NVIDIA PerfKit has now been replaced with an updated C++ API and a new name - NVIDIA® Nsight™ Perf SDK. You can find more information about it and download from here. The new Nsight™ Perf SDK supports NVIDIA GPU Architectures from Volta through the latest Ampere chips. The API is easy to use and integrate into your application. Tegra versions will be coming in late 2021/early 2022.
NVIDIA PerfKit is a comprehensive suite of performance tools to help debug and profile OpenGL and Direct3D applications.
It gives you access to low-level performance counters inside the driver and hardware counters inside the GPU itself. The counters can be used to determine exactly how your application is using the GPU, identify performance issues, and confirm that performance problems have been resolved.
NVIDIA PerfKit is available separately for 3 target platforms. PC packages includes support for 32-bit and 64-bit Windows 10, Windows 8, Windows 7, and Vista platforms. Android packages includes support for NVIDIA Tegra TK1 and TX1 devices running Android OS. Linux for Tegra support is available under NVIDIA PerfKit (L4T) targeting the NVIDIA Jetson Embedded Platform.
The performance counters are available directly in your OpenGL and DirectX applications, giving you low-latency access to PerfKit performance counters directly from the driver.
To access older versions of NVIDIA PerfKit, please visit NVIDIA GameWorks™ Download Center.
Please see PerfKit End User License Agreement for license details.