Nio-backed artificial intelligence and autonomous driving chip maker Black Sesame Technologies' new self-driving chip, the A1000 Pro, has taped out with a record high computing performance among such chips built by local companies.
The A1000 Pro is based on the company's A1000 chip, which is optimized to achieve 106 TOPS of computing power as standard and up to 196 TOPS in the acceleration mode, according to Black Sesame.
(A1000 Pro.)
The A1000 Pro's built-in high-performance GPU can support high-definition 360-degree 3D panoramic image rendering, covering L3/L4 high-level autonomous driving functions, supporting autonomous driving scenarios from parking, city roads, to highways, it said.
The A1000 Pro is the only chip with high computing performance in China that can meet the requirements of ISO 26262 ASIL D, the company said.
ASIL D is the highest safety level and is a safety requirement for intelligent driving systems and body stability control systems.
The company's A1000, released last year, received ISO 26262 ASIL B certification.
Black Sesame said it has worked with companies including Nio, SAIC, BYD, Dongfeng Motor, FAW and Bosch on L2/L3 ADAS and autonomous driving sensing system solutions.
Founded in August 2016 with R&D centers in Shanghai and Silicon Valley, Black Sesame had received Series A funding from Northern Light Ventures in November 2016.
In January 2018, Black Sesame announced a strategic Series A+ funding round of nearly RMB 100 million ($15.4 million), led by Nio Capital, the venture capital business of Nio. This is also the second project Nio Capital has invested in since its inception in 2016.
In April 2019, Black Sesame received close to $100 million in Series B funding led by Legend Capital.
Black Sesame's primary business is the development of artificial intelligence system-on-chips (SoCs) with core technologies including image/video processing, optical processing, perceptual understanding algorithms, deep neural networks and fused perception systems.
This solution uses light control technology to process the light field for information from vehicles, pedestrians, lane lines, traffic signs, and signals, enabling the camera to image under various special driving cycles.
After these signals enter Black Sesame's perception system, the SoC computing platform passes the perception results to self-driving companies for decision making and control.
