“…The algorithm performance is limited on CPU, due to the lack of parallelism, with the additional issue of the very large memory requirement. …”
Enlace del recurso

“…Peripherals implement in hardware threshold checking, p edestal sup- pression, waveform recording and histogram building. The CPU has some attractive features for real-time applications: high working frequency, con- stant instruction execution time, short and xed interrupt latency and a tiny logic fo otprint. …”
Enlace del recurso

“…In addition, demonstrating the ability to use an opportunistic resource can lead to securing ATLAS allocations on the facility, hence the importance of this work goes beyond merely the initial CPU cycles gained. In this presentation, we give an overview and compare the performance, development effort, flexibility and robustness of the various approaches. …”
Enlace del recurso

“…LHCb will also receive a factor of 5 increase in the instantaneous luminosity, which further contributes to the challenge of reconstructing and selecting events in real time with the CPU farm. We discuss the plans and progress towards achieving efficient reconstruction and selection with a 30 MHz throughput. …”
Enlace del recurso

“…Then it will focus on some scaling performance measurements executed with a cluster of 1000 CPU cores. In particular, this paper will report about the way Kubernetes scales in deploying containers as a function of the cluster size and show how a proper tuning of the Query per Second (QPS) Kubernetes parameter set can improve the scaling of applications in terms of running replicas. …”
Enlace del recurso
Enlace del recurso

“…To better match the increasing CPU core count and, therefore, the decreasing available memory per core, a multi-threaded framework, AthenaMT, has been designed and is now being implemented. …”
Enlace del recurso
Enlace del recurso

“…This new tool supports typical HEP workflows and data formats and it has been designed to flexibly scale up from data exploration on a laptop to analysis of millions of events exploiting hundreds of CPU cores. As a result, ROOT users can now write simpler code that runs faster. …”
Enlace del recurso

“…Similarly to Upgrade-I, the next detector generation will not have a trigger at the hardware level, and event selection will be done by complete event reconstruction in real time in a CPU farm. To cope with the large increase in pile-up, new techniques to efficiently assign each b-hadron to the primary vertex from which it originates are needed. …”
Enlace del recurso
Enlace del recurso

“…Each FLP receives data from parts of individual detectors, performs a first level of data compression by zero suppression as well as calibration tasks, and sends its output to the EPNs over an Infiniband network. Using the EPN’s CPU cores and GPUs, data is reconstructed and further compressed. …”
Enlace del recurso
Enlace del recurso

“…The GooFit fitter, running on GPUs, shows a remarkable improvement in the computing speed compared to a ROOT/RooFit implementation of the same analysis running on multi-core CPU clusters. Furthermore, it shows sensitivity to components with small contributions to the overall fit. …”
Enlace del recurso
Enlace del recurso

“…The real-time reconstruction of complex events arriving with an average rate of 30 MHz is a very significant computational challenge, which the collaboration has decided to tackle with a heterogeneous computing system, in which CPU, GPU and FPGA cards are employed at the same time. …”
Enlace del recurso

“…We also describe our experience running a high-performance self-managed Kubernetes ATLAS T2 cluster at the scale of 8,000 CPU cores for the last 2 years, and compare with the conventional setup of grid services.…”
Enlace del recurso

“…With an increased dataset obtained during the Run-3 of the LHC at CERN and the even larger expected increase of the dataset by more than one order of magnitude for the HL-LHC, the ATLAS experiment is reaching the limits of the current data processing model in terms of traditional CPU resources based on x86_64 architectures and an extensive program for software upgrades towards the HL-LHC has been set up. …”
Enlace del recurso

“…With an increased dataset obtained during the Run-3 of the LHC at CERN and the even larger expected increase of the dataset by more than one order of magnitude for the HL-LHC, the ATLAS experiment is reaching the limits of the current data processing model in terms of traditional CPU resources based on x86\_64 architectures and an extensive program for software upgrades towards the HL-LHC has been set up. …”
Enlace del recurso

“…They are well-suited for track reconstruction tasks by learning on an expressive structured graph representation of hit data and considerable speedup over CPU-based execution is possible on FPGAs. The focus of this talk is a study of track reconstruction for the Phase-II EF system using GNNs on FPGAs. …”
Enlace del recurso

“…They are well-suited for track reconstruction tasks by learning on an expressive structured graph representation of hit data and considerable speedup over CPU-based execution is possible on FPGAs. The focus of this talk is a study of track reconstruction for the Phase-II EF system using GNNs on FPGAs. …”
Enlace del recurso

“…The implementation described in this paper is based on a distributed architecture. An event builder CPU handles the two main tasks of synchronizing a variable number of front-end processors and formatting the data in preparation for the transfer to a dedicated high-performance storage system, while the front-end processors handle the hardware and the real-time readout. …”
Enlace del recurso
Enlace del recurso

“…It allows to measure individual/aggregate data rates,collected data volumes, and CPU loads. All these values can be visualized on web pages both on a run-by-run and global basis. (3) Various plots will be shown to illustrate the usefulness of this online monitoring system and to document the outcome of the ADC III. …”
Enlace del recurso

“…It will be upgraded to provide LHCb with an all-software, trigger-free readout starting from 2020. Consequently, more CPU power in the form of servers will be needed and the DAQ network will grow to a capacity of 40 Tbps. …”
Enlace del recurso
Enlace del recurso
Enlace del recurso

“…Also connected to the increased signal yield is the need to produce more Monte Carlo samples. The increase in CPU work cannot be absorbed by an increase in hardware resources. …”
Enlace del recurso
Enlace del recurso