Baidu and Samsung Electronics announced on Wednesday that Baidu's first cloud-to-edge AI accelerator, Baidu KUNLUN, has completed its development and will be mass-produced early next year.
The chip is built on Baidu's advanced XPU, a home-grown neural processor architecture for cloud, edge, and AI, as well as Samsung's 14-nanometer (nm) process technology with its I-Cube (Interposer-Cube) package solution.
It offers 512 gigabytes per second memory bandwidth and supplies up to 260 Tera operations per second (TOPS) at 150 watts. In addition, the new chip allows Ernie, a pre-training model for natural language processing, to infer three times faster than the conventional GPU/FPGA-accelerating model.
Baidu hopes to support a wide variety of functions including large-scale AI workloads, such as search ranking, speech recognition, image processing, natural language processing, autonomous driving, and deep learning platforms like PaddlePaddle by leveraging the chip's limit-pushing computing power and power efficiency.
Compared to previous technology, these solutions maximize product performance with more than 50% improved power/signal integrity, the two companies said.
It is anticipated that I-Cube technology will mark a new epoch in the heterogeneous computing market. Samsung is also developing more advanced packaging technologies, such as redistribution layers (RDL) interposer and 4x, 8x HBM integrated package.
