Distributed Architectures and Constellations for γ-ray Burst Science

The gravitational wave/γ-ray burst GW/GRB170817 event marked the beginning of the era of multi-messenger astrophysics, in which new observations of Gravitational Waves (GW) are combined with traditional electromagnetic observations from the very same astrophysical source. In the next few years, Advanced LIGO/VIRGO and KAGRA in Japan and LIGO-India will reach their nominal/ultimate sensitivity. In the electromagnetic domain, the Vera C. Rubin Observatory and the Cherenkov Telescope Array (CTA) will come online in the next few years, and they will revolutionize the investigation of transient and variable cosmic sources in the optical and TeV bands. The operation of an efficient X-ray/γ-ray all-sky monitor with good localisation capabilities will play a pivotal role in providing the high-energy counterparts of the GW interferometers and Rubin Observatory, bringing multi-messenger astrophysics to maturity. To reach the required precision in localisation and timeliness for an unpredictable physical event in time and space requires a sensor distribution covering the whole sky. We discuss the potential of large-scale, small-platform-distributed architectures and constellations to build a sensitive X-ray/γ-ray all-sky monitor and the programmatic implications of this, including the set-up of an efficient assembly line for both hardware development and data analysis. We also discuss the potential of a constellation of small platforms operating at other wavelengths (UV/IR) that are capable of repointing quickly to follow-up high-energy transients.

High-Performance Computing Probabilistic Fracture Mechanics Implementation for Gas Turbine Rotor Disks On Distributed Architectures Including Graphics Processing Units (GPUS)

We present an efficient Monte Carlo (MC) based probabilistic fracture mechanics simulation implementation on heterogeneous high-performance (HPC) architectures including CPUs and GPUs for large heavy-duty gas turbine rotor components for the energy sector. A reliable probabilistic risk quantification requires simulating millions to billions of MC samples. We apply a modified Runge-Kutta algorithm to solve numerically the fatigue crack growth for this large number of cracks for varying initial crack sizes, locations, material and service conditions. This compute intensive simulation was demonstrated to perform efficiently and scalable on parallel and distributed architectures with hundreds of CPUs utilizing Message Passing Interface (MPI). In this work, we include GPUs in parallelization strategy. We develop a load distribution scheme to share one or more GPUs on compute nodes distributed over network. We detail technical challenges and strategies in performing the simulations on GPUs efficiently. We show that the key computation of the modified Runge-Kutta integration step speeds up over two orders of magnitude on a typical GPU compared to a single threaded CPU supported by use of GPU textures for efficient interpolation of multi-dimensional tables. We demonstrate weak and strong scaling of our GPU implementation, i.e., that we can efficiently utilize large number of GPUs/CPUs to solve for more MC samples, or reduce the computational turnaround time, respectively. On seven different GPUs spanning four generations, our probabilistic fracture mechanics simulation tool ProbFM achieves speedups ranging from 16.4x to 47.4x compared to single threaded CPU implementation.

A Flexible Software/Hardware Adaptive Network for Embedded Distributed Architectures

Embedded platforms are projected to integrate hundreds of cores in the near future, and expanding the interconnection network remains a key challenge. We propose SNet, a new Scalable NETwork paradigm that extends the NoCs area to include a software/hardware dynamic routing mechanism. To design routing pathways among communicating processes, it uses a distributed, adaptive, non-supervised routing method based on the ACO algorithm (Ant Colony Optimization). A small footprint hardware unit called DMC speeds up data transfer (Direct Management of Communications). SNet has the benefit of being extremely versatile, allowing for the creation of a broad range of routing topologies to meet the needs of various applications. We provide the DMC module in this work and assess SNet performance by executing a large number of test cases.