Taiwanese firm Asus IoT announced at last week’s Embedded World in Nuremberg the Tinker V, a single-board computer (SBC) powered by a 64bit Risc-V-based processor, which supports Linux Debian and Yocto operating systems.

Tinker V packs connectivity into a compact Pico-ITX form factor, and pairs longevity with support, making it suitable for diverse IoT and gateway applications.

The Risc-V processor in Tinker V employs the open-source Instruction Set Architecture (ISA), based on risc principles. Compared with traditional x86 and Arm platforms, the benefit of Risc-V is that ISA is open source. Individual developers and enterprises can change, optimise and deploy freely based on the Risc-V architecture, bypassing licensing and copyright fees.

Tinker V is equipped with a Renesas RZ/Five MPU, which incorporates the Risc-V AndesCore AX45MP single-core supporting 1.0GHz operating frequencies.

“We are thrilled to collaborate with Asus and witness how our general-purpose RZ/Five MPU can contribute to the expansion of Risc-V in IoT systems,” said Shigeki Kato, vice president at Renesas. “Asus has been instrumental in integrating our device in the Tinker V SBC.”

Charlie Su, president and CTO of Andes Technology, added: “Andes has collaborated with Asus IoT for the exciting Tinker V product. This powerful single-board computer employs the Andes AX45MP, and I look forward to seeing more devices from innovators in the global industrial market embedded with Andes’ advanced Risc-V processor families.”

The SBC is also engineered with a spread of peripheral connectors for industrial use, including GPIO, Micro-USB, dual Gigabit Ethernet, a pair of Can bus interfaces and two RS232 com ports. It has 1Gbyte of built-in RAM and an optional 16Gbyte eMMC, while supporting operating temperatures from -20 to +60˚C.

With the purchase of Tinker V, customers receive at least five years of support from Asus IoT, and dedicated on-site technical support is available to shorten customer development cycles and accelerate application deployment.

Asus IoT also announced at the show the PE6000G edge AI system that supports up to a 450W GPU for high-throughput, demanding GPU-computing applications. Powered by a 12th-generation Intel Core processor and paired with the Intel R680E chipset, the PE6000G supports up to 450W graphics card power and is ready for the latest PCI Express 5.0 standard, meeting requirements for enabling real-time AI inference at the edge.

Demand for high-performance GPU-acceleration at the edge is increasing to satisfy mission-critical AI applications. Users who require rugged and durable systems to withstand shocks and vibration, plus wide-range operating temperatures to accommodate high GPU computing power, face the dilemma of providing the necessary specifications to meet physical space constraints, along with heat dissipation and power consumption within a rugged mechanical design. The PE6000G is said to strike a balance between all these needs for deployment in various difficult environments.

The high-end, AI-enabled computing platform is suitable for deep learning training and inference at the edge. It supports up to 64Gbyte ECC and non-ECC DDR5 4800 SDRAM, four 2.5in SSDs and one each of M.2 M key (NVMe), M.2 B key (5G NR) and M.2 E key (Wifi 6). It also provides connectivity with a spread of common IO ports, plus support for the latest full-height, full-length graphics cards, enabling real-time inferencing, and transferring AI to the edge.

When processing huge data sets, sudden bursts of current undermine system stability, and processing under extreme temperature or volatile voltages can aggravate the situation. The PE6000G devices combine robust thermal and power options to mitigate the circumstances that could lead to problems or even a system crash, increasing uptime. The thermal design ensures reliable, resilient operation in temperatures from -20 to +60˚C.

The PE6000G can also be used for in-vehicle environments, with 8 to 48V DC-in support, including built-in ignition power control, plus the ability to monitor the power, and a solid mechanical structure. In particular, the chassis design complies with the MIL810H military-grade standard, and is engineered to withstand shocks and vibration.

It can withstand harsh vibrations, making it suitable for applications such as machine vision, AI-powered factory automation, intelligent video analytics (IVA), and more rugged conditions such as roadside units (RSUs) and autonomous vehicles.