category: Architectures

category: IoT, Security & Automotive

Improving Performance and Power Efficiency By Safely Eliminating Load Instruction Execution (ETH Zürich, Intel)
By Technical Paper Link - 22 Jul, 2024 - Comments: 0

A technical paper titled “Constable: Improving Performance and Power Efficiency by Safely Eliminating Load Instruction Execution” was published by researchers at ETH Zürich and Intel Corporation.  This paper earned the Best Paper Award in the International Symposium on Computer Architecture (ISCA). Abstract: "Load instructions often limit instruction-level parallelism (ILP) in modern pr... » read more

NVMs: In-Memory Fine-Grained Integrity Verification Technique (Intel Labs, IISc)
By Technical Paper Link - 16 Jul, 2024 - Comments: 0

A new technical paper titled "iMIV: in-Memory Integrity Verification for NVM" was published by researchers at Intel Labs and Indian Institute of Science (IISc), Bengaluru. Abstract "Non-volatile Memory (NVM) could bridge the gap between memory and storage. However, NVMs are susceptible to data remanence attacks. Thus, multiple security metadata must persist along with the data to protect th... » read more

In Situ Backpropagation Strategy That Progressively Updates Neural Network Layers Directly in HW (TU Eindhoven)
By Technical Paper Link - 16 Jul, 2024 - Comments: 0

A new technical paper titled "Hardware implementation of backpropagation using progressive gradient descent for in situ training of multilayer neural networks" was published by researchers at Eindhoven University of Technology. Abstract "Neural network training can be slow and energy-expensive due to the frequent transfer of weight data between digital memory and processing units. Neuromorp... » read more

On-Chip Communication For Programmable Accelerators In Heterogeneous SoCs (Columbia, IBM)
By Technical Paper Link - 10 Jul, 2024 - Comments: 0

A technical paper titled “Towards Generalized On-Chip Communication for Programmable Accelerators in Heterogeneous Architectures” was published by researchers at Columbia University and IBM Thomas J. Watson Research Center. Abstract: "We present several enhancements to the open-source ESP platform to support flexible and efficient on-chip communication for programmable accelerators in het... » read more

Roadmap To Neuromorphic Computing (Collaboration of 27 Universities/Companies)
By Technical Paper Link - 09 Jul, 2024 - Comments: 0

A technical paper titled “Roadmap to Neuromorphic Computing with Emerging Technologies” was published by researchers at University College London, Politecnico di Milano, Purdue University, ETH Zurich and numerous other institutions. Summary: "The roadmap is organized into several thematic sections, outlining current computing challenges, discussing the neuromorphic computing approach, ana... » read more

Lower Energy, High Performance LLM on FPGA Without Matrix Multiplication
By Technical Paper Link - 27 Jun, 2024 - Comments: 0

A new technical paper titled "Scalable MatMul-free Language Modeling" was published by UC Santa Cruz, Soochow University, UC Davis, and LuxiTech. Abstract "Matrix multiplication (MatMul) typically dominates the overall computational cost of large language models (LLMs). This cost only grows as LLMs scale to larger embedding dimensions and context lengths. In this work, we show that MatMul... » read more

Dedicated Approximate Computing Framework To Efficiently Compute PCs On Hardware
By Technical Paper Link - 20 Jun, 2024 - Comments: 0

A technical paper titled “On Hardware-efficient Inference in Probabilistic Circuits” was published by researchers at Aalto University and UCLouvain. Abstract: "Probabilistic circuits (PCs) offer a promising avenue to perform embedded reasoning under uncertainty. They support efficient and exact computation of various probabilistic inference tasks by design. Hence, hardware-efficient compu... » read more

Rowhammer Bit Flips On A High-End RISC-V CPU (ETH Zurich)
By Technical Paper Link - 13 Jun, 2024 - Comments: 0

A new technical paper titled "RISC-H: Rowhammer Attacks on RISC-V" was published by researchers at ETH Zurich.  RISC-H will be presented at DRAMSec (co-located with ISCA 2024) Abstract: "The first high-end RISC-V CPU with DDR4 support has been released just a few months ago. There are currently no Rowhammer studies on RISC-V devices and it is unclear whether it is possible to compromise ... » read more

KAN: Kolmogorov Arnold Networks: An Alternative To MLPs (MIT, CalTech, et al.)
By Technical Paper Link - 13 Jun, 2024 - Comments: 0

A new technical paper titled "KAN: Kolmogorov-Arnold Networks" was published by researchers at MIT, CalTech, Northeastern University and The NSF Institute for Artificial Intelligence and Fundamental Interactions. Abstract: "Inspired by the Kolmogorov-Arnold representation theorem, we propose Kolmogorov-Arnold Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs). While... » read more

Efficient TNN Inference on RISC-V Processing Cores With Minimal HW Overhead
By Technical Paper Link - 10 Jun, 2024 - Comments: 0

A new technical paper titled "xTern: Energy-Efficient Ternary Neural Network Inference on RISC-V-Based Edge Systems" was published by researchers at ETH Zurich and Universita di Bologna. Abstract "Ternary neural networks (TNNs) offer a superior accuracy-energy trade-off compared to binary neural networks. However, until now, they have required specialized accelerators to realize their effic... » read more

← Older posts Newer posts →

  • Sponsors

About

Navigation

Connect With Us

Copyright ©2013-2025 SMG   |  Terms of Service  |  Privacy Policy