Optimization of AI Performance of SoCs for AD/ADAS

时间： 2023-06-16 来源：RENESAS Blogs

In recent years, advances in artificial intelligence (AI) technology based on deep learning have led to an increasing number of situations where AI is directly useful in our daily lives, such as improving the accuracy of automatic translation and making recommendations that match consumers' preferences. One example is automated driving (AD) and advanced driver assistance (ADAS) in automobiles.

Since the processing of recent AI models represented by deep neural networks (DNNs) requires large-scale parallel operations, GPUs capable of general-purpose parallel operations are often used for development on PCs. On the other hand, SoCs for AD and ADAS are increasingly equipped with dedicated circuits (hereinafter referred to as "accelerators") that realize DNN processing with low power consumption and high performance. However, it is generally not easy to confirm at an early stage of SoC development whether the on-chip accelerator can deliver sufficient performance for the DNN that one wishes to use. TOPS (Tera Operations Per Second) values, which represent the maximum arithmetic performance of the accelerator design, and TOPS/W values, which are calculated by dividing the above by the power consumption during operation, are often used as indicators for performance comparisons. But since accelerators are designed specifically to perform specific processing at high speed (*1), even if the TOPS values are sufficient, the performance of the accelerator may not be sufficient due to the existence of operations that cannot be processed efficiently or insufficient data transfer bandwidth. In addition, the power consumption of the overall SoC may exceed the acceptable range due to an increase in accelerator power.

(*1) Dedicated design: While it is possible to use a general-purpose GPU as an accelerator, hardware design focused on specific processing can achieve higher processing performance with less circuit size and power consumption. For example, the accelerators in RENESAS' automotive SoCs, R-Car V3H, R-Car V3M, and R-Car V4H, have a structure suitable for processing convolutional neural networks (CNN), which use convolutional operations for feature extraction among DNNs.

As SoC development progresses, the degree of difficulty in making design changes due to insufficient performance or excessive power consumption generally increases, and the impact on the SoC development schedule and development cost also increases. For this reason, it is very important in the development of SoCs for automotive AI devices to confirm at an early stage of SoC development whether the accelerator to be installed can deliver sufficient performance for the DNN that the customer product wants to use and whether the power consumption is within an acceptable range.

The general flow of AI development for AD/ADAS

Before going into an explanation of our approach to the above issues, we will briefly explain the flow of AI development in AD/ADAS. Figure 1 below shows an example of the flow of AI development for AD/ADAS, focusing on software and including part of SoC development.

Figure 1: Example of AI development flow in AD/ADAS

Figure 1 divides the entire development into six phases, with phases 2 and 3 being SoC circuit design and the other phases 1 and 4-6 being software development. The outline of work in each phase is as follows.

In Phase 1, AI Application/Service Common Development, we continuously develop AI applications and services for AD/ADAS using PC and cloud environments in response to market needs and technology trends.

In AI Accelerator Detail Design in phase 2, we design the components that make up the accelerator hardware, such as the arithmetic unit, built-in memory, and data transfer unit.

In AI Accelerator Configuration Design in Phase 3, the components designed in Phase 2 are integrated to optimize the trade-offs among area, power, and performance. This integration process enables the determination of the accelerator configuration within the System-on-Chip (SoC), aligning with the desired design objectives.

In DNN Model Architecture Design in phase 4, the accelerator configuration determined in phase 3 is used to optimize the network structure of each DNN which is expected to be used in the customer's product.

In DNN Inference Optimization in phase 5, code generation for accelerators, detailed evaluation of accuracy and processing time, and optimization of code and model data are performed for each network whose structure has been optimized in phase 4.

In the final application development stage in phase 6, the AI processing component, which has been optimized in step 5 through code and model data enhancements, is integrated into an application that performs specific tasks such as automated driving. This involves implementing and evaluating the application side, ensuring that the AI processing functions effectively within the overall system.

Renesas' Approach

In the flow of AI development in AD/ADAS described in the previous section, it is necessary to determine whether the accelerator equipped with the DNN that you want to use can provide sufficient performance in the AI Accelerator Configuration phase, which basically determines the configuration of the accelerator. The following is a brief overview of the AI Accelerator Configuration phase.

In the past, judgments at this stage were made by estimating from the results of benchmarks conducted using existing SoCs with similar accelerators. However, the estimation accuracy is limited because benchmark results cannot be obtained for areas where specifications differ from those of existing SoCs due to the addition or modification of functions, it was impossible to make judgments about whether the design goals could be achieved or not, based on accurate estimation.

Renesas has effectively addressed this issue by employing the PPA Estimator (Performance, Power, Area) instead of relying solely on benchmarking with existing System-on-Chips (SoCs). The PPA Estimator utilizes a calculation model that considers the design specifics of each accelerator component, enabling the estimation of performance and power consumption before finalizing the accelerator configuration.

To evaluate different accelerator configurations, a list of potential configurations is generated, each comprising various adjustable parameters like the number of processing units and internal memory capacity. One configuration is selected at a time and inputted into the PPA Estimator, which calculates the corresponding time required for processing and power consumption. This iterative process is repeated for the desired number of Deep Neural Networks (DNNs) and accelerator configurations, generating data that facilitates the identification of the optimal accelerator configuration.

This approach not only enables the assessment of whether a particular accelerator configuration and DNN combination yield adequate performance but also allows for the collection of a broad range of data. Ultimately, this data-driven analysis aids in selecting the most optimal accelerator configuration from the available options.

