On Scalability Issues of the Elastodynamics Equations on Multicore Platforms

Dupros, Fabrice; Thuan, Hiep; Aochi, Hideo

doi:10.1016/j.procs.2013.05.289

Cited by 8 publications

(10 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dupros et al [19] presented a review of the scalability issues for distributed and shared-memory platforms with a focus on mapping processes/threads on hierarchical clusters. Dursun et al [20] introduced several additional strategies, including inter-node and intra-node optimizations.…”

mentioning

confidence: 99%

Energy Efficient Seismic Wave Propagation Simulation on a Low-Power Manycore Processor

Castro

Dupros

Francesquini

et al. 2014

2014 IEEE 26th International Symposium on Computer Architecture and High Performance Computing

Self Cite

View full text Add to dashboard Cite

Large-scale simulation of seismic wave propagation is an active research topic. Its high demand for processing power makes it a good match for High Performance Computing (HPC). Although we have observed a steady increase on the processing capabilities of HPC platforms, their energy efficiency is still lacking behind. In this paper, we analyze the use of a low-power manycore processor, the MPPA-256, for seismic wave propagation simulations. First we look at its peculiar characteristics such as limited amount of on-chip memory and describe the intricate solution we brought forth to deal with this processor's idiosyncrasies. Next, we compare the performance and energy efficiency of seismic wave propagation on MPPA-256 to other commonplace platforms such as general-purpose processors and a GPU. Finally, we wrap up with the conclusion that, even if MPPA-256 presents an increased software development complexity, it can indeed be used as an energy efficient alternative to current HPC platforms, resulting in up to 71% and 81% less energy than a GPU and a general-purpose processor, respectively.

show abstract

mentioning

confidence: 99%

Energy Efficient Seismic Wave Propagation Simulation on a Low-Power Manycore Processor

Castro

Dupros

Francesquini

et al. 2014

2014 IEEE 26th International Symposium on Computer Architecture and High Performance Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Despite this apparent regularity, Ondes3D suffers from major load imbalance that limits its scalability. The main source of imbalance has been previously identified as the extra‐computation needed to deal with boundary conditions. The processes on the border of the domain have thus more work, which causes significant spatial imbalance when compared to processes that compute the inner part of the 3D region being simulated.…”

Section: Ondes3d: a Typical Imbalanced Mpi Codementioning

confidence: 99%

“…The design of this code is representative for a typical iterative application tailored for homogeneous HPC platforms with static domain decomposition. Despite the regularity of the FDM micro‐kernels it employs, Ondes3D has limited scalability because of both spatial and temporal load imbalance.…”

Section: Introductionmentioning

confidence: 99%

“…Simulated makespan predictions for the Ligurian earthquake simulation with (left) six load balancing intervals (in number of iterations) and (right) with five over-decomposition levels(2,3,4,8, and 16) on 16 cores the load carelessly whereas RefineLB is much more conservative, the communication performance of the system is sufficiently good to hide the migration costs.Investigating the influence of the decomposition level:Another important performance affecting parameter is the over-decomposition level. The results on how over-decomposition affects the makespan of Ondes3D, when calling MPI_Migrate every 20 time steps, are in the right plot of The average makespan (vertical axis) is shown as a function of five over-decomposition configurations (horizontal) plus the absence of over-decomposition (eg, 16 × 1).…”

mentioning

confidence: 99%

See 1 more Smart Citation

Performance modeling of a geophysics application to accelerate over‐decomposition parameter tuning through simulation

Tesser

Schnorr

Legrand

et al. 2018

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Summary Finite‐difference methods are commonplace in High Performance Computing applications. Despite their apparent regularity, they often exhibit load imbalance that damages their efficiency. We characterize the spatial and temporal load imbalance of Ondes3D, a typical finite‐differences application dedicated to earthquake modeling. Our analysis reveals imbalance originating from the structure of the input data, and from low‐level CPU optimizations. Ondes3D was successfully ported to AMPI/CHARM++ using over‐decomposition and MPI process migration techniques to dynamically rebalance the load. However, this approach requires careful selection of the over‐decomposition level, the load balancing algorithm, and its activation frequency. These choices are usually tied to application structure and platform characteristics. In this article, we propose a workflow that leverages the capabilities of SimGrid to conduct such study at low experimental cost. We rely on a combination of emulation, simulation, and application modeling that requires minimal code modification and manages to capture both spatial and temporal load imbalance to faithfully predict the performance of dynamic load balancing. We evaluate the quality of our simulation by comparing simulation results with the outcome of real executions and demonstrate how this approach can be used to quickly find the optimal load balancing configuration for a given application/hardware configuration.

show abstract

“…Firstly, the imbalance coming from the absorbing boundary conditions could be partially addressed by using a dynamic schedule across the loop iterations. This leads to significant improvements in the distribution of the load [12]. This solution comes at the expense of introducing an irregular access of the data with higher NUMA penalties on hierarchical platforms.…”

Section: Multi-threaded Algorithmmentioning

confidence: 99%

On the energy efficiency and performance of irregular application executions on multicore, NUMA and manycore platforms

Francesquini

Castro

Penna

et al. 2015

Journal of Parallel and Distributed Computing

Self Cite

View full text Add to dashboard Cite

h i g h l i g h t s• Programming for a manycore is challenging.• Limited memory and NoC are among the most important constraints of manycores. • For CPU-bound and mixed workloads, MPPA-256 achieves better performance than Xeon. • MPPA-256 consumes up to 13× less energy than embedded and general-purpose multicores. a b s t r a c t Until the last decade, performance of HPC architectures has been almost exclusively quantified by their processing power. However, energy efficiency is being recently considered as important as raw performance and has become a critical aspect to the development of scalable systems. These strict energy constraints guided the development of a new class of so-called light-weight manycore processors. This study evaluates the computing and energy performance of two well-known irregular NP-hard problems -the Traveling-Salesman Problem (TSP) and K-Means clustering -and a numerical seismic wave propagation simulation kernel -Ondes3D -on multicore, NUMA, and manycore platforms. First, we concentrate on the nontrivial task of adapting these applications to a manycore, specifically the novel MPPA-256 manycore processor. Then, we analyze their performance and energy consumption on those different machines. Our results show that applications able to fully use the resources of a manycore can have better performance and may consume from 3.8× to 13× less energy when compared to low-power and general-purpose multicore processors, respectively.

show abstract

On Scalability Issues of the Elastodynamics Equations on Multicore Platforms

Cited by 8 publications

References 22 publications

Energy Efficient Seismic Wave Propagation Simulation on a Low-Power Manycore Processor

Energy Efficient Seismic Wave Propagation Simulation on a Low-Power Manycore Processor

Performance modeling of a geophysics application to accelerate over‐decomposition parameter tuning through simulation

On the energy efficiency and performance of irregular application executions on multicore, NUMA and manycore platforms

Contact Info

Product

Resources

About