Author's Latest Posts


SpiNNaker2 Neuromorphic Platform: HW-Aware Fine-Tuning of Spiking Q-Networks (TU Dresden Et Al.)


A new technical paper titled "Hardware-Aware Fine-Tuning of Spiking Q-Networks on the SpiNNaker2 Neuromorphic Platform" was published by researchers at TU Dresden, ScaDS.AI and Centre for Tactile Internet with Human-in-the-Loop (CeTI). Excerpt "Spiking Neural Networks (SNNs) promise orders-of-magnitude lower power consumption and low-latency inference on neuromorphic hardware for a wide ran... » read more

Optical Next-Gen Reservoir Computing Framework (Sorbonne, CNRS, Tsinghua U. et al)


A new technical paper titled "Optical next generation reservoir computing" was published by researchers at Sorbonne Université, CNRS, Tsinghua University, University of Hong Kong, and University of Tokyo. Excerpt "Artificial neural networks with internal dynamics exhibit remarkable capability in processing information. Reservoir computing (RC) is a canonical example that features rich comp... » read more

Double Intra-Cavity VCSELs: Properties And Design Challenges At Cryogenic Temperatures (Tampere Univ.)


A new technical paper titled "Thermal characteristics of a double intra-cavity contact VCSEL for cryogenic optical links" was published by researchers at Tampere University. Excerpt "Cryogenic computing systems, including quantum computers, cryo-CMOS and superconducting processors, necessitate efficient optical data links capable of operation at temperatures as low as 4 K. Vertical-cavity s... » read more

Non-ideal Subthreshold Swing In Aligned CNTs Due To Variable Occupancy Discrete Charge Traps (Berkeley Lab, Sandia)


A new technical paper titled "Non-ideal subthreshold swing in aligned carbon nanotube transistors due to variable occupancy discrete charge traps" was published by researchers at Lawrence Berkeley National Laboratory and Sandia National Laboratories. Excerpt "Carbon nanotube transistors have been experimentally demonstrated to reach performance comparable and even surpassing that of silicon... » read more

Framework To Control And Interact With SystemC-based Virtual Platforms Using The FMI (RWTH Aachen Univ. et al.)


A new technical paper titled "FMI Meets SystemC: A Framework for Cross-Tool Virtual Prototyping" was published by researchers at RWTH Aachen University, MachineWare and tracetronic. Excerpt "As systems become more complex, the demand for thorough testing and virtual prototyping grows. To simulate whole systems, multiple tools are usually needed to cover different parts. These parts include ... » read more

Challenges And Outlook of Photonic-Integrated Circuit Packaging (Hanyang Univ.)


A new technical paper titled "Advanced Optical Integration Processes for Photonic-Integrated Circuit Packaging" was published by researchers at Hanyang University. Excerpt "This review discusses the latest developments in photonic integrated chip packaging at the component, chip, and system levels. It also highlights the current issues and challenges of these technologies and provides futur... » read more

Overview Of The End-to-End Autonomous Driving through V2X Challenge (Tsinghua, HK Univ., Stanford, TU Munich et al.)


A new technical paper titled "Research Challenges and Progress in the End-to-End V2X Cooperative Autonomous Driving Competition" was published by researchers at Tsinghua University, Hong Kong University, Stanford University, TU Munich, Imperial College of London et al. Abstract "With the rapid advancement of autonomous driving technology, vehicle-to-everything (V2X) communication has emerge... » read more

LLM Inference: Core Bottlenecks Imposed By Memory, Compute Capacity, Synchronization Overheads (NVIDIA)


A new technical paper titled "Efficient LLM Inference: Bandwidth, Compute, Synchronization, and Capacity are all you need" was published by NVIDIA. Abstract "This paper presents a limit study of transformer-based large language model (LLM) inference, focusing on the fundamental performance bottlenecks imposed by memory bandwidth, memory capacity, and synchronization overhead in distributed ... » read more

Statistical BER Analysis For Two Types Of Communication Systems In Chiplet Integration (TSMC)


An new technical paper titled "Fast and Accurate Jitter Modeling for Statistical BER Analysis for Chiplet Interconnect and Beyond" was published by researchers at TSMC. Abstract "In this paper, we investigate Statistical Bit Error Rate (BER) analysis for low-loss short-reach chiplet interface and high-loss long-reach serial interface. We used jitter filtering to account for the residue jitt... » read more

3D Heterogeneous Integration System To Accelerate LLMs (Georgia Tech)


A new technical paper titled "A3D-MoE: Acceleration of Large Language Models with Mixture of Experts via 3D Heterogeneous Integration" was published by researchers at Georgia Institute of Technology. Abstract "Conventional large language models (LLMs) are equipped with dozens of GB to TB of model parameters, making inference highly energy-intensive and costly as all the weights need to be ... » read more

← Older posts Newer posts →