To enhance the effectiveness of the AI Accelerator Configuration phase (phase 3), Renesas implements concurrent improvements on the software side. This is achieved by leveraging the insights gained from the execution results of the PPA Estimator and applying them as feedback to the network model of the target Deep Neural Network (DNN). This process involves performing hardware-software co-design (co-design) to optimize the overall system performance. Figure 2 below shows the workflow of the AI Accelerator Configuration phase.

Figure 2: Workflow of AI Accelerator Configuration

Renesas has started applying PPA Estimator to the development of some SoCs for AD/ADAS with accelerators for AI processing from 2023 and plans to expand the scope of application gradually. Renesas will use PPA Estimator to search for optimal configurations and develop in-vehicle AI accelerators with high performance and low power consumption.

发送到邮箱 |
+1 赞 0
收藏
评论 0
| 转发至：

本文由上山打老虎转载自RENESAS Blogs，原文标题为:Optimization of AI Performance of SoCs for AD/ADAS，本站所有转载文章系出于传递更多信息之目的，且明确注明来源，不希望被转载的媒体或个人可与我们联系，我们将立即进行删除处理。

全部评论（0）

暂无评论

【经验】R-Car V3M/H接入2片AVT的RX芯片NS2521实现4路摄像头360环视探索的方法

Renesas的R-Car V3M、R-Car V3H的摄像头并口接入瑞发科的AVT接收芯片，实现4路摄像头的图像接入，从而来实现360度环视拼接功能，那么具体是如何对接的呢？本文详细讲解2颗AVT的RX芯片NS2521接入R-Car V3M/H的原理以及具体方法。

2020-08-13 - 设计经验

【经验】瑞萨R-Car V3M的eagle摄像头适配过程

R-Car V3M的eagle板自带4路摄像头输入解串器max9286，前端可以接入美信的max96705,max9271等串行器，从而实现R CAR V3M平台的4路摄像头的输入，本文记录了接入美信的max96705+OV490(isp)+OV9284(sensor)摄像头的过程。

2021-04-07 - 设计经验

【经验】R-Car H3 bsp如何实现PCIE endpoint模式？

R-Car系列的大多数型号都集成了PCIE2.0接口的，该接口可以支持root port和endpoint也就是主从两种模式的，最近有用户在使用两颗R-Car H3做PCIE通讯测试时发现无法配置成endpoint模式，经过测试及追查源代码发现，bsp中PCIE驱动没有对endpoint模式做支持，因此需要自行修改相应的驱动代码。

2020-05-04 - 设计经验

ROHM(罗姆) IC/功率器件/分立式半导体/无源元件/光学器件/模块选型指南

描述- ROHM launched the ComfySIL™ brand for customers involved in the design of functional safety to use products that support SIL (Safety Integrity Level) in a ‘Comfy’ (comfortable) manner, and for social systems' greater safety, security, and convenience to which ROHM can contribute through its products.

