An efficient code generation technique for tiled iteration spaces

Goumas, Georgios; Athanasaki, Maria; Koziris, Nectarios

doi:10.1109/tpds.2003.1239870

Cited by 24 publications

(20 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…. , u n and the matrix H , as described in [1,21]. Each point j S in this ndimensional integer space J S is a distinct tile with coordinates ( j S 1 , j S 2 , .…”

Section: Algorithmic Model-loop Tilingmentioning

confidence: 99%

Hyperplane Grouping and Pipelined Schedules: How to Execute Tiled Loops Fast on Clusters of SMPs

et al. 2005

View full text Add to dashboard Cite

Abstract. This paper proposes a novel approach for the parallel execution of tiled Iteration Spaces onto a cluster of SMP PC nodes. Each SMP node has multiple CPUs and a single memory mapped PCI-SCI Network Interface Card. We apply a hyperplane-based grouping transformation to the tiled space, so as to group together independent neighboring tiles and assign them to the same SMP node. In this way, intranode (intragroup) communication is annihilated. Groups are atomically executed inside each node. Nodes exchange data between successive group computations. We schedule groups much more efficiently by exploiting the inherent overlapping between communication and computation phases among successive atomic group executions. The applied non-blocking schedule resembles a pipelined datapath, where group computation phases are overlapped with communication ones, instead of being interleaved with them. Our experimental results illustrate that the proposed method outperforms previous approaches involving blocking communication or conventional grouping schemes.

show abstract

“…. , u n and the matrix H , as described in [1,21]. Each point j S in this ndimensional integer space J S is a distinct tile with coordinates ( j S 1 , j S 2 , .…”

Section: Algorithmic Model-loop Tilingmentioning

confidence: 99%

Hyperplane Grouping and Pipelined Schedules: How to Execute Tiled Loops Fast on Clusters of SMPs

et al. 2005

View full text Add to dashboard Cite

show abstract

“…In addition, we consider rectangular basic tile shapes. A general, parallelogram tiling transformation can only be implemented by automatic parallelizing compilers due to the complexity of the code that traverses non-rectangular tiles [10], [12]. For the above problem class we propose a new criterion for the selection of an efficient tile shape.…”

Section: Introductionmentioning

confidence: 99%

Communication-Aware Supernode Shape

Goumas

Drosinos

Koziris

2009

IEEE Trans. Parallel Distrib. Syst.

Self Cite

View full text Add to dashboard Cite

Abstract-In this paper we revisit the supernode-shape selection problem, that has been widely discussed in bibliography. In general, the selection of the supernode transformation greatly affects the parallel execution time of the transformed algorithm. Since the minimization of the overall parallel execution time via an appropriate supernode transformation is very difficult to accomplish, researchers have focused on scheduling-aware supernode transformations that maximize parallelism during the execution. In this paper we argue that the communication volume of the transformed algorithm is an important criterion, and its minimization should be given high priority. For this reason we define the metric of the per process communication volume and propose a method to miminize this metric by selecting a communication-aware supernode shape. Our approach is equivalent to defining a proper Cartesian process grid with MPI Cart Create, which means that it can be incorporated in applications in a straightforward manner. Our experimental results illustrate that by selecting the tile shape with the proposed method, the total parallel execution time is significantly reduced due to the minimization of the communication volume, despite the fact that a few more parallel execution steps are required.

show abstract

“…The problem of the application of general tiling transformations has been attacked in [1] and [2], where it is shown that the general case can be handled only by an automatic parallelizing compiler. However, the problem of efficiently mapping non-rectangular tiles to a fixed number of processes is still open.…”

Section: Introductionmentioning

confidence: 99%