Antmicro Ltd.

Over the years Antmicro has been at the forefront of the FPGA SoC technology, designing effective high-speed signal platforms for edge computing, especially in computer/machine vision multi-camera applications, which - coupled with our experience in providing end-to-end services of writing FPGA IP, AI/camera processing, BSPs and drivers (Linux, Zephyr) - makes us uniquely positioned to leverage open FPGA development workflows tools and languages such as Chisel and Migen. 

Antmicro’s Zynq Video Board is an example of a smart piece of open hardware for image processing with an open FPGA MIPI CSI-2 IP core for grabbing video streams. Moreover, at the recent RISC-V Summit we unveiled our rapid turnaround chiplet-based ASIC series, GEM. Utilizing zGlue’s smart ASIC SiP development tech, Antmicro engineers are now capable of creating full-blown custom hardware within a practical, quick-prototyping / quick-tape-out process, employing all the benefits of modern open digital design.

Thanks to innovative edge computing platforms (be it GPGPU-, FPGA- or heterogeneous CPU-based) and custom ASIC accelerators, Deep Learning has been making its way to new use cases, with Antmicro’s in-depth competence spanning all of these areas.

At EW 2020 we will be showcasing exciting edge AI demonstrators such as a modular high-speed industrial stereovision camera platform with AI-supported, real-time object tracking, as well as the AI drone identification and tracking module developed by Antmicro for the highly successful SkyWall Auto - the world’s first automatic counter-drone system, and a Deep Learning application running on Antmicro’s open Jetson Nano baseboard with Allied Vision’s modular ISP cameras from the acclaimed Alvium series.

Be sure to ask us about our smart cloud CI/CD solutions and the Renode Cloud Environment, which allow us to perform reproducible builds, mitigate the black box effect and ensure traceability of the software stack. At this year’s show, see how we use our custom CI setups deployed in RCE with a broad list of demonstrator tests. Renode’s capability to co-simulate SoC and FPGA components with Verilator, or to connect blocks running in physical eFPGAs to enable a “divide-and-conquer” HW/SW co-design philosophy, resonates perfectly with the hybrid SoC FPGA nature of the EOS S3 platform by QuickLogic we’ll also be showcasing this year.

To deliver high-class computer vision systems, Antmicro often combines its expertise in the FPGA SoC and CPU/GPU areas. We have provided solutions to numerous customers seeking excellence in high-speed video processing through work with the latest technologies, such as the NVIDIA Jetson family of edge computing platforms (TX2 / Xavier / Xavier NX / Nano). 

At EW 2020 we will be showcasing exciting CV/MV demonstrators such as a modular high-speed industrial stereovision camera platform with AI-supported, real-time object tracking, as well as the AI drone identification and tracking module developed by Antmicro for the highly successful SkyWall Auto - the world’s first automatic counter-drone system, and a Deep Learning application running on Antmicro’s open Jetson Nano baseboard with Allied Vision’s modular ISP cameras from the acclaimed Alvium series.

Antmicro’s customers leverage our vision and methodologies based on the firm belief that open source is changing the world of technology. Our work approach makes use and promotes the open sourcing of vital tools for more accessible, transparent and easily modifiable solutions, with the lack of vendor lock-in giving us and our customers the freedom to develop based on the best technologies available. This year at EW, see how we’ve been sharing this approach with our customers and partners: by developing open Jetson TX2 (and Jetson Nano) drivers for Allied Vision’s Alvium camera series, or the Antmicro-designed Quick Feather development board for the EOS S3 by QuickLogic with a port of the likewise open Zephyr RTOS, and more.

Renode is Antmicro’s own open source development framework which accelerates IoT and embedded systems development by simulating physical hardware systems, including the CPU, peripherals, sensors, environment and wired or wireless medium between nodes. It lets you run, debug and test unmodified embedded software on your PC - from bare System-on-Chips, through complete devices, to multi-node systems. 

Renode and the practices of Continuous Integration / Continuous Development available in the Renode Cloud Environment is what helps us achieve high quality and effective scalability in our technologies, as it allows us to perform reproducible builds, mitigate the black box effect and ensure traceability of the software stack. Check out our recently open sourced Renode support for QuickLogic’s EOS S3, which offers developers a more efficient hardware/software co-design approach. Moreover, Antmicro’s Renode and Google’s TensorFlow Lite teams have been collaborating to use the Renode simulator for demonstration and testing of Google’s Machine Learning framework, and to bring it to new frontiers with real industrial use cases. Renode is a new and open work methodology already in use by Google, Microchip, Intel, Zephyr, QuickLogic, Dover Microsystems and other Antmicro partners, most notably in the RISC-V ecosystem.