Amlogic Launches A123X & C305X2: Next-gen 6nm SoCs built to power the Edge AI ecosystem
MOUNTAIN VIEW, CA, UNITED STATES, September 9, 2026 /EINPresswire.com/ -- Amlogic, a global leader in AI System-on-Chip (SoC) solutions for smart and connected devices, today announced two new 6nm SoCs, C305X2 and A123X, one of the pioneering edge AI SoCs to be powered by the ultra-efficient Arm® Cortex®-A320 CPU. The unified platform delivers transformative machine learning (ML) performance and provides hardware-grade Armv9 security for battery-powered IPCs (IP cameras), industrial machine vision, smart home cameras, and multi-scenario IoT devices. Samples are available now, with mass production scheduled for Q4 2026.
Arm Cortex-A320 CPU: Armv9 Architecture Powers Breakthrough ML & Native Hardware Security
At the core of C305X2 and A123X lies the Arm Cortex-A320—the smallest and most power-efficient Armv9 CPU tailored for IoT workloads:
· Significant Performance Boost: Delivers a 34% SPECint2006 performance increase over the legacy Armv8 Cortex-A35
· Industry-Leading ML Acceleration: Equipped with SVE2 vector extensions, Cortex-A320 delivers multiple folds (10x) of ML processing uplift compared to Cortex-A35. Paired with Amlogic’s in-house 8 TOPS Transformer-native ADLA3 NPU, the platform seamlessly runs lightweight computer vision (CV) algorithms and compact LLMs locally, eliminating cloud latency while strictly safeguarding on-device data privacy.
Differentiated Vision Platform Capabilities Built on Arm Cortex-A320
A123X – Flagship Industrial Multi-Scenario SoC
·Advanced Process Node: TSMC 6nm
·Compute Engine: Quad-core Armv9 Cortex-A320 CPU for concurrent video, AI, and industrial control workloads
·Multi-NPU Architecture: Integrates 4 TOPS ADLA2 NPU (for object detection and tracking CNN models) and 8 TOPS ADLA3 NPU (supporting hardware-acceleratedTransformer operations for ViT, LLM, etc.)
·Sound Event Detection: Neural network-based hardware SED engine for low-power audio event identification
·Professional-Grade ISP: Low-light HDR ISP supporting dual 4-lane MIPI image sensor inputs; supports up to 16M@30fps (SDR) and 13M@30fps (HDR) resolution; integrated AI-ISP technology (up to 4K@30fps) to significantly enhance image quality in ultra-low-light environments
·Powerful Video Codec: H.264/H.265 encoding at 4K@60fps and decoding at 4K@30fps
·Memory & Interfaces: 32-bit LPDDR4/4X/5 interface supporting up to 6400Mbps; 2x4L MIPI CSI, BT.656/BT.1120, sub-LVDS 8-lane; MIPI DSI display up to 1080P60; USB 3.0 OTG, USB 2.0 Host, GEMAC (Gigabit Ethernet), and 2x CAN FD
·Target Applications: Engineered for heavy multi-tasking industrial scenarios including machine vision, dashcams, sweeping robots, access control, and video conferencing hardware
C305X2 – Low-Power Vision SoC
·Advanced Process Node: TSMC 6nm
·Compute Engine: Dual-core Armv9 Cortex-A320 CPU
·Multi-NPU Architecture: Integrates ADLA2 NPU (for AI-ISP algorithms, supporting up to 4K@30fps) and 8 TOPS ADLA3(supporting hardware-accelerated Transformer operations for ViT, LLM, etc.)
·Ultra-Low Power & Long Battery Life: Supports Always-on Video (AOV) and Pre-roll low-power modes to extend battery life; integrated neural network SED engine for low-power audio detection
·Professional-Grade ISP: Low-light HDR ISP supporting dual 4-lane MIPI image sensor inputs; supports up to 4K@30fps resolution with AI-ISP enhancement (up to 4K@30fps) to boost low-light image quality
·Powerful Video Codec: H.264/H.265 encoding at 4K@60fps and decoding at 4K@30fps
·Memory & Interfaces: 32-bit LPDDR4/4X/5 interface supporting up to 4266Mbps; 2x4L MIPI CSI, BT.656/BT.1120; MIPI DSI display up to 1080P60; USB 3.0 OTG, USB 2.0 Host, and GEMAC
·Target Applications: Deeply optimized for ultra-low-power battery devices including solar doorbells, portable hunting cameras, and compact 2K/4K battery IPCs
Unified Ecosystem & End-to-End Developer Enablement
Leveraging the Cortex-A320’s broad Linux software compatibility, Amlogic delivers complete turnkey reference designs, pre-validated embedded OS stacks, and unified NN SDKs compatible with mainstream ML frameworks. The Arm-based Amlogic platform shortens OEM/ODM product iteration cycles by unifying hardware schematics, production-ready firmware, and global certification support. The Armv9 software ecosystem enables seamless migration from legacy Armv8-based Amlogic chips without massive code rework.
