Recent #energy efficiency news in the semiconductor industry

about 1 year ago

➀ Stanford University is researching a hybrid memory that combines the density of DRAM with the speed of SRAM, funded by CHIPS and Science Act.

➁ The research is part of the California Pacific Northwest AI Hardware Center project, which will receive $16.3 million from the US Department of Defense.

➂ The team, led by H.S. Philip Wong, focuses on developing more energy-efficient hardware for AI, with memory being the core.

➃ The hybrid gain cell memory combines the small footprint of DRAM with the almost as fast speed of SRAM.

➄ The gain cell, similar to DRAM, uses a second transistor instead of a capacitor to store data, with the data stored as charge on the gate of the transistor.

➅ Reading signals are无损 in the gain cell, and the reading transistor provides gain to the storage transistor during reading.

➆ Liu and Wong's mixed gain cell memory, combining silicon read transistors with indium tin oxide write transistors, overcomes limitations and achieves a data retention time of over 5000 seconds.

➇ These hybrid storage cells can be integrated into logic chips, potentially changing the way memory is used in computers.

AI HardwareMemory Technologyenergy efficiency
about 1 year ago
➀ The article discusses the energy consumption of train heating, cooling, and battery management systems. ➁ It highlights the efficiency of the DB-Baureihe 490, which uses a heat pump and waste heat recovery. ➂ The study suggests that integrated thermal management can improve the efficiency and range of battery-electric and hydrogen fuel cell trains.
Cooling SystemsRailway TechnologyThermal ManagementTransportationenergy efficiency
about 1 year ago
➀ Researchers at ICFO have developed a post-deposition in situ passivation technique to minimize surface defects in eco-friendly solar cells, achieving a new efficiency record; ➁ The technique improves surface passivation and optoelectronic properties of nanocrystal ink films, leading to higher efficiency solar cells; ➂ The team synthesized AgBiS2 nanocrystal ink with a multifunctional molecular agent for enhanced performance.
energy efficiencyphotovoltaicssustainability
about 1 year ago
The Fraunhofer Heinrich-Hertz-Institut (HHI) has launched the HYPERCORE project, aimed at developing energy-efficient, secure, and high-performance communication infrastructure for the hyper-connected society. The project, funded by the German Federal Ministry of Education and Research (BMBF), focuses on optimizing metro and core networks, exploring a combination of all three physical dimensions (time, frequency, and space) for increasing transmission capacity. The project involves developing multiband transmission systems, coherent OTDR systems for network control, and expanding digital twin technology for optical communication networks. Field tests are planned for 2026 in Kiel and Berlin.
Autonomous VehiclesDigitalizationFraunhofer HHIGermanyIoTNetworkingResearch ProjectSmart Citiesenergy efficiencyoptical communication
about 1 year ago
➀ Starting with your first NAS, Arm-powered NAS is a good choice for beginners; ➁ Arm-powered NAS is more affordable due to the lower cost of Arm processors; ➂ An Arm processor is sufficient for basic NAS tasks and doesn't require a powerful CPU; ➃ Arm CPUs use less power than x86 chips, saving on utility bills; ➄ Arm NAS can be used for various tasks, including home surveillance, without requiring high power consumption.
NASenergy efficiency
about 1 year ago
➀ HBM4 is the key to advancing AI by providing high capacity and performance for large-scale data-intensive applications; ➁ HBM4 improves AI and ML performance through increased bandwidth and memory density, reducing bottlenecks and improving system performance; ➂ HBM4 is designed with energy efficiency in mind, achieving better performance per watt and is crucial for the sustainability of large-scale AI deployments; ➃ HBM4's scalability allows for growth without becoming too expensive or inefficient, making it crucial for deploying AI in various applications.
AIAI PerformanceHBM4Memory Technologyenergy efficiency
about 1 year ago
➀ A 30 billion parameter LLM is demonstrated with a prototype inference device equipped with 16 IBM AIU NorthPole processors, achieving a system throughput of 28,356 tokens/second and a latency below 1 ms/token; ➁ NorthPole offers 72.7 times better energy efficiency and lower latency compared to GPUs at the lowest GPU delay; ➂ NorthPole architecture is inspired by the brain, optimized for AI inference, and demonstrates superior performance in LLM推理.
GPULLMenergy efficiency
about 1 year ago
➀ The rise of indoor solar cells is transforming how we power our homes and devices, aiming for sustainability and energy efficiency; ➁ Indoor solar cells efficiently harness solar power from artificial light sources, reducing carbon footprints; ➂ Technological advancements are driving the efficiency and versatility of indoor solar cells, making them suitable for various applications.
Indoor Solar Cellsenergy efficiency
about 1 year ago
➀ Infineon Technologies AG has launched a new XENSIV PAS CO2 5V sensor to improve building energy efficiency. The sensor uses Photoacoustic Spectroscopy (PAS) technology to tailor ventilation based on real-time occupancy, reducing carbon emissions and improving indoor air quality. It is suitable for HVAC systems, room controllers, and thermostats in both commercial and residential settings. ➁ The sensor delivers real-time, accurate air quality data, with a compact size and a fast response time. It is dust-proof and complies with the WELL TM Green Building Standard. ➂ All key components of the sensor are developed internally, and it offers configuration options for power consumption management.
IoTbuilding automationenergy efficiencysensors
about 1 year ago
➀ Smart manikins equipped with sensor technology and mathematical modeling help optimize office temperatures for energy efficiency and comfort. ➁ 'HVAC' and 'ANDI' manikins measure thermal radiation and humidity to create a virtual thermal model of a human workplace. ➂ The research aims to optimize building energy needs and improve conditions in operating rooms and other environments.
HVACenergy efficiencysensors
over 1 year ago
1. The Fraunhofer Institute for Energy Economics and Energy System Technology (IEE) is developing models and methods to assess the impact of local restrictions on realizable wind energy capacities and yields. 2. These models help in evaluating the usability of existing and planned sites and estimating repowering potentials. 3. The project, funded by the Federal Ministry for Economic Affairs and Climate Action, aims to accelerate the expansion of wind energy by providing tools for optimal land use and early warning systems for potential shortfalls in energy targets.
Environmental PolicyWind Energyenergy efficiency
over 1 year ago
1. Researchers at ETH Zurich have developed a new method to significantly reduce the amount of environmentally harmful fluorine in lithium-metal batteries, making them more sustainable. 2. This new approach involves using electrostatic attraction to control the formation of a protective layer in the battery, enhancing stability and reducing costs. 3. The method has been successfully tested in coin-sized batteries and is now being scaled up for use in pouch cells, commonly used in smartphones.
Battery TechnologyEnvironmental Impactenergy efficiency
over 1 year ago
1. Nuvoton Technology introduces the Arm Cortex-M23 M2L31 microcontroller series, focusing on energy-efficient computing. 2. The series features high power efficiency and robust processing capabilities, suitable for battery management and industrial automation. 3. It includes advanced features like ReRAM and USB Type-C PD 3.0 support, enhancing sustainability and security.
MicrocontrollerNuvoton Technologyenergy efficiency
over 1 year ago
1. Researchers from UC Santa Cruz have discovered a method to run large language models (LLMs) at a mere 13 watts without compromising performance. 2. The key to this efficiency is the elimination of matrix multiplication in LLM processing, which, when optimized, significantly boosts performance-per-watt. 3. The broader applicability of this approach to AI in general is yet to be determined.
AI researchLLMsenergy efficiency