型号- DTC143TE3,KA2004-H05N20A,ML62Q20XX,RCJ220N25,SML-S13UT,DTC143TEB,RSX101VYM30,SML-D12M8W(C),SDR,R6002JND4,BD60A00NUX,RB238NS150,SML-D12Y8W,SMLA12BN8T,MG6405WZ,BDJ0GA3VEFJ-M,SML-811UT (A),SML-010VT,BD94130EFV-M,DTA124XM,BM2SC123FP2-LBZ,RS3L110AT,RB298T100,DTC143TCA,RSS060P05,BD71L4LG-1,SFR,BR25A512,RGPR20BM36HR,BD95821MUV,BD6995FV,KD2002-G0JB10A,BU23TD2W,SML-S13VT,BD12IC0WEFJ,BU97941FV,SLI-325YC(W),RQ5L015SP,BH7673G,SML-811UT (C),BD52XXG-2C,BD6046GUL,RGW60TS65HR,BD10KA5WFP,BA03CC0FP,SML-D12Y3W,BM6241FS,BD450S5FP2-C,MH2206WZ,BD63521EFV,BU94702AKV,SML-S13PT,RB168MM200,DTC144WCA,BD22621G-M,SLI-343URC,RS6R035BH,BDJ2FC0WFP,RGT20NL65,DTD123TC,DTA015TUB,BD750L5FP-C,BM521Q25F,R8003KNX,BD52XXG-1 SERIES,SML-D12D8W (C),DTA023YEB,UCR006,BD95514MUV,BD9S200MUF-C,SML-H10PD2B,DTD123TK,RFN6T2D,IMX25,BD80FD0WHFP,R6000ENH,SML-S13RT,BU64253GWZ,BD70GC0VEFJ-M,BD52XXG-2M,RBR2LAM30A,CSL0902DT (C),RBR5L30B,RBR5L30A,RSX501LAM20,RCX300N20,KD2003-F0FW00A,BH76363FV,RQ1E075XN,TFZV,RF4G060AT,BD83A04EFV-M,BV1LC085EFJ-C,BD10IC0WHFV,BU2394KN,BAXXBC0,SML-A12MT (J),BU4094BCF,KR2002-D06B71A,BD33C0AWFP2-C,ML86V76580,DTC114YEB,RQ5E020SP,BD63573NUV,DTA015TEB,BA90BC0,DTC114YE3,SML813BNT,BH1730FVC,DAN222WM,BD68888MUV,BM2P241W-Z,PML100,BU34DV7NUX,DTC143TKA,SCS220AJ,SMLK1,BD33GC0VEFJ-M,SCS220AG,R6511ENX,BDJ6FD0WHFP,SMLK18WBNCW,R6511ENJ,CSL0901UT (C),RX3L07BBG,QS8J2,RF305BM6S,SML-011VT (A),BH1603FVC,RS1E180BN,BD53108G-CZ,DTA124EEB,BD8317GWL,BD3508MUV,RB238NS100,BD950M5EFJ-C,BD450S2FP3-C,SML-S13YT,BD00FC0W,SML-010YT,DTA124EE3,BD50HC5VEFJ-M,BD60HA5VEFJ-,SML-H12D8T(C),BD81870MUF-M,RB168LAM-30,RFUH25TB3S,BD9B600MUV,DTD123YC,BM2P159PF,DTC024XUB,SML-P11DT (R),BD725L05G-C,DTA124ECA,RB168LAM-40,RSS065N06,DTD123YK,RH6E040BG,2SC2412K,BD25IC0V,BD25IC0W,BDJ2FC0W,LBP-602MA2,BD46EXX5G-M SERIES,FMY1A,BD7691FJ,BD82004FVJ-M,BDJ0GA3WNUX,BD450S5WFP2-C,SML-522MY8W,DAN222ZM,BM2P060MF-Z,RFS60TZ6S,DTC114YCA,RBR10BGE30A,RBR40NS60A,BH76809FVM,RRH100P03,SCT3105KL,DTC043ZEB,SCT3105KR,BD9060F-C,RQ6E080AJ,BA15DD0WT,RB168LAM-60,R6035KNZ4,DTC144EU3,2SA1037AK,RESD1CANY,DTC144EUB,SML-D13WW (C),BD2266G-M,DTC023EEB,SML-012PT (A),SML-S13DT,RBS1LAM40A,BD7690FJ,DTA143XCA,SMLP2,BSM180C12P2E202,RGTH60TS65D,BD50C0AFP-C,R6035VNX3,BD99950MUV,RE1J002YN,RF101LAM2S,BM61S41RFV-C,2SCR587D3,BD1HC500HFN-C,BU7205S,2SAR553P,BV1LE080EFJ-C,BV1LC150EFJ-C,SML-011DT,RS3E095BN,BD54105G-CZ,2SAR553R,RQ3E130BN,BU2FSA4WGWL,BD15HC5WEFJ,SML-812MT,DTA143XEB,BD9862MUV,BD52W03G-C,BD48W00G-C,DTA143XE3,SLI-325DU(W),LMR982,SLR343WBN2PT2□□□□□□,LMR981,BD37522FS,RB088BM150,RB088LAM100,2SAR552P,BD26503GUL,R8002KND3,2SCR512P5,QS8K2,BU7465S,RFNL15TJ6S,BD733L2FP-C,BD30KA5FP,LM8391EY,QS8J4,BD90C0AFP2-C,QS8J5,BD68710EFV,LB-402VN,BD50C0AWFP-C,BM1Z103FJ,2SAR554P,BD9060HFP-C,BC848BW,YQ30NL10SE,BR25G640,2SAR554R,RGTV80TS65,RB715FM-40,BD62120JEFJ,LB-402VD,RBR15BM30A,DTA124EKA,BA30JC5T,BA178M05FP,BD800M5WFPJ-C,SMLP2 SERIES,BD33IA5WEFJ,BAJ2DD0,2SCR523EBTL□□□,BDXXHC0WEFJ,DTB513ZM,RSDT27BM,SMLEN3WBC8W,BU33UV7NUX,SML-011UT(A),BU97550KV-M,RF101LAM4S,BM2P121X-Z,TE3004-TP1W00A,LBP-602MK2,RB078BM30S,BD8961NV,BD67173NUX,MG7901WZ,DTD123EK,SCS304AM,BU7461S,SCT3060ALHR,BD30FC0WFP,RB088LAM150,RGW00TS65DHR,YQ20BM10SD,RSS100N03,RQ6E045BN,2SAR552P5,BU7462S,RD3L220SN,BD7J101EFJ-LB,1SS390SMFHT2R,DTD123EC,DAN235FM,RFN2LAM6S,SCS215AJHR,BD65496MUV,KA2002-B05B70A,2SC5824,BU52272NUZ,2SC4102U3,BD9B300MUV,RB558WM,DTC114GU3,SML-D12Y1W,BU33SD2MG-M,RBQ15BM45A,BU7464S,BA178M18FP,RV3C002UN,BA178M05CP,SCS304AG,SLI-570 SERIES,BU29TA2W,SCS304AJ,SML-S13MT,BM63374S-VA,BM63374S-VC,RFN2LAM4S,BDJ0GA3V,BD49EXXG-M,BD3575YFP-M,BDJ0GA3W,BM2P13B1J-Z,BU32TD3W,DTA124EUB,RB168MM150,BA178M18CP,BD18IA5VEFJ-M,RB461FM,BU33SA4WGWL,BV1HLC45EFJ-C,DTA124EU3,SIR-56ST3F,BU18JA2VG-C,BD37068FV-M,RB162VAM-20,BU9794AKV,2SCR574D3,BU32TD2W,RGCL60TS60,BD9615MUV-LB,BM2P151X-Z,BD3814FV,LB-402MN,BD41041FJ-C,BD15GA3WNUX,LB-402MD,2SC5866,BU52077GWZ,SLI-343V8R,SML-D13WW (A),BD9573MUF-M,RB088BM100,BD18336NUF-M,SLA580ENT,VS14VUA1LAM,DTC043ZUB,MR7930,BD6326ANUX,SH2104WN,RSX101MM-30,SCT3030KLHR,BU7487,BU7486,BU7485,BU7481,UMZC6-8NFMFHT106,DTC144EE3,BD50GC0VEFJ-M,PMR18L,RD3R05BBH,DTC144ECA,MCR01,VS13VUA1LAM,MCR03,BD2200GUL,RS1E130GN,BD33GA5VEFJ-LB,BU7475,RQ6E030SP,BP3622,BD14210G-LA,BP3621,BSM180D12P3C007,BD63725BEFV,RBR5L40A,SML-Z14YT (A),BU7465,BA17815FP,BU7464,BU7462,BU7461,BU4051BCF,RCJ700N20,VS24VUA1VWM,BD00HC5VEFJ-LB,BD9408FV,BD00HA3VEFJ-LB,RX3P10BBH,KDZV SERIES,BU1ATD2WNVX,RB168MM100,BD8314NUV,BD9107FVM,BD34700FV,BD5466GUL,RF4E080BN,DTC144VCA,DAP202FM,SML-Z14YT (C),BA05CC0T,BA05CC0W,RF6G035BG,UT6KE5,SML-D13FW (C),BD60HC0VEFJ-M,BM2P134EF,BD00GA5VEFJ-M,BD30KA5WF,BU1JTD3W,BD60GA5VEFJ-LB,BD52XXNVX-2C,SML-D15YW (C),BM2P137TKF,MMBZ27VCLY,SML-811VT(A),BU90005GWZ,DTA123YM,RGWX5TS65D,LM358,ML62Q1714C,BA17815CP,BD16950EFV-C,KD3004-TQFW00A,RBR2LAM40A,DTC114WUA,BD33HA5WEFJ,BD00EA5W,UT6KC5,BD18340FV-M,LM324,ML62Q1713C,MCR10,RQ3G110AT,MNR12,MNR15,MNR14,2SCR586J,MNR18,SML-811VT(C),BM6242FS,BU28SA4WGWL,KA2003-B35N00A,MH2205WZ,RFS30TZ6S,LM339,LAP-601DB,BU7495,CSL1101WBDW,BD63536FJ,MNR02,QS6Z5,MNR04,STM 331U,BU1JTD2W,MC

