New-Tech Europe Magazine | Q2 2022

Latest News task, and since the value-added features are central to the development, we developed ImperasDV to be adaptable for all implementations to allows our customers and users to verify state-of-the-art designs independently. NSITEXE are pioneers in developing advanced RISC-V vector accelerators for AI, and we are pleased to see the Imperas technology and ImperasDV supporting the quality requirements for automotive applications.” Availability ImperasDV is available now, with more details available at Imperas.com/ImperasDV. The ImperasDV RISC-V processor verification technology is already in active use with many leading customers, some of which have working silicon prototypes and are now working on 2nd generation designs. These customers, partners and users span the breadth of RISC-V adopters from open source to commercial; research to industrial; microcontrollers to high performance computing. A select sample of these include – Codasip, EM Microelectronics (Swatch), NSITEXE (Denso), Nvidia Networking (Mellanox), OpenHW Group, MIPS Technology, Seagate Technology,

Silicon Labs, and Valtrix Systems, plus many others yet to be made public. The open standard RVVI (RISC-V Verification Interface) provides the essential guidelines for the infrastructure around the processor testbench that supports the growing ecosystem of Verification IP for RISC-V processor verification. The new RVVI open standard and methodology, is based on an open specification (https://github.com/riscv- verification/RVVI) and can be adapted to any configuration permitted within the RISC-V specifications. In adopting the RVVI standard, developers can leverage all the common components off the shelf and explore additional options with reusable Verification IP across projects. The free riscvOVPsimPlus package, including the Imperas RISC-V Reference Model, sample test suites and instruction coverage analysis, including updates for the latest RISC-V ratified specifications is also available on OVPworld at www. ovpworld.org/riscvOVPsimPlus.

Lanner Electronics Launches Falcon H8 PCIe AI Accelerator Card, Powered by Hailo-8™AI Processors

the edge, including intelligent transport systems (ITS), smart cities, smart retail, and Industry 4.0. The Falcon H8 is one of the most cost-efficient PCIe AI accelerator cards on the market, with a low power consumption and record high of up to 156 tera operations per second (TOPS) to allow high- end deep learning applications on edge servers. Lanner’s Falcon H8 modular, PCIe FHHL form factor provides a compact and easily deployable

Lanner Electronics & Hailo collaborate on one of the most cost-efficient PCIe accelerator cards on the market, with record high tera operations per second (TOPS), enabling high-end deep learning applications on edge servers Lanner Electronics, a global leader in the design and manufacturing of intelligent edge computing appliances, announced its first Hailo-8™AI- powered PCIe accelerator card,

NXP Brings Dolby Atmos® and DTS:X® to the Masses with its New Immersiv3D Audio Solution credit: Lanner Electronics

solution for engineers looking to offload CPU loading for low-latency deep learning inference. With high-density AI processors, the Falcon H8 accommodates 4, 5, or 6 Hailo-8™ AI processors, offering a modular, cost-

the Falcon H8. Lanner Electronics collaborated with leading AI (Artificial Intelligence) chipmaker Hailo to design the Falcon H8, enabling scalable and powerful intelligent video analytics applications for multiple industries operating at

New-Tech Magazine Europe l 11