Chip Industry Technical Paper Roundup: Jan 6

SRAM efficiency and performance; channel-last GAA NS oxide transistors; DL model for nanomaterials; HW acceleration for neural networks; memristive FeRAM; scalable AI/ML method for MTJs; HBM for AI inference; HW fuzzing; MoS2 memristors with fast switching for low power.

popularity

New technical papers recently added to Semiconductor Engineering’s library:

Technical Paper Research Organizations
Prefill vs. Decode Bottlenecks: SRAM-Frequency Tradeoffs and the Memory-Bandwidth Ceiling Uppsala University
Channel-last gate-all-around nanosheet oxide semiconductor transistors Stanford, TSMC, ETH Zurich, SLAC, Polish Academy of Sciences
Deep-learning atomistic semi-empirical pseudopotential model for nanomaterials UC Berkeley, LBNL, Brown University et al.
Hardware Acceleration for Neural Networks: A Comprehensive Survey Arizona State University
Nitride Ferroelectric Domain Wall Memory for Next-Generation Computing Kiel University, Fraunhofer ISIT, NaMLab, TU Dresden
LEAD: Literature Enhanced Ab Initio Discovery of Nitride Dusting Layers for Enhanced Tunnel Magnetoresistance and Lower Resistance Magnetic Tunnel Junctions UT Austin, TSMC, TDK Headway
Making Strong Error-Correcting Codes Work Effectively for HBM in AI Inference Rensselaer Polytechnic Institute, ScaleFlux, IBM T.J. Watson Research Center
GoldenFuzz: Generative Golden Reference Hardware Fuzzing TU Darmstadt
Intermediate Resistive State in Wafer-Scale Vertical MoS2 Memristors Through Lateral Silver Filament Growth for Artificial Synapse Applications AMO GmbH, RWTH Aachen, Forschungszentrum Jülich, Peter Grünberg Institute, TU Eindhoven et al.

Find more semiconductor research papers here.



Leave a Reply


(Note: This name will be displayed publicly)