scholarly journals Numerical Cosmology powered by GPUs

2010 ◽  
Vol 6 (S270) ◽  
pp. 397-400 ◽  
Author(s):  
Dominique Aubert
Keyword(s):  
Radiative Transfer ◽  
Graphics Processing Units ◽  
Large Scale ◽  
Numerical Calculations ◽  
Cosmological Simulations ◽  
Gpu Clusters ◽  
Graphics Processing ◽  
Large Scale Simulations ◽  
Gpu Implementation ◽  
Numerical Cosmology

AbstractGraphics Processing Units (GPUs) offer a new way to accelerate numerical calculations by means of on-board massive parallelisation. We discuss two examples of GPU implementation relevant for cosmological simulations, an N-Body Particle-mesh solver and a radiative transfer code. The latter has also been ported on multi-GPU clusters. The range of acceleration (x30-x80) achieved here offer bright perspective for large scale simulations driven by GPUs.

scholarly journals A lightweight approach to performance portability with targetDP

2016 ◽  
Vol 32 (2) ◽  
pp. 288-301
Author(s):  
Alan Gray ◽  
Kevin Stratford
Keyword(s):  
Particle Physics ◽  
Message Passing ◽  
Graphics Processing Units ◽  
High Performance ◽  
Large Scale ◽  
Message Passing Interface ◽  
Graphics Processing Unit ◽  
Processing Unit ◽  
Performance Portability ◽  
Graphics Processing

Leading high performance computing systems achieve their status through use of highly parallel devices such as NVIDIA graphics processing units or Intel Xeon Phi many-core CPUs. The concept of performance portability across such architectures, as well as traditional CPUs, is vital for the application programmer. In this paper we describe targetDP, a lightweight abstraction layer which allows grid-based applications to target data parallel hardware in a platform agnostic manner. We demonstrate the effectiveness of our pragmatic approach by presenting performance results for a complex fluid application (with which the model was co-designed), plus separate lattice quantum chromodynamics particle physics code. For each application, a single source code base is seen to achieve portable performance, as assessed within the context of the Roofline model. TargetDP can be combined with Message Passing Interface (MPI) to allow use on systems containing multiple nodes: we demonstrate this through provision of scaling results on traditional and graphics processing unit-accelerated large scale supercomputers.

scholarly journals XVA PRINCIPLES, NESTED MONTE CARLO STRATEGIES, AND GPU OPTIMIZATIONS

2018 ◽  
Vol 21 (06) ◽  
pp. 1850030 ◽  
Author(s):  
LOKMAN A. ABBAS-TURKI ◽  
STÉPHANE CRÉPEY ◽  
BABACAR DIALLO
Keyword(s):  
Monte Carlo ◽  
Interest Rate ◽  
Outer Layer ◽  
Graphics Processing Units ◽  
Lower Layer ◽  
Credit Derivatives ◽  
Square Root ◽  
Root Number ◽  
Graphics Processing ◽  
Gpu Implementation

We present a nested Monte Carlo (NMC) approach implemented on graphics processing units (GPUs) to X-valuation adjustments (XVAs), where X ranges over C for credit, F for funding, M for margin, and K for capital. The overall XVA suite involves five compound layers of dependence. Higher layers are launched first, and trigger nested simulations on-the-fly whenever required in order to compute an item from a lower layer. If the user is only interested in some of the XVA components, then only the sub-tree corresponding to the most outer XVA needs be processed computationally. Inner layers only need a square root number of simulation with respect to the most outer layer. Some of the layers exhibit a smaller variance. As a result, with GPUs at least, error-controlled NMC XVA computations are doable. But, although NMC is naively suited to parallelization, a GPU implementation of NMC XVA computations requires various optimizations. This is illustrated on XVA computations involving equities, interest rate, and credit derivatives, for both bilateral and central clearing XVA metrics.

scholarly journals Artist: fast radiative transfer for large-scale simulations of the epoch of reionization

2019 ◽  
Vol 489 (4) ◽  
pp. 5594-5611 ◽  
Author(s):  
Margherita Molaro ◽  
Romeel Davé ◽  
Sultan Hassan ◽  
Mario G Santos ◽  
Kristian Finlator
Keyword(s):  
Radiative Transfer ◽  
Large Scale ◽  
Power Spectra ◽  
Physical Parameters ◽  
Speed Of Light ◽  
Photon Propagation ◽  
Wide Range ◽  
Gas Ionization ◽  
Excursion Set ◽  
Large Scale Simulations

ABSTRACT We introduce the ‘Asymmetric Radiative Transfer In Shells Technique’ (artist), a new method for photon propagation on large scales that explicitly conserves photons, propagates photons at the speed of light, approximately accounts for photon directionality, and closely reproduces results of more detailed radiative transfer (RT) methods. Crucially, it is computationally fast enough to evolve the large cosmological volumes required to predict the 21cm power spectrum on scales that will be probed by future experiments targeting the epoch of reionization (EoR). Most seminumerical models aimed at predicting the EoR 21cm signal on these scales use an excursion set formalism (ESF) to model the gas ionization, which achieves computational viability by making a number of approximations. While artist is still roughly two orders of magnitude slower than ESF, it does allow to model the EoR without the need for such approximations. This is particularly important when considering a wide range of reionization scenarios for which artist would help limit the assumptions made. By implementing our RT method within the seminumerical code simfast21, we show that Artist predicts a significantly different evolution for the EoR ionization field compared to the code’s native ESF. In particular, artist predicts up to a factor of two difference in the power spectra, depending on the physical parameters assumed. Its application to large-scale EoR simulations will therefore allow more physically motivated constraints to be obtained for key EoR parameters. In particular, it will remove the need for the artificial rescaling of the escape fraction.

scholarly journals Graphics processing unit implementation of the F-statistic for continuous gravitational wave searches

2021 ◽  
Author(s):  
Liam Dunn ◽  
Patrick Clearwater ◽  
Andrew Melatos ◽  
Karl Wette
Keyword(s):  
Gravitational Wave ◽  
Graphics Processing Units ◽  
Graphics Processing Unit ◽  
Computational Cost ◽  
Processing Unit ◽  
Central Processing ◽  
Long Baseline ◽  
Using Data ◽  
Graphics Processing ◽  
Gpu Implementation

Abstract The F-statistic is a detection statistic used widely in searches for continuous gravitational waves with terrestrial, long-baseline interferometers. A new implementation of the F-statistic is presented which accelerates the existing "resampling" algorithm using graphics processing units (GPUs). The new implementation runs between 10 and 100 times faster than the existing implementation on central processing units without sacrificing numerical accuracy. The utility of the GPU implementation is demonstrated on a pilot narrowband search for four newly discovered millisecond pulsars in the globular cluster Omega Centauri using data from the second Laser Interferometer Gravitational-Wave Observatory observing run. The computational cost is 17:2 GPU-hours using the new implementation, compared to 1092 core-hours with the existing implementation.

Sign in / Sign up

Export Citation Format

Share Document