Memory
Memory technology uses electric current to read and write data
Today's computers often use as many as four different kinds of memory technology, from the hard drive to the memory chips, each with its own strengths and weaknesses. A new memory technology may be poised to disrupt this landscape, however, with a unique combination of features. It goes by the unwieldy acronym STT-MRAM, which stands for spin-transfer torque magnetic random access memory.
Compact bidirectional data memory module
A compact, bidirectional data memory module for tight mounting spaces is being offered by Balluff. The compact memory module with IP 67 protection is just 34x16x8mm in size and can be used as a memory storage device on interchangeable units such as milling heads on gantry type machining centres.
Total memory market expected to increase ten percent in 2017
The 20th anniversary edition of IC Insights' McClean Report will be released in January of next year. The following represents a portion of the memory forecast that will appear in the new report. After increasing by more than 20% in both 2013 and 2014, the memory market fell upon difficult times in 2015.
Record tunneling magnetoresistance for p-MTJ device
At the 2016 IEEE International Electron Devices Meeting, in a special poster session on MRAM, imec presented a 8nm p-MTJ device with 100% tunnel magnetoresistance (TMR) and coercive field as high 1,500Oe.
Memristive devices can mimic synaptic plasticity
Leti researchers have demonstrated that memristive devices are excellent candidates to emulate synaptic plasticity, the capability of synapses to enhance or diminish their connectivity between neurons, which is widely believed to be the cellular basis for learning and memory. The breakthrough was presented at IEDM 2016 in San Francisco in the paper, “Experimental Demonstration of Short and Long Term Synaptic Plasticity Using OxRAM Mult...
In-memory data deduplication technology doubles write speeds
The development of a high-speed in-memory data deduplication technology for all-flash arrays has been announced by Fujitsu Laboratories. These are large-scale, high-speed storage systems and use multiple flash devices such as solid-state drives.
Memory may be more energy efficient than previously thought
Scientists often discover interesting things without completely understanding how they work. That has been the case with an experimental memory technology in which temperature and voltage work together to create the conditions for data storage. But precisely how was unknown. But when a Stanford team found a way to untangle the chip’s energy and heat requirements, their tentative findings revealed a pleasant surprise: The process may be...
Perovskite could lead to next-gen data storage
EPFL scientists have developed a perovskite material with unique properties that can be used to build next-gen hard drives. As we generate more and more data, we need storage systems, e.g. hard drives, with higher density and efficiency. But this also requires materials whose magnetic properties can be quickly and easily manipulated in order to write and access data on them. EPFL scientists have now developed a perovskite material whose magn...
Alternative storage concepts for better quantum memories
Conventional memories used in today’s computers only differentiate between the bit values 0 and 1. In quantum physics, however, arbitrary superpositions of these two states are possible. Most of the ideas for new quantum technology devices rely on this “Superposition Principle”. One of the main challenges in using such states is that they are usually short-lived. Only for a short period of time can information be read out of qua...
64-bit memory architecture for real-time operating system
Consolidation solutions for multicore PCs from TenAsys have been extended with full access to available system memory and programming language support. Version 6.2 of the INtime real-time operating system enables memory extension technology providing each process access to 4GB of physical memory, regardless of the number of processes and cores used on any given system.