arXiv subjects

Rio Yokota

Publications and source records attributed to Rio Yokota.

81 records · Page 5Linked to original sources

arXiv2014

A Performance Model for the Communication in Fast Multipole Methods on HPC Platforms

Exascale systems are predicted to have approximately one billion cores, assuming Gigahertz cores. Limitations on affordable network topologies for distributed memory systems of such massive scale bring new challenges to the current parallel programing model. Currently, there are many efforts to evaluate the hardware and software bottlenecks of exascale designs. There is therefore an urgent need to model application performance and to understand what changes need to be made to ensure extrapolated scalability. The fast multipole method (FMM) was originally developed for accelerating N-body problems in astrophysics and molecular dynamics, but has recently been extended to a wider range of problems, including preconditioners for sparse linear solvers. It's high arithmetic intensity combined with its linear complexity and asynchronous communication patterns makes it a promising algorithm for exascale systems. In this paper, we discuss the challenges for FMM on current parallel computers and future exascale architectures, with a focus on inter-node communication. We develop a performance model that considers the communication patterns of the FMM, and observe a good match between our model and the actual communication time, when latency, bandwidth, network topology, and multi-core penalties are all taken into account. To our knowledge, this is the first formal characterization of inter-node communication in FMM, which validates the model against actual measurements of communication time.

cs.DC↗

arXiv2012

An FMM Based on Dual Tree Traversal for Many-core Architectures

The present work attempts to integrate the independent efforts in the fast N-body community to create the fastest N-body library for many-core and heterogenous architectures. Focus is placed on low accuracy optimizations, in response to the recent interest to use FMM as a preconditioner for sparse linear solvers. A direct comparison with other state-of-the-art fast N-body codes demonstrates that orders of magnitude increase in performance can be achieved by careful selection of the optimal algorithm and low-level optimization of the code. The current N-body solver uses a fast multipole method with an efficient strategy for finding the list of cell-cell interactions by a dual tree traversal. A task-based threading model is used to maximize thread-level parallelism and intra-node load-balancing. In order to extract the full potential of the SIMD units on the latest CPUs, the inner kernels are optimized using AVX instructions. Our code -- exaFMM -- is an order of magnitude faster than the current state-of-the-art FMM codes, which are themselves an order of magnitude faster than the average FMM code.

math.NA↗

arXiv2012

FMM-based vortex method for simulation of isotropic turbulence on GPUs, compared with a spectral method

The Lagrangian vortex method offers an alternative numerical approach for direct numerical simulation of turbulence. The fact that it uses the fast multipole method (FMM)--a hierarchical algorithm for N-body problems with highly scalable parallel implementations--as numerical engine makes it a potentially good candidate for exascale systems. However, there have been few validation studies of Lagrangian vortex simulations and the insufficient comparisons against standard DNS codes has left ample room for skepticism. This paper presents a comparison between a Lagrangian vortex method and a pseudo-spectral method for the simulation of decaying homogeneous isotropic turbulence. This flow field is chosen despite the fact that it is not the most favorable flow problem for particle methods (which shine in wake flows or where vorticity is compact), due to the fact that it is ideal for the quantitative validation of DNS codes. We use a 256^3 grid with Re_lambda=50 and 100 and look at the turbulence statistics, including high-order moments. The focus is on the effect of the various parameters in the vortex method, e.g., order of FMM series expansion, frequency of reinitialization, overlap ratio and time step. The vortex method uses an FMM code (exaFMM) that runs on GPU hardware using CUDA, while the spectral code (hit3d) runs on CPU only. Results indicate that, for this application (and with the current code implementations), the spectral method is an order of magnitude faster than the vortex method when using a single GPU for the FMM and six CPU cores for the FFT.

math.NA↗

arXiv2012

Data-Driven Execution of Fast Multipole Methods

Fast multipole methods have O(N) complexity, are compute bound, and require very little synchronization, which makes them a favorable algorithm on next-generation supercomputers. Their most common application is to accelerate N-body problems, but they can also be used to solve boundary integral equations. When the particle distribution is irregular and the tree structure is adaptive, load-balancing becomes a non-trivial question. A common strategy for load-balancing FMMs is to use the work load from the previous step as weights to statically repartition the next step. The authors discuss in the paper another approach based on data-driven execution to efficiently tackle this challenging load-balancing problem. The core idea consists of breaking the most time-consuming stages of the FMMs into smaller tasks. The algorithm can then be represented as a Directed Acyclic Graph (DAG) where nodes represent tasks, and edges represent dependencies among them. The execution of the algorithm is performed by asynchronously scheduling the tasks using the QUARK runtime environment, in a way such that data dependencies are not violated for numerical correctness purposes. This asynchronous scheduling results in an out-of-order execution. The performance results of the data-driven FMM execution outperform the previous strategy and show linear speedup on a quad-socket quad-core Intel Xeon system.

