Click the blue text to follow us
This is a very detailed description of the functions and characteristics of the Rockchip series SoC processors, including RV1103, RV1106, RV1109, RV1126 and RK3562, RK3568, RK3576, RK3588. These chips are designed for IPC (network cameras), CVR (video recorders) and AI-related applications, with the following features:
RV1103 is a highly integrated IPC vision processor SoC, especially suitable for AI-related applications.
It is based on a single-core ARM Cortex-A7 32-bit core with integrated NEON and FPU, featuring 32KB I-cache, 32KB D-cache, and 128KB unified L2 cache.
RV1106 is a highly integrated IPC vision processor SoC, particularly suitable for AI-related applications. It is based on a single-core ARM Cortex-A7 32-bit core with integrated NEON and FPU, featuring 32KB I-cache, 32KB D-cache, and 128KB unified L2 cache.
Core: Single-core ARM Cortex-A7, supporting NEON and FPU.
NPU: Supports INT4/INT8/INT16, with a computing power of 0.5TOPs.
ISP: RV1103 supports 4 million pixels, while RV1106 is enhanced to 5 million pixels.
RV1103: Supports two MIPI CSI or LVDS.
It also supports multi-stream encoding. With this feature, the camera’s video can be encoded at a higher resolution and stored in local memory, while another lower resolution video is transmitted to cloud storage. To accelerate video processing, an intelligent video engine with 22 computing units is embedded. RV1103 has built-in 16-bit DRAM DDR2, capable of handling demanding memory bandwidth. It also integrates built-in POR, audio codec, and MAC PHY.
RV1106: Supports two MIPI CSI and one DVP.
The embedded video encoder in RV1106 supports H.265/H.264 encoding. It also supports multi-stream encoding. With this feature, the camera’s video can be encoded at a higher resolution and stored in local memory, while another lower resolution video is transmitted to cloud storage. To accelerate video processing, an intelligent video engine with 22 computing units is embedded.
RV1106 has built-in 16-bit DRAM DDR3L, capable of handling demanding memory bandwidth. It also integrates built-in RTC, POR, audio codec, and MAC PHY.
Video encoding: Supports H.265/H.264, supports multi-stream encoding.
RV1109 is a high-performance AI vision processor SoC aimed at IPC or other intelligent vision applications. It is based on a dual-core ARM Cortex-A7 32-bit core with integrated NEON and FPU. Each core has 32KB I-cache and 32KB D-cache, along with 512KB unified L2 cache. The built-in NPU supports INT8/INT16 mixed operations, with a computing power of up to 1.2TOPs. Furthermore, due to its strong compatibility, it can easily convert network models based on frameworks like TensorFlow/MXNet/PyTorch/Caffe.
One Cow Network RV1109/1126 module
RV1109 also introduces a new generation of hardware-based 5 million pixel ISP (image signal processor) and post-processor. It implements many algorithm accelerators typically used for IPC and CVR, such as HDR, 3A functions (AE, AF, AWB), LSC, 3DNR, 2DNR, sharpening, dehazing, fisheye correction, gamma correction, feature point detection, etc. All of these are processed in real-time. With two MIPI CSI and one DVP (BT.601/BT.656/BT.1120) interface, users can build a system that receives video data from three camera sensors simultaneously.
RV1109’s embedded video encoder supports 5M H.265/H.264 encoding. It also supports multi-stream encoding, allowing for one 5M30FPS and one 720P30 stream simultaneously. With this feature, the video captured by the camera can be encoded at a higher resolution and stored in local memory, while another lower resolution video is transmitted to cloud storage.
RV1109: Dual-core Cortex-A7.
RV1126: Quad-core Cortex-A7.
RV1109: 5 million pixels.
RV1126: 14 million pixels, supporting more advanced real-time image processing algorithms.
RV1126 is a high-performance vision processor SoC aimed at IPC/CVR, especially suitable for AI-related applications.
It is based on a quad-core ARM Cortex-A7 32-bit core with integrated NEON and FPU. Each core has 32KB I-cache and 32KB D-cache, along with 512KB unified L2 cache.
