Intel Unveils New GPU, Seeking Korean AI Deals
Article excerpt
Highlighted: the sentence this signal was extracted from
While the Nvidia 'dynasty' is shaking, the original processor powerhouse Intel is sending a love call to the Korean market by highlighting its design capabilities. It is expanding its artificial intelligence (AI) infrastructure product line with graphics processing units (GPUs), a market dominated by Nvidia, and is enthusiastically pursuing collaboration with Korean AI infrastructure startups. The new product unveiled by Intel at the 'AI Summit' held at COEX in Gangnam-gu, Seoul on Nov. 12 was not Intel's flagship central processing unit (CPU), but the GPU 'Crescent Island.' Crescent Island, whose mock-up product was unveiled for the first time in Korea on this day after news of its development emerged last year, is a GPU developed with the intention of enabling high-capacity, low-power AI computing without expensive high bandwidth memory (HBM). The goal is to launch it next year. The advantage cited by Intel is that large memory capacity can be expanded using low power. According to Intel, Crescent Island supports a memory capacity of up to 480 gigabytes (GB) using 'LPDDR5X,' a general-purpose low-power DRAM, instead of HBM. This capacity is up to 5 times larger than Nvidia's similar product line, the GPU 'RTX Pro 6000'. Power usage is 350 watts (W), which is slightly over half of the RTX Pro 6000 (600W). Anil Nanduri, Vice President of AI Products and Market Strategy at...
Keep reading with a free account
The rest of this article, and every signal for Intel, is in your free account.