A Dell government has teased a blockbuster GPU to be launched by Nvidia later this yr.
Nvidia, the main international provider of chips utilized in synthetic intelligence (AI), is on the brink of unleash the B100 which is able to blow the H100 out of the water.
That spectacular commodity, working at 700W, shall be outstripped by its successor with the B100 set to devour 1000 watts – a rise of 42%.
Nvidia is alleged to get pleasure from an enviable 80% market share within the high-end AI chip sector, however it plans additional enlargement together with the formation of a devoted unit for designing customized chips for cloud computing corporations and different sectors.
Jeff Clarke, COO at Dell Technologies, has expressed his anticipation for the upcoming AI accelerator, talking on his firm’s latest earnings name.
“We’re excited about what’s happening with the H200 and its performance improvement,” he instructed buyers, with the identical sentiment expressed towards the B100 chip and an unknown B200.
When will Nvidia launch the B100 chip?
It was claimed direct cooling liquid gained’t be required for GPU’s sapping by way of 1000 watts, however it could possibly be launched “next year with the B200”.
This side of the dialogue has provoked curiosity and intrigue as there isn’t a present chip with that label on the horizon at Nvidia, a minimum of not on the roadmap shared with its buyers in October 2023.
It could possibly be Clarke was referring to the GB200 Superchip which is anticipated to carry collectively Nvidia’s Grace CPU with its B100 GPU, just like the GH200. Alternatively, a trump card could possibly be up the proverbial sleeve of the Delaware-incorporated tech multinational.
The firm declined to remark, following the remarks made by the Dell chief, however additional info shall be forthcoming at Nvidia’s GTC occasion from 17-21 March.
The arrival of the B100 isn’t anticipated till late this yr, given the launch of to launch of the H200 GPU within the first half of the yr.
Image: Marketing Maverick/X
