NVIDIA is making a substantial push into the AI market with its new Blackwell GPUs, targeting significant performance gains.

For instance, modern data centers running Nvidia’s advanced Hopper H100 GPUs need 10 times more fiber optics than traditional setups, which means that Corning’s optical solutions are in high demand.

Nvidia is still the fastest AI and HPC accelerator across all MLPerf benchmarks; Hopper performance increased by 30% thanks ...

On paper, the B200 is capable of churning out 9 petaFLOPS of sparse FP8 performance, and is rated for a kilowatt of power and ...

Specifically, each EX154n accelerator blade will feature a pair of 2.7 kW Grace Blackwell Superchips (GB200), each of which ...

With a near-monopoly on the most powerful GPUs used for AI training, Nvidia has struggled to keep up with demand for its AI ...

SoftBank conducts world’s first outdoor test with 20 5G cells on a single server featuring the NVIDIA GH200 Grace Hopper ...

The top goal for Nvidia Jensen Huang is to have AI designing the chips that run AI. AI assisted chip design of the H100 and H200 Hopper AI chips. Jensen wants to use AI to explore combinatorially the ...

While both companies hold strong potential amid rising AI demand, AI models suggest that Nvidia stands out as the safer and ...

With over 1 billion parameters trained using trillions of tokens on a cluster of AMD’s Instinct GPUs, OLMo aims to challenge ...

The historic addition of artificial intelligence (AI) colossus Nvidia may spell trouble for Wall Street's most iconic index.

Despite export restrictions, enough AI processors have been smuggled into China to build world-class AI supercomputers. Workarounds including proxies and imports via other countries haven't stopped ...