Author: kissdev

Intel Movidius Myriad X is a cutting-edge Vision Processing Unit (VPU) designed specifically for artificial intelligence (AI) inference, particularly in computer vision applications. It represents the third generation of Intel’s Movidius VPUs and introduces several advanced features that enhance its performance and capabilities. Key Features Neural Compute Engine: The Myriad X is notable for its integrated Neural Compute Engine, a dedicated hardware accelerator that significantly boosts deep learning inference performance. This allows the VPU to handle complex neural network tasks efficiently. High Throughput: With the capability to achieve over one trillion operations per second, the Myriad X is optimized for…

The OpenMV Cam H7 is a compact and powerful camera module designed for machine vision projects, featuring built-in AI capabilities. It is equipped with an ARM Cortex-M7 processor running at 480 MHz, along with 1MB of SRAM and 2MB of flash memory, making it suitable for various applications in robotics and computer vision. Key Features Programming: The OpenMV Cam H7 can be programmed using MicroPython, which simplifies the implementation of machine vision algorithms. This allows developers to focus on high-level data structures and complex outputs without delving into lower-level programming languages like C/C++. Image Processing: The camera supports multiple image…

The Arm Ethos-N77 is a highly efficient Neural Processing Unit (NPU) designed for advanced AI inferencing on edge devices. It delivers exceptional performance and energy efficiency, making it suitable for a variety of applications, including mobile devices, IoT, automotive, and embedded systems. Key Features Performance: The Ethos-N77 provides up to 4 TOPS (Tera Operations Per Second) of performance, scaling to hundreds of TOPS in multicore configurations. This makes it capable of handling complex AI tasks such as object detection, image segmentation, and speech recognition efficiently. Efficiency: Achieving up to 5 TOPs/W, the Ethos-N77 utilizes an optimized architecture that includes distributed…

Kendryte K210 is a dual-core RISC-V processor specifically designed for edge AI and machine vision applications. Operating at a clock speed of 400 MHz, it is built on the RV64IMAFDC architecture, enabling efficient processing for various AI tasks. Key Features Dual-Core Architecture: The K210 features two 64-bit RISC-V cores, providing a solid foundation for parallel processing tasks, which is essential for real-time AI applications. Neural Network Processor (KPU): The K210 includes a dedicated KPU that can perform up to 0.8 TOPS (Tera Operations Per Second). This hardware accelerator is optimized for convolutional neural networks (CNN), making it suitable for tasks…

Lattice sensAI is a comprehensive solution stack designed to simplify the development and deployment of AI/ML models for low-power edge applications[2]. This innovative toolkit leverages the flexibility and efficiency of Lattice FPGAs to enable rapid creation of AI-powered devices at the network edge[5]. The sensAI stack comprises several key components: Hardware platforms IP cores Software tools Reference designs At the heart of sensAI is the new sensAI Studio, a GUI-based design environment that facilitates end-to-end AI/ML model training, validation, and compilation[2]. This web-based framework supports multiple users collaborating on projects and allows easy configuration of target FPGAs, I/Os, and AI/ML…

The NXP i.MX 8M Plus is a cutting-edge application processor that integrates advanced artificial intelligence (AI) and machine learning (ML) capabilities[1][2]. At its core, it features a quad-core Arm Cortex-A53 processor running at up to 2.0 GHz, complemented by an 800 MHz Arm Cortex-M7 real-time processor[1][2]. Key Features Neural Processing Unit (NPU): A dedicated 2.3 TOPS NPU enables advanced machine learning inference at the edge[1][2] Image Processing: Dual Image Signal Processors (ISPs) support high-definition cameras for real-time stereo vision[2] Multimedia Capabilities: Includes H.265/H.264 video encoding/decoding, 3D GPU, and audio processing with a HiFi 4 DSP[1][2] Connectivity: Features dual Gigabit Ethernet…

NVIDIA’s Jetson AGX Xavier is a high-performance AI computing platform designed to bring advanced AI and computer vision capabilities to edge devices, particularly in robotics and autonomous machines. As part of NVIDIA’s Jetson series, it is engineered to deliver workstation-level performance in a compact form factor, enabling devices to operate autonomously without the need for human intervention or cloud connectivity. Key Features Performance Jetson AGX Xavier offers up to 32 TeraOPS (TOPS) of AI performance, making it capable of handling complex tasks such as visual odometry, sensor fusion, localization and mapping, obstacle detection, and path planning. It integrates a 512-core…

Pine64 RockPro64: A Versatile SBC with AI Capabilities The Pine64 RockPro64 is a powerful single-board computer (SBC) that combines versatility with artificial intelligence capabilities. At its core lies the Rockchip RK3399 System-on-Chip (SoC), featuring a hexa-core processor with dual ARM Cortex A72 and quad ARM Cortex A53 cores[1][3]. This SBC boasts impressive specifications, including: Up to 4GB of LPDDR4 RAM Mali T-860 quad-core GPU PCIe x4 open-ended slot USB 3.0 and USB-C ports with DisplayPort 1.2 support Gigabit Ethernet eMMC module socket MicroSD card slot The RockPro64’s AI capabilities are enabled by its powerful RK3399 SoC, which can handle complex…

The UDOO Bolt V8 is a powerful x86 maker board designed for demanding applications such as AI, machine learning, and edge computing. This board is equipped with an AMD Ryzen™ Embedded V1605B Quad Core/eight Thread CPU, which can reach speeds up to 3.6 GHz, and features AMD Radeon™ Vega 8 Graphics, making it capable of handling intensive graphical and computational tasks[3]. Key Features High Performance CPU and GPU: The AMD Ryzen™ Embedded V1605B processor and Radeon™ Vega 8 graphics provide robust performance for AI and machine learning tasks, competing with mid-range desktop GPUs like the GTX 950[3]. Memory and Storage:…

The Maixduino is a development board that integrates the Kendryte K210 AI processor, designed for applications in artificial intelligence (AI) and the Internet of Things (IoT). Manufactured by Sipeed, the Maixduino combines the power of the K210 with the connectivity features of the ESP32 module, making it a versatile and powerful tool for developers. Key Features of the Maixduino Kendryte K210 AI Processor The heart of the Maixduino is the Kendryte K210, a system-on-chip (SoC) that excels in machine vision and machine hearing applications. The K210 is built using TSMC’s 28nm process, featuring dual-core 64-bit RISC-V processors clocked at 400…