RK3562 includes an embedded 3D GPU, ensuring full compatibility with OpenGL ES 1.1/2.0/3.2, OpenCL 2.0, and Vulkan 1.1. Additionally, it includes a special 2D hardware engine to maximize display performance and ensure smooth operation. The built-in NPU supports mixed operations with INT4/INT8/INT16/FP16 data types.
Moreover, it has strong compatibility with a range of frameworks like TensorFlow, MXNet, PyTorch, and Caffe, allowing easy conversion of network models.
RK3562 features a high-performance external memory interface (DDR3/DDR3L/DDR4/LPDDR3/LPDDR4/LPDDR4X), capable of handling demanding memory bandwidth.
RK3568 is a high-performance low-power quad-core application processor designed for personal mobile internet devices and AIoT devices. It provides many embedded powerful hardware engines to optimize performance for high-end applications.
RK3568 supports nearly all formats of 4K@60fps H.264 decoder, 4K@60fps H.265 decoder, and also supports 1080p@60fps H.264/H.265 encoders, high-quality JPEG encoder/decoder. The embedded 3D GPU makes RK3568 fully compatible with OpenGL ES 1.1/2.0/3.2, OpenCL 2.0, and Vulkan 1.1. The special 2D hardware engine maximizes display performance and provides very smooth operation. The built-in NPU supports INT8/INT16 mixed operations. Additionally, due to its strong compatibility, it can easily convert network models based on frameworks like TensorFlow/MXNet/PyTorch/Caffe. RK3568 features a high-performance external memory interface (DDR3/DDR3L/DDR4/LPDDR3/LPDDR4/LPDDR4X), capable of handling demanding memory bandwidth. 1.2 The following features may or may not be present in actual products and may be subject to third-party licensing requirements. Please contact Rockchip for actual product feature configurations and licensing requirements.
RK3576 is a low-power, high-performance processor suitable for ARM-based PCs and edge computing devices, personal mobile internet devices, and other digital multimedia applications, integrating four Cortex-A72 cores and four Cortex-A53 cores, each with NEON coprocessor.
RK3576 video decoder supports H.264, H.265, VP9, AV1, and AVS2, up to 8K@30fps or 4K@120fps, while the video encoder supports H.264 and H.265, up to 4K@60fps, high-quality JPEG encoder/decoder up to 4K@60fps. The embedded 3D GPU makes RK3576 fully compatible with OpenGL ES 1.1, 2.0, and 3.2, OpenCL up to 2.0, and Vulkan 1.1. The dedicated 2D hardware engine with MMu maximizes display performance and provides very smooth operation. RK3576 introduces a new generation of 16 million pixel ISP (image signal processor). It implements many algorithm accelerators such as HDR, 3A, CAC, 3DNR, 2DNR, sharpening, dehazing, enhancement, Debayer, and small angle lens distortion correction. The built-in NPU supports INT4/INT8/INT16/FP16/BF16/TF32 mixed operations. Additionally, due to its strong compatibility, network models based on frameworks like TensorFlow/MXNet/PyTorch/Caffe can be easily converted.
RK3588 is a low-power, high-performance processor suitable for ARM-based PCs and edge computing devices, personal mobile internet devices, and other digital multimedia applications, integrating four Cortex-A76 cores and four Cortex-A55 cores, each with NEON coprocessor.
Many embedded powerful hardware engines provide optimized performance for high-end applications. RK3588 supports 8K@60fps H.265 and VP9 decoders, 8K@30fps H.264 decoder, and 4K@60fps AV1 decoder, as well as 8K@30fps H.264 and H.265 encoders, high-quality JPEG encoder/decoder, dedicated image preprocessor and post-processor. The embedded 3D GPU makes RK3588 fully compatible with OpenGLES 1.1, 2.0, and 3.2, OpenCL up to 2.2, and Vulkan 1.2. The dedicated 2D hardware engine with MMU maximizes display performance and provides very smooth operation.
