Meta, Microsoft commit to buying AMD's new AI chip Instinct MI300X as NVIDIA GPU alternative
Views : 802
Update time : 2024-01-04 10:23:28
Meta, OpenAI and Microsoft said at an AMD investor event that they will all be using AMD's newly developed AI chip, the Instinct MI300X, suggesting that while NVIDIA's GPU chips are critical to the development and deployment of AI programs like ChatGPT, many tech companies are looking for alternatives. If AMD's latest high-end chip, the Instinct MI300X, can start shipping early next year and meet the needs of AI companies and related cloud service providers, it could lower the cost of developing AI models and put competitive pressure on NVIDIA's soaring AI chip business.
On Wednesday AMD Chief Executive Officer Zifeng Su said, "All the focus is on large processors and large GPUs used in cloud computing." AMD said the MI300X is based on a new architecture that delivers significant performance improvements. The chip's best feature is 192GB of high-performance HBM3 memory, which transfers data faster and can accommodate larger AI models. Su Zifeng directly compared the MI300X and the systems it builds to the H100, a mainstream AI GPU chip from NVIDIA. "This performance translates directly into a better user experience," said Zifeng Su. "When you ask a model a question, you always want it to respond faster, especially when the response is increasingly complex." The main question facing AMD is whether the company, which has been based on NVIDIA, will invest any more time and money in another GPU supplier. "Acceptance of AMD still needs to come down the pike," Suzie Fung said. AMD told investors and partners Wednesday that the company has made improvements to its ROCm software suite. A key flaw has been addressed in order to compete with NVIDIA's CUDA software, which is the industry benchmark.That original flaw in the ROCm software suite has been one of the main reasons AI developers now prefer NVIDIA. Chip price is also important. On Wednesday AMD did not reveal pricing for the MI300X. NVIDIA GPU chips currently sell for about $40,000 each, and Su said AMD's chips would have to be less expensive than NVIDIA's and have lower operating costs to convince customers to buy them. On Wednesday, AMD also said it had signed usage agreements with some of the companies that need GPU chips the most. According to a recent report from market research firm Omidia, Meta and Microsoft are the two biggest buyers of NVIDIA's H100 GPU chips in 2023. meta said it will use the MI300X chips for AI inference workloads such as AI stickers, image editing, and the operation of voice assistants. Kevin Scott, Microsoft's chief technology officer, said the company will provide access to the MI300X chips through Azure Web Services.
The LDK220 series of low-dropout linear regulators (LDOs) is a high-performance device designed specifically for low-power consumption and high-precision voltage regulation, widely used in scenarios such as consumer electronics, industrial control, and po
Xilinx Spartan®-7 FPGA Family stands as a defining solution in the mid-range FPGA landscape, blending high performance, energy efficiency, and cost-effectiveness to redefine versatility for industrial, IoT, and consumer electronics applications. Built on
The Altera FLEX series was more than a lineup of FPGAs—it was a blueprint for how programmable logic devices could evolve to meet diverse market needs. The FLEX 8000 laid the architectural groundwork, the FLEX 10K redefined functionality with embedded mem
Among TI standout offerings, the LM4765 and LM4766 are dual-channel amplifiers designed to cater to diverse audio needs—from compact setups to high-fidelity systems. While sharing the same product lineage, these chips differ significantly in power output,
