A Synergetic Approach to Throughput Computing on x86-Based Multicore Desktops

Luk, Chi-Keung; Newton, Ryan; Hasenplaugh, Will; Hampton, Mark; Lowney, Geoff

doi:10.1109/ms.2011.2

Cited by 12 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [16], the authors propose a methodology based on Cilk with many similarities to ours. However, the study deals with a set of synthetic examples based on regular or naturally recursive structures, such as grids and trees.…”

Section: Divide-and-conquer Parallel Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Scalable and efficient implementation of 3d unstructured meshes computation: a case study on matrix assembly

Thébault

Petit

Dinh

2015

Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming

View full text Add to dashboard Cite

Con sis te n t * Comple te * W ell Docu m e n te d * Easy to R e us e * * E v a lu ate d * P oP * A r t ifact * A EC P PExposing massive parallelism on 3D unstructured meshes computation with efficient load balancing and minimal synchronizations is challenging. Current approaches relying on domain decomposition and mesh coloring struggle to scale with the increasing number of cores per nodes, especially with new many-core processors. In this paper, we propose an hybrid approach using domain decomposition to exploit distributed memory parallelism, Divide-and-Conquer, D&C, to exploit shared memory parallelism and improve locality, and mesh coloring at core level to exploit vectors. It illustrates a new trade-off for many-cores between structuredness, memory locality, and vectorization. We evaluate our approach on the finite element matrix assembly of an industrial fluid dynamic code developed by Dassault Aviation. We compare our D&C approach to domain decomposition and to mesh coloring. D&C achieves a high parallel efficiency, a good data locality as well as an improved bandwidth usage. It competes on current nodes with the optimized pure MPI version with a minimum 10% speed-up. D&C shows an impressive 319x strong scaling on 512 cores (32 nodes) with only 2000 vertices per core. Finally, the Intel Xeon Phi version has a performance similar to 10 Intel E5-2665 Xeon Sandy Bridge cores and 95% parallel efficiency on the 60 physical cores. Running on 4 Xeon Phi (240 cores), D&C has 92% efficiency on the physical cores and performance similar to 33 Intel E5-2665 Xeon Sandy Bridge cores.

show abstract

Section: Divide-and-conquer Parallel Algorithmsmentioning

confidence: 99%

“…To make the approach practical for the developers, we are using the Cilk Plus array notation [16] as an entry level. From our experiments, this array notation is efficiently transformed in vectorial loops by the compiler and makes the usage of intrinsics in the source code obsolete.…”

Section: Implementing the Vectorizationmentioning

confidence: 99%

Scalable and efficient implementation of 3d unstructured meshes computation: a case study on matrix assembly

Thébault

Petit

Dinh

2015

Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming

View full text Add to dashboard Cite

show abstract

“…This has been proven to be suitable in quantifying the performance on different scientific problems in the context of flow simulations [13], [36], [37]. Software auto tuning tools [38] and dynamics schedulers based on work stealing [39]- [41] have proven to increase the achieved fraction of peak performance of multicore platforms. Other advancements related to memory placement can substantially improve the performance in the context of multiprocessors such as nexttouch policies [42]- [44].…”

Section: Related Workmentioning

confidence: 99%

High throughput software for direct numerical simulations of compressible two-phase flows

Hejazialhosseini

Rossinelli

Conti

et al. 2012

2012 International Conference for High Performance Computing, Networking, Storage and Analysis

View full text Add to dashboard Cite

We present an open source, object-oriented software for high throughput Direct Numerical Simulations of compressible, two-phase flows. The Navier-Stokes equations are discretized on uniform grids using high order finite volume methods. The software exploits recent CPU micro-architectures by explicit vectorization and adopts NUMA-aware techniques as well as data and computation reordering. We report a compressible flow solver with unprecedented fractions of peak performance: 45% of the peak for a single node (nominal performance of 840 GFLOP/s) and 30% for a cluster of 47'000 cores (nominal performance of 0.8 PFLOP/s). We suggest that the present work may serve as a performance upper bound, regarding achievable GFLOP/s, for two-phase flow solvers using adaptive mesh refinement. The software enables 3D simulations of shockbubble interaction including, for the first time, effects of diffusion and surface tension, by efficiently employing two hundred billion computational elements.

show abstract