Cadence Neo NPU (Neural Processing Unit) IP delivers 8 GOPS to 80 TOPS in single core configuration and can be scaled to multicore configuration for hundreds of TOPS. The company says the Neo NPUs deliver high AI performance and energy efficiency for optimal PPA (Power, Performance, Area) and cost points for next-generation AI SoCs for intelligent sensors, IoT, audio/vision, hearables/wearables, mobile vision/voice AI, AR/VR and ADAS. Some highlights of the new Neo NPU IP include: Scalability – Single-core solution is scalable from 8 GOPS to 80 TOPS, with further extension to hundreds of TOPS with multicore Supports 256 to 32K MACs per cycle to allow SoC architects to meet power, performance, and area (PPA) tradeoffs Works with DSPs, general-purpose microcontrollers, and application processors Support for Int4, Int8, Int16, and FP16 data types for CNN, RNN and transformer-based networks. Up to 20x higher performance than the first-generation Cadence AI IP, with […]
TRACEPaw sensorized paw helps legged robots “feel the floor” with Arduino Nicla Vision
Our four-legged friends don’t walk on tarmac the same way as they do on ice or sand as they can see and feel the floor with their eyes and nerve endings and adapt accordingly. The TRACEPaw open-source project, which stands for “Terrain Recognition And Contact force Estimation through Sensorized Legged Robot Paw“, aims to bring the same capabilities to legged robots. Autonomous Robots Lab achieves this through the Arduino Nicla Vision board leveraging its camera and microphone to run machine learning models on the STM32H7 Cortex-M7 microcontroller in order to determine the type of terrain and estimate the force exercized on the leg. But the camera is apparently not used to look at the terrain, but instead, at the deformation of the silicone hemisphere – made of “Dragon Skin” – at the end of the leg to estimate 3D force vectors, while the microphone is used to recognize terrain types […]
Hailo-8L 13 TOPS AI accelerator targets entry-level edge devices
Hailo introduced the Hailo-8 AI accelerator offering up to 26 TOPS in 2020, and we’ve found it integrated into many designs since then. The company has now launched a cost-down version with the Hailo-8L AI accelerator delivering up to 13 TOPS for more cost-sensitive entry-level edge devices, or workloads that do not require the more powerful Hailo-8. Hailo says the Hailo-8L offers low-latency, high-efficiency processing, and is capable of handling pipelines with multiple real-time streams and concurrent processing of multiple models and AI tasks. The new Hailo-8L is compatible with the Hailo-8 and relies on the same Hailo-8 software suite, so they could be integrated into existing designs for cost savings. Hailo-8L key features and specifications: 13 Tera-Operations Per Second (TOPS) Real-time, low latency & high-efficiency AI inferencing on edge devices No external memory required Scalable with simultaneous processing of multi-streams & multi-models Typical power consumption – 1.5W Commercial & […]
Firefly AIO-1684XQ motherboard features BM1684X AI SoC with up to 32 TOPS for video analytics, computer vision
Firefly AIO-1684XQ is a motherboard based on SOPHGO SOPHON BM1684X octa-core Cortex-A53 AI SoC delivering up to 32TOPS for AI inference, and designed for computer vision applications and video analytics. The headless machine vision board is equipped with 16GB RAM, 64GB eMMC flash, and 128MB SPI flash, and comes with a SATA 3.0 port, dual Gigabit Ethernet, optional 4G LTE or 5G modules, four USB 3.0 ports, and a terminal block with two RS485 interface, two relay outputs, and a few GPIOs. Firefly AIO-1684XQ specifications: SoC – SOPHGO SOPHON BM1684X CPU – Octa-core Arm Cortex-A53 processor @ up to 2.3 GHz TPU – Up to 32TOPS (INT8), 16 TFLOPS (FP16/BF16), 2 TFLOPS (FP32) VPU Up to 32-channel H.265/H.264 1080p25 video decoding Up to 32-channel 1080p25 HD video processing (decoding + AI analysis) Up to 12-channel H.265/H.264 1080p25fps video encoding System Memory – 16GB LPDDR4x Storage 64GB eMMC flash 128MB SPI […]
Edgeble AI Neural Compute Module 2 (Neu2) follows 96Boards SoM form factor
