Related papers: Data Acquisition System with Shared Memory Network
Many scientific applications from rare-event searches to condensed matter system characterization to high-rate nuclear experiments require time-domain triggering on a raw stream of data, where the triggering is generally threshold-based or…
As the scale of distributed training grows, communication becomes a bottleneck. To accelerate the communication, recent works introduce In-Network Aggregation (INA), which moves the gradients summation into network middle-boxes, e.g.,…
The status of R&D activities for CLIC module acquisition are discussed [1]. LAPP is involved in the design of the local CLIC module acquisition crate, described in the document Study of the CLIC Module Front-End Acquisition and Evaluation…
In this paper we propose a new engine management system for hybrid vehicles to enable energy providers and car manufacturers to provide new services. Energy forecasts are used to collaboratively orchestrate the behaviour of engine…
Neural networks are increasingly used in real-time systems, such as automated driving applications. This requires high-performance hardware with predictable timing behavior. State-of-the-art real-time hardware is limited in memory and…
The growing gap between processor and memory speeds results in complex memory hierarchies as processors evolve to mitigate such divergence by taking advantage of the locality of reference. In this direction, the BSC performance analysis…
The PEP-II storage rings at SLAC each have 3492 'buckets' into which electrons and positrons can be injected into the high- and low-energy rings. Equipment to measure the currents of all the individual buckets was originally provided by the…
Current HPC systems provide memory resources that are statically configured and tightly coupled with compute nodes. However, workloads on HPC systems are evolving. Diverse workloads lead to a need for configurable memory resources to…
The Spin Physics Detector (SPD) experiment at the NICA collider in JINR aims to investigate the spin structure of nucleons and spin-related phenomena. The combination of the number of background processes, the event rate and conditions for…
Processing-in-memory (PIM) has emerged as a promising solution for accelerating memory-intensive workloads as they provide high memory bandwidth to the processing units. This approach has drawn attention not only from the academic community…
We present scalable distributed-memory algorithms for sparse matrix permutation, extraction, and assignment. Our methods follow an Identify-Exchange-Build (IEB) strategy where each process identifies the local nonzeros to be sent, exchanges…
With the proposition to install a large number of phasor measurement units (PMUs) in the future power grid, it is essential to provide robust communications infrastructure for phasor data across the network. We make progress in this…
Most recent speaker verification systems are based on extracting speaker embeddings using a deep neural network. The pooling layer in the network aims to aggregate frame-level features extracted by the backbone. In this paper, we propose a…
Applications with low data reuse and frequent irregular memory accesses, such as graph or sparse linear algebra workloads, fail to scale well due to memory bottlenecks and poor core utilization. While prior work with prefetching,…
Data analysis in the Internet of Things (IoT) requires us to combine event streams from a huge amount of sensors. This combination (join) of events is usually based on the time stamps associated with the events. We address two challenges in…
On December 15th the Swiss Light Source (SLS) produced a stored beam for the first time. This important milestone was achieved in a very tight time schedule. The fact that all major systems are controlled by Epics made this challenge…
Exponential increases in scientific experimental data are outstripping the rate of progress in silicon technology. As a result, heterogeneous combinations of architectures and process or device technologies are increasingly important to…
A PC based high speed silicon microstrip beam telescope consisting of several independent modules is presented. Every module contains an AC-coupled double sided silicon microstrip sensor and a complete set of analog and digital signal…
The integration of image and event streams offers a promising approach for achieving robust visual object tracking in complex environments. However, current fusion methods achieve high performance at the cost of significant computational…
Federated Learning (FL) is a newly emerged decentralized machine learning (ML) framework that combines on-device local training with server-based model synchronization to train a centralized ML model over distributed nodes. In this paper,…