James Xie, Senior Vice President of Corporate Business Strategy at Amlogic, said: “We’re redefining what low-power edge vision hardware can achieve. By deeply integrating Armv9 high-efficiency Cortex-A320 processors, Amlogic’s proprietary high-performance NPUs, and the 6nm process into our C305X2 and A123X platforms, we empower global partners to launch next-generation Edge AI solutions that balance low power consumption, on-device generative AI compute, and robust data protection. This deep collaboration with Arm unlocks unified, scalable silicon solutions spanning mass-market battery IPCs to high-end industrial vision.”
Lionel Belnet, Senior Director of Edge Computing at Arm, said: “As AI moves into more devices at the edge, the challenge is delivering the performance these new experiences demand within tight power and efficiency constraints. Amlogic’s new Arm-based SoCs deliver the performance, efficiency and security needed to enable a new generation of intelligent vision and AI devices, from battery-powered consumer products to more demanding industrial systems.”
As edge AI applications grow increasingly complex, the C305X2 and A123X are designed to help mainstream IoT devices balance powerful AI computing capability with low power consumption and robust hardware-level data security. Combining the ultra-efficient Armv9 Cortex-A320 CPU with Amlogic’s self-developed NPU and professional ISP technologies, the new SoC platforms deliver efficient, low-latency and highly trusted on-device AI computing, and accelerate the large-scale deployment of consumer and industrial edge AI solutions.
About Amlogic
Amlogic is a world-leading fabless semiconductor company that specializes in the design, development, and application of high-intelligence system-on-chips (SoCs). As a result of its cutting-edge technologies and best-in-class solutions, the company has actively expanded into new areas including edge AI processors, wireless connectivity, and automotive electronics — ushering in a new era of smart living. By providing complete turnkey solutions in combination with industry-leading software and hardware technologies — including multimedia processing, AI accelerators, state-of-the-art security systems, and advanced CPUs and GPUs — customers can rapidly optimize and develop market-leading products with world-class performance.
Amlogic is dedicated to sustainability and implements state-of-the-art silicon processing techniques along with advanced power management solutions. Founded in Silicon Valley, Amlogic has R&D, support, and sales offices worldwide. To learn more about products of Amlogic visit: https://www.amlogic.com/
Arm Cortex-A320 CPU: Armv9 Architecture Powers Breakthrough ML & Native Hardware Security
At the core of C305X2 and A123X lies the Arm Cortex-A320—the smallest and most power-efficient Armv9 CPU tailored for IoT workloads:
· Significant Performance Boost: Delivers a 34% SPECint2006 performance increase over the legacy Armv8 Cortex-A35
· Industry-Leading ML Acceleration: Equipped with SVE2 vector extensions, Cortex-A320 delivers multiple folds (10x) of ML processing uplift compared to Cortex-A35. Paired with Amlogic’s in-house 8 TOPS Transformer-native ADLA3 NPU, the platform seamlessly runs lightweight computer vision (CV) algorithms and compact LLMs locally, eliminating cloud latency while strictly safeguarding on-device data privacy.
Differentiated Vision Platform Capabilities Built on Arm Cortex-A320
A123X – Flagship Industrial Multi-Scenario SoC
·Advanced Process Node: TSMC 6nm
·Compute Engine: Quad-core Armv9 Cortex-A320 CPU for concurrent video, AI, and industrial control workloads
·Multi-NPU Architecture: Integrates 4 TOPS ADLA2 NPU (for object detection and tracking CNN models) and 8 TOPS ADLA3 NPU (supporting hardware-acceleratedTransformer operations for ViT, LLM, etc.)
·Sound Event Detection: Neural network-based hardware SED engine for low-power audio event identification
·Professional-Grade ISP: Low-light HDR ISP supporting dual 4-lane MIPI image sensor inputs; supports up to 16M@30fps (SDR) and 13M@30fps (HDR) resolution; integrated AI-ISP technology (up to 4K@30fps) to significantly enhance image quality in ultra-low-light environments
·Powerful Video Codec: H.264/H.265 encoding at 4K@60fps and decoding at 4K@30fps
·Memory & Interfaces: 32-bit LPDDR4/4X/5 interface supporting up to 6400Mbps; 2x4L MIPI CSI, BT.656/BT.1120, sub-LVDS 8-lane; MIPI DSI display up to 1080P60; USB 3.0 OTG, USB 2.0 Host, GEMAC (Gigabit Ethernet), and 2x CAN FD
·Target Applications: Engineered for heavy multi-tasking industrial scenarios including machine vision, dashcams, sweeping robots, access control, and video conferencing hardware
C305X2 – Low-Power Vision SoC
·Advanced Process Node: TSMC 6nm
·Compute Engine: Dual-core Armv9 Cortex-A320 CPU
·Multi-NPU Architecture: Integrates ADLA2 NPU (for AI-ISP algorithms, supporting up to 4K@30fps) and 8 TOPS ADLA3(supporting hardware-accelerated Transformer operations for ViT, LLM, etc.)
