Related papers: Highly-Multiplexed Superconducting Detector Readou…
In this paper, we propose LoopLynx, a scalable dataflow architecture for efficient LLM inference that optimizes FPGA usage through a hybrid spatial-temporal design. The design of LoopLynx incorporates a hybrid temporal-spatial architecture,…
The SeaQuest experiment (Fermilab E906) detects pairs of energetic {\mu}+ and {\mu}- produced in 120 GeV/c proton-nucleon interactions in a high rate environment. The trigger system consists of several arrays of scintillator hodoscopes and…
Edge AI deployment faces critical challenges balancing computational performance, energy efficiency, and resource constraints. This paper presents FPGA-accelerated RISC-V instruction set architecture (ISA) extensions for efficient neural…
The aim of this study is to design and evaluate a simple free running Analog-Digital Converter (ADC) based on the Field Programmable Gate Array (FPGA) device to accomplish the energy and position readout of the silicon photomultiplier…
Recent advances in logic schemes and fabrication processes have renewed interest in using superconductor electronics for energy-efficient computing and quantum control processors. However, scalable superconducting memory still poses a…
InductEx is a software tool used for the analysis of integrated circuit designs and extraction of design parameters by way of numerical electromagnetic field solving. This tool was originally developed with Rapid Single Flux Quantum (RSFQ)…
While embedded FPGAs are attractive platforms for DNN acceleration on edge-devices due to their low latency and high energy efficiency, the scarcity of resources of edge-scale FPGA devices also makes it challenging for DNN deployment. In…
The design, construction and performance of the H1 silicon vertex detector is described. It consists of two cylindrical layers of double sided, double metal silicon sensors read out by a custom designed analog pipeline chip. The analog…
The speed of quantum gates and measurements is a decisive factor for the overall fidelity of quantum protocols when performed on physical qubits with finite coherence time. Reducing the time required to distinguish qubit states with high…
We have developed a quantum annealing processor, based on an array of tunably coupled rf-SQUID flux qubits, fabricated in a superconducting integrated circuit process [1]. Implementing this type of processor at a scale of 512 qubits and…
Visual tracking is one of the most important application areas of computer vision. At present, most algorithms are mainly implemented on PCs, and it is difficult to ensure real-time performance when applied in the real scenario. In order to…
The radiation hardness of passive CMOS pixel sensors fabricated in 150 nm LFoundry technology is investigated. CMOS process lines are especially of interest for large-scale silicon detectors as they offer high production throughput at…
A fast readout system for the upgrade of the COMPASS RICH detector has been developed and successfully used for data taking in 2006 and 2007. The new readout system for the multi-anode PMTs in the central part of the photon detector of the…
An upgrade of the ATLAS experiment for the High Luminosity phase of LHC is planned for 2024 and foresees the replacement of the present Inner Detector (ID) with a new Inner Tracker (ITk) completely made of silicon devices. Depleted active…
Binary neural networks provide a promising solution for low-power, high-speed inference by replacing expensive floating-point operations with bitwise logic. This makes them well-suited for deployment on resource-constrained platforms such…
The attention layer, a core component of Transformer-based LLMs, brings out inefficiencies in current GPU systems due to its low operational intensity and the substantial memory requirements of KV caches. We propose a High-bandwidth…
Digital off-detector electronics in trigger and data acquisition systems of High-Energy Physics experiments is often implemented by means of SRAM-based FPGAs, which make it possible to achieve reconfigurable, real-time processing and…
We present FlexLLM, a composable High-Level Synthesis (HLS) library for rapid development of domain-specific LLM accelerators. FlexLLM exposes key architectural degrees of freedom for stage-customized inference, enabling hybrid designs that…
Increasing development in embedded systems, VLSI and processor design have given rise to increased demands from the system in terms of power, speed, area, throughput etc. Most of the sophisticated embedded system applications consist of…
High Voltage CMOS sensors are a promising technology for tracking detectors in collider experiments. Extensive R&D studies are being carried out by the ATLAS Collaboration for a possible use of HV-CMOS in the High Luminosity LHC upgrade of…