Qualcomm QCS610 and QCS410 Application Processors
Products of Qualcomm Technologies, Inc.
Artificial intelligence is moving out of the cloud and onto devices at the network edge. The Qualcomm® QCS610 and QCS410 application processors offer high performance and power efficiency for on-device AI. They are designed for edge applications like industrial IoT, smart AI enterprise security, home IP cameras, dash cams, body cams, smart displays and videoconferencing.
Design your devices around the big advantages of edge AI: high performance computing, lower latency, enhanced privacy and actions taken where the data resides. The QCS610 and QCS410 are ideal for compute intensive applications like object and human detection, people counting and license plate recognition that are designed to enable AI inferencing at the network edge. Keeping the workloads on the device also resolves the cloud computing challenges of privacy, latency, connection, and cost.
Both processors integrate the power management, audio, image processing and connectivity to reduce your bill-of-materials costs and help shorten your time to commercialization. They offer multiple CPU cores (QCS610: 8 cores; QCS410: 4 cores) and the heterogeneous computing power needed for high-quality images and video with low power consumption. The Octa-core architecture of the QCS610 is powerful enough to run multiple AI models simultaneously.
The QCS610 and QCS410 let you develop applications at the network edge for video encode/decode (QCS610: 4K30; QCS410: 1080p90), advanced ISP, machine learning, sensor processing and voice control. For AI development, they support Linux and Android, plus a complete software stack from the application level down to the compute core.
The QCS610 and QCS410 support an array of developer tools:
- Qualcomm® Artificial Intelligence (AI) Engine — The engine combines dedicated hardware and software designed to accelerate the execution of machine learning inference workloads on the device.
- Qualcomm® Neural Processing SDK for AI — Our software-accelerated runtime for the execution of deep neural networks lets you program the Qualcomm AI Engine. Use the SDK to develop custom AI models based on industry-standard frameworks like TensorFlow, TensorFlow Lite, ONNX and Caffe2. Then determine the optimal mix of cores (Kryo CPU, Adreno GPU, Hexagon DSP) for running your workloads. The SDK comes with an easy-to-use reference guide and learning resources.
- AI Model Efficiency Toolkit (AIMET) — Getting accuracy from floating-point models in the integer world of embedded applications takes work. AIMET’s goal is to enable power-efficient integer inference through a simple library plugin for AI developers.
In addition to providing core software and documentation for QCS610 and QCS410, Qualcomm Technologies, Inc. works with original design manufacturers who provide reference devices like systems-on-module and development kits.
Qualcomm QCS610, Qualcomm QCS410, Qualcomm Kryo, Qualcomm Hexagon, Qualcomm Adreno, Qualcomm Artificial Intelligence, and Qualcomm Neural Processing SDK are products of Qualcomm Technologies, Inc., and/or its subsidiaries.