AI Starter Kits
AI Starter Kits is a comprehensive set of FPGA-based prototyping tools including optimized Open Neural Network Compiler (ONNC), drivers (KMD/UMD), Linux kernel, virtual platform, FPGA netlist and RTL code (NVDLA). Using AI Starter Kits, you will benefit from an optimal design experience with our extensive suite of advanced design tools, a well-tested open source solution, and a fast-time-to-market prototyping FPGA board, all in one platform. AI Starter Kits optimize your design process and ensures that your software runs and exploits the full power of the underlying AI chips. Skymizer aims at providing a unique solution tailored to your needs to help you build a strong hardware/software co-design team and efficiently save your time ahead of AI chip fabrication.
Full-fledged NVDLA compiler
The NVDLA runtime environment includes software to run compiled neural network layers in a loadable file. Drivers (UMD/KMD) are released with source code and exists as defined API, but official compiler is released in binary form and only limited operators and hardware configuration are supported. By diving deeply into NVDLA RTL code, we successfully make ONNC supports complex operators and multiple hardware configurations. Now, ONNC in AI Starter Kits is a full-fledged NVDLA compiler. It supports more ONNX models; supports more hardware configurations; and produces high performance loadable files.
More than a compiler - SDK and BSP
Compiler experts make not only compiler but a chain of tools. AI Starter Kits includes a series tools for customization of NVDLA runtime environment.
Software Development Kits
- Open Nerual Network Compiler (ONNC v1.1)
- Cross Compilers GCC 8.3.0 for RISC-V and 7.3.1 for ARM Cortex-A
- ONNX model checker
- ONNX model reader
- GreenSocs virtual platform for ARM and RISC-V
- Lander BSP generator r1.2
Board Support Packages
- Linux distribution (buildroot and busybear)
- Bug-fixed user mode driver
- Bug-fixed kernel mode driver
- Slides show example program
- Streaming example program
Strong FPGA ecosystem
AI Starter Kits provides various platforms for different types of developers.
GreenSocs-based virtual platform
- supports ARM Cortex-A processors (aarch64)
- supports RISC-V processors (riscv64)
- supports various NVDLA hardware configuration (nv_small, nv_full)
Rich FPGA supports
- Xilinx ZCU102 for nv_small 64MACs
- Xilinx ZCU104 for nv_small 64MACs
- S2C KU115 for nv_small 1024MACs
- S2C VU440 for nv_small 2048MACs
Contact for More Information
Email: [email protected] | Tel: +886 2 8797 8337