12.2023 - ROHM - 选型指南 - 2024 Edition 代理服务技术支持批量订货

ROHM’s PMICs for SoCs Have Been Adopted in Reference Designs for Telechips‘ Next-Generation Cockpits

ROHM has announced the adoption of its PMICs in power reference designs focused on the next-generation cockpit SoCs ‘Dolphin3’ (REF67003) and ‘Dolphin5’ (REF67005) by Telechips. Intended for use inside the cockpits of European automakers, these designs are scheduled for mass production in 2025.

2024-12-13 - 原厂动态代理服务技术支持批量订货

ROHM and Nanjing SemiDrive Technology jointly Develop a Reference Design:Utilizing PMICs and SerDes ICs for SoCContributes to spread of smart vehicle cockpits

ROHM and Nanjing SemiDrive Technology Ltd., China’s largest SoC manufacturer for smart cockpits, have jointly developed a smart cockpit reference design. The design is primarily based on SemiDrive’s X9M and X9E automotive SoCs, and includes PMICs, SerDes ICs, LED driver IC, and other components from ROHM. A reference board based on this design is also available, consisting of three boards: the CoreBoard, the SerDes Board, and the Display Board.In recent years, the proliferation of smart cockpits and ADAS in vehicles has increased the demand for automotive electronics and components.

2024-06-05 - 原厂动态代理服务技术支持批量订货

Renesas（瑞萨）汽车产品选型指南

目录- 汽车微控制器汽车信息系统 - 微控制器微控制器工具片上系统片上系统工具电源电压产品分立式电源产品电机驱动器可配置的混合信号IC 触觉驱动器汽车传感器解决方案无线电源产品时钟和时序解决方案视频和显示控制器光电耦合器零件编号系统一般信息介绍

