Nvidia Corp. on Tuesday announced a number of new chips and technologies that it said will boost the computing speed of increasingly complex artificial intelligence algorithms, increasing competition for a lucrative data center business against rival chipmakers. Nvidia’s graphic chips (GPUs), which initially helped propel and enhance video quality in the gaming market, have become the flagship chips for companies for AI workloads. The company said the latest GPU, dubbed the H100, could help reduce computing time from weeks to days for some tasks associated with training AI models.
The announcements were made online at Nvidia’s AI Developers Conference. “Data centers are becoming AI factories – processing and refining mountains of data to produce intelligence,” said Nvidia chief executive Jensen Huang in a statement, calling the H100 chip the “engine” of the AI infrastructure.
Companies are using AI and machine learning for everything from recommending the next video to discovering a new drug, and the technology is fast becoming an important tool for business.
Nvidia said the H100 chip will be produced on Taiwan Manufacturing Semiconductor Company’s state-of-the-art four-nanometer process with 80 billion transistors and will be available in the third quarter. The H100 will also be used to build Nvidia’s new “Eos” supercomputer, which Nvidia said will be the world’s fastest AI system when it begins operations later this year.
Facebook’s parent Meta announced in January that it would build the world’s fastest AI supercomputer this year and that it would perform at around 5 exFLOPS. Nvidia said Tuesday that its supercomputer will run at more than 18 exFLOPS.
Exaflop performance is the ability to perform 1 quintillion – or 1,000,000,000,000,000,000 – calculations per second.
In addition to the GPU chip, Nvidia introduced a new processor chip (CPU) called the Grace CPU Superchip which is based on Arm technology. This is Nvidia’s first new chip based on the Arm architecture, announced since the company’s deal to buy Arm Ltd. due to regulatory hurdles last month. The Grace CPU Superchip, which will be available in the first half of next year, combines two CPU chips and will focus on AI and other tasks that require intensive computing power.
More companies are connecting chips using technology that allows faster data flow between them. Earlier this month Apple Inc introduced its M1 Ultra chip, which combines two M1 Max chips. [nL2N2VB1DI]Nvidia said the two CPU chips were connected using its NVLink-C2C technology, which was also unveiled on Tuesday.
Nvidia shares were up more than 1% in afternoon trading.
read all breaking news , today’s fresh news And Ukraine-Russia War Live Updates Here.