AMD has the strongest AI chip, 153 billion transistors, and a single GPU runs a large model
Views : 144
Update time : 2023-06-17 11:31:31
It was reported on June 14 that in the early morning of this morning, AMD, Nvidia's number one competitor, finally released its long-awaited AI trick. As the generative AI hurricane swept the world, Nvidia GPUs were snapped up by major manufacturers, and the focus quickly shifted to AMD. Can AMD produce AI chips powerful enough to break Nvidia's near-monopoly market position and seize the new wave of AI? Today, AMD has now issued a phased response.
The MI300X is a GPU-only version that uses AMD CDNA 3 technology and uses up to 192 GB of high bandwidth HBM3 memory to accelerate large language models and generative AI computing. Major AMD customers will begin MI300X trials in the third quarter and full production in the fourth quarter. Another model, the Instinct MI300A, is now on sale to customers. AMD announced a new partnership with star AI unicorn Hugging Face to optimize their models for AMD's CPUs, GPUs and other AI hardware. In addition to AI chips, AMD also introduced a new EPYC server processor designed for cloud computing and hyperscale users, codenamed Bergamo, with up to 128 cores per slot and optimized for a variety of containerized workloads. Executives from Amazon's cloud computing divisions AWS, Oracle Cloud, Meta, and Microsoft Azure all came to the scene to share their feelings about using AMD chips and software in their data centers. Nvidia and Intel, the world's leading data center GPUs and CPUs, are both highlighting their power to accelerate AI. AMD, the "second child" of both tracks, is also racing to meet the growing demand for AI computing and challenge Nvidia's dominance in emerging markets by launching data center GPUs adapted to the latest demands. The boom in generative AI and large language models is pushing data centers to their limits. So far, Nvidia has the edge in providing the technology needed to handle these workloads. According to market research firm New Street Research, Nvidia holds 95% of the GPU market available for machine learning. "We are still in the very, very early stages of the AI lifecycle," Su said, predicting that the total addressable market for data center AI accelerators will grow fivefold by 2027, from about $30 billion this year at a compound annual growth rate of more than 50% to more than $150 billion by 2027. AMD did not disclose the price of the two new MI300 chips, but that could put some price pressure on Nvidia, where the H100 was previously rumored to be as high as $30,000 or more.
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,