型号- R-CAR V3X,Y-RH850-P1X-144PIN-PB-T1-V2,NP60N04VUK,Y-RH850-F1X-100PIN-PB-T1-V3,Y-RH850-F1X-233PIN-PB-T2-V1,NP45N06PUK,NP75N04YUK,NP75N04YUG,R-CAR V4H,NP35N04YUG,R8A779M8,R8A779M7,R8A779M0,NP16N06YLL,R8A779M2,R8A779M1,R8A779M4,R-CAR GEN4,R8A779M3,R-CAR V4X,R-CAR E3E,R8A779M6,R8A779M5,DA9131-A,5P49V60,RL78/F1X,R-CAR M3E-2G,R8A779MB,DA9214-AT,DA7280-A,Y-R-CAR-M3N-SIP-BOARD-SKT-ES20,R5F109LD,R5F109LC,R5F109LB,RH850/D1M1A,R5F109LA,R-CAR D3,SLG46857-A,R5F109LE,NP36P04SDG,Y-RH850-F1X-324PIN-PB-T1-V1,ISL78714,Y-RCAR-V4H-WHITEHAWK-BRD-WS10,DA9215-AT,RTE0T00020KCE00000RE2,Y-ASK-RL78F14-V2,R-CAR D3E,R8A77980A,RAJ2800024H11HPF,R7F702300EABA,DA9132-A,NP160N055TUK,R-CAR S4-4,Y-ASK-RL78F15-V2,ZSC31150,NP45N06VDK,RL78/F13-CAN,DA9213-AT,RH850/ F1K,DA9141-A,NP50P04SDG,Y-QB-V850E2-EE,R-CAR S4-8,Y-RH850-P1XC-404PIN-PB-T1-V2,RH850/F1KM-S1,RH850/F1KM-S4,Y-RH850-X2X-MB-T1-V1,RTE0T00001FWREA000R,RTE7702200EAB00000J,Y-ASK-RH850F1KM-S1-V3,Y-RH850-D1L2-PB-TET-V1,R7F702300EBBG,R7F702300EBBB,RTP8A77980ASKB-0CW0SA001#WS,DA9224-AT,R5F10BAG,R5F10BAF,R5F10BAE,R5F10BAD,R7F702011EABG,R5F10BAC,NP29N06QUK,RTP0RC77995SEB0010S,NP89N04PUK,R-CAR H3,RH850/F1KH-D8,R7F702011EABA,RTP0RC7796SIPB0012SS5A,DA9142-A,NP20P06YLG,Y-RH850-E2X-292PIN-PB-T1-V2,NP179N04TUK,R5F10BBG,R5F10BBF,EWRL78,R5F10BBE,R5F10BBD,R5F10BBC,Y-RH850-E2X-373PIN-PB-T1-V3,R8A779FXLAX0BG,NP75P04YLG,RL78/F12,RL78/F13,RL78/F14,DA9130-A,RL78/F15,R-CAR V3M,R5F10AAA,R5F10DGD,Y-QB-R5F113TL-TB-V2,R5F10DGC,Y-R-CAR-V3M-BOARD-DEV-ES20,R-CAR V3H,RBA250N04AHPF-4UA01,NP30N06QDK,TW8832S,R5F10AAE,R5F10AAD,Y-ASK-RCAR-M3W-8GB-WS30,R5F10AAC,NP35N04YLG,R5F10DGE,R7F701412,Y-ASK-RCAR-V3H-WS11,R7F701652,R7F701410,R7F701653,R7F701411,Y-RH850-P1X-100PIN-PB-T1-V2,R7F701650,R7F701651,Y-RH850-F1X-144PIN-PB-T1-V3,R7F701649,R7F701408,R7F701647,R7F701648,R7F701645,R7F701403,NP15P06SLG,R7F701646,ISL79988,R5F10ABA,ISL79987,Y-QB-RL78D1A2-ZZZ-EE,NP90N04VUK,Y-RH850-D1M2H-PB-DEV-V1,R5F10ABE,R5F10ABD,QB-R5F109GE-TB,RBA160N04AHPF-4UA01,R5F10ABC,R7F701421,R7F701422,ΜPD166033,ΜPD166032,RAA279971,ΜPD166034,RAA279972,R7F701417,R-CAR M3,RV1S2752Q,R5F10CGD,R5F10CGC,R5F10CGB,Y-RH850-U2A-144PIN-PB-T1-V1,Y-QB-RL78F14-ZZZ-EE,Y-SBEV-RCAR-KF-M06,SLG46827-A,RH850/C1M-A2,RH850/C1M-A1,R7F702012AEABG,RTE7701460EPA00000R,R5F10PAE,RAA2S4251B,R5F10PAD,R7F701623,R-CAR GEN4 系列,R7F702012AEABA,ZSSC4132,Y-R-CAR-H3-8GB-BOARD-SKT-WS30,NP109N055PUK,ISL78434,R7F701401,R7F701644,R7F701402,Y-ASK-RCAR-V3H-WS21,DA9223-AT,NP90N06VLK,R5F10PBE,R5F10PBD,R5F10BGF,Y-RCAR-V3H-CONDOR-I-BRD-WS20,R5F10BGE,SLG46880-A,R5F10BGD,Y-RH850-X1X-MB-T1-V1,R5F10BGC,R8A77970,ISL78424,ZSSC3154,DA9062-A,ISL76671,R5F10BGG,NP75N055YUK,NP89N055PUK,NP20P04SLG,R5F113GL,RH850/P1L-C,R5F113GK,ZSSC4151,R5F10DLE,R5F10DLD,R5F10968,R-CAR M3NE-2G,ISL78610,R5F1096E,R5F1096D,R5F1096C,R5F1096B,R5F1096A,Y-ASK-RCAR-V3M-WS20-REV2,RTP0RC77951SKBX010SA03,P9149W,R5F10AGG,R5F10DMJ,QB-R5F10BMG-TB,R5F10AGF,ZSSC3170,R5F10AGE,R5F10AGD,R5F10DMG,R5F10AGC,R5F10DMF,Y-RH850-U2A-292PIN-PB-T1-V2,R5F10DME,R5F10AGA,R5F10DMD,ISL78600,RL78/F13-LIN,Y-R-CAR-D3-BOARD-DEV-WS11,DA9063-A,R- CAR H3NE-1.7G,R7F701710,RH850/P1M-C,RH850/P1M-E,DA9063L-A,QB-R5F10PPJ-TB,Y-RH850-X1X-MB-T2-V1,NP50P06KDG,ZSSC4175,R7F701708,R5F10CLD,R7F701709,NP75N04VUK,5P35023,5P35021,Y-ASK-RCAR-V3M-WS20,NP15P04SLG,R7F701278EAFP,Y-RH850-F1X-048PIN-PB-T1-V1,ZSSC4169,NP100P04PDG,R7F701715,R7F701714,R7F701711,Y-RH850-P1XC-292PIN-PB-T1-V2,ZSSC4161,ZSSC4162,ISL76683,Y-QB-RL78F15-ZZZ-EE,ZSSC4165,R5F10CME,R5F10CMD,R7F701371,R7F701372,NP60N04VDK,R-CAR V4X系列,RH850/X2X,Y-RH850-TFT-EXT-BRD,RH850/F1K,R5F10PGH,R7F701379,R5F10PGG,R5F10PGF,R7F701377,R5F10PGE,R7F701378,Y-RH850-E2X-40NM-EMU-ADAPTER-REV2,R5F10PGD,R7F701375,NP100P06PDG,R7F701376,DA9214-A,R7F701373,R7F701374,R5F10BLC,R5F10DPE,TW8819,R5F10PGJ,SLG46620-A,F1KM-S4,R5F10DPL,R5F10DPK,R5F10DPJ,R5F10BLG,R5F10BLF,R5F10BLE,R5F10DPG,R5F10BLD,R5F10DPF,R7F701382,R7F701383,R7F701380,R7F701381,ISL78365,R-CAR M3E,NP16N06QLK,R5F113LK,R7F701388,R7F701389,R5F10TPJ,R7F701386,R7F701384,R7F701385,NP90N04VLK,R5F113LL,TW8809,RTP8J77961ASKB0SK0SA05A,R5F10BMG,R5F10BMF,R5F10BME,R-CAR M3N,NP33N06YDG,5PB1110,RTE0T0002LKCE00000R,Y-ASK-RCAR-H3-8GB-WS30,R7F701275EABG,Y-BLDC-RH850F1KM-S1-V2,R5F113ML,R5F113MK,R7F701597,NP90N06VDK,NP50P03YDG,DA9215-A,ΜPD166031A,R5F10ALD,R5F10ALC,Y-RH850-F1X-176PIN-PB-T1-V4,NP20P06SLG,NP30N04QUK,TW8832,R5F10ALG,TW8836,R5F10ALF,R5F10ALE,NP83P04PDG,TW8834,DA9141-AT,RH850/X1X,RAA271005,RAJ2800044H12HPF,F1KM-S1,RAA271001,RAA271000,5PB1104,NP36P04KDG,R5F10AME,R-CAR S4,DA9130-AT,RH850/U2A16,RTP0RC77990SEB0020SA00,NP100N04PUK,RH850,Y-RH850-P1XC-144PIN-PB-T1-V1,R5F10DSL,R5F10DSK,R5F10AMG,R5F10DSJ,TW8824,R5F10AMF,TW8823,R7F701690,R7F701691,RH850/ F1KH-D8,DA9142-AT,RTP0RC77965SIPB012S-S,RV1S9184Q,R7F701694,R7F701695,R7F701692,R7F701693,RAA2S4253B,R7F701689,RH850/P1H-C,IPS2550DE1R,NP45N06VUK,NP50P04KDG,R5F10PLE,R5F113PG,R7F701580,R7F701581,DA9063L-AT,Y-R-CAR-M3W-8GB-BOARD-SKT-WS30,R-CAR GEN3E 系列,RH850/P1X-C,R7F701586,R5F10PLJ,R5F113PL,R7F701587,R5F113PK,R-CAR V3X 系列,NP36P06KDG,R5F10PLH,R5F113PJ,DA9224-A,R5F10PLG,R7

