Designed based mostly on Samsung’s 14nm course of and I-Cube TM bundle know-how,
Baidu KUNLUN chip to broaden AI ecosystem and rework the person expertise
Baidu, a number one Chinese-language Internet search supplier, and Samsung Electronics, a world chief in superior semiconductor know-how, at the moment introduced that Baidu’s first cloud-to-edge AI accelerator, Baidu KUNLUN, has accomplished its improvement and might be mass-produced early subsequent 12 months.
Baidu KUNLUN chip is constructed on the corporate’s superior XPU, a home-grown neural processor structure for cloud, edge, and AI, in addition to Samsung’s 14-nanometer (nm) course of know-how with its I-Cube™ (Interposer-Cube) bundle resolution.
The chip provides 512 gigabytes per second (GBps) reminiscence bandwidth and provides as much as 260 Tera operations per second (TOPS) at 150 watts. In addition, the brand new chip permits Ernie, a pre-training mannequin for pure language processing, to deduce 3 times quicker than the standard GPU/FPGA-accelerating mannequin.
Leveraging the chip’s limit-pushing computing energy and energy effectivity, Baidu can successfully assist all kinds of capabilities together with large-scale AI workloads, comparable to search rating, speech recognition, picture processing, pure language processing, autonomous driving, and deep studying platforms like PaddlePaddle.
Through the primary foundry cooperation between the 2 corporations, Baidu will present superior AI platforms for maximizing AI efficiency, and Samsung will broaden its foundry enterprise into excessive efficiency computing (HPC) chips which might be designed for cloud and edge computing.
“We are excited to lead the HPC industry together with Samsung Foundry,” stated OuYang Jian, Distinguished Architect of Baidu. “Baidu KUNLUN is a very challenging project since it requires not only a high level of reliability and performance at the same time, but is also a compilation of the most advanced technologies in the semiconductor industry. Thanks to Samsung’s state of the art process technologies and competent foundry services, we were able to meet and surpass our goal to offer superior AI user experience. ”
“We are excited to start a new foundry service for Baidu using our 14nm process technology,” stated Ryan Lee, vp of Foundry Marketing at Samsung Electronics. “Baidu KUNLUN is an important milestone for Samsung Foundry as we’re expanding our business area beyond mobile to datacenter applications by developing and mass-producing AI chips. Samsung will provide comprehensive foundry solutions from design support to cutting-edge manufacturing technologies, such as 5LPE, 4LPE, as well as 2.5D packaging.”
As larger efficiency is required in numerous functions comparable to AI and HPC, chip integration know-how is changing into increasingly more vital. Samsung’s I-Cube™ know-how, which connects a logic chip and excessive bandwidth reminiscence (HBM) 2 with an interposer, gives larger density/ bandwidth on minimal measurement by using Samsung’s differentiated options.
Compared to earlier know-how, these options maximize product efficiency with greater than 50% improved energy/sign integrity. It is anticipated that I-Cube™ know-how will mark a brand new epoch within the heterogeneous computing market. Samsung can be creating extra superior packaging applied sciences, comparable to redistribution layers (RDL) interposer and 4x, 8x HBM built-in bundle.
2.5D Package Structure
About Baidu
Baidu, Inc. is the main Chinese language Internet search supplier. Baidu goals to make the difficult world easier by know-how. Baidu’s ADSs commerce on the NASDAQ Global Select Market underneath the image “BIDU”. Currently, ten ADSs signify one Class A odd share.
