Get all your news in one place.

100's of premium titles.
One app.

Get all your news in one place.

100's of premium titles. One news app.

The Latest Breaking News from Semianalysis

Nvidia's Huang vows to deliver 'giant amounts' of Vera Rubin — company says that 'our roadmap is intact'

Chief executive of Nvidia says the company is on track to produce 'giant amounts' of Vera Rubin-based machines, but fails to address rumored delays of Kyber NVL144 racks from 2027 to 2028.

Tom’s Hardware

A New Report Says Meta Platforms Could Overtake Google AI. How to Play META Stock Here.

Meta’s shares gained after SemiAnalysis predicted the company could leapfrog Google’s AI capabilities within months. How should investors position themselves in META stock?

Barchart

Nebius Stock Sold Off on Meta’s Data Center News. Buy the Dip.

Nebius stock sank on Meta’s cloud ambitions. SemiAnalysis believes Meta's AI expansion strengthens the buy-the-dip case.

Barchart

From analysis to the latest developments in health,
read the most diverse news in one place.

Nvidia's Next AI Rack Hit A Manufacturing Snag. The Company's Fastest Product Cycle Just Slowed Down.

Nvidia's next-generation Kyber NVL144 rack-scale AI system has reportedly been delayed by more than a year after manufacturing challenges emerged with a critical component.

International Business Times

Nvidia's Kyber rack for Rubin Ultra reportedly delayed to 2028, stopgap solution also axed due to customer pushback — Analyst firm SemiAnalysis says PCB midplane problems led to the delay [Updated]

Nvidia reportedly won't ship its Kyber NVL144 rack until 2028, a delay of more than 12 months.

Tom’s Hardware

Meta Employees Burned $221M in AI Tokens in One Month: Now Big Tech Starts Counting Every AI Prompt

Companies are moving from unlimited AI usage to budgeted management, focusing on cost-effective productivity while maintaining significant gains. AI adoption continues to grow, with refined usage strategies.

International Business Times UK

Nvidia reportedly cancels quad-die Rubin Ultra GPU in favor of dual-GPU design, report claims — complex design purportedly scrapped over 'manufacturing execution concerns'

Nvidia reportedly abandons quad-dire Rubin Ultra GPUs in favor of dual-die Rubin Ultra due to 'manufacturing execution concerns.'

Tom’s Hardware

Read news from The Economist, FT, and more,
with one subscription

'The math doesn't work': Why your $200 AI subscription is secretly worth thousands

New research suggests heavy ChatGPT and Claude users are getting an enormous discount on compute. The catch: the math doesn't work, and the first cracks are already showing.

Tom’s Guide

Chinese fab SMIC's 7nm metal pitch beats Intel 18A but lags 38% on density, teardown finds — Huawei's sanctions-beating HiSilicon Kirin 9030 is the first subject of SemiAnalysis's new teardown lab

SemiAnalysis has published the first teardown from its new in-house lab, focusing on the minimum local metal pitch on SMIC’s third-gen 7nm at 32.5nm.

Tom’s Hardware

Why Experts Think Intel Should Raise Capital Right Now, and What It Means for INTC Stock

After a stunning AI-fueled comeback, Intel may have a chance to raise capital and supercharge its turnaround. But should shareholders be fine with the dilution?

Barchart

AI costs spike as subscriptions hit pricing wall — firms turn towards Chinese LLMs, open-source models to extend budget

Companies look for cheaper alternatives as token costs for frontier AI models skyrocket, potentially impacting OpenAI and Anthropic's bottom lines. Subscriptions also take a bite out of these startup's profitability, as utilization rates higher than 5.7% could lead to losses.

Tom’s Hardware

China's control over indium phosphide exports threatens AI data centre rollout

Anderson's visit was partly to raise the issue of delays in China's export licenses involving the highly strategic material, essential in manufacturing high-speed optical chips for AI data centres, said three sources familiar with the matter.

The Economic Times

Memory will consume 30% of hyperscaler AI data center spending this year, a 4X increase over 2023 — Nvidia gets preferential supply terms well below standard market rates, says analyst firm

SemiAnalysis estimates on Thursday that memory will account for roughly 30% of total hyperscaler capex in calendar year 2026.