2022.04 - RENESAS - 选型指南 - 版本 5.0-1

【产品】瑞萨新一代SOC R-Car V3H，专为自动驾驶前置摄像头应用

瑞萨开发了专门针对前置摄像头应用的SoC——R-Car V3H，集成了专门针对图像处理的功能单元，它比R-Car V3M在视觉处理方面的性能提高了5倍，并只有0.3瓦的超低功耗，更好的适应自动驾驶的需求。

2018-03-07 - 新产品

How to Build Together a Safe and Efficient AD ＆ ADAS Central Computing Solution

Should RENESAS stop here and call it a success? Clearly no! Progress has no limits and by working together we ensure to constantly update our understanding of how autonomous systems of tomorrow will be and anticipate that by providing state-of-the-art processing solutions that would bring them successfully to the mass market.

2023-11-30 - 技术探讨

【产品】全新开放式平台，加大对ADAS及自动驾驶的支持

新型R-Car V3M SoC符合ISO26262功能安全标准，为视觉处理提供了低功耗硬件加速功能，还配有内置图像信号处理器。

2017-04-25 - 新产品

瑞萨电子携多款智能工业、物联网及汽车电子的先进解决方案亮相2023进博会

11月5日-10日，第六届中国国际进口博览会在上海国家会展中心盛大举办。本届进博会吸引了来自世界154个国家、地区超过3400家企业参加，规模为历届之“最”。瑞萨电子带来多款智能工业、物联网及汽车电子的先进解决方案再次亮相，展望产业可持续发展“芯”未来。

2023-11-16 - 原厂动态

Renesas Unveils Processor Roadmap for Next-Gen Automotive SoCs and MCUs

Renesas Electronics Corporation, a premier supplier of advanced semiconductor solutions, today laid out plans for its next-generation system on chips (SoCs) and microcontrollers (MCUs) targeting all major applications across the automotive digital domain.