Edgeble AI’s Neurable Compute Module 2, or Neu2 for shorts, is a system-on-module for computer vision applications based on the Rockchip RV1126 quad-core Cortex-A7 camera processor that follows the 96Boards SoM form factor. I first found the Neu2 and Neu6 (Rockchip RK3588) in the release log for the Linux 6.3 kernel, but at the time I found there was not enough information about those. The specifications for the Neu6 are still wrong (e.g. “64-bit processor with 4x Cortex-A7 core”) at the time of writing, so I’ll check the Neu2 system-on-module and its industrial version – the Neu2K based on RK1126K – for which we have more details. Edgeble Neu2 SoM specifications: SoC – Rockchip RV1126/RV1126K with CPU – Quad-core Arm Cortex-A7 @ 1.5GHz, RISC-V MCU @ 200MHz; (14nm SMIC process) GPU – 2D graphics engine NPU – 2 TOPS with INT8/INT16 VPU 4K H.264/H.265 video encoder up to 3840 x […]
AndesAIRE AnDLA I350 AI/ML IP block is configurable from 64 GOPS to 8TOPS for Edge AI SoCs
Andes Technology has just announced the AndesAIRE product line, where AndesAIRE stands for Andes AI Runs Everywhere, comprised of the AndesAIRE AnDLA I350 (Andes Deep Learning Accelerator) AI/ML hardware accelerator intellectual property (IP) and the AndesAIRE NN SDK with neural network software tools and runtimes. AndesAIRE AnDLA I350 AnDLA I350 specifications: Configurable MACs from 32 to 4096 (INT8) Maximum performance – 8 TOPS at 1GHz Configurable local memory – 16KB to 4MB Multi-dimension DMA Four 64-bit AXI bus interfaces NN type – CNN inference NN models Image and Video: AlexNet, VGG-16/19, MobileNet-v1/v2/v3, ResNet-8/50, Tiny YOLO v1/v2, YOLO v1/v2/v3/v4/v5, SSD MobileNet v1/v2, Inception v2, EfficientNet-lite, MobileFaceNet, BlazeNet Speech/Voice and audio: LSTM, RNN, GRU Operators: Conv2d, depthwise convolution, pointwise convolution, transpose convolution, dilated convolution, element-wise (add, sub, mul), fully-connected, activation (ReLU, leaky ReLU, sigmoid, Tanh, ReLU6, SiLU), pooling (max, ave), upsample, concatenation, batch normalization, channel padding Operator fusion NHWC data format The IP […]
SOPHON BM1684/BM1684X Edge AI computer delivers up to 32 TOPS, decodes up to 32 Full HD videos simultaneously
Firefly EC-A1684JD4 FD and EC-A1684XJD4 FD are nearly identical Edge AI embedded computers based on respectively SOPHON BM1684 and BM1684X Arm AI SoC delivering up to 32 TOPS of AI inference, and capable of decoding up to 32 H.265/H.264 Full HD videos simultaneously for video analytics applications. The BM1684(X) SoCs are equipped with eight Cortex-A53 cores clocked at 2.3 GHz to run Linux, and the systems come with up to 16GB RAM, 128GB flash, two Gigabit Ethernet ports to receive the video streams, one HDMI output up to 1080p30 for monitoring, as well as RS232 and RS485 DB9 connectors, and a few USB ports. Firefly EC-A1684JD4 FD and EC-A1684XJD4 FD specifications: SoC – SOPHGO SOPHON BM1684/BM1684X CPU – Octa-core Arm Cortex-A53 processor @ up to 2.3GHz TPU BM1684 64 NPU arithmetic units with each NPU containing 16 EU arithmetic units, or 1,024 EU in total Up to 17.6 TOPS (INT8), […]
Coral Dev Board Micro combines NXP i.MX RT1176 MCU with Edge TPU in Pi Zero form factor
Coral Dev Board Micro is the latest iteration of Google’s Edge AI devkit with an NXP i.MX RT1176 Cortex-M7/M4 crossover processor/microcontroller coupled with the company’s 4 TOPS Edge TPU, a camera, and a microphone in a board that’s about the size of a Raspberry Pi Zero SBC. The new board follows the original NXP i.MX 8M-based Coral Dev board that was introduced in 2019, and Coral Dev Board mini based on MediaTek MT8167S processor launched in 2020, and keeps with the trend of providing more compact solutions with lower-end host processors for edge AI. Coral Dev Board Micro specifications: MCU – NXP i.MX RT1176 processor with an Arm Cortex-M7 core @ up to 1 GHz, Cortex-M4 core up to 400 MHz, 2MB internal SRAM, 2D graphics accelerators; System Memory – 512 Mbit (64 MB) RAM Storage – 1 Gbit (128 MB) flash memory ML accelerator – Coral Edge TPU coprocessor […]