Introducing NVIDIA® Nsight™ Visual Studio Code Edition

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.

Benefits

  • Higher Productivity
    Using smart CUDA auto-code completion features improves the overall development experience and enables 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 enables 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 streaming multiprocessor (SM), warp, and lane numbers to switch the debugger focus.

Want to know more?

1 Like

This sounds great! Do you know when it will appear in the extensions marketplace for VS Code?

1 Like

It is amazing. So, when it will be released?

Is it possible to get an early extension prior to marketplace?

Just want to know, when is it available

wow, I can’t wait for it. Please release soon! could I get an early version of it? I need it for a competition uses CUDA programming.

Thanks for your working! Please release soon. Cannot wait.