Lifeboat Foundation: Safeguarding Humanity
Toggle light / dark theme

Blog – Page 3730

Unmanned aerial vehicles (UAVs), also known as drones, can help humans to tackle a variety of real-world problems; for instance, assisting them during military operations and search and rescue missions, delivering packages or exploring environments that are difficult to access. Conventional UAV designs, however, can have some shortcomings that limit their use in particular settings.

For instance, some UAVs might be unable to land on uneven terrains or pass through particularly narrow gaps, while others might consume too much power or only operate for short amounts of time. This makes them difficult to apply to more complex missions that require reliably moving in changing or unfavorable landscapes.

Researchers at Zhejiang University have recently developed a new unmanned, wheeled and hybrid that can both roll on the ground and fly. This unique system, introduced in a paper pre-published on arXiv, is based on a unicycle design (i.e., a cycling vehicle with a single wheel) and a rotor-assisted turning mechanism.

Read more | >

A model system created by stacking a pair of monolayer semiconductors is giving physicists a simpler way to study confounding quantum behavior, from heavy fermions to exotic quantum phase transitions.

The group’s paper, “Gate-Tunable Heavy Fermions in a Moiré Kondo Lattice,” published March 15 in Nature. The lead author is postdoctoral fellow Wenjin Zhao in the Kavli Institute at Cornell.

The project was led by Kin Fai Mak, professor of physics in the College of Arts and Sciences, and Jie Shan, professor of applied and engineering physics in Cornell Engineering and in A&S, the paper’s co-senior authors. Both researchers are members of the Kavli Institute; they came to Cornell through the provost’s Nanoscale Science and Microsystems Engineering (NEXT Nano) initiative.

Read more | >

For individuals suffering from drug addiction, certain cues—whether it’s specific people, places or things—can trigger powerful cravings for repeated use.

A new University of Michigan study has identified signals, traditionally associated with inflammation, contributing to people’s vulnerability to . With repeated drug use with the same exposure to cues, some individuals develop an inability to control their drug use, even in the face of negative consequences.

The study is published in the journal eNeuro.

Read more | >

A team of geochemists from the Chinese Academy of Sciences, working with colleagues from the University of Hong Kong, Tianjin University and the University of California, has found evidence that suggests much of the oxygen in early Earth’s early atmosphere may have come from rocks. In their study, reported in Proceedings of the National Academy of Sciences, the group conducted lab experiments involving crushing rocks, exposing the results to water and measuring reactive oxygen species that were emitted.

Prior research has shown that Earth experienced what has been called the Great Oxidation Event approximately 2.3 to 2.4 billion years ago. During this time, microbe numbers increased dramatically, as they released during photosynthesis. But prior research has also suggested that a common life ancestor existed before the Great Oxidation Event, which further suggests that there was some amount of oxygen exposure. In this new effort, the researchers suggest that such oxygen could have come from rocks interacting with water.

The work involved crushing samples of quartz and then exposing them to water, which replicates some of the conditions that existed on early Earth prior to the rise of high levels of oxygen in the atmosphere. Adding water to freshly crushed quartz, the researchers found, led to reactions between the water and newly broken crystals. This resulted it the formation of molecular oxygen along with other like hydrogen peroxide. Such species are also known as free radicals and they would have played an important role in the evolution of . This is because by damaging DNA and other cell components, the would have pressured early life to adapt.

Read more | >

ChatGPT is currently deployed on A100 chips that have 80 GB of cache each. Nvidia decided this was a bit wimpy so they developed much faster H100 chips (H100 is about twice as fast as A100) that have 94 GB of cache each and then found a way to put two of them on a card with high speed connections between them for a total of 188 GB of cache per card.

So hardware is getting more and more impressive!

While this year’s Spring GTC event doesn’t feature any new GPUs or GPU architectures from NVIDIA, the company is still in the process of rolling out new products based on the Hopper and Ada Lovelace GPUs its introduced in the past year. At the high-end of the market, the company today is announcing a new H100 accelerator variant specifically aimed at large language model users: the H100 NVL.

The H100 NVL is an interesting variant on NVIDIA’s H100 PCIe card that, in a sign of the times and NVIDIA’s extensive success in the AI field, is aimed at a singular market: large language model (LLM) deployment. There are a few things that make this card atypical from NVIDIA’s usual server fare – not the least of which is that it’s 2 H100 PCIe boards that come already bridged together – but the big takeaway is the big memory capacity. The combined dual-GPU card offers 188GB of HBM3 memory – 94GB per card – offering more memory per GPU than any other NVIDIA part to date, even within the H100 family.

Continue reading “NVIDIA Announces H100 NVL — Max Memory Server Card for Large Language Models” | >

While virtually all of the industry is buzzing about AI, accelerated computing and AI powerhouse NVIDIA has just announced a new software library, called cuLitho, that promises an exponential acceleration in chip design development times, as well as reduced chip fab data center carbon footprint and the ability to push the boundaries of bleeding-edge semiconductor design. In fact, NVIDIA cuLitho has already been adopted by the world’s top chip foundry, TSMC, leading EDA chip design tools company Synopsys and chip manufacturing equipment maker ASML.

Industry partners like EDA design tools bellwether Synopsys are chiming in as well, with respect to the adoption of cuLitho and what it can do for their customers that may want to take advantage of the technology. “Computational lithography, specifically optical proximity correction, or OPC, is pushing the boundaries of compute workloads for the most advanced chips,” said Aart de Geus, chair and CEO of Synopsys. “By collaborating with our partner NVIDIA to run Synopsys OPC software on the cuLitho platform, we massively accelerated the performance from weeks to days! The team-up of our two leading companies continues to force amazing advances in the industry.”

As semiconductor fab process nodes get smaller, requiring finer geometry, more complex calculation and photomask patterning, offloading and accelerating these workloads with GPUs makes a lot of sense. In addition, as Moore’s Law continues to slow, cuLitho will also accelerate additional cutting-edge technologies like high NA EUV Lithography, which is expected to help print the extremely tiny and complex features of chips being fabricated at 2nm and smaller.

I personally expect cuLitho to be another inflection point for NVIDIA. If the chip fab industry shifts to this technology, the company will have a huge new revenue pipeline for its DGX H100 servers and GPU platforms, just like it did when it seeded academia with GPUs and its CUDA programming language in Johnny Appleseed fashion to accelerate AI. NVIDIA is now far and away the AI processing leader, and it could be setting itself up for similar dominance in semiconductor manufacturing infrastructure as well.

Continue reading “NVIDIA cuLitho Computational Lithography Massively Accelerates Chip Design Using GPUs” | >