same as they do for C++ functions.

    • CUDA Kernel Breakpoint Support and Kernel Execution Control

      Break into a debugging session in CPU or GPU device code using standard breakpoints, including support for conditional breakpoints with expression evaluation. GUI controls allow you to step over, into, or out of statements in the source code, just like normal CPU debugging. Breakpoints are evaluated for every kernel thread and will halt execution when any thread encounters them.

    • GPU and Kernel State Inspection

      Break into the debugger to see all the detailed information at any point in the application with GPU debugging support for register, variable, and call-stack. There is watchlist support to add specific variables of interest for tracking. Additionally, there are focus controls to manually select CUDA block and thread numbers to switch the debugger focus.

    Want to know more?
  • CUDA Debugger

    • See cuda-gdb release notes in the NVIDIA CUDA Toolkit 11.3.

6. Known Issues

The following are known issues in the current release. Also, because Nsight VSCE is based on cuda-gdb, check the cuda-gdb release notes and cuda-gdb known issues in the associated CUDA Toolkit.

6.1. Known Issues as of the 2023.2 Release of the CUDA Debugger

  1. See cuda-gdb release notes in the NVIDIA CUDA Toolkit 12.0 Update 1

  2. Parity with other products. We hope to add this functionality in upcoming releases.

Notices

Notice

NVIDIA® Nsight™ Application Development Environment for Heterogeneous Platforms, Visual Studio Code Edition 2023.1.0 User GuideSend Feedback

THE INFORMATION IN THIS GUIDE AND ALL OTHER INFORMATION CONTAINED IN NVIDIA DOCUMENTATION REFERENCED IN THIS GUIDE IS PROVIDED “AS IS.” NVIDIA MAKES NO WARRANTIES, EXPRESSED, IMPLIED, STATUTORY, OR OTHERWISE WITH RESPECT TO THE INFORMATION FOR THE PRODUCT, AND EXPRESSLY DISCLAIMS ALL IMPLIED WARRANTIES OF NONINFRINGEMENT, MERCHANTABILITY, AND FITNESS FOR A PARTICULAR PURPOSE. Notwithstanding any damages that customer might incur for any reason whatsoever, NVIDIA’s aggregate and cumulative liability towards customer for the product described in this guide shall be limited in accordance with the NVIDIA terms and conditions of sale for the product.

THE NVIDIA PRODUCT DESCRIBED IN THIS GUIDE IS NOT FAULT TOLERANT AND IS NOT DESIGNED, MANUFACTURED OR INTENDED FOR USE IN CONNECTION WITH THE DESIGN, CONSTRUCTION, MAINTENANCE, AND/OR OPERATION OF ANY SYSTEM WHERE THE USE OR A FAILURE OF SUCH SYSTEM COULD RESULT IN A SITUATION THAT THREATENS THE SAFETY OF HUMAN LIFE OR SEVERE PHYSICAL HARM OR PROPERTY DAMAGE (INCLUDING, FOR EXAMPLE, USE IN CONNECTION WITH ANY NUCLEAR, AVIONICS, LIFE SUPPORT OR OTHER LIFE CRITICAL APPLICATION). NVIDIA EXPRESSLY DISCLAIMS ANY EXPRESS OR IMPLIED WARRANTY OF FITNESS FOR SUCH HIGH RISK USES. NVIDIA SHALL NOT BE LIABLE TO CUSTOMER OR ANY THIRD PARTY, IN WHOLE OR IN PART, FOR ANY CLAIMS OR DAMAGES ARISING FROM SUCH HIGH RISK USES.

NVIDIA makes no representation or warranty that the product described in this guide will be suitable for any specified use without further testing or modification. Testing of all parameters of each product is not necessarily performed by NVIDIA. It is customer’s sole responsibility to ensure the product is suitable and fit for the application planned by customer and to do the necessary testing for the application in order to avoid a default of the application or the product. Weaknesses in customer’s product designs may affect the quality and reliability of the NVIDIA product and may result in additional or different conditions and/or requirements beyond those contained in this guide. NVIDIA does not accept any liability related to any default, damage, costs or problem which may be based on or attributable to: (i) the use of the NVIDIA product in any manner that is contrary to this guide, or (ii) customer product designs.

Other than the right for customer to use the information in this guide with the product, no other license, either expressed or implied, is hereby granted by NVIDIA under this guide. Reproduction of information in this guide is permissible only if reproduction is approved by NVIDIA in writing, is reproduced without alteration, and is accompanied by all associated conditions, limitations, and notices.

Trademarks

NVIDIA, the NVIDIA logo, and cuBLAS, CUDA, CUDA-GDB, CUDA-MEMCHECK, cuDNN, cuFFT, cuSPARSE, DIGITS, DGX, DGX-1, DGX Station, NVIDIA DRIVE, NVIDIA DRIVE AGX, NVIDIA DRIVE Software, NVIDIA DRIVE OS, NVIDIA Developer Zone (aka "DevZone"), GRID, Jetson, NVIDIA Jetson Nano, NVIDIA Jetson AGX Xavier, NVIDIA Jetson TX2, NVIDIA Jetson TX2i, NVIDIA Jetson TX1, NVIDIA Jetson TK1, Kepler, NGX, NVIDIA GPU Cloud, Maxwell, Multimedia API, NCCL, NVIDIA Nsight Compute, NVIDIA Nsight Eclipse Edition, NVIDIA Nsight Graphics, NVIDIA Nsight Integration, NVIDIA Nsight Systems, NVIDIA Nsight Visual Studio Edition, NVIDIA Nsight Visual Studio Code Edition, NVLink, nvprof, Pascal, NVIDIA SDK Manager, Tegra, TensorRT, Tesla, Visual Profiler, VisionWorks and Volta are trademarks and/or registered trademarks of NVIDIA Corporation in the United States and other countries. Other company and product names may be trademarks of the respective companies with which they are associated.