Google said Tuesday that its Cloud TPU v5p, one of the few alternatives to Nvidia’s AI chips, is now available to developers.
Will Tesla finally unveil a self-driving vehicle?
The AI chip was first announced in December, the same day as its chatbot Gemini. The new TPU, or tensor processing unit, can train large language models almost three times faster than its predecessor, Google’s TPU v4, the company said. Large language models (LLMs) power AI chatbots like ChatGPT.
Google’s announcement marks another milestone in Big Tech’s AI arms race. Nvidia is the main supplier of the AI chips known as GPUs, or graphics processing units. Google parent Alphabet is one of Nvidia’s biggest customers, behind Microsoft and Facebook parent Meta.
And Google, Microsoft, Amazon, and Meta are all developing their own AI chips.
But Nvidia is still important to Google. In the same blog post announcing its latest AI chip, Google mentioned Nvidia 20 times. Right under its detailing of the TPU v5p, the company said it’s updating its A3 supercomputer, which runs on Nvidia GPUs. And Google reminded users that it’s using Nvidia’s latest chip, the Blackwell, in its AI Hypercomputer.
Google also its new Arm-based CPU, AxionGoogle also announced an Arm-based central processing unit called Google Axion to rival the CPUs of Microsoft and Amazon. The British tech company Arm licenses its design for chips’ infrastructure for actual chip manufacturers to build upon. Google’s new chip marks the first time it has licensed Arm’s chip infrastructure for a CPU.
Google said its new Arm-based CPU provides “up to 30% better performance than the fastest general-purpose Arm-based instances available in the cloud today, up to 50% better performance and up to 60% better energy-efficiency” than other general purpose Arm chips.
Google customers can use Axion CPU on its cloud services, which basically means those users would be opting to run their cloud services on a more efficient computer processor in Google’s physical data centers. Google also told Reuters that “customers using Arm anywhere can easily adopt Axion without re-architecting or re-writing their apps.” Its rivals Amazon and Microsoft have already developed Arm-based CPUs.
{Categories} _Category: Applications,*ALL*{/Categories}
{URL}https://qz.com/google-ai-chip-nvidia-axion-arm-microsoft-1851397201{/URL}
{Author}Laura Bratton{/Author}
{Image}https://i.kinja-img.com/image/upload/c_fill,h_675,pg_1,q_80,w_1200/215749b27d9413739e3b92cd540a2f03.jpg{/Image}
{Keywords}amazon,google,nvidia,microsoft,artificial intelligence,graphics processing unit,axion,fabless semiconductor companies,google cloud,ai accelerators,microprocessors,arm holdings,thomas kurian,technology internet,tensor processing unit,application specific integrated circuits,sundar pichai,alphabet,blackwell,cloud tpu v5p{/Keywords}
{Source}All{/Source}
{Thumb}https://i.kinja-img.com/image/upload/c_fit,q_80,w_636/215749b27d9413739e3b92cd540a2f03.jpg{/Thumb}