Chips
Exploring the RTX Pro 6000D, Nvidia’s China-only GPU, which is now banned from sale — neutered specs cannot compete with grey-market chips
Nvidia’s RTX 6000D was never going to be a hero product. Built specifically for the Chinese market to navigate U.S. export restrictions, it has a constrained design: a GDDR-based Blackwell GPU with no NVLink, targeting AI inference instead of full-scale training. Two procurement sources speaking to the South China Morning Post say that demand is…
CHIPS Act funding could herald an era where the U.S. is not offering grants, but buying equity — Lutnick’s semiconductor strategy might not end with Intel
President Donald Trump was no fan of the CHIPS and Science Act. The U.S. President said in a March speech to Congress that he wanted to eliminate the subsidy: “Your CHIPS Act is a horrible, horrible thing. We give hundreds of billions of dollars, and it doesn’t mean a thing.” The leader then proposed that…
Positron believes it has found the secret to take on Nvidia in AI inference chips — here’s how it could benefit enterprises
Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now As demand for large-scale AI deployment skyrockets, the lesser-known, private chip startup Positron is positioning itself as a direct challenger to market leader Nvidia by offering dedicated, energy-efficient, memory-optimized…
A timeline of the US semiconductor market in 2025 | TechCrunch
It’s been a tumultuous year for the U.S. semiconductor industry. The semiconductor industry plays a sizable role in the “AI race” that the U.S. seems determined to win, which is why this context is worth paying attention to: from Intel’s appointment of Lip-Bu Tan to CEO — who wasted no time getting to work trying…
System-level test’s expanding role in producing complex chips
System-level test (SLT), once used largely as a stopgap measure to catch issues missed by automated test equipment (ATE), has evolved into a necessary test insertion for high-performance processors, chiplets, and other advanced computational devices. Today, SLT is critical for ensuring that chips function correctly in real-world conditions, and all major CPUs, APUs, and GPUs…
Nvidia’s Arm chips rapidly gain share in server market as AI booms — Nvidia’s Arm-powered GB200 servers surge as market reaches a record $95 billion in the first quarter
The global server market experienced an unprecedented surge to nearly $100 billion in the first quarter as companies heavily invested in AI-related infrastructure, according to IDC, and ‘accelerated’ servers running Arm-based processors comprise one of the most rapidly growing categories, with Arm-powered server shipments rising 70% this year. It appears that the vast majority of…
Can microchannels, manifolds, and two-phase cooling keep chips happy?
Two-phase cooling Thermal management is an ongoing concern for many designs. The process usually begins with a tactic for dissipating or removing heat from the primary sources (mostly but not exclusively “chips”), then progresses to keeping the circuit-board assembly cool, and finally getting the heat out of the box and “away” to where it becomes…
Meet the companies racing to build quantum chips | TechCrunch
Quantum computing has long been announced as “just around the corner,” but several companies are now determined to make this a commercial reality, with the promise of solving complex problems beyond classical computers’ reach. The problems in question are wide-ranging, from medicine and cybersecurity to materials science and chemistry. But first, there are very practical…
Smarter Chips Start With Streamlined RTL-To-GDSII Flow
– Advertisement – Can smarter RTL-to-GDSII flows revolutionise chip design? With AI, automation, and better design practices, semiconductor development is getting faster, leaner, and more efficient than ever. The semiconductor industry is continuously driven by the need to deliver higher performance, lower power, and smaller form-factor chips at increasingly rapid turnaround times. As chip designs…
Addressing hardware failures and silent data corruption in AI chips
Meta trained one of its AI models, called Llama 3, in 2024 and published the results in a widely covered paper. During a 54-day period of pre-training, Llama 3 experienced 466 job interruptions, 419 of which were unexpected. Upon further investigation, Meta learned 78% of those hiccups were caused by hardware issues such as GPU…
- 1
- 2