Qualcomm has announced its QCS7230 SoC, a new smart camera IoT solution. This processor is designed to help deliver superior performance for compute-intensive cameras and Edge AI applications with Wi-Fi 6 for the Internet of Things (IoT).
The QCS7230 SoC is purpose-built for enterprise and commercial IoT applications such as video collaboration, smart cameras, connected healthcare, smart retail, and more. It offers a heterogeneous computing architecture coupled with the Qualcomm AI Engine to efficiently run complex AI and deep learning workloads. There's a dedicated CV hardware block and HTA designed to deliver up to 7 TOPS of AI performance for enterprise and commercial IoT applications.
The processor also offers a powerful image signal processor (ISP) with support for up to seven concurrent cameras, or up to 24 video streaming cameras. It also brings g a broad set of wired and wireless connectivity options, including 5G mmW and Sub-6 GHz, and Bluetooth 5.1.
>>> Qualcomm Unveils Snapdragon 8 Gen 1 Chip | 4x Faster AI Performance
Qualcomm QCS7230 Features
- Qualcomm Kryo 585 CPU with 1x Kryo Gold (2.8GHz) + 3x Gold @2.42GHX + 2x Kryo Silver (1.8 GHz) with 4MB L3 cache
- Camera: Dual 14-bit Qualcomm Spectra 480 ISP support 64MP single camera capture
- Qualcomm Adreno 650 GPU with improved GPU performance and power efficiency
- Native 8-bit integer support for efficient GPU DNN
- Hexagon DSP with quad Hexagon Vector eXtensions (HVX) V66Q, 1.5 GHz, for machine learning, integrated DNN for advanced VA and Qualcomm Neural Processing SDK framework
- Support for up to 24 cameras, or seven concurrent cameras
- Superior image quality in zzHDR, video denoising, mid/low-frequency denoising, lens shading correction, video super-resolution
- Supports triple 4K displays
- Video/display: Concurrent UHD encode/ decode, 2X display port, MIPI-DSI
- Video processing at up to 4K240 decode/4K120 encode, multiple video codecs
- Computer Vision: CVP 2.0 for improved video de-noising, digital video stabilization, and image correction adjustment
- NPU (Neural Processing Unit) for performance and always-on Neural Network (NN) use cases
- Audio: Multi-mic, source tracking, ECNS, voice activation
- Support for 2x2 11ax 80MHz for faster downloads
- Qualcomm Technologies video collaboration reference design feature set
>>> Qualcomm announces earnings report for first-quarter fiscal 2022 | sales up by 30%
Qualcomm QCS7230 Specifications
- Process Node: 7nm
- CPU: Kryo 585, Hexa-core 64-bit Arm V-8 compliant
- Memory: Quad-channel PoP high-speed LPDDR5 SDRAM up to 2750 MHz
- GPU: Adreno GPU 650
- Compute DSP: Hexagon DSP with Quad HVX V66Q, 1.5 GHz
- Machine Learning: Dedicated NPU 230
- Camera: Dual ISP: 64 MP @ 30fps ZSL
- Connectivity: WLAN 2 x 2 802.11ax with DBS, Bluetooth 5.1
- Display: Adreno 995 DPU, supports up to three 4K displays, 2x 4-Lane DSI, Display Port, and Miracast support
- Video: Decode: 8K60/4K240; Encode: 8K30/4K120
- Security: Dedicated SPU with Improved Crypto
- I/O Storage: eMMC 5.1, SPI NOR/NAND flash, SD 3.0
- Operating System: Android 10
>>> Qualcomm unveils Snapdragon G3x Gen 1 chipset aimed for handheld gaming devices
News source: Qualcomm | IT Home
