Related papers: Synchronous High-frequency Distributed Readout For…
With the increasing physical event rate and number of electronic channels, traditional readout scheme meets the challenge of improving readout speed caused by the limited bandwidth of crate backplane. In this paper, a high-speed data…
A new beam injection scheme is proposed for the Fermilab Booster to increase beam brightness. The beam is injected on the deceleration part of the sinusoidal magnetic ramp and capture is started immediately after the injection. During the…
Dynamic Vision Sensors (DVS) offer a unique advantage in control applications due to their high temporal resolution and asynchronous event-based data. Still, their adoption in machine learning algorithms remains limited. To address this gap…
The rapid growth of LLMs demands high-throughput, memory-capacity-intensive inference on resource-constrained edge devices, where single-batch decoding remains fundamentally memory-bound. Existing out-of-core GPU-based and SSD-like…
Artificial intelligence and machine learning models deployed on edge devices, e.g., for quality control in Additive Manufacturing (AM), are frequently small in size. Such models usually have to deliver highly accurate results within a short…
Fault diagnosis is a crucial area of research in industry. Industrial processes exhibit diverse operating conditions, where data often have non-Gaussian, multi-mode, and center-drift characteristics. Data-driven approaches are currently the…
Despite the impressive search rate of one key per clock cycle, the update stage of a random-access-memory-based content-addressable-memory (RAM-based CAM) always suffers high latency. Two primary causes of such latency include: (1) the…
In Fermilab's PIP-II machine protection system, beam loss signals from various detectors are digitized at 125 MS/s. Noise from both high-frequency sources and low-frequency 60 Hz AC power equipment can contaminate the data. To suppress…
Here, we introduce Linac_Gen, a tool developed at Fermilab, which combines machine learning algorithms with Particle-in-Cell methods to advance beam dynamics in linacs. Linac_Gen employs techniques such as Random Forest, Genetic Algorithms,…
We discuss the progress made on a new installation in Fermilab's Main Injector that will help investigate the electron cloud phenomenon by making direct measurements of the secondary electron yield (SEY) of samples irradiated in the…
In recent years, machine learning has developed rapidly, enabling the development of applications with high levels of recognition accuracy relating to the use of speech and images. However, other types of data to which these models can be…
We present READMem (Robust Embedding Association for a Diverse Memory), a modular framework for semi-automatic video object segmentation (sVOS) methods designed to handle unconstrained videos. Contemporary sVOS works typically aggregate…
To improve the efficiency of distributed large language model (LLM) inference, various parallelization strategies, such as tensor and pipeline parallelism, have been proposed. However, the distinct computational characteristics inherent in…
This paper presents a memory efficient architecture that implements the Multi-Scale Line Detector (MSLD) algorithm for real-time retinal blood vessel detection in fundus images on a Zynq FPGA. This implementation benefits from the FPGA…
Event-based vision sensors produce asynchronous event streams with high temporal resolution based on changes in the visual scene. The properties of these sensors allow for accurate and fast calculation of optical flow as events are…
A real-time beam profile monitoring system is proposed for GeV photon beams at the BM4 beamline of the Mikamine site, Research Center for Accelerator and Radioisotope Science (RARiS; previously known as ELPH) at Tohoku University. This…
The introduction of silicon chipsets with the capability of processing incoming optical packet traffic, creates a new generation of packet-optical nodes, the whiteboxes. Their inherent functionality of carrying pluggable coherent…
In this paper, we propose StruM, a novel structured mixed-precision-based deep learning inference method, co-designed with its associated hardware accelerator (DPU), to address the escalating computational and memory demands of deep…
The deployment of large language models (LLMs) presents significant challenges due to their enormous memory footprints, low arithmetic intensity, and stringent latency requirements, particularly during the autoregressive decoding stage.…
The readout electronics for the resonant beam position monitors (BPMs) in the Fermilab Switchyard (SY) have been upgraded, utilizing a low noise amplifier transition board and Fermilab designed digitizer boards. The stripline BPMs are…