NVIDIA’s GPUs powered the AI revolution. Its new Blackwell chips are up to 30 times faster

In less than two years, NVIDIA’s H100 chips, which are used by nearly every AI company in the world to train large language models that power services like ChatGPT, made it one of the world’s most valuable companies. On Monday, NVIDIA announced a next-generation platform called Blackwell, whose chips are between seven and 30 times faster than the H100 and use 25 times less power.

“Blackwell GPUs are the engine to power this new Industrial Revolution,” said NVIDIA CEO Jensen Huang at the company’s annual GTC event in San Jose attended by thousands of developers, and which some compared to a Taylor Swift concert. “Generative AI is the defining technology of our time. Working with the most dynamic companies in the world, we will realize the promise of AI for every industry,” Huang added in a press release.

NVIDIA’s Blackwell chips are named in honor of David Harold Blackwell, a mathematician who specialized in game theory and statistics. NVIDIA claims that Blackwell is the world’s most powerful chip. It offers a significant performance upgrade to AI companies with speeds of 20 petaflops compared to just 4 petaflops that the H100 provided. Much of this speed is made possible thanks the 208 billion transistors in Blackwell chips compared to 80 billion in the H100. To achieve this, NVIDIA connected two large chip dies that can talk to each other at speeds up to 10 terabytes per second.

In a sign of just how dependent our modern AI revolution is on NVIDIA’s chips, the company’s press release includes testimonials from seven CEOs who collectively lead companies worth trillions of dollars. They include OpenAI CEO Sam Altman, Microsoft CEO Satya Nadella, Alphabet CEO Sundar Pichai, Meta CEO Mark Zuckerberg, Google DeepMind CEO Demis Hassabis, Oracle chairman Larry Ellison, Dell CEO Michael Dell, and Tesla CEO Elon Musk.

“There is currently nothing better than NVIDIA hardware for AI,” Musk says in the statement. “Blackwell offers massive performance leaps, and will accelerate our ability to deliver leading-edge models. We’re excited to continue working with NVIDIA to enhance AI compute,” Altman says.

NVIDIA did not disclose how much Blackwell chips would cost. Its H100 chips currently run between 25,000 and $40,000 per chip, according to CNBC, and entire systems powered by these chips can cost as much as $200,000.

Despite their costs, NVIDIA’s chips are in high demand. Last year, delivery wait times were as high as 11 months. And having access to NVIDIA’s AI chips is increasingly seen as a status symbol for tech companies looking to attract AI talent. Earlier this year, Zuckerberg touted the company’s efforts to build “a massive amount of infrastructure” to power Meta’s AI efforts. “At the end of this year,” Zuckerberg wrote, “we will have ~350k Nvidia H100s — and overall ~600k H100s H100 equivalents of compute if you include other GPUs.”

Source link


gaitQ and machineMD secure million dollar research grant to monitor Parkinson’s development in UK and Switzerland

Oxford-based medical technology start-up gaitQ and Swiss medical device company machineMD have announced the joint award of a million dollar research grant from Innovate UK and Innosuisse to enable the collection and analysis of critical movement data from people with Parkinson’s (PwP). The grant will fund an 18-month research project that will record movement data […]

Read More

Take-Two plans to lay off 5 percent of its employees by the end of 2024

Take-Two Interactive plans to lay off 5 percent of its workforce, or about 600 employees, by the end of the year, as reported in an SEC filing Tuesday. The studio is also canceling several in-development projects. These moves are expected to cost $160 million to $200 million to implement, and should result in $165 million […]

Read More

10 tips to avoid planting AI timebombs in your organization

At the recent HIMSS Global Health Conference & Exhibition in Orlando, I delivered a talk focused on protecting against some of the pitfalls of artificial intelligence in healthcare. The objective was to encourage healthcare professionals to think deeply about the realities of AI transformation, while providing them with real-world examples of how to proceed safely […]

Read More