category: Power & Performance

category: IoT, Security & Automotive

LLM Inference on GPUs (Intel)
By Technical Paper Link - 02 Feb, 2024 - Comments: 0

A technical paper titled “Efficient LLM inference solution on Intel GPU” was published by researchers at Intel Corporation. Abstract: "Transformer based Large Language Models (LLMs) have been widely used in many fields, and the efficiency of LLM inference becomes hot topic in real applications. However, LLMs are usually complicatedly designed in model structure with massive operations and... » read more

HW/SW Techniques To Regulate Supply Voltage And Clock Frequency Of Intermittently-Computing Devices
By Technical Paper Link - 02 Feb, 2024 - Comments: 0

A technical paper titled “Dynamic Voltage and Frequency Scaling for Intermittent Computing” was published by researchers at Politecnico di Milano, Georgia Institute of Technology, Lahore University of Management Sciences, and Uppsala University. Abstract: "We present hardware/software techniques to intelligently regulate supply voltage and clock frequency of intermittently-computing devic... » read more

A New Phase-Change Memory For Processing Large Amounts Of Data 
By Technical Paper Link - 30 Jan, 2024 - Comments: 0

A technical paper titled “Novel nanocomposite-superlattices for low energy and high stability nanoscale phase-change memory” was published by researchers at Stanford University, TSMC, NIST, University of Maryland, Theiss Research and Tianjin University. Abstract: "Data-centric applications are pushing the limits of energy-efficiency in today’s computing systems, including those based on... » read more

RISC-V Ultra-Low-Power Edge Accelerators (EPFL)
By Technical Paper Link - 30 Jan, 2024 - Comments: 0

A technical paper titled “X-HEEP: An Open-Source, Configurable and Extendible RISC-V Microcontroller for the Exploration of Ultra-Low-Power Edge Accelerators” was published by researchers at EPFL. Abstract: "The field of edge computing has witnessed remarkable growth owing to the increasing demand for real-time processing of data in applications. However, challenges persist due to limitat... » read more

Training Large LLM Models With Billions To Trillion Parameters On ORNL’s Frontier Supercomputer
By Technical Paper Link - 16 Jan, 2024 - Comments: 0

A technical paper titled “Optimizing Distributed Training on Frontier for Large Language Models” was published by researchers at Oak Ridge National Laboratory (ORNL) and Universite Paris-Saclay. Abstract: "Large language models (LLMs) have demonstrated remarkable success as foundational models, benefiting various downstream applications through fine-tuning. Recent studies on loss scaling ... » read more

Properties Of The State-Of-The-Art Commercially Available SiC and GaN Power Transistors
By Technical Paper Link - 15 Jan, 2024 - Comments: 0

A technical paper titled “Review and Outlook on GaN and SiC Power Devices: Industrial State-of-the-Art, Applications, and Perspectives” was published by researchers at University of Padova. Abstract: "We present a comprehensive review and outlook of silicon carbide (SiC) and gallium nitride (GaN) transistors available on the market for current and next-generation power electronics. Materi... » read more

Security Threats To Multitenant FPGAs: A Remote Undervolting Attack That Activates A Trojan Concealed Within A Victim Design 
By Technical Paper Link - 15 Jan, 2024 - Comments: 0

A technical paper titled “X-Attack 2.0: The Risk of Power Wasters and Satisfiability Don’t-Care Hardware Trojans to Shared Cloud FPGAs” was published by researchers at EPFL, Cyber-Defence Campus (Switzerland), and Northwestern Polytechnical University (China). Abstract: "Cloud computing environments increasingly provision field-programmable gate arrays (FPGAs) for their programmability ... » read more

Chiplet Heterogeneity And Advanced Scheduling With Pipelining
By Technical Paper Link - 12 Jan, 2024 - Comments: 0

A technical paper titled “Inter-Layer Scheduling Space Exploration for Multi-model Inference on Heterogeneous Chiplets” was published by researchers at University of California Irvine. Abstract: "To address increasing compute demand from recent multi-model workloads with heavy models like large language models, we propose to deploy heterogeneous chiplet-based multi-chip module (MCM)-based... » read more

A Potentially CMOS Compatible Integration Of Reconfigurable FETs Based On Al-Si-Al Heterostructure Sheets
By Technical Paper Link - 11 Jan, 2024 - Comments: 0

A technical paper titled “Reconfigurable Si Field-Effect Transistors With Symmetric On-States Enabling Adaptive Complementary and Combinational Logic” was published by researchers at TU Vienna and Swiss Federal Laboratories for Materials Science and Technology. Abstract: "Reconfigurable field-effect transistors (RFETs), combining n-and p-type operation in a single device, have already sho... » read more

The 40-Million-Core Sunway Supercomputer: 5 ExaFlop/s HPL-MxP Benchmark With Linear Scalability
By Technical Paper Link - 11 Jan, 2024 - Comments: 0

A technical paper titled “5 ExaFlop/s HPL-MxP Benchmark with Linear Scalability on the 40-Million-Core Sunway Supercomputer” was published by researchers at the National Research Center of Parallel Computer Engineering and Technology and Tsinghua University. Abstract: "HPL-MxP is an emerging high performance benchmark used to measure the mixed-precision computing capability of leading sup... » read more

← Older posts Newer posts →

  • Sponsors

About

Navigation

Connect With Us

Copyright ©2013-2024 SMG   |  Terms of Service  |  Privacy Policy