Linley microprocessor report: Ceva SensPro Fuses AI and Vector DSP – Traditional Chinese

Ceva SensPro 融合 AI 及向量 DSP 應用層面涵蓋小型IoT 裝置、無人機、小型機器人 作者:Mike Demler (2020.04.20) ……………………………………………………………………………………………………. Ceva的新SensPro為設計人員提供一組通用且高度 可配置的授權知識產權(IP)內核,用於純量和向量信號 處理以及神經網路加速。Ceva結合BX2 DSP、XM6電腦 視覺引擎、NeuPro深度學習加速器(DLA)技術設計而成 的SensPro已在最近的Linley春季處理器大會上推出。儘 管新產品的神經網路容量不及NeuPro,但其AI /傳感器 融合性能非常適合從IoT設備、智慧型手機及ADAS、AR / VR頭盔到無人機和機器人等各種產品。

Linley microprocessor report: Ceva SensPro Fuses AI and Vector DSP – Simplified Chinese

CEVA SENSPRO 融合AI 和矢量DSP 应用包括智能IoT 设备、无人机和小型机器人 Mike Demler(2020年4月20日) ……………………………………………………………………………………………………. Ceva新推出的SensPro为设计者提供一套多用途、可 高度配置的可授权知识产权(IP)内核,可实现标量和矢 量信号处理以及神经网络加速。公司在最近召开的 Linley春季处理器会议上推出SensPro,作为一款功能强 大的Sensor Hub,它将其BX2 DSP、XM6计算机视觉引 擎采用的技术与NeuPro深度学习加速器(DLA)相结合。

Linley microprocessor report: Ceva XC16領先5G部署

受惠於動態多線程功能的新式無線架構 作者:Mike Demler (2020.03.23) ……………………………………………………………………………………………………. Ceva XC16是採用Ceva第四代XC架構的首批產品,此一架構新增動態可配置多核/多線程等功能。本設計涵蓋兩組八向VLIW內核,依Ceva的定義則是配備四組向量運算單元(VCU)的純量處理器(SP)。進行運算時,可用軟體配置本處理器的SP及VCU為兩組對稱的雙向量(DV) 處理器,或將四個VCU分配給單一SP,以形成一個四向量(QV)處理器(搭配一個控制作業專用的SP)。

Linley microprocessor report: CEVA XC16率先实现5G布局

动态多线程功能可提升新空口架构的性能 Mike Demler(2020年3月23日) ……………………………………………………………………………………………………. XC16 DSP是首款实现Ceva第四代XC架构的产品,其中包含新增的动态可配置多核/多线程功能。产品设计由两个八路VLIW内核(CEVA公司称为标量处理器,SP)以及四个向量计算单元(VCU)构成。运行期间,可动态通过软件将SP和VCU配置为两个对称双向量(DV)处理器,或将全部四个VCU分配给一个SP以构成四向量(QV)处理器,而另一个SP则用于处理控制操作。

Linley microprocessor report: Ceva SensPro Fuses AI and Vector DSP

Applications Include Smart IoT Devices, Drones, and Small Robots By Mike Demler (April 20, 2020) ……………………………………………………………………………………………………. Ceva’s new SensPro gives designers a versatile and highly configurable set of licensable intellectual-property (IP) cores for scalar and vector signal processing as well as neural-network acceleration. The company designed SensPro, which it introduced at the recent Linley Spring … Continued

Linley microprocessor report: Ceva XC16 Stays Ahead of 5G Rollout

The XC16 DSP is the first product to implement Ceva’s fourth-generation XC architecture, which includes a new dynamically configurable multicore/multithread feature. The design comprises two eight-way VLIW cores—scalar processors (SPs), in the company’s parlance—along with four vector compute units (VCUs). During run time, it allows software to configure the SPs and VCUs as two symmetric … Continued

Linley Microprocessor Report: Ceva and Synopsys Spin More TOPS

IP Vendors Roll Out Multicore Deep-Learning Accelerators By Mike Demler (October 7, 2019) The rapid adoption of machine learning is driving IP vendors to compete by scaling up performance in each new generation of licensable deep-learning accelerators (DLAs). Last year, DLAs integrating up to 4,096 multiply-accumulate (MAC) units per core set the standard for licensable … Continued

Linley Microprocessor Report: Ceva’s BX Hybrid Boosts DSP Engine

By Mike Demler (February 4, 2019). Ceva’s new BX DSP cores offer upgrades to the first-generation X-series models, which employ a hybrid architec-ture combining multicore scalar CPUs for control functions with a highly configurable five-way SIMD/VLIW DSP en-gine for signal processing. The new intellectual property (IP) core tightens security by using a TrustZone-like memory subsystem … Continued