2023-11-10 - 原厂动态

产品侦察车

描述- 这份资料主要介绍了汽车信息系统中使用的微控制器，包括其功能、特性、软件工具和评估板。资料涵盖了多种微控制器型号，如RL78和RH850系列，并详细介绍了它们在汽车应用中的优势。此外，资料还提供了相关软件开发工具和评估套件，以帮助开发者进行产品开发和测试。

型号- R-CAR V3X,Y-RH850-P1X-144PIN-PB-T1-V2,R7F7017623,Y-RH850-F1X-100PIN-PB-T1-V3,Y-RH850-F1X-233PIN-PB-T2-V1,R-CAR V4M,R-CAR V4H,R8A779M8,R8A779M7,R8A779M0,R8A779M2,R8A779M1,R8A779M4,R8A779M3,R-CAR GEN4,R-CAR V4X,R-CAR E3,R8A779M6,R-CAR E3E,R8A779M5,RL78/F1X,Y-R-CAR-M3N-SIP-BOARD-SKT-ES20,R7F7017603,R5F109LD,R5F109LC,RH850/D1M1A,R5F109LB,R5F109LA,R-CAR D3,R5F109LE,Y-RH850-F1X-324PIN-PB-T1-V1,Y-RCAR-V4H-WHITEHAWK-BRD-WS10,V3H2,Y-ASK-RL78F14-V2,RTP8J779M1ASKB0SL0SA103,F SERIES,R-CAR D3E,R7F702301BEBBA,R8A779G0LA01BA,R8A77980A,RTP8J779M3ASKB0SL0SA103,M3NE-2G,R-CAR S4-4,Y-ASK-RL78F15-V2,RL78/F13-CAN,R-CAR S4-8,Y-RH850-P1XC-404PIN-PB-T1-V2,RH850/F1KM-S1,RH850/F1KM-S2,RH850/F1KM-S4,Y-RH850-X2X-MB-T1-V1,RTE0T00001FWREA000R,RTE7702200EAB00000J,Y-ASK-RH850F1KM-S1-V3,R7F702002AEABA,R7F702002AEABG,R5F10BAG,R5F10BAF,R5F10BAE,R5F10BAD,R7F702011EABG,R5F10BAC,RTP0RC77995SEB0010S,R-CAR H3,RH850/F1KH-D8,R7F702011EABA,RTP0RC7796SIPB0012SS5A,Y-R-CAR-M3WE-8GB-BRD-DEV-WS30,R7F702301BFABG,Y-RH850-E2X-292PIN-PB-T1-V2,R5F10BBG,R5F10BBF,R5F10BBE,R5F10BBD,R5F10BBC,Y-RH850-E2X-373PIN-PB-T1-V3,H3,RL78/F12,RL78/F13,RL78/F14,RL78/F15,R5F10AAA,R5F10DGD,Y-QB-R5F113TL-TB-V2,R5F10DGC,Y-R-CAR-V3M-BOARD-DEV-ES20,R-CAR V3H,Y-ASK-RCAR-H3E-8GB-WS30,R5F10AAE,R5F10AAD,R5F10AAC,R5F10DGE,R7F701412,C SERIES,R7F701652,R7F701410,R7F701653,R7F701411,Y-RH850-P1X-100PIN-PB-T1-V2,R7F701650,E SERIES,R7F701651,Y-RH850-F1X-144PIN-PB-T1-V3,R7F701649,R7F701408,R7F701647,R7F701648,R7F701645,R7F701403,R7F701646,R5F10ABA,Y-QB-RL78D1A2-ZZZ-EE,M3E-2G,H3/M3,R5F10ABE,R5F10ABD,QB-R5F109GE-TB,R5F10ABC,R7F701423,R7F701421,R7F701422,U SERIES,R7F701417,R-CAR M3,R5F10CGD,R5F10CGC,R5F10CGB,Y-QB-RL78F14-ZZZ-EE,Y-SBEV-RCAR-KF-M06,Y-R-CAR-H3E-8GB-BRD-DEV-WS30,RH850/C1M-A2,RH850/C1M-A1,R7F702012AEABG,V3M,R5F10PAE,R5F10PAD,R7F701623,R7F702012AEABA,Y-R-CAR-H3-8GB-BOARD-SKT-WS30,R7F701401,RTP0RC77980SEBS012SA01,R7F701644,R7F701402,Y-ASK-RCAR-V3H-WS21,RTP8A77970ASKB0EG0SA001#WS,RTP8J779M5ASKB0SL0SA103,R5F10PBE,R5F10PBD,R5F10BGF,Y-RCAR-V3H-CONDOR-I-BRD-WS20,R5F10BGE,R5F10BGD,Y-RH850-X1X-MB-T1-V1,R5F10BGC,R8A77970,R5F10BGG,RH850/P1L-C,R5F113GL,R5F113GK,R5F10DLE,R5F10DLD,R5F10968,R7F701609,R5F1096E,R5F1096D,R5F1096C,R5F1096B,R5F1096A,Y-ASK-RCAR-V3M-WS20-REV2,R5F10AGG,R5F10DMJ,QB-R5F10BMG-TB,R5F10AGF,R5F10AGE,R5F10AGD,R5F10DMG,R5F10AGC,R5F10DMF,Y-RH850-U2A-292PIN-PB-T1-V2,R5F10DME,R5F10AGA,R5F10DMD,RL78/F13-LIN,Y-R-CAR-D3-BOARD-DEV-WS11,R7F701710,RH850/P1M-C,RH850/P1M-E,QB-R5F10PPJ-TB,Y-RH850-X1X-MB-T2-V1,R7F701708,R7F702300BEBBC,R5F10CLD,R7F701709,R7F702300BEBBB,Y-ASK-RCAR-V3M-WS20,R7F701278EAFP,Y-RH850-F1X-048PIN-PB-T1-V1,R7F701715,H3E-2G,R7F701714,R7F701711,Y-RH850-P1XC-292PIN-PB-T1-V2,Y-QB-RL78F15-ZZZ-EE,R5F10CME,R5F10CMD,R7F701371,R7F701372,Y-RH850-TFT-EXT-BRD,RH850/X2X,RH850/F1K,R5F10PGH,R7F701379,R5F10PGG,R5F10PGF,R7F701377,R5F10PGE,R7F701378,Y-RH850-E2X-40NM-EMU-ADAPTER-REV2,R5F10PGD,R7F701375,D