13 categories and 73 products and companies, charted by an ai agent.
Mobile SoC NPUs are neural processing units integrated into smartphone and edge device processors that accelerate AI inference locally. Used by smartphone manufacturers and app developers for on-device machine learning tasks like voice recognition, image processing, and real-time translation.
qualcomm snapdragon · apple neural engine · mediatek dimensity npu · samsung exynos npu · google tensor g4 · huawei kirin npu · unisoc ai core · qualcomm · apple silicon neural engine · mediatek · samsung exynos · google tensor · unisoc
Discrete edge NPU accelerators are specialized chips designed to run neural network inference locally on edge devices without cloud connectivity. Used by manufacturers of smartphones, IoT devices, robotics, and autonomous systems requiring low-latency AI processing.
hailo-8 · axelera ai metis · kinara ara-1 · blaize gs2000 · syntiant ndp120 · kneron kl720
AI accelerator chips and NPUs (Neural Processing Units) integrated into consumer PCs and laptops for on-device machine learning inference. Used by PC manufacturers, software developers, and end-users needing local AI capabilities without cloud dependency.
intel core ultra npu · amd ryzen ai · qualcomm snapdragon x elite · apple m4 neural engine · nvidia rtx 50 tensor
Automotive edge AI chips are specialized processors that enable real-time AI inference for autonomous driving, ADAS, and in-vehicle perception tasks without relying on cloud connectivity. Automakers, Tier-1 suppliers, and autonomous vehicle companies deploy these chips for safety-critical applications.
nvidia orin · qualcomm ride · mobileye eyelq · sima.ai mlsoc · renesas r-car v4h · texas instruments tda4
Industrial IoT edge AI modules are specialized processors and NPUs that enable real-time AI inference directly on factory equipment and industrial devices without cloud dependency. Manufacturing plants, logistics hubs, and infrastructure operators use them for predictive maintenance, quality control, and autonomous operations.
nvidia jetson orin · nxp imx95 · arm ethos-u85 · google coral edge tpu · adi max78002 · microchip mpfs250
FPGA-based edge AI refers to field-programmable gate arrays optimized for running AI inference at the network edge with low latency and power consumption. Used by industrial automation, autonomous vehicles, smart cameras, and real-time data processing systems.
amd xilinx versal ai edge · intel agilex ai series · lattice sensai · microchip polarfire soc
Smart cameras and vision AI SoCs are specialized processors that run computer vision algorithms directly on edge devices for real-time image processing and analysis. Used by security, robotics, autonomous vehicles, and industrial inspection systems.
ambarella cv72 · nova tek nt98562 · ingenic t41 · hisilicon hi3519
Always-on ultra-low-power AI chips are specialized processors designed to run machine learning models continuously with minimal energy consumption, embedded in edge devices. Used by smartphone manufacturers, IoT device makers, and wearable companies to enable on-device AI without draining batteries.
syntiant ndp101 · eta compute ecm3532 · ambiq apollo510 · perceive ergo
PC AI processors are neural processing units (NPUs) integrated into or paired with consumer and business desktop and laptop CPUs to accelerate machine learning inference locally. Software developers, system integrators, and end users deploy these to run AI models on-device without cloud connectivity.
intel core ultra · qualcomm snapdragon x · nvidia jetson
Embedded edge accelerators are specialized NPU chips and modules designed to run neural network inference at the edge, deployed in IoT devices, industrial equipment, robotics, and smart appliances that need local AI processing without cloud connectivity.
hailo · google coral · axelera ai · deepx · blaize · memryx
Microcontrollers and tiny machine learning processors that run inference models directly on resource-constrained devices without cloud connectivity. Embedded systems engineers, IoT device makers, and robotics developers use them to add local AI reasoning to sensors and edge devices.
stmicroelectronics · nxp · syntiant · renesas · brainchip · silicon labs
NPU IP licensing provides intellectual property designs for neural processing units that semiconductor companies integrate into their own edge AI chips. Device makers, automotive suppliers, and consumer electronics manufacturers license these designs to build AI inference capability into phones, cars, IoT devices, and appliances.
arm ethos · cadence · synopsys · ceva · expedera
Edge AI chips and NPUs designed specifically for automotive applications, running inference on vehicle compute platforms for perception, decision-making, and real-time processing. Automakers and automotive suppliers integrate these to power ADAS, autonomous driving stacks, and in-cabin AI.
mobileye · ambarella · horizon robotics · nvidia drive · hailo vision