math.NA↗

arXiv2011

Hierarchical N-body simulations with auto-tuning for heterogeneous systems

With the current hybridization of treecodes and FMMs, combined with auto-tuning capabilities on heterogeneous architectures, the flexibility of fast N-body methods has been greatly enhanced. These features are a requirement to developing a black-box software library for fast N-body algorithms on heterogeneous systems, which is our immediate goal.

math.NA↗

arXiv2011

A Tuned and Scalable Fast Multipole Method as a Preeminent Algorithm for Exascale Systems

Among the algorithms that are likely to play a major role in future exascale computing, the fast multipole method (FMM) appears as a rising star. Our previous recent work showed scaling of an FMM on GPU clusters, with problem sizes in the order of billions of unknowns. That work led to an extremely parallel FMM, scaling to thousands of GPUs or tens of thousands of CPUs. This paper reports on a a campaign of performance tuning and scalability studies using multi-core CPUs, on the Kraken supercomputer. All kernels in the FMM were parallelized using OpenMP, and a test using 10^7 particles randomly distributed in a cube showed 78% efficiency on 8 threads. Tuning of the particle-to-particle kernel using SIMD instructions resulted in 4x speed-up of the overall algorithm on single-core tests with 10^3 - 10^7 particles. Parallel scalability was studied in both strong and weak scaling. The strong scaling test used 10^8 particles and resulted in 93% parallel efficiency on 2048 processes for the non-SIMD code and 54% for the SIMD-optimized code (which was still 2x faster). The weak scaling test used 10^6 particles per process, and resulted in 72% efficiency on 32,768 processes, with the largest calculation taking about 40 seconds to evaluate more than 32 billion unknowns. This work builds up evidence for our view that FMM is poised to play a leading role in exascale computing, and we end the paper with a discussion of the features that make it a particularly favorable algorithm for the emerging heterogeneous and massively parallel architectural landscape.

math.NA↗

arXiv2011

Biomolecular electrostatics using a fast multipole BEM on up to 512 GPUs and a billion unknowns

We present teraflop-scale calculations of biomolecular electrostatics enabled by the combination of algorithmic and hardware acceleration. The algorithmic acceleration is achieved with the fast multipole method (FMM) in conjunction with a boundary element method (BEM) formulation of the continuum electrostatic model, as well as the BIBEE approximation to BEM. The hardware acceleration is achieved through graphics processors, GPUs. We demonstrate the power of our algorithms and software for the calculation of the electrostatic interactions between biological molecules in solution. The applications demonstrated include the electrostatics of protein--drug binding and several multi-million atom systems consisting of hundreds to thousands of copies of lysozyme molecules. The parallel scalability of the software was studied in a cluster at the Nagasaki Advanced Computing Center, using 128 nodes, each with 4 GPUs. Delicate tuning has resulted in strong scaling with parallel efficiency of 0.8 for 256 and 0.5 for 512 GPUs. The largest application run, with over 20 million atoms and one billion unknowns, required only one minute on 512 GPUs. We are currently adapting our BEM software to solve the linearized Poisson-Boltzmann equation for dilute ionic solutions, and it is also designed to be flexible enough to be extended for a variety of integral equation problems, ranging from Poisson problems to Helmholtz problems in electromagnetics and acoustics to high Reynolds number flow.

cs.CE↗

arXiv2010

Treecode and fast multipole method for N-body simulation with CUDA

Due to the variety and importance of applications of treecodes and FMM, the combination of algorithmic acceleration with hardware acceleration can have tremendous impact. Alas, programming these algorithms efficiently is no piece of cake. In this contribution, we aim to present GPU kernels for treecode and FMM in, as much as possible, an uncomplicated, accessible way. The interested reader should consult some of the copious literature on the subject for a deeper understanding of the algorithms themselves. Here, we will offer the briefest of summaries. We will focus our attention on achieving a GPU implementation that is efficient in its utilization of the architecture, but without applying the most advanced techniques known in the field (which would complicate the presentation).

physics.comp-ph↗

arXiv2009

PetRBF--A parallel O(N) algorithm for radial basis function interpolation

We have developed a parallel algorithm for radial basis function (RBF) interpolation that exhibits O(N) complexity,requires O(N) storage, and scales excellently up to a thousand processes. The algorithm uses a GMRES iterative solver with a restricted additive Schwarz method (RASM) as a preconditioner and a fast matrix-vector algorithm. Previous fast RBF methods, --,achieving at most O(NlogN) complexity,--, were developed using multiquadric and polyharmonic basis functions. In contrast, the present method uses Gaussians with a small variance (a common choice in particle methods for fluid simulation, our main target application). The fast decay of the Gaussian basis function allows rapid convergence of the iterative solver even when the subdomains in the RASM are very small. The present method was implemented in parallel using the PETSc library (developer version). Numerical experiments demonstrate its capability in problems of RBF interpolation with more than 50 million data points, timing at 106 seconds (19 iterations for an error tolerance of 10^-15 on 1024 processors of a Blue Gene/L (700 MHz PowerPC processors). The parallel code is freely available in the open-source model.

cs.MS↗