Amazon’s Inferentia chip to handle some Alexa voice assistant services
Amazon said Thursday it switched some of the computing for its Alexa voice assistant to its own custom-designed chips, with the aim of making the job faster and cheaper while moving away from Nvidia-supplied chips.
When device users like From amazon The Echo line of smart speakers asks the voice assistant a question, the query is sent to one of Amazon’s data centers for various processing steps. When Amazon’s computers spit out a response, that response is in a text format that must be translated into audible speech for the voice assistant.
Amazon previously handled that computing using chips Nvidia but now the “majority” will occur using its own Inferentia computing chip. First announced in 2018, Amazon’s chip is custom designed to speed up large volumes of machine learning tasks, such as translating text to speech or recognizing images.
Cloud computing clients such as Amazon, Microsoft and from Alpahbet Google have become some of the largest buyers of computer chips, fueling the boom in data center sales in Intel, Nvidia and others.
But major tech companies are increasingly abandoning traditional silicon suppliers to design their own chips. Apple on Tuesday inserted his first Mac computers with their own central processors, moving away from Intel chips.
Amazon said the switch to the Infertia chip for some of its Alexa work has resulted in 25 percent better latency, which is a measure of speed, at a 30 percent lower cost.
Amazon has also said that Rekognition, its cloud-based facial recognition service, has started adopting its own Inferentia chips. However, the company did not say which chips the facial recognition service had previously used or how much of the work had been transferred to its own chips.
The service has come under scrutiny by civil rights groups due to its use by law enforcement. Amazon in June imposed a one-year moratorium on its use by police after the murder of George Floyd.