RK3588S 介绍

部署运行你感兴趣的模型镜像

RK3588是瑞芯微2021年底推出的首款高端8nm旗舰芯片,而RK3588S 则是针对消费端市场在RK3588基础上缩减了部分外围接口,CPU、GPU和NPU等主要参数得到了保留,主要应用范围为高端ARM平板、ARM笔电产品,会议平板类、ARM服务器、智能机器人、AI视频编解码领域、IP Camera、 NVR/XVR、工控行业以及智能驾舱等各行各业。

Chapter 1 Introduction
1.1 Overview
RK3588S is a low power, high performance processor for ARM-based PC and Edge
Computing device, personal mobile internet device and other digital multimedia
applications, and integrates quad-core Cortex-A76 and quad-core Cortex-A55 with
separately NEON coprocessor.
Many embedded powerful hardware engines provide optimized performance for high-end
application. RK3588S supports H.265 and VP9 decoder by 8K@60fps, H.264 decoder by
8K@30fps, and AV1 decoder by 4K@60fps, also support H.264 and H.265 encoder by
8K@30fps, high-quality JPEG encoder/decoder, specialized image preprocessor and
postprocessor.
Embedded 3D GPU makes RK3588S completely compatible with OpenGLES 1.1, 2.0, and
3.2, OpenCL up to 2.2 and Vulkan1.2. Special 2D hardware engine with MMU will maximize
display performance and provide very smoothly operation.
RK3588S introduces a new generation totally hardware-based maximum 48-Megapixel ISP
(image signal processor). It implements a lot of algorithm accelerators, such as HDR, 3A,
LSC, 3DNR, 2DNR, sharpening, dehaze, fisheye correction, gamma correction and so on.
The build-in NPU supports INT4/INT8/INT16/FP16 hybrid operation and computing power is
up to 6TOPs. In addition, with its strong compatibility, network models based on a series of
frameworks such as TensorFlow/MXNet/PyTorch/Caffe can be easily converted.
RK3588S has high-performance quad channel external memory interface
(LPDDR4/LPDDR4X/LPDDR5) capable of sustaining demanding memory bandwidths, also
provides a complete set of peripheral interface to support very flexible applications.

文章内容较多,就不详细阐述,详细datasheet 可以点击下载

RK3588S datasheet v1.1
 




 

您可能感兴趣的与本文相关的镜像

GPT-oss:20b

GPT-oss:20b

图文对话
Gpt-oss

GPT OSS 是OpenAI 推出的重量级开放模型,面向强推理、智能体任务以及多样化开发场景

### RK3588S 和 RK3588 的规格对比 #### 处理器架构 RK3588S 和 RK3588 均采用八核 ARM 架构处理器,但具体配置有所不同。RK3588 配备四个高性能 Cortex-A76 核心以及四个高效能 Cortex-A55 核心;而 RK3588S 则更侧重于多媒体处理能力,在 GPU 和 NPU 方面有所增强[^1]。 #### 图形处理单元 (GPU) 在图形性能方面,RK3588 搭载 Mali-G610 MP4 GPU,能够支持多种图形 API 并提供良好的游戏体验。相比之下,RK3588S 提升至更高版本的 GPU 或者相同型号但在频率上进行了优化,从而带来更强的游戏表现力和图像渲染速度。 #### 神经网络处理器 (NPU) 对于人工智能应用的支持,两款芯片都内置有强大的神经网络加速引擎。然而,RK3588S 对 AI 计算能力做了进一步加强,其 NPU 性能得到显著提升,更适合用于复杂的机器学习模型推理任务和其他高负载的人工智能应用场景。 #### 显示与视频编解码功能 两者均具备出色的显示输出能力和多路视频编码/解码特性。不过,RK3588S 可能在分辨率支持范围、HDR 效果等方面做出改进,以适应更多样化的视觉需求场景,如高端显示器连接或专业级影像编辑工作流中的实时预览等功能。 ```python # Python 伪代码展示如何获取 CPU/GPU/NPU 参数差异 def compare_specs(chipset_a, chipset_b): specs_diff = {} # 获取CPU核心数差异 cpu_cores_a = get_cpu_core_count(chipset_a) cpu_cores_b = get_cpu_core_count(chipset_b) if cpu_cores_a != cpu_cores_b: specs_diff['cpu_cores'] = f"{chipset_a}: {cpu_cores_a}, {chipset_b}: {cpu_cores_b}" # 获取GPU型号差异 gpu_model_a = get_gpu_model(chipset_a) gpu_model_b = get_gpu_model(chipset_b) if gpu_model_a != gpu_model_b: specs_diff['gpu_model'] = f"{chipset_a}: {gpu_model_a}, {chipset_b}: {gpu_model_b}" # 获取NPU性能指标差异 npu_performance_a = get_npu_performance_metrics(chipset_a) npu_performance_b = get_npu_performance_metrics(chipset_b) if npu_performance_a != npu_performance_b: specs_diff['npu_performance'] = f"{chipset_a}: {npu_performance_a}, {chipset_b}: {npu_performance_b}" return specs_diff ```
评论
成就一亿技术人!
拼手气红包6.0元
还能输入1000个字符
 
红包 添加红包
表情包 插入表情
 条评论被折叠 查看
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值