AMD Vitis™ unified software platform

The AMD Vitis™ unified software platform is a new tool that combines all aspects of AMD software development into one unified environment. The AMD Vitis™ software platform supports both the AMD Vitis™ embedded software development flow, for Xilinx Software Development Kit (SDK) users looking to move into the next-generation technology, and the AMD Vitis™ application acceleration development flow, for software developers looking to use the latest in Xilinx FPGA-based software acceleration.

Key features

• AI Development Environment: TensorFlow, Caffe, PyTorch
• Core Development Kit: set of developers tools support C, C++ or OpenCL
• Accelerated Libraries: Open-source, out-of-the-box written in C, C++ or Python
• Xilinx Runtime library, host ARM or x86, APIs, kernel drivers, firmware, board utilities

Additional features

• Comprehensive core development kit to seamlessly build accelerated applications
• Rich set of hardware-accelerated open-source libraries optimized for Xilinx hardware platforms
• Plug-in domain-specific development environments enabling development directly in familiar, higher-level frameworks
• A Growing ecosystem of hardware-accelerated partner libraries and pre-built applications 

• Vitis IDE includes:
  • Feature-rich C/C++ code editor and compilation environment
  • Project management
  • Application build configuration and automatic Makefile generation
  • Error navigation
  • An integrated environment for seamless debugging and profiling of embedded targets
  • Source code version control
  • System-level performance analysis
  • Focused special tools to configure FPGA
  • Bootable image creation
  • Flash programming
  • Script-based command-line tool 

• Vitis AI provides:
  • Supports mainstream frameworks and the latest models capable of diverse deep learning tasks.
  • Provides a comprehensive set of pre-optimized models that are ready to deploy on Xilinx® devices.
  • Provides a powerful quantizer that supports model quantization, calibration, and fine-tuning. For advanced users, Xilinx also offers an optional AI optimizer that can prune a model by up to 90%.
  • The AI profiler provides layer by layer analysis to help with bottlenecks.
  • The AI library offers unified high-level C++ and Python APIs for maximum portability from edge to cloud.
  • Customizes efficient and scalable IP cores to meet your needs for many different applications from a throughput, latency, and power perspective.

Applications

• Aerospace & defense
• Radar & EW
• Wireless & wired communications
• High performance computing
• Medical
• Smart city - vision system AI

Upcoming seminars

FPGA Conference, September 30th, Stanislaw Klinke: Introduction to Vitis AI – unified development environment for AI inference.