Related papers: The GRAPE-4, a Teraflops Stellar Dynamics Computer
Finite-difference methods based on high-order stencils are widely used in seismic simulations, weather forecasting, computational fluid dynamics, and other scientific applications. Achieving HPC-level stencil computations on one…
In the blooming field of exoplanetary science, NASA's Kepler Space Telescope has revolutionized our understanding of exoplanets. Kepler's very precise and long-duration photometry is ideal for detecting planetary transits around Sun-like…
There is a growing interest in custom spatial accelerators for machine learning applications. These accelerators employ a spatial array of processing elements (PEs) interacting via custom buffer hierarchies and networks-on-chip. The…
The DEEP projects have developed a variety of hardware and software technologies aiming at improving the efficiency and usability of next generation high-performance computers. They evolve around an innovative concept for heterogeneous…
Stencil computation is one of the most important kernels in various scientific computing. Nowadays, most Stencil-driven scientific computing still relies heavily on supercomputers, suffering from expensive access, poor scalability, and…
Future computing systems, from handhelds to supercomputers, will undoubtedly be more parallel and heterogeneous than todays systems to provide more performance and energy efficiency. Thus, GPUs are increasingly being used to accelerate…
We developed a high-speed image reduction pipeline using Graphics Processing Units (GPUs) as hardware accelerators. Astronomers desire detecting EM counterpart of gravitational-wave sources as soon as possible for sharing positional…
This paper concentrates on four key tools for performing star cluster simulations developed during the last decade which are sufficient to handle all the relevant dynamical aspects. First we discuss briefly the Hermite integration scheme…
Upcoming large scale telescope projects such as the Square Kilometre Array (SKA) will see high data rates and large data volumes; requiring tools that can analyse telescope event data quickly and accurately. In modern radio telescopes,…
General purpose computing on graphic processing units (GPU) is a potential method of speeding up scientific computation with low cost and high energy efficiency. We experimented with the particle physics simulation toolkit Geant4 used at…
The latest Graphics Processing Units (GPUs) are reported to reach up to 200 billion floating point operations per second (200 Gflops) and to have price performance of 0.1 cents per M flop. These facts raise great interest in the…
We present GIGA-Lens: a gradient-informed, GPU-accelerated Bayesian framework for modeling strong gravitational lensing systems, implemented in TensorFlow and JAX. The three components, optimization using multi-start gradient descent,…
With the end of both Dennard's scaling and Moore's law, computer users and researchers are aggressively exploring alternative forms of computing in order to continue the performance scaling that we have come to enjoy. Among the more salient…
The primary use of technical computing in the oil and gas industries is for seismic imaging of the earth's subsurface, driven by the business need for making well-informed drilling decisions during petroleum exploration and production.…
During the last couple of years, observers have started to make plans for a Virtual Observatory, as a federation of existing data bases, connected through levels of software that enable rapid searches, correlations, and various forms of…
The numerical simulations of massive collisional stellar systems, such as globular clusters (GCs), are very time-consuming. Until now, only a few realistic million-body simulations of GCs with a small fraction of binaries (5%) have been…
Large-scale graph problems are of critical and growing importance and historically parallel architectures have provided little support. In the spirit of co-design, we explore the question, How fast can graph computing go on a fine-grained…
Developing complex, reliable advanced accelerators requires a coordinated, extensible, and comprehensive approach in modeling, from source to the end of beam lifetime. We present highlights in Exascale Computing to scale accelerator…
We present direct astrophysical N-body simulations with up to a few million bodies using our parallel MPI/CUDA code on large GPU clusters in China, Ukraine and Germany, with different kinds of GPU hardware. These clusters are directly…
The time required for training the neural networks increases with size, complexity, and depth. Training model parameters by backpropagation inherently creates feedback loops. These loops hinder efficient pipelining and scheduling of the…