Xilinx/Vitis_Libraries

Health v2 · maintenance only

Adoption not part of the score

1122 stars · 411 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A collection of open-source, performance-optimized accelerated libraries for the AMD Vitis Unified Software Platform, offering out-of-the-box FPGA acceleration for math, linear algebra, DSP, vision, security, and other domains. Libraries are callable from C, C++, Python, and Matlab with minimal code changes to existing host applications.

Use cases

• accelerate math and linear algebra kernels on FPGA hardware
• offload image and vision processing workloads to programmable logic
• run DSP signal processing pipelines on AMD adaptive SoCs
• speed up cryptographic operations with hardware acceleration
• port existing x86 host application code to FPGA accelerators
• build accelerated applications for AMD embedded platforms

When to choose

• you develop for AMD/Xilinx FPGAs or adaptive SoCs with Vitis
• you need pre-optimized hardware acceleration without writing RTL
• your workload matches a covered domain like vision, DSP, or security

When to avoid

• you target GPUs or CPUs rather than AMD FPGA hardware
• you need the deprecated PL libraries like graph, hpc, or data_compression in new releases
• you work on unsupported Alveo platforms such as U200, U250, or U280

Facets

library · maturity active

math image-processing cryptography audio-processing simulation graphics hardware embedded-systems image-processing developer-tools cpp c python embedded fpga xilinx amd hardware-acceleration vitis fpga-accelerated-libraries dsp linear-algebra alveo aie algorithms linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Xilinx/Vitis_Libraries")