Articles tagged with Moores Law
Study by Duke engineers reveals that a common device architecture used to test 2D transistors overstates their performance prospects up to sixfold. The back-gated architecture amplifies the transistor's performance using contact gating, but has physical limitations that prevent its use in commercial technologies.
The ACM Gordon Bell Prize-winning team developed a full-physics Bayesian inversion framework called 'digital twin' to predict tsunami early warning. This approach enabled real-time, data-driven forecasting with dynamic adaptivity, achieving a ten-billion-fold speedup over existing state-of-the-art methods.
A team of researchers developed a groundbreaking Full Earth System Simulation at 1 km resolution, capturing energy, water, and carbon flow through the atmosphere, ocean, and land. This innovation has enormous potential to provide detailed global information on local scales about future warming implications.
Researchers are combining machine learning algorithms with neuromorphic hardware to build brain-like devices that can learn from data and adapt in real-time. These devices have the potential to revolutionize industries such as manufacturing by enabling machines to sense their environment, adapt to new tasks, and make decisions without ...
Researchers from The University of Tokyo developed a novel water-cooling system with three-dimensional microfluidic channel structures to enhance heat transfer. The new design achieved a significant increase in performance, reaching up to 10^5 COP, surpassing conventional cooling techniques.
Researchers at Lancaster University are developing high-performance memory devices using self-assembled molecular technology to overcome the von Neumann bottleneck in computing. The Memristive Organometallic Devices (MemOD) project aims to deliver faster, more stable, and energy-efficient AI hardware.
Researchers at KTH Royal Institute of Technology have developed a novel 3D printing method to fabricate glass micro-supercapacitors with enhanced performance. The approach utilizes ultrashort laser pulses to create electrodes with increased surface area and rapid ion transport, leading to improved energy storage capabilities.
Scientists from Penn created a non-volatile memory device using ferroelectric aluminum scandium nitride (AlScN) to retain data at high temperatures. The device's stability and fast switching properties enable efficient computation in harsh conditions, including space exploration and deep-earth drilling.
Researchers summarize existing compiler technologies in deep learning co-design and propose a new framework, the Buddy Compiler, to address performance bottlenecks in current AI applications. The study highlights the importance of hardware-software co-design in achieving optimal efficiency and effectiveness in deep learning systems.
Ferroelectric materials have shown promising solutions for intelligent computing, including low-power logic devices, high-performance memory cells, and neuromorphic devices. These advancements can break the 'heat wall', 'memory wall', and von Neumann bottleneck, respectively.
The new computer chip uses a transistor-free design that eliminates data transfer time and minimizes energy consumption. It offers up to 100 times faster performance than conventional computing architectures, making it ideal for AI applications.
Researchers developed a thin-layer version of barium titanate, enabling faster switching and lower voltages for next-gen memory and logic devices. The findings could pave the way for more sustainable computing power with reduced energy consumption.
Researchers have discovered that negative capacitance in topological transistors can switch at lower voltage, potentially reducing energy losses. This new design could help alleviate the unsustainable energy load of computing, which consumes about 8% of global electricity supply.
Researchers have demonstrated ultrafast optical circuit switching for datacenters using integrated soliton microcombs, which can handle increasing bursty datacenter applications while reducing overheads. The proposed architecture employs a central comb system to improve power efficiency and reduce complexity.
Researchers explore joining topological insulators with magnetic materials to achieve quantum anomalous Hall effect, promising building blocks for low-power electronics. The 'cocktail' approach allows tuning of both magnetism and topology in individual materials, enabling operation closer to room temperature.
A new technique that synchronises the clocks of computers in under a billionth of a second can eliminate one of the hurdles for the deployment of all-optical networks, potentially leading to more efficient data centers. This method, called clock phase caching, can reduce the time to recover the clock and increase performance of optical...
Researchers at the University of Texas at Austin have discovered a new material, 2D antimony, which holds promise for manufacturing even smaller computer chips. The material has high charge mobility, making it a suitable alternative to silicon, and its properties could lead to the discovery of even better materials.
Researchers have developed a new type of processor called PAXEL, which uses light to speed up computation and increase efficiency. This approach has potential applications in areas such as fog computing, medical testing, and biodefense.
IBM researchers have successfully fabricated futuristic components on silicon chips using a new technique. The breakthrough allows for the integration of III-V materials onto silicon wafers, which may enable further miniaturization and cost reduction in computer chips.
A new model called Step and Wait (SAW) predicts technological innovation in six markets, offering a more accurate alternative to outdated models like Moore's Law. The SAW model tracks performance improvements in steps and waits, helping companies invest in the right technologies.
Scientists at Rice University have found a method to attach molecules to semiconducting silicon, potentially helping manufacturers reach beyond Moore's Law limits. The new process, known as silicon with afterburners, works better at the nanometer scale and can be used to complement traditional doping methods.
Researchers at McGill University have discovered a quasi-three-dimensional electron crystal in a material similar to those used in transistors, which could help the industry overcome quantum limits and continue Moore's Law. The discovery was made using ultra-low temperatures and powerful magnetic fields.
Researchers have developed a model to explain the mechanism behind the molecular switch, which could fit more than a trillion switches onto a centimeter-square chip. The model reveals a quantum phase transition that could enable the creation of a new type of switch with promise as a digital electronics foundation.