1. [Topics](/topics/) 2. [Embedded](/embedded-computing) Programmable Vision Accelerator SDK # NVIDIA Programmable Vision Accelerator SDK The NVIDIA Programmable Vision Accelerator (PVA) Software Development Kit (SDK) lets you write, debug, and optimize applications targeting PVA. PVA is a programmable VLIW SIMD DSP accelerator included on NVIDIA DRIVE AGX™, Jetson AGX™, and Jetson NX™ platforms that is optimized for low-latency processing, determinism, and power efficiency. PVA programs can be executed concurrently with the CPU, GPU, and other accelerators as part of a heterogeneous compute pipeline, achieving high system performance and low power consumption for image processing, computer vision, and other sensor data processing tasks. [Download Now](https://docs.nvidia.com/pva/sdk/installation.html)[PVA Solutions on GitHub ](http://github.com/nvidia/pva-solutions)[Developer Forum](https://forums.developer.nvidia.com/c/robotics-edge-computing/jetson-embedded-systems/70) * * * ## Key Features #### Optimize Performance With PVA Offload Leverage PVA to offload pre-processing tasks, freeing up the GPU to boost performance, meet latency budgets, and enhance power and thermal efficiency. #### Develop Your Own Custom PVA Algorithms The software development kit offers tools that let you build and deploy custom algorithms on PVA, accelerating AI applications with greater efficiency. #### Accelerate Developing With Customizable PVA Solutions Jumpstart development with PVA Solutions that provide source-code implementations of common algorithms—fully customizable for quick transition to production. * * * ## How the PVA SDK Works [PVA](https://docs.nvidia.com/pva/sdk/architecture.html)on NVIDIA Jetson and DRIVE AGX platforms offers a low-power solution to tackle compute and efficiency challenges in AI applications. It boosts system performance by offloading non-AI tasks—like feature extraction and object localization in multi-object tracking—to free up GPUs for AI workloads. **The PVA SDK ** provides runtime APIs, tools, and tutorials for the development and deployment of image processing, computer vision and other sensor processing applications. It provides a seamless build-to-deploy framework that enables efficient PVA code development, verification using an emulator, validation through debuggers and profiling utilities, and cross-compilation of code into a binary executable. The cuPVA runtime extends the NVIDIA CUDA™ programming model: PVA programs operate directly on CUDA device pointers without extra copies, and PVA programs can be submitted to CUDA streams, allowing users to assemble complex multi-engine pipelines with low overhead. With extensive documentation, beginner- to expert-level tutorials, and PVA Solutions, you can easily get started developing your own production-ready algorithms using the PVA SDK. **PVA Solutions** provide operators, primitives, and samples powered by the PVA SDK. Source-code availability lets you use them as-is or customize them as needed. PVA Solutions are designed to accelerate application development across a diverse range of domains, including vision, lidar, and radar. Get access to PVA Solutions [here](http://github.com/nvidia/pva-solutions). [Learn More](https://docs.nvidia.com/pva/solutions) ![A chart showing NVIDIA Programmable Vision Accelerator (PVA) SDK structure and how it works](https://developer.download.nvidia.com/images/jetson/jetson-how-it-works.jpg) ### Multimodal sensor processing for physical AI Learn more about centralized radar processing, an example of the diverse sensor processing workloads supported by PVA. [Read the Blog](/blog/how-centralized-radar-processing-on-nvidia-drive-enables-safer-smarter-level-4-autonomy/) ### Real-World Applications Learn how automotive manufacturers like NIO are optimizing their CV pipelines on the DRIVE AGX platform using PVA. [Read the Blog](/blog/optimizing-the-cv-pipeline-in-automotive-vehicle-development-using-the-pva-engine/) ### Boosting AI Performance on Jetson Orin Learn how developers can use multiple compute engines like PVA, GPU, and DLA to boost system performance and efficiency on NVIDIA Jetson Orin™. [Read the Blog](https://developer.nvidia.com/blog/leading-mlperf-inference-v3-1-results-gh200-grace-hopper-superchip-debut/#maximizing_parallelism_on_nvidia_jetson_orin_with_programmable_vision_accelerator) ### Jetson Partner Ecosystem for PVA Access partners like RidgeRun to support your development effort on PVA. [Learn More About RidgeRun](https://developer.ridgerun.com/wiki/index.php/RidgeRun_NVIDIA_PVA_Development) * * * ## Get Started With the PVA SDK Use the right development and learning tools to start developing your algorithms on PVA. ![Step-by-step PVA hardware and SDK tutorials](https://developer.download.nvidia.com/icons/m48-document-support-guide-1.svg) ### Explore and Learn Begin with exploring and learning the PVA hardware and SDK capabilities using the comprehensive documentation and step-by-step tutorials. [See Tutorials](https://docs.nvidia.com/pva/sdk/step-by-step-tutorial.html) ![Develop PVA algorithms locally](https://developer.download.nvidia.com/icons/m48-demo-topics.svg) ### Develop Locally Create PVA algorithms from scratch or start with source samples in PVA Solutions on your local machine using an PVA SDK EMU. [Learn More About EMU](https://docs.nvidia.com/pva/sdk/emu.html) ![Get a Trial License to build and deploy](https://developer.download.nvidia.com/icons/m48-robot-manufacturing.svg) ### Debug, Optimize, Deploy The PVA SDK contains a full set of tools for debugging and optimizing PVA applications. Step through target code and generate detailed performance profiling reports, which can be ingested by AI agents for iterative optimization. * * * ## Case Study: Real-Time Multi-Object Tracking on NVIDIA Jetson Developers on Jetson implement state-of-the-art multi-object tracking pipelines containing processing algorithms with multiple streams using trackers like [NvDCF in NVIDIA DeepStream](/blog/state-of-the-art-real-time-multi-object-trackers-with-nvidia-deepstream-sdk-6-2/). In these applications, it’s critical to achieve real-time performance without compromising accuracy within the energy and thermal constraints. These compute-demanding systems can use the PVA backend to free up the GPU for AI-specific and more critical tasks. ![Multi-object tracking (using nvDCF) deployed on the Jetson platform](https://developer.download.nvidia.com/images/pva/multi-object-trackers.gif) Multi-object tracking (using nvDCF) deployed on the Jetson platform. ![Leveraging PVA to offload an object-tracking algorithm and free up the GPU](https://developer.download.nvidia.com/images/pva/jetson-pie-graph-pva-sdk(1).jpg)Leveraging PVA to offload an object-tracking algorithm and free up the GPU. * * * ## More Resources for NVIDIA Jetson Developers ![](https://developer.download.nvidia.com/icons/m48-computer-vision-industrial-inspection.svg) ### Access PVA on Jetson Using the VPI Library ![](https://developer.download.nvidia.com/icons/m48-misc-question-faq.svg) ### Read the FAQ ![](https://developer.download.nvidia.com/icons/m48-people-group.svg) ### Explore the Community ![](https://developer.download.nvidia.com/icons/m48-robotics-and-humanoids-256px-blk.svg) ### Explore Isaac ROS for Jetson ![](https://developer.download.nvidia.com/icons/m48-orin-256px-blk.svg) ### Get Started With Jetson Using the NVIDIA JetPack™ SDK * * * ## Get started with the PVA SDK for Jetson today. [Download Now](https://docs.nvidia.com/pva/sdk/installation.html)[PVA Solutions on GitHub](http://github.com/nvidia/pva-solutions)