SparseP: Towards Efficient Sparse Matrix Vector Multiplication on Real Processing-In-Memory Systems


Abstract "Several manufacturers have already started to commercialize near-bank Processing-In-Memory (PIM) architectures. Near-bank PIM architectures place simple cores close to DRAM banks and can yield significant performance and energy improvements in parallel applications by alleviating data access costs. Real PIM systems can provide high levels of parallelism, large aggregate memory bandwi... » read more

Non-destructive Thickness Characterisation of 3D Multilayer Semiconductor Devices Using Optical Spectral Measurements and Machine Learning


Abstract: "Three-dimensional (3D) semiconductor devices can address the limitations of traditional two-dimensional (2D) devices by expanding the integration space in the vertical direction. A 3D NOT-AND (NAND) flash memory device ispresently the most commercially successful 3D semiconductor device. It vertically stacks more than 100 semiconductor material layers to provide more storage capac... » read more

Comprehensive Model of Electron Conduction in Oxide-Based Memristive Devices


Abstract "Memristive devices are two-terminal devices that can change their resistance state upon application of appropriate voltage stimuli. The resistance can be tuned over a wide resistance range enabling applications such as multibit data storage or analog computing-in-memory concepts. One of the most promising classes of memristive devices is based on the valence change mechanism in oxide... » read more

Hybrid architecture based on two-dimensional memristor crossbar array and CMOS integrated circuit for edge computing


Abstract "The fabrication of integrated circuits (ICs) employing two-dimensional (2D) materials is a major goal of semiconductor industry for the next decade, as it may allow the extension of the Moore’s law, aids in in-memory computing and enables the fabrication of advanced devices beyond conventional complementary metal-oxide-semiconductor (CMOS) technology. However, most circuital demons... » read more

A crossbar array of magnetoresistive memory devices for in-memory computing


Samsung has demonstrated the world’s first in-memory computing technology based on MRAM. Samsung has a paper on the subject in Nature. This paper showcases Samsung’s effort to merge memory and system semiconductors for next-generation artificial intelligence (AI) chips. Abstract "Implementations of artificial neural networks that borrow analogue techniques could potentially offer low-po... » read more

Spin–orbit torque engineering in β-W/CoFeB heterostructures with W–Ta or W–V alloy layers between β-W and CoFeB


Abstract "The spin–orbit torque (SOT) resulting from a spin current generated in a nonmagnetic transition metal layer offers a promising magnetization switching mechanism for spintronic devices. To fully exploit this mechanism, in practice, materials with high SOT efficiencies are indispensable. Moreover, new materials need to be compatible with semiconductor processing. This study introduce... » read more

Field-free spin-orbit torque-induced switching of perpendicular magnetization in a ferrimagnetic layer with a vertical composition gradient


Abstract "Current-induced spin-orbit torques (SOTs) are of interest for fast and energy-efficient manipulation of magnetic order in spintronic devices. To be deterministic, however, switching of perpendicularly magnetized materials by SOT requires a mechanism for in-plane symmetry breaking. Existing methods to do so involve the application of an in-plane bias magnetic field, or incorporation o... » read more

A review of interconnect materials used in emerging memory device packaging: first- and second-level interconnect materials


Abstract "The main motivation of this review is to study the evolution of first and second level of interconnect materials used in memory device semiconductor packaging. Evolutions of bonding wires from gold (Au) to silver (Ag) or copper (Cu) have been reported and studied in previous literatures for low-cost solution, but Au wire still gives highest rating in terms of the performance of tempe... » read more

NeuroSim Simulator for Compute-in-Memory Hardware Accelerator: Validation and Benchmark


Abstract:   "Compute-in-memory (CIM) is an attractive solution to process the extensive workloads of multiply-and-accumulate (MAC) operations in deep neural network (DNN) hardware accelerators. A simulator with options of various mainstream and emerging memory technologies, architectures, and networks can be a great convenience for fast early-stage design space exploration of CIM hardw... » read more

Toward Software-Equivalent Accuracy on Transformer-Based Deep Neural Networks With Analog Memory Devices


Abstract:  "Recent advances in deep learning have been driven by ever-increasing model sizes, with networks growing to millions or even billions of parameters. Such enormous models call for fast and energy-efficient hardware accelerators. We study the potential of Analog AI accelerators based on Non-Volatile Memory, in particular Phase Change Memory (PCM), for software-equivalent accurate i... » read more

← Older posts Newer posts →