Tom’s Hardware

AMD denies report of MI455X delays as Nvidia VR200 systems are rumored to arrive early — company says Helios systems 'on target for 2H 2026'

AMD's Helios rack-scale solution based on the MI455X accelerators, the company's major hope for AI market, may slip to 2027, whereas Nvidia may speed up roll out of the Vera Rubin platform if the latest market rumors are to be believed.

Tom’s Hardware

Get all your
news in one place.

100's of premium titles.
One news app.

Tom’s Hardware

Elon Musk says xAI will have more AI compute than everyone else combined within five years — Macrohard-branded Colossus 2 data center a nod to Musk's AI project to challenge Microsoft

Elon Musk claimed on X that xAI will have more computing power than everyone else combined in less than five years.

Tom’s Hardware

InferenceMax AI benchmark tests software stacks, efficiency, and TCO — vendor-neutral suite runs nightly and tracks performance changes over time

InferenceMax AI benchmark measures software stacks, efficiency, and TCO

International Business Times

Competition Heats Up To Challenge Nvidia's AI Chip Dominance

The artificial intelligence (AI) revolution has whetted the appetites of Nvidia's competitors, who are seeking to close the gap on the chip giant, which has so far been the central playmaker in the AI revolution.

Tom’s Hardware

xAI's new gas turbine facility gets halfway to Elon Musk's 1-gigawatt 'AI factory' goal

According to a new report from SemiAnalysis, Elon Musk’s AI startup already has 460MW of natural gas generation either installed or under construction.

Get all your
news in one place.

100's of premium titles.
One news app.

Tom’s Hardware

AMD preps Mega Pod with 256 Instinct MI500 AI GPUs, Verano CPUs — Leak suggests platform with better scalability than Nvidia will arrive in 2027

First details about AMD's next-generation AI rack solution emerge: three racks, 64 compute racks, 256 Instinct MI500-series GPUs, 64 EPYC 'Verano' CPUs, 18 switch trays.

Benzinga

Nvidia's Reign At Risk? Dylan Patel Says Google's TPU, Amazon's Trainium Could Outshine GPUs If Sold To Public

Nvidia Corp. (NASDAQ:NVDA) faces pressure from custom silicon competitors as tech giants scale up alternative artificial intelligence chip production, according to SemiAnalysis founder Dylan Patel.

PC Gamer

Meta is expanding its AI capabilities so quickly it's housing data centers in tents, which would make them data tenters, no?

My editors are going to hate this headline.

Benzinga

Elon Musk's Tesla Once Built Cars In A Tent To Meet Production Goals: Now, Mark Zuckerberg Is Channeling His Nemesis As Meta Builds AI Data Centers In Tents

Meta Platforms Inc. (NASDAQ:META) CEO Mark Zuckerberg is investing heavily in AI as the company plans to build data centers that would use over 1 Gigawatt of power each.

Tom’s Hardware

CHIPS Act beneficiaries 'mired in NIMBY fights and two-year permits' — delays to Micron, Amkor, and SK hynix NY fabs costing $5M per day

Several major U.S. semiconductor projects — including Amkor’s packaging plant in Arizona, Micron’s $100B DRAM fab in New York, and SK hynix’s HBM site in Indiana — are facing delays or opposition due to environmental reviews and local protests.

Tom’s Hardware

AMD to split flagship AI GPUs into specialized lineups for AI and HPC, add UALink — Instinct MI400-series models takes a different path

AMD will split its Instinct MI400-series into separate AI-focused (MI450X) and HPC-focused (MI430X) GPUs in H2 2026 to maximize performance per workload, but limited availability of UALink switches may hinder scalability.

Tom’s Hardware

Limited scalability of AMD's Instinct MI325X limits scale of its sales, says analyst firm

AMD’s Instinct MI325X failed to gain traction due to poor scalability, high power consumption, and delayed shipments, while its successor, MI355X, faces an uphill battle against Nvidia's more advanced and rack-scale-capable Blackwell GPUs.

1 2

People

From analysis to the latest developments in health,
read the most diverse news in one place.

Organisations