Contention-free communication scheduling for array redistribution

Guo, Minyi; Nakata, Ikuo; Yamashita, Yoshiyuki

doi:10.1016/s0167-8191(00)00027-2

Cited by 24 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Park et al in [10] Optimal × Desprez et al in [22] Optimal optimal (larger overhead) Optimal × Guo et al in [23] Optimal ⊗…”

Section: Resultsmentioning

confidence: 99%

“…Apparently, there exist node contentions between the source processors P 1 and P 2 , e.g., both processors will send messages to the destination processor P 1 in step 3, to the destination processor P 0 in step 4, and to the destination processors P 5 in step 5. Generally, for an r → kr redistribution over M processors with the processor mapping technique applied and with k < M, using the Caterpillar algorithm and the scheduling methods proposed in [13,20,23] to schedule communications will all cause node contentions.…”

Section: B Receive Scheduling Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

An Efficient Communication Scheduling Method for the Processor Mapping Technique Applied Data Redistribution

Huang

Chu

2006

J Supercomput

View full text Add to dashboard Cite

Array redistribution is usually required for more efficiently executing a data-parallel program on distributed memory multi-computers. In performing array redistribution using synchronous communication mode, data communications among the processors should be properly arranged to avoid incurring higher data transfer cost. Some efficient communication scheduling methods for the Block-Cyclic redistribution have been proposed. On the other hand, the processor mapping technique can help reduce the data transfer cost of redistribution. To avoid degrading the benefit of data transfer cost reduction, it is needed to construct optimal communication schedules for the redistribution in which the processor mapping technique is applied. In this paper, we present a unified approach to constructing optimal communication schedules for the processor mapping technique applied Block-Cyclic redistribution. The proposed method is founded on the processor mapping technique and can more efficiently construct the required communication schedules than other optimal scheduling methods.

show abstract

“…Park et al in [10] Optimal × Desprez et al in [22] Optimal optimal (larger overhead) Optimal × Guo et al in [23] Optimal ⊗…”

Section: Resultsmentioning

confidence: 99%

Section: B Receive Scheduling Algorithmmentioning

confidence: 99%

An Efficient Communication Scheduling Method for the Processor Mapping Technique Applied Data Redistribution

Huang

Chu

2006

J Supercomput

View full text Add to dashboard Cite

show abstract

“…For a program with nested loops, data access pattern analyzing approaches was proposed by Lam et al [24,25] and was used to enable the program to run on a parallel machine in a communication-free manner with certain constraints. On the other hand, for multidimensional redistribution, Guo et al [13][14][15] focused on the automatic generation of communication routines. For multistatements in perfect and imperfect loops, Shih et al [35] confirmed the problem on communication-free partition statement-iteration and data spaces along hyperplanes.…”

Section: Existing Known Methods For Solving the Alignment Problemmentioning

confidence: 99%

Communication-free data alignment for arrays with exponential references in parallelizing compilers for scalable parallel systems

et al. 2009

Self Cite

View full text Add to dashboard Cite

In loops, some arrays are referenced with induction variables. To parallelize such kind of loops, those induction variables should be substituted. Thus, those array references that were substituted are formulated as nonlinear expressions. The goal of data alignment is to intelligently map the computations and data onto a set Communication-free data alignment for arrays with exponential references 5 of virtual processors which are organized as a Cartesian grid (or a template in HPF terms), and to provide data locality for parallelizing compilers so that data access communication costs can be minimized. Most data alignment methods are mainly devised to align the referenced arrays using linear subscripts or quadratic subscripts with n loop index variables, and the methods are well developed. Seldom work, however, is researched on the nonlinear expressions of index variables. This paper proposes a new communication-free data alignment technique to align the referenced arrays using exponential subscripts with n loop index variables or other complex nonlinear expressions. The experimental results using SPEC95FP Benchmarks point out that the techniques proposed in the paper can improve the execution time of the subroutines in these benchmarks.

show abstract

“…Figure 2a shows an initial communication patterns. The source GEN_BLOCK distribution is of (7,10,4,18,7,18,36) and the destination GEN_BLOCK distribution is of (10,14,18,14,14,12,18). The redistribution is carried out over seven processors with maximum degree 3.…”

Section: The Two-phase Degree Reduction Methodsmentioning

confidence: 99%

“…Examples are the processor mapping techniques [4,10,12] for minimizing data transmission overheads, the multiphase redistribution strategy [11] for reducing message startup cost, the communication scheduling approaches [2,7,13,20] for avoiding node contention and the strip mining approach [18] for overlapping communication and computational overheads.…”

Section: Related Workmentioning

confidence: 99%

Scheduling contention-free irregular redistributions in parallelizing compilers

2007

View full text Add to dashboard Cite

Irregular array redistribution has been paid attention recently since it can distribute different size of data segment to heterogeneous processors according to their computational ability. It's also the reason why it has been kept an eye on load balance. High Performance Fortran Version 2 (HPF2) provides GEN_BLOCK distribution format which facilitates generalized block distributions. In this paper, we present a two-phase degree-reduction (TPDR) method for scheduling HPF2 irregular array redistribution. Using a bipartite communication graph, the first phase of TPDR schedules communication links adjacent to processors that with degree greater than two. A communication step will be scheduled follow each degree-reduction iteration. The second phase of TPDR schedules remaining messages of all processors that with degree-2 and degree-1 using an adjustable coloring mechanism. An extended algorithm based on TPDR is also presented in this paper. Effectiveness of the proposed methods not only avoids node contention but also shortens the overall communication cost. The proposed methods are also practicable due to low algorithmic complexity. To evaluate the performance of our methods, we have implemented both algorithms along with the divide-and-conquer algorithm and two scheduling mechanism. The simulation results show improvement of total communication costs.

show abstract

Contention-free communication scheduling for array redistribution

Cited by 24 publications

References 9 publications

An Efficient Communication Scheduling Method for the Processor Mapping Technique Applied Data Redistribution

An Efficient Communication Scheduling Method for the Processor Mapping Technique Applied Data Redistribution

Communication-free data alignment for arrays with exponential references in parallelizing compilers for scalable parallel systems

Scheduling contention-free irregular redistributions in parallelizing compilers

Contact Info

Product

Resources

About