Magnetic tunnel junction-based computational random-access memory
A study demonstrates computational random-access memory (CRAM) using magnetic tunnel junctions, enhancing energy efficiency and performance by enabling logic operations within memory cells, crucial for machine intelligence applications.
Read original article
A recent study published in npj Unconventional Computing presents an experimental demonstration of computational random-access memory (CRAM) utilizing magnetic tunnel junctions (MTJs). This new computing paradigm aims to address the limitations of traditional computing architectures, particularly the energy and performance bottlenecks caused by data transfers between logic and memory modules. CRAM allows logic operations to be performed directly within memory cells, eliminating the need for data to leave the memory, which enhances energy efficiency and processing performance, especially for machine intelligence applications.
The research involved testing basic memory operations and various multi-input logic operations, culminating in the demonstration of a 1-bit full adder with two designs. The experimental results led to the development of models to assess the computational accuracy of CRAM, which showed promising results in scalar addition, multiplication, and matrix multiplication—key operations for both conventional and machine intelligence applications.
The MTJ-based CRAM architecture incorporates transistors to improve electrical accessibility and allows for larger memory arrays compared to previous in-memory computing paradigms. The study highlights the potential of CRAM to significantly impact power- and energy-demanding applications, reinforcing the viability of MTJs as a foundation for future computing technologies. Overall, the findings suggest that CRAM could play a crucial role in advancing computing systems to meet the growing demands of emerging applications.
Related
Mechanical computer relies on kirigami cubes, not electronics
Researchers at North Carolina State University created a mechanical computer based on kirigami, using polymer cubes for data storage. The system offers reversible data editing and complex computing capabilities, with potential applications in encryption and data display.
An Analog Network of Resistors Promises Machine Learning Without a Processor
Researchers at the University of Pennsylvania created an analog resistor network for machine learning, offering energy efficiency and enhanced computational capabilities. The network, supervised by Arduino Due, shows promise in diverse tasks.
Mechanical Computer Relies on Kirigami Cubes, Not Electronics
Researchers at North Carolina State University created a mechanical computer based on kirigami, using polymer cubes for data storage. The system allows reversible data editing and offers potential in encryption and complex computing. Published in Science Advances, the study demonstrates high-density memory capabilities and envisions collaborations for coding and haptic systems.
Bubble Memory
Bubble memory, a non-volatile computer memory from the 1970s, used magnetic bubbles to store data. Despite early potential, it declined due to competition from faster chips and hard drives, becoming obsolete.
The Ternary Computing Manifesto
Douglas W. Jones advocates for ternary computing to boost security and cut data leakage. Ternary logic offers efficient data representation, potentially reducing malware threats and enhancing computer architecture with smaller wiring. Jones explores fast addition, heptavintimal encoding, and ternary data types, proposing Trillium and Tritium architectures for future systems.
0 commentsRelated
Mechanical computer relies on kirigami cubes, not electronics
Researchers at North Carolina State University created a mechanical computer based on kirigami, using polymer cubes for data storage. The system offers reversible data editing and complex computing capabilities, with potential applications in encryption and data display.
An Analog Network of Resistors Promises Machine Learning Without a Processor
Researchers at the University of Pennsylvania created an analog resistor network for machine learning, offering energy efficiency and enhanced computational capabilities. The network, supervised by Arduino Due, shows promise in diverse tasks.
Mechanical Computer Relies on Kirigami Cubes, Not Electronics
Researchers at North Carolina State University created a mechanical computer based on kirigami, using polymer cubes for data storage. The system allows reversible data editing and offers potential in encryption and complex computing. Published in Science Advances, the study demonstrates high-density memory capabilities and envisions collaborations for coding and haptic systems.
Bubble Memory
Bubble memory, a non-volatile computer memory from the 1970s, used magnetic bubbles to store data. Despite early potential, it declined due to competition from faster chips and hard drives, becoming obsolete.
The Ternary Computing Manifesto
Douglas W. Jones advocates for ternary computing to boost security and cut data leakage. Ternary logic offers efficient data representation, potentially reducing malware threats and enhancing computer architecture with smaller wiring. Jones explores fast addition, heptavintimal encoding, and ternary data types, proposing Trillium and Tritium architectures for future systems.