EyeQ进展The Evolution of EyeQ
EyeQ進展The Evolution of EyeQ
Mobileye’s proven leadership in ADAS technologies is based in our EyeQ?family system-on-chip (SoC) devices. More than 27 car manufacturers have chosen the EyeQ for their assisted-driving technologies based on its ability to support complex and computationally intense vision processing, while maintaining low power consumption.
Mobileye’s latest fifth-generation EyeQ is able to support fully-autonomous (Level 5) vehicles.
Mobileye在在ADAS技術成熟的領導地位是基于EyeQ?系列系統級芯片（SoC）器件。超過27家汽車制造商選擇了EyeQ作為輔助駕駛技術的基礎，具有支持復雜且計算強度大的視覺處理能力，同時又保持了低功耗。
Mobileye的最新第五代EyeQ能夠支持全自動（Level 5）車輛。
Mobileye has been able to achieve the power-performance-cost targets by employing proprietary computation cores (known as accelerators), which are optimized for a wide variety of computer-vision, signal-processing, and machine-learning tasks, including deep neural networks.These accelerator cores have been designed specifically to address the needs of the ADAS and autonomous-driving markets. Each EyeQchip features heterogeneous, fully programmable accelerators; with each accelerator type optimized for its own family of algorithms. This diversity of accelerator architectures enables applications to save both computation time and chip power by using the most suitable core for every task.Optimizing the assignment of tasks to cores thus ensures that the EyeQprovides “super-computer” capabilities within a low-power envelope to enable price-efficient passive cooling.
通過使用專有的計算核心（稱為加速器），Mobileye能夠實現功率性能成本的目標，這些核心針對各種計算機視覺，信號處理和機器學習任務（包括深度神經網絡）進行了優化。這些加速器內核是專門為滿足ADAS和自動駕駛市場的需求而設計的。每個EyeQ芯片均具有異構的，完全可編程的加速器。每種加速器類型都針對算法系列進行了優化。加速器體系結構的多樣性，使應用程序可以通過對每個任務使用最合適的內核來節省計算時間和芯片功耗。
The fully programmable accelerator cores are as follows:
The Vector Microcode Processors (VMP), which debuted in the EyeQ2, are now in their 4th generation of implementation in the EyeQ5, and are designed in most advanced VLSI process technology nodes – down to 7nm FinFET in the 5th generation. The VMP, a VLIW SIMD processor with cheap and flexible memory access, provides hardware support for operations common to computer vision applications and is well-suited to multi-core scenarios. Its computational power targets 24 trillion operations per second, while drawing only10 watts in a typical application.
The Multithreaded Processing Cluster (MPC) was introduced in the EyeQ4 and now reaches its 2nd generation of implementation in the EyeQ5. The MPC is more versatile than any GPU and more efficient than any CPU.
The Programmable Macro Array (PMA) was introduced in the EyeQ4 and now reaches its 2nd generation of implementation in the EyeQ5. The PMA enables computation density nearing that of fixed-function hardware accelerators without sacrificing programmability.
In addition to Mobileye’s innovative and well-proven computer vision accelerators, the EyeQfeatures generic multithread CPU cores to provide the complete and robust computing platform that ADAS/AV applications demand.
完全可編程的加速器內核如下：
在EyeQ2中首次亮相的矢量微碼處理器（VMP），已經在EyeQ5中實現了其第四代實現，并在最先進的VLSI處理技術節點中進行了設計-第五代中的最小7nm FinFET。VMP是一種VLIW SIMD處理器，具有廉價，靈活的內存訪問功能，為計算機視覺應用程序常見的操作提供硬件支持，非常適合于多核方案。計算能力目標為每秒24萬億次操作，而在典型應用中僅消耗10瓦。
EyeQ4中引入了多線程處理集群（MPC），現在在EyeQ5中實現了其第二代實現。MPC比任何GPU都更通用，比任何CPU都更高效。
可編程宏陣列（PMA）是在EyeQ4中引入的，現已在EyeQ5中達到其第二代實現。PMA使計算密度接近固定功能硬件加速器的計算密度，而不會犧牲可編程性。
除了Mobileye的創新和久經考驗的計算機視覺加速器外，EyeQ還具有通用的多線程CPU內核，可提供ADAS / AV應用程序所需的完整而強大的計算平臺。
Mobileye has a long-standing cooperation with STMicroelectronics (STM) for implementation of the EyeQdevices Leveraging its substantial experience in automotive-grade designs, STM provides support in state-of-the-art physical implementation, as well as automotive-grade memories, high-speed interfaces, and system-in-package design to ensure that the EyeQdevices meet the full qualification process according to the highest automotive standards.