SERIES,R7F701376,R7F701373,R7F701374,R5F10BLC,R5F10DPE,R5F10PGJ,F1KM-S4,R5F10DPL,R5F10DPK,R5F10DPJ,R5F10BLG,F1KM-S1/-S4,R5F10BLF,R5F10BLE,R5F10DPG,R5F10BLD,R5F10DPF,R7F701382,R7F701383,R7F701380,R7F701381,R-CAR M3E,R5F113LK,R7F701388,R7F701389,R5F10TPJ,R7F701386,R7F701384,R7F701385,R8A779H1LL31BA,R5F113LL,R5F10BMG,R5F10BMF,R5F10BME,R-CAR M3N,RTE0T0002LKCE00000R,R7F701275EABG,Y-BLDC-RH850F1KM-S1-V2,R5F113ML,R5F113MK,R7F701597,R5F10ALD,R5F10ALC,Y-RH850-F1X-176PIN-PB-T1-V4,R5F10ALG,RTP8J779M1ASKB0SK0SA003,R5F10ALF,R5F10ALE,RH850/X1X,F1KM-S1,R5F10AME,R-CAR S4,RH850/U2A16,RTP0RC77990SEB0020SA00,RH850,Y-RH850-P1XC-144PIN-PB-T1-V1,R5F10DSL,R5F10DSK,R5F10AMG,R5F10DSJ,R5F10AMF,R7F701690,R7F701691,RTP0RC77965SIPB012S-S,Y-R-CAR-M3NE-2GB-BRD-DEV-WS11,R7F701694,R7F701695,R7F701692,R7F701693,RH850/P1H-C,R7F701689,R5F10PLE,R5F113PG,R7F701580,R7F701581,Y-R-CAR-M3W-8GB-BOARD-SKT-WS30,RH850/P1X-C,R7F701586,R5F10PLJ,R5F113PL,R7F701587,R5F113PK,R5F10PLH,R5F113PJ,R5F10PLG,R7F701582,R7F701461,R5F10PLF,R5F113PH,R7F701583,R7F701462,R7F702300BFABA,RL78,Y-RH850-U2A-516PIN-PB-T1-V1,R5F10PMF,R5F10PME,R7F701432,R5F10PMJ,R7F701430,R-CAR M3NE,R7F701431,R5F10PMH,R5F10PMG,RH850/D1L1,RH850/D1L2,R7F701428,R7F701687,R7F701688,R7F701685,P SERIES,R7F701686,R7F701441,R7F701684,R7F701442,R5F109AA,RH850/D1M2,Y-RH850-F1X-064PIN-PB-T1-V1,R7F701437,R5F109AE,R5F109AD,R5F109AC,R5F109AB,R-CAR GEN3E,RH850/D1S1,RH850/U2A8,R5F113TK,R-CAR,R5F10PPH,R5F113TJ,R5F10PPG,R5F10PPF,R5F113TH,R5F10PPE,R5F113TG,Y-RH850-P1XC-080PIN-PB-T1-V1,RTE0T00020KCE00000R,R5F10PPJ,R5F113TL,Y-RH850-E2X-468PIN-PB-T1-V1,Y-QB-RL78F12-ZZZ-EE,R-CAR S4N-8,R8A779F5,R8A779F4,R8A779F7,R8A779F6,Y-RH850-U2A-373PIN-PB-T1-V1,Y-RTE0T0850AKCT00000J-EU,R-CAR S4N-4,Y-ASK-RH850F1K-V3,RH850/D1M1-V2,Y-R-CAR-E3-BOARD-DEV-WS11,RTP8A779F0ASKB0SP2S,Y-RH850-P1XC-100PIN-PB-T1-V1,RL78/D1A,RH850/E2UH,RTP0RC7795SIPB0012S-S03,RH850/D1M2H,RH850/E2X,Y-SBEV-RCAR-KF-GMSL02,Y-SICA20I2P,Y-ASK-RH850F1KH-D8-V3,Y-ASK-RL78F12-V2,R5F10A6E,R5F10A6D,R5F10A6C,R5F10A6A,Y-QB-RL78D1A-ZZZ-EE,RH850/D1X,R5F109GE,Y-ASK-RH850F1KM-S4-V3,R5F109GD,R5F109GC,R5F109GB,R5F109GA,Y-ASK-RL78F13-V2,R7F701391,R7F701390,F1KH-D8,R

FEBRUARY 2023 - RENESAS - 商品及供应商介绍 - EDITION FEBRUARY 2023

【产品】R-Car V3H的Starter kit开发板ASK-RCAR-V3H-WS10/WS11

Renesas R-Car V3H使用了IMP-X5+作为图像识别的引擎以及专门的硬件加速器，并取得了先进的传感能力，这些算法中包括了密集的光流处理、密集的立体视觉差的处理和目标分类算法。R-Car V3H集成的CNN功能可以加速深度学习，并只有0.3瓦的超低功耗。本文主要介绍R-Car V3H的Starter kit开发板ASK-RCAR-V3H-WS10/WS11介绍。

2019-11-12 - 新产品