- Nvidia Corp has unveiled new flagship chips for video gamers using artificial intelligence to enhance graphics.
- The graphics cards, known as ‘Ada Lovelace’, will be made by Taiwanese giant TSMC using the latest “4N” chip manufacturing technology.
Nvidia may have lost nearly half of its stock value this year, but the semiconductor clock is growing at a fantastic rate in terms of growth. To date, it continues to lead in the world when it comes to graphics processing units (GPUs) and artificial intelligence (AI) chips – all while giving a big boost to the automotive industry. At that time, the American chipmaker announced a slew of new chips for gaming, AI and autonomous driving space.
Nvidia founder and CEO Jensen Huang Jen-hsun during the company GPU Technology Conference Tuesday unveiled its new H100 AI processor, a successor to the A100 used today to train AI systems to do things like translate human speech, recognize what’s in pictures, and plot the route of a self-driving car through traffic.
In fact, the A100 is the best member of the family of GPUs that propelled Nvidia to business success. The company’s NVLink high-speed communications route also allows customers to link as many as 256 H100 chips together in “essentially one stunning GPU,” Huang said at the online conference. The A100 is based on a design called Hopper and can interface with Nvidia’s new central processing unit called Grace, the CEO noted at the conference.
Huang shared that the H100 GPUs will ship in the third quarter of this year and that Grace is “on track to ship next year.” Currently, there’s actually plenty of competition for the H100, which is made up of a whopping 80 billion transistors that make up its data processing circuitry. Rivals include Intel’s upcoming Ponte Vecchio processor, with more than 100 billion transistors, and a host of special AI accelerator chips from startups like Graphcore, Samba Nova Systems and brain.
Newer Nvidia chips for gaming
No doubt Nvidia has gained attention in recent years with its thriving data center business, which sells chips used in AI work, such as natural language processing. However, the company’s roots are still in graphics chips, which still accounted for 59% of $26.9 billion in revenue in its most recent fiscal year. At the conference, Huang also introduced the company’s latest line of graphics cards, known as Ada Lovelace.
“The world’s first GPUs based on the new NVIDIA® Ada Lovelace architecture, the RTX 40 series delivers massive generational leaps in performance and efficiency, representing a new era of real-time ray tracing and neural imagingthat uses AI to generate pixels,” Nvidia said in a statement.
While Nvidia designs its chips, the company has partners make them, and Huang said this latest series of chips will be made by Taiwan Semiconductor Manufacturing Co (TSMC) with its 4N chip manufacturing technology, a change from Nvidia’s previous-generation flagship gaming chips. that are made by Samsung Electronics. Huang also announced: NVIDIA DLSS 3 — the next revolution in the company’s Deep Learning Super Sampling neural-graphics technology for games and creative apps.
The AI-powered technology can generate entire frames for vastly faster gameplay. It can overcome CPU performance limitations in games by letting the GPU generate full frames independently. The technology comes to the world’s most popular game engines, such as Unity and Unreal Engine, and has received support from many of the world’s leading game developers, including coming soon more than 35 games and appssaid Nvidia.
Nvidia’s global GeForce marketing vice president Matt Wuebbling said in a web briefing that the Lovelace chips will be available for sale worldwide and will not be affected by a recently imposed US ban on the sale of Nvidia’s best data center AI chips to China. As a reminder, in the second quarter of this year, Nvidia’s gaming division revenue fell 33% year-on-year (YoY) to US$2.04 billion, which was a sharper decline than the company had anticipated.
The miss was attributed to lower sales of its gaming products, which are primarily PC graphics cards. In contrast, the company’s data center operations slightly outperformed, up 61% year-over-year to $3.8 billion, driven by what the company calls “hyperscale” customers, major cloud providers.