Mobileye has a proven track record of developing hardware to meet the challenges of each new level of autonomous driving and we expect our computing capabilities to continue to grow exponentially.Indeed, in order to support running increasingly greater numbers of different algorithms simultaneously, each generation of the EyeQhas been approximately eight times more powerful than its predecessor, all the while maintaining the requisite low power dissipation.
ADAS and especially high levels of autonomous driving require an unprecedented level of focus on functional safety. EyeQdevices are developed to be designed into systems that require the highest grade of safety in automotive applications (i.e., ASIL D, according to the ISO 26262 standard).
In addition to the safety requirements inherent to an automotive application, security is no less a concern.To support the cyber-security requirements of ADAS/AV applications, the EyeQ5 was designed with an integrated hardware security module which includes various innovative HW security features.This enables system integrators to support secure over-the-air software updates, secure in-vehicle communication, etc.
Mobileye與意法半導體（STM）在實施EyeQ器件方面有著長期合作關系，憑借其在汽車級設計方面的豐富經驗，STM為最新的物理實現以及汽車級存儲器提供了支持，高速接口和系統級封裝設計，以確保EyeQ設備符合最高汽車標準的完整認證流程。
Mobileye在開發硬件以應對自動駕駛每個新水平的挑戰方面有著良好的記錄，希望計算能力將繼續呈指數增長。為了支持同時運行越來越多的不同算法，每一代EyeQ的性能都比其前代產品高出大約八倍，同時始終保持必需的低功耗。
ADAS，尤其是高水平的自動駕駛，要求對功能安全的關注達到前所未有的水平。EyeQ設備被開發用于在汽車應用中要求最高安全等級的系統（即，根據ISO 26262標準的ASIL D）。
EyeQdevices are delivered to automakers and Tier1 suppliers along with a full suite of hardware accelerated algorithms and applications that are required for ADAS and autonomous driving. Along with this, Mobileye supports an automotive-grade standard operating system and provides a complete software development kit (SDK) to allow customers to differentiate their solutions by deploying their algorithms on EyeQ5.The SDK may also be used for prototyping and deployment of neural networks, and for access to Mobileye pre-trained network layers. Uses of EyeQ5 as an open software platform are facilitated by such architectural elements such as hardware virtualization and full cache coherency between CPUs and accelerators.
Autonomous driving requires fusion processing of dozens of sensors, including high-resolution cameras, radars, and LiDARs. The sensor-fusion process has to simultaneously grab and process all the sensors’ data. For this purpose, EyeQ5 dedicated IOs support at least 40Gbps data bandwidth. More sensors may be supported via PCIe and Gigabit Ethernet ports with 18Gbps additional data bandwidth.
EyeQ5 implements two PCIe Gen4 ports for inter-processor communication, which could enable system expansion with multiple EyeQ5 devices or for connectivity with an application processor. EyeQdevices implement high performance network on chip interconnect and multi-channel low power DDR interfaces, to support high computational and data bandwidth requirements.
除了汽車應用固有的安全要求外，安全性同樣是關注的重點。為了滿足ADAS / AV應用程序的網絡安全要求，EyeQ5設計帶有集成的硬件安全模塊，該模塊包括各種創新的硬件安全功能。使系統集成商能夠支持安全的空中軟件更新，安全的車載通信等。
EyeQ設備連同ADAS和自動駕駛所需的全套硬件加速算法和應用程序，一起提供給汽車制造商和Tier1供應商。除此之外，Mobileye支持汽車級標準操作系統，提供完整的軟件開發套件（SDK），允許客戶通過在EyeQ5上部署算法來區分其解決方案。該SDK還可以用于神經網絡的原型設計和部署，以及用于訪問Mobileye預先訓練的網絡層。諸如硬件虛擬化以及CPU和加速器之間的完全緩存一致性之類的體系結構元素，促進了EyeQ5作為開放軟件平臺的使用。
自動駕駛需要融合數十個傳感器的融合處理，包括高分辨率攝像頭，雷達和LiDAR。傳感器融合過程必須同時獲取和處理所有傳感器的數據。EyeQ5專用IO至少支持40Gbps數據帶寬。通過具有18Gbps附加數據帶寬的PCIe和千兆以太網端口，可以支持更多傳感器。
EyeQ5實現了兩個PCIe Gen4端口，進行處理器間通信，可以通過多個EyeQ5設備擴展系統或與應用處理器進行連接。EyeQ設備實現了高性能的片上網絡互連和多通道低功耗DDR接口，支持較高的計算和數據帶寬要求。
人工智能芯片與自動駕駛
總結
以上是生活随笔為你收集整理的EyeQ进展The Evolution of EyeQ的全部內容，希望文章能夠幫你解決所遇到的問題。