·Ultra-Low Power & Long Battery Life: Supports Always-on Video (AOV) and Pre-roll low-power modes to extend battery life; integrated neural network SED engine for low-power audio detection
·Professional-Grade ISP: Low-light HDR ISP supporting dual 4-lane MIPI image sensor inputs; supports up to 4K@30fps resolution with AI-ISP enhancement (up to 4K@30fps) to boost low-light image quality
·Powerful Video Codec: H.264/H.265 encoding at 4K@60fps and decoding at 4K@30fps
·Memory & Interfaces: 32-bit LPDDR4/4X/5 interface supporting up to 4266Mbps; 2x4L MIPI CSI, BT.656/BT.1120; MIPI DSI display up to 1080P60; USB 3.0 OTG, USB 2.0 Host, and GEMAC
·Target Applications: Deeply optimized for ultra-low-power battery devices including solar doorbells, portable hunting cameras, and compact 2K/4K battery IPCs
Unified Ecosystem & End-to-End Developer Enablement
Leveraging the Cortex-A320’s broad Linux software compatibility, Amlogic delivers complete turnkey reference designs, pre-validated embedded OS stacks, and unified NN SDKs compatible with mainstream ML frameworks. The Arm-based Amlogic platform shortens OEM/ODM product iteration cycles by unifying hardware schematics, production-ready firmware, and global certification support. The Armv9 software ecosystem enables seamless migration from legacy Armv8-based Amlogic chips without massive code rework.
James Xie, Senior Vice President of Corporate Business Strategy at Amlogic, said: “We’re redefining what low-power edge vision hardware can achieve. By deeply integrating Armv9 high-efficiency Cortex-A320 processors, Amlogic’s proprietary high-performance NPUs, and the 6nm process into our C305X2 and A123X platforms, we empower global partners to launch next-generation Edge AI solutions that balance low power consumption, on-device generative AI compute, and robust data protection. This deep collaboration with Arm unlocks unified, scalable silicon solutions spanning mass-market battery IPCs to high-end industrial vision.”
Lionel Belnet, Senior Director of Edge Computing at Arm, said: “As AI moves into more devices at the edge, the challenge is delivering the performance these new experiences demand within tight power and efficiency constraints. Amlogic’s new Arm-based SoCs deliver the performance, efficiency and security needed to enable a new generation of intelligent vision and AI devices, from battery-powered consumer products to more demanding industrial systems.”
As edge AI applications grow increasingly complex, the C305X2 and A123X are designed to help mainstream IoT devices balance powerful AI computing capability with low power consumption and robust hardware-level data security. Combining the ultra-efficient Armv9 Cortex-A320 CPU with Amlogic’s self-developed NPU and professional ISP technologies, the new SoC platforms deliver efficient, low-latency and highly trusted on-device AI computing, and accelerate the large-scale deployment of consumer and industrial edge AI solutions.
About Amlogic
Amlogic is a world-leading fabless semiconductor company that specializes in the design, development, and application of high-intelligence system-on-chips (SoCs). As a result of its cutting-edge technologies and best-in-class solutions, the company has actively expanded into new areas including edge AI processors, wireless connectivity, and automotive electronics — ushering in a new era of smart living. By providing complete turnkey solutions in combination with industry-leading software and hardware technologies — including multimedia processing, AI accelerators, state-of-the-art security systems, and advanced CPUs and GPUs — customers can rapidly optimize and develop market-leading products with world-class performance.
Amlogic is dedicated to sustainability and implements state-of-the-art silicon processing techniques along with advanced power management solutions. Founded in Silicon Valley, Amlogic has R&D, support, and sales offices worldwide. To learn more about products of Amlogic visit: https://www.amlogic.com/
Marketing Team
Amlogic (USA) Ltd.
email us here
Legal Disclaimer:
EIN Presswire provides this news content "as is" without warranty of any kind. We do not accept any responsibility or liability for the accuracy, content, images, videos, licenses, completeness, legality, or reliability of the information contained in this article. If you have any complaints or copyright issues related to this article, kindly contact the author above.