RK3588 introduces a new generation of hardware-based 480,000 pixel ISP (image signal processor). It implements many algorithm accelerators, such as HDR, 3A, LSC, 3DNR, 2DNR, sharpening, dehazing, fisheye correction, gamma correction, etc.
The built-in NPU supports INT4/INT8/INT16/FP16 mixed operations, with a computing power of up to 6TOPs. Furthermore, due to its strong compatibility, it can easily convert network models based on frameworks like TensorFlow/MXNet/PyTorch/Caffe.
RK3588 features a high-performance four-channel external memory interface (LPDDR4/LPDDR4X/LPDDR5), capable of handling demanding memory bandwidth, and also provides a complete set of peripheral interfaces to support very flexible applications.
Undertaking various platform DDR and UFS testing project customization for MTK pop process,
Dimensity 9300 is mt6989
Dimensity 9200 is mt6985
Dimensity 9000 is mt6983
Dimensity 8300 is mt6897
| Agriculture Meets AI: Opening a New Chapter in Intelligent Development |
AI Empowerment: Benz’s No-Map L2++ Intelligent Driving Starts “China Speed” |
| The “Pioneer of Technology” in the Air Conditioning Industry & AI Energy Saving Prince Changes Lives |
Comprehensive List of MediaTek (MTK) 4G/5G Platforms and CPU Models |
| Game Phone Recommendations: Red Magic 10 Pro vs. ROG 9 AI Performance Comparison |
Smart Disassembly vivo X100 (Dimensity 9300) AI Performance Reveal |
| MediaTek Dimensity 9400 VS Qualcomm Snapdragon 8gen4 SM8750/SM8750P Android Chip Comparison |
Game Phone Recommendations: Red Magic 10 Pro vs. ROG 9 AI Performance Comparison |
Sigmastar & Junzheng & Lianying Solutions
Sigmastar 120fps high frame rate smart network camera WIFI module/solution customization
Junzheng T31ZX+GC4653 4 million PTZ fixed-focus camera/solution customization
SC8836Q 2 million HDMI HD camera module/solution customization suitable for network video conferencing, drones, industrial robots, etc.
Junzheng T40 NOR quick AI camera (supports algorithms for pedestrian/flame/bicycle/safety helmet recognition)/solution customization
Junzheng A1 Full HD network video decoder/solution customization
SSC8836Q 2 million HDMI HD camera module/solution customization
Sigmastar SSD268G 12 million low-light smart HD network camera module
Sigmastar SSD268G 12 million low-light smart HD network camera module
Hisilicon & RK AI Perspective Solutions
Hisilicon Hi3520 single SDI input HDMI output encoding board/solution customization
Yizhi SV830C dual-camera (RGB+NIR) face recognition/solution customization
RK3566 commercial display (supports HDMI2.0+LVDS output single/dual 6/8 bit, max 1080p) intelligent general standard motherboard solution
Hisilicon Hi3520 single SDI input HDMI output encoding board/solution customization
Rockchip RK3562 (Android 13/Linux/1 TOPS computing power) smart core board/solution customization
Rockchip RK3568 display video terminal/solution (supports RGB/LVDS/MIPI-DSI interface/dual-screen display) customization
Rockchip RK3568 edge computing smart 4G/5G gateway/solution customization
Rockchip RK3568 (NVR+AI+SATA3.0+networked) Linux development board/core board/solution customization
RK3588 smart board (supports 8-channel AHD 1080p@30fps+SSD hard drive+5G) solution customization
Rockchip RK3588 Android industrial control board (6T computing power NPU/supports same display or different display)/solution customization
RK & Allwinner & Hisilicon Decoding Solutions
Rockchip RK3399 (supports dual-screen different display/6 USB ports) Android 7.1 smart motherboard
Rockchip RK3288 Android 8.1 10.1 inch dual-screen smart interactive digital signage
Rockchip RK3288 wall-mounted WeChat face payment module/solution customization
To learn more, please open the link or add the following WeChat, thank you for following!
What is One Cow Network? Let you understand One Cow Network in 1 minute!
