The K computer: Japanese next-generation supercomputer development project

Yokokawa,; Shoji, Fumiyoshi; Uno,; Kurokawa,; Watanabe, Toru

doi:10.1109/islped.2011.5993668

Cited by 65 publications

(41 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This high scalability is important to attain a sustained peta-scale performance for practical simulations. Figure 20 shows the sustained performance of MHD_Spectral on SX-ACE, SX-9, ES2, and the K computer [22]. The performances of SX-9, ES2 and the K computer are quoted from [17], and the code is optimized for individual systems.…”

Section: Performance Evaluation Of Multiple Nodes Of Sx-acementioning

confidence: 99%

Potential of a modern vector supercomputer for practical applications: performance evaluation of SX-ACE

et al. 2017

View full text Add to dashboard Cite

Achieving a high sustained simulation performance is the most important concern in the HPC community. To this end, many kinds of HPC system architectures have been proposed, and the diversity of the HPC systems grows rapidly. Under this 123Potential of a modern vector supercomputer for practical… 3949 circumstance, a vector-parallel supercomputer SX-ACE has been designed to achieve a high sustained performance of memory-intensive applications by providing a high memory bandwidth commensurate with its high computational capability. This paper examines the potential of the modern vector-parallel supercomputer through the performance evaluation of SX-ACE using practical engineering and scientific applications. To improve the sustained simulation performances of practical applications, SX-ACE adopts an advanced memory subsystem with several new architectural features. This paper discusses how these features, such as MSHR, a large on-chip memory, and novel vector processing mechanisms, are beneficial to achieve a high sustained performance for large-scale engineering and scientific simulations. Evaluation results clearly indicate that the high sustained memory performance per core enables the modern vector supercomputer to achieve outstanding performances that are unreachable by simply increasing the number of fine-grain scalar processor cores. This paper also discusses the performance of the HPCG benchmark to evaluate the potentials of supercomputers with balanced memory and computational performance against heterogeneous and cutting-edge scalar parallel systems.

show abstract

Section: Performance Evaluation Of Multiple Nodes Of Sx-acementioning

confidence: 99%

Potential of a modern vector supercomputer for practical applications: performance evaluation of SX-ACE

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Local discovery (per substep) (lines [11][12][13][14][15][16][17][18][19][20] Search for parents with the information available locally.…”

Section: Parallel and Distributed Bfs Algorithmmentioning

confidence: 99%

“…The zand b-axes connect system boards, and the a-and c-axes are coordinate axes with a length of 2 that connect processors on each system board [1,15]. For 2-D partitioning of a graph, yz Â xabc is used instead of xyz À abc and then we can obtain 288 Â 288 for balanced 2-D mesh.…”

Section: Using the Entire K-computermentioning

confidence: 99%

“…Our new work extends the data structures and algorithm called hybrid BFS [2] that is known to be effective small-diameter graphs, so that it scales to top-tier supercomputers with tens of thousands of nodes with million-scale CPU cores with multi-gigabyte/s interconnect. In particular, we apply our algorithm to the Riken's K-Computer [15] with 82,944 compute nodes and 663,552 CPU cores, once the fastest supercomputer in the world on the Top500 in 2011 with over 10 Petaflops. The result obtained is currently No.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Breadth-First Search on Massively Parallel and Distributed-Memory Machines

et al. 2017

View full text Add to dashboard Cite

“…The newest generation of high-end supercomputer networks is beginning to move to higher dimensionality (e.g. IBM Blue Gene/Q is 5D [4], K computer is 6D [14]). This transition is natural since the minimal-cost (bisection bandwidth with respect to number of pins) topology for a network of 100,000 nodes is 3D, while for 1,000,000 nodes it is 5D or 6D [5].…”

Section: Introductionmentioning

confidence: 99%

Matrix Multiplication on Multidimensional Torus Networks

Solomonik

Demmel

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Blocked matrix multiplication algorithms such as Cannon's algorithm and SUMMA have a 2-dimensional communication structure. We introduce a generalized 'Split-Dimensional' version of Cannon's algorithm (SD-Cannon) with higher-dimensional and bidirectional communication structure. This algorithm is useful for higher-dimensional torus interconnects that can achieve more injection bandwidth than single-link bandwidth. On a bidirectional torus network of dimension d, SD-Cannon can lower the algorithmic bandwidth cost by a factor of up to d. With rectangular collectives, SUMMA also achieves the lower bandwidth cost but has a higher latency cost. We use Charm++ virtualization to efficiently map SD-Cannon on unbalanced and odd-dimensional torus network partitions. Our performance study on Blue Gene/P demonstrates that an MPI version of SD-Cannon can exploit multiple communication links and improve performance.

show abstract

The K computer: Japanese next-generation supercomputer development project

Cited by 65 publications

References 2 publications

Potential of a modern vector supercomputer for practical applications: performance evaluation of SX-ACE

Potential of a modern vector supercomputer for practical applications: performance evaluation of SX-ACE

Efficient Breadth-First Search on Massively Parallel and Distributed-Memory Machines

Matrix Multiplication on Multidimensional Torus Networks

Contact Info

Product

Resources

About