Delivers 60.4 TOPS and 13.8 TOPS/W, processing complicated duties for autonomous driving techniques on a single chip

Automotive SoC Processor Applied sciences. Picture courtesy: Renesas

Renesas Electronics Company has efficiently developed processor applied sciences for automotive systems-on-chip (SoC) that can be utilized for optimising each efficiency and energy effectivity of superior driver help techniques (ADAS) and autonomous driving (AD) techniques whereas supporting a excessive stage of practical security. 

Purposes resembling next-generation ADAS and AD techniques require excellent deep studying efficiency of 60 TOPS and even 120 TOPS alongside energy effectivity. Apart from, since sign processing from object identification to the issuing of management directions constitutes a bulk of the processing load in AD techniques, attaining the practical security equal to ASIL D is a urgent concern. Due to this fact the brand new applied sciences meet these wants, together with a {hardware} accelerator that delivers excellent CNN processing efficiency with superior energy effectivity.

The newly-developed applied sciences used within the R-Automobile V3U SoC are:

  • Excessive-performance CNN {hardware} accelerator with superior energy effectivity

 Because the variety of sensors utilised in next-generation ADAS and AD techniques will increase, extra highly effective processing efficiency is required. There may be additionally a necessity to scale back the warmth generated by energy consumption to make doable electronics management models (ECUs) which might be air-cooled, bringing weight and value benefits. Due to this fact the brand new convolutional neural community (CNN) {hardware} accelerator core comes with superior deep studying efficiency and implements three such cores, in a high-density configuration, on the R-Automobile V3U. 

Moreover, the R-Automobile V3U has 2 megabytes (MB) of devoted reminiscence per CNN accelerator core for a complete reminiscence of 6 MB. This reduces information transfers between exterior DRAM and the CNN accelerator by greater than 90 per cent and efficiently achieves a excessive CNN processing efficiency of 60.4 TOPS with best-in-class energy effectivity of 13.8 TOPS/W.

  • Improvement of security mechanisms for ASIL D techniques able to self-diagnosis

 The ISO 26262 automotive practical security commonplace specifies numerical targets (metrics) for numerous practical security ranges. The metrics for ASIL D, the best practical security stage, are 99 per cent or above for the only level fault metric (SPFM) and 90 per cent or above for the latent fault metric (LFM), which signifies that an especially excessive detection price is required for random {hardware} failures. 

Additionally, as a result of excessive stage of involvement in automobile operation of techniques resembling next-generation ADAS and AD techniques, automotive SoCs have total included extra features topic to ASIL D necessities. Security mechanisms for quick detection of and response to random {hardware} failures occurring within the SoC have been developed, permitting diminished energy consumption and a excessive failure detection price. The incorporation of those mechanisms into the R-Automobile V3U is anticipated to deliver the vast majority of the SoC’s sign processing into attaining the ASIL D metrics, which is able to impartial self-diagnosis and reduces the complexity of fault-tolerant AD system design.

  • Assist mechanism for freedom from interference (FFI) between software program duties

 Attaining freedom from interference (FFI) between software program duties is a vital side of assembly practical security requirements. When software program elements with totally different security ranges are current within the system, it’s important to forestall lower-level duties from inflicting dependent failures in higher-level duties. FFI must also be ensured when accessing management registers in numerous {hardware} modules and shared reminiscence. For this, an FFI help mechanism has been developed that displays all information flowing by interconnects within the SoC and blocks unauthorised entry between duties. This allows FFI between all duties working on the SoC, making it doable to understand an SoC for ASIL D purposes able to managing object identification, sensor fusion with radar or LiDAR, route planning and issuing of management directions with a single chip.

Renesas offered these achievements on the lately concluded Worldwide Strong-State Circuits Convention 2021 (ISSCC 2021).


LEAVE A REPLY

Please enter your comment!
Please enter your name here