Articles from semianalysis.com

Articles from semianalysis.com

AI deals that the US struck with the UAE and Saudi Arabia reinforce its AI leadership, but raise security concerns that the US can mitigate through safeguards (semianalysis.com)
30 days ago AI Arabia Saudi Arabia

A look at Microsoft freezing ~1.5GW of data centers set for 2025 and 2026; Microsoft has walked away from significantly more than 2GW of non-binding contracts (semianalysis.com)
2025-4-28 Microsoft

A deep dive on AMD 2.0: a new sense of urgency, rapid AI software stack progress, a critical talent retention challenge, ROCm lags Nvidia's CUDA, and more (semianalysis.com)
2025-4-24 AI Nvidia AMD

A look at Huawei's AI CloudMatrix 384 rack-scale system, which is less power-efficient than Nvidia's GB200 NVL72, though this is not a limiting factor in China (semianalysis.com)
2025-4-16 China AI Nvidia

A deep dive on what Trump's Liberation Day tariffs mean for AI infrastructure: how the tariffs work, the USMCA's GPU loophole, GPU/XPU global trade, and more (semianalysis.com)
2025-4-10 Trump AI

A close look at Nvidia's GTC 2025 announcements, which focused on addressing pre- and post- training scaling, inference-time scaling working in tandem, and more (semianalysis.com)
2025-3-19 Nvidia

As automation and robotics undergo a revolution, a call to action for the US and the West, which are missing the new labor economy that China is set to capture (semianalysis.com)
2025-3-11 China Robot

A close look at DeepSeek, which is estimated to have access to ~50K Hopper GPUs, a total server capex of ~$1.3B, and a GPU spend of $500M+ over its history (semianalysis.com)
2025-1-31

Benchmarking AMD's MI300X and Nvidia's H100 and H200; in theory, AMD's GPU has advantages in specs and Total Cost of Ownership, but software bugs hold it back (semianalysis.com)
2024-12-25 Nvidia AMD

A deep dive into AI scaling laws, including an outline of the old pre-training trends as well as the new scaling trends for post-training and inference time (semianalysis.com)
2024-12-12 AI

A look at Intel's problems, starting with 2016's 10nm node: 7/11 board members have no chip experience, most CEO options are worse than Pat Gelsinger, and more (semianalysis.com)
2024-12-9 Intel

A deep dive into Amazon's Trainium2, which shows the company is on a path to eventually provide competitive custom AI chips, especially for LLM inference (semianalysis.com)
2024-12-5 Amazon AI

Previous Page Next Page