Vitis Unified Software Platform
For Hardware & Software Developers
Vitis Overview
Unlock a New Design Experience
True Software Programmability
Access AMD adaptive computing technology within familiar developer workflows and environments with no RTL knowledge
Rich Set of Libraries
Chose from many open-source, performance-optimized libraries that offer out-of-the-box acceleration with minimal to zero-code changes to your existing applications
Unified Design Methodology
Experience single design methodology and programming model for deploying accelerated applications on all AMD platforms including Alveo™ accelerator cards, embedded platforms or FPGA instances in the cloud
Build Advanced, Performance-Optimized System Designs
Discover the benefits of AMD Vitis™ unified software platform—a comprehensive development environment for hardware and software developers to design, simulate, and implement complex systems using AMD adaptive SoCs and FPGAs.
Vitis Unified Software Platform
No Hardware Knowledge Needed
Unified design methodology for all AMD platforms
- Single design methodology and programming model for deploying accelerated applications on all AMD platforms
- Develop and deploy your accelerated applications on different hardware platforms with a simple makefile change.
- Including Alveo accelerator cards, embedded platforms, or FPGA instances in the cloud
Familiar software development experience
- Leverage integration or develop accelerated applications with high-level frameworks and languages including Tensorflow and Caffe, C, C++ or Python
Vitis Video Analytics SDK
Build and Deploy AI-Based Intelligent Video Analytics Applications
Turning Vision into Insight
Vitis Video Analytics SDK consists of several hardware accelerator plug-ins that use various accelerators such as Video Encoder, Decoder, Multiscaler (for resize and color space conversion), Deep Learning Processing Unit (DPU) for AI inference etc. By performing all the compute-heavy operations in dedicated accelerators, it can achieve the highest performance for video analytics applications.
Highly optimized GStreamer plug-in
Vitis Video provides a framework in the form of generic Infrastructure plugins, software acceleration libraries, and a simplified interface for users to develop their own acceleration library to control a custom hardware accelerator. With this framework, users can easily integrate their custom accelerators/kernels into the Vitis Video Analytics SDK.
Vitis AI
Implement Efficient AI Inference Applications from Familiar Tools and Frameworks
Powerful, Adaptable,and Easy-to-Use
- Supports mainstream frameworks and neural networks capable of diverse applications
- Provides powerful AI Quantizer, Optimizer and Compiler to realize significant processing efficiency optimization
- High-level C++/Python AI library APIs for fast AI implementation from edge, through on-premise, to cloud
- Highly adaptable DPU overlays to meet the demands of lower latency, higher throughput, or better scalability
Software Tools Portfolio
Vitis™ Software Platform
A comprehensive development environment that enables all developers to leverage the power of AMD adaptive platforms for edge to cloud deployments while continuing to work at an application level and develop in familiar programming languages like C and C++.
Languages: C, C++, Python
Standalone Software: Yes
Hardware Required: Yes
Required Downloads: Vitis Accelerated Libraries and XRT
Additional Compatible Software: Vitis Video Analytics SDK and Vitis AI
Vitis™ Video Analytics SDK
Complete software stack to build AI-powered intelligent video analytics solutions on AMD platforms that builds on top of Xilinx Run Time (XRT), Vitis, and Vitis AI and abstracts these complex interfaces, making it easier for developers to build video analytics applications.
Frameworks: GStreamer
Standalone Software: Yes
Required Download: Vitis Video Analytics SDK
Hardware Required: Yes
Additional Compatible Software: Vitis Unified Software Platform and Vitis AI
Developer Types: AI Developers
Frameworks: PyTorch, Caffe, Tensorflow
Standalone Software: Yes
Hardware Required: Yes
Required Download: Vitis AI
Additional Compatible Software: Vitis Video Analytics SDK and Vitis Unified Software Platform
Embedded Software
AMD embedded tools provide all the components needed to create an embedded system using AMD Zynq™ SoC and Zynq™ UltraScale+™ MPSoC devices, MicroBlaze™ processor cores, and Arm® Cortex® M1/M3 microcontrollers including open-source operating systems and bare metal drivers, multiple runtimes and Multi-OS environments, sophisticated Integrated Development Environments, and compilers, debuggers, and profiling tools.
Languages: C, C++, Python
Standalone Software: No
Hardware Required: Yes
Required Downloads: XRT and Vitis Core Development Kit
Additional Compatible Software: Vitis Video Analytics SDK and Vitis AI
Legacy Tools (Discontinued)
Starting in 2019.2, AMD SDK, SDSoC™ and SDAccel™ development environments were unified into an all-in-one Vitis™ unified software platform for application acceleration and embedded software development.
If you need the legacy tools that are discontinued, please access here:
Resources
Join the Developer Program
Joining the Developer Program gives you access to the resources necessary to build your applications successfully on all platforms. Benefits of your membership include access to free training courses on tools and platforms, opportunities to showcase your projects and articles on the Developer site, and much more!
Integrate into familiar developer environments and workflows with Vitis
Vitis Unified Software Platform
The Vitis™ unified software platform enables the development of embedded software and accelerated applications on AMD adaptive SoCs and FPGAs. It provides a unified programming model for accelerating edge, cloud, and hybrid computing applications.
Leverage integration with high-level frameworks, develop in C, C++, or Python using accelerated libraries or use RTL-based accelerators and low-level runtime APIs for more fine-grained control over implementation — Choose the level of abstraction you need.