Alibaba unveil groundbreaking AI chip
Alibaba Group released a new artificial intelligence-driven chip that specializes in machine-learning tasks, as China sharpens its focus on the integration of emerging technologies such as AI and 5G into its economy.
The home-grown AI inference chip, a neural processing unit (NPU) named Hanguang 800, was unveiled during Alibaba Cloud’s annual computing conference in Hangzhou, as the company looks to make its e-commerce platform more efficient using AI.
“The launch of Hanguang 800 is an important step in our pursuit of next-generation technologies, boosting computing capabilities that will drive both our current and emerging businesses while improving energy-efficiency,” Jeff Zhang, Alibaba CTO and president of Alibaba Cloud Intelligence, said in a statement.
“We plan to empower our clients by providing access through our cloud business to the advanced computing that is made possible by the chip, anytime and anywhere.”
The chip was developed by DAMO Academy, a research institute Alibaba launched in late 2017, and T-Head, the company’s specialized semiconductor division.
While not available for commercial sales at the moment, the chip is currently being used in optimizing consumer experience product searches and automatic translation on e-commerce sites, personalized recommendations, advertising, and intelligent customer services.
Around one billion product images are uploaded to Taobao, Alibaba’s e-commerce site, every day by merchants.
According to Zhang, it used to take the machine one hour to categorize such a large volume of images for tailored searches and personalized recommendations for consumers.
But with Hanguang 800, it only takes the machine five minutes to complete the same task.
“The differentiator here is that algorithms are directly built into the chip. Alibaba is proving that its technological strength not only lies in software, but hardware as well,” said a senior technology executive with over two decades’ industry experience who attended the launch event.
Alibaba said its single-chip computing performance reached a peak 78,563 IPS, while the computation efficiency was 500 IPS/W during the Resnet-50 Inference test, both of which it claimed to be “largely outpacing industry average”.
Huawei unveiled last month a new high-end artificial intelligence chip for servers, Ascend 910, which it claimed to be “the world’s most powerful AI processor” targeted at AI model training.
Normally chips are largely classified as either’training’ – feeding algorithms to machines to recognize and categorize objects – or ‘inference’, which, based on training, take real-world data and quickly return the correct answer, the source said.
“While traditionally GPUs enhance the capabilities to do the ‘training, that is, recognize items, NPUs are better at inference, like enriching application scenarios,” he said.
Alibaba had earlier released its first core processor IP based on RISC-V open-source chip architecture.
Such architecture will provide the company an alternative to the dominant architecture supplied by Arm Holdings Inc, the source said.