AI chip explainers
Explainers on AI chips: data-center GPU generations, custom accelerators, HBM, the supply chain and export rules.

AMD Taalas acquisition: the $2.9 billion price and what Taalas builds
AMD's 10-Q puts the Taalas deal at about $2.9 billion, up to $1.4 billion contingent, plus the HC1 chip's specs.

AI inference vs training compute: what's the difference
Training builds a model and inference runs it, and the two stress AI hardware in different ways.

Huawei Ascend: China's AI chips explained
Huawei Ascend AI chips from the 910 series to the 950, 960, 970 and 980, as Huawei described them at Huawei Connect.

Intel Gaudi explained: specs and where it stands
Intel Gaudi explained: Gaudi 3 specs from Intel's own paper, where to get it, and Intel's next AI chip.

HBM suppliers: SK hynix, Samsung and Micron in the HBM race
SK hynix, Samsung and Micron all say they ship HBM4 in volume as of October 2026; here is where each supplier stands.

TSMC and AI chips: why so many accelerators run through it
TSMC makes and packages the silicon behind Nvidia GPUs, Broadcom XPUs and Intel Gaudi 3: nodes, CoWoS and Arizona.

Broadcom AI chips: custom XPUs and who designs them
Broadcom's AI chips are custom accelerators (XPUs) built for Google, Meta, OpenAI and others.

AI chip export controls: what the US rules restrict
US AI chip export rules as of November 5, 2026: TPP limits worked through, the China and UAE rules, the affiliates rule.

Nvidia's data-center GPU roadmap, Hopper to Rubin
Nvidia went from Hopper through Blackwell and Blackwell Ultra to Vera Rubin in four years; here is each generation.

Groq AI and its LPU: what the inference chip does
Groq built the LPU, an inference chip that keeps model weights in on-chip SRAM, and runs it as the GroqCloud service.

Cerebras Systems: the wafer-scale chip and its business
Cerebras Systems builds AI processors from a whole silicon wafer and sells both systems and inference cloud access.

AWS Trainium: what it is and which models train on it
AWS Trainium is Amazon's own AI chip, rented through EC2 Trn2 and Trn3 instances and UltraServers.

Google TPU: generations and who can use them
Google's TPUs run Gemini and are rented through Google Cloud, from v5e to Ironwood and the announced TPU 8t and 8i.

HBM memory explained: HBM2E, HBM3, HBM3E and HBM4 compared
HBM2E, HBM3, HBM3E, HBM4 and HBM4E compared by width, pin speed, bandwidth and capacity per stack.

AMD Instinct MI355X: specs and how it compares
The AMD Instinct MI355X is AMD's CDNA 4 accelerator with 288 GB of HBM3E at 8 TB/s and 1,400 W board power.

GB200 NVL72 explained: one rack, 72 GPUs
The GB200 NVL72 is Nvidia's liquid-cooled rack joining 72 Blackwell GPUs and 36 Grace CPUs in one NVLink domain.

Nvidia Rubin: what Nvidia has announced about Vera Rubin so far
Nvidia Rubin is the GPU generation after Blackwell, with the Vera CPU and the Vera Rubin NVL72 rack.

Nvidia B200 vs H100: what Blackwell changes
B200 vs H100 from Nvidia's own spec sheets: two dies instead of one, FP4, fifth-generation NVLink and more memory.

H100 rental price: what clouds charge per GPU-hour
The H100 rental price on the providers' own pricing pages runs from $1.78 to $11.06 per GPU-hour.

Nvidia H100: specs, memory and what it is used for
Nvidia H100 specs: 80 GB HBM3 (SXM) or 94 GB (NVL), FP8 dense and sparse, 700 W per GPU, 10.2 kW per DGX H100.
These pages explain how chip generations such as Nvidia H100, B200 and Rubin differ, what AMD Instinct, Google TPU, AWS Trainium, Intel Gaudi, Cerebras and Groq offer, why AI chips depend on HBM and TSMC, and what US export controls restrict, from the vendors’ own datasheets. Specs are compared in AI chips, rental prices in GPU prices, and launches in AI chip news.
