Loading...
Please wait, while we are loading the content...
Similar Documents
The promises of hybrid hexagonal/classical tiling for gpu (2013).
| Content Provider | CiteSeerX |
|---|---|
| Author | Grosser, Tobias Verdoolaege, Sven Cohen, Albert |
| Abstract | Time-tiling is necessary for efficient execution of iterative stencil computations. But the usual hyper-rectangular tiles cannot be used because of positive/negative dependence distances along the stencil's spatial dimensions. Several prior efforts have addressed this issue. However, known techniques trade enhanced data reuse for other causes of inefficiency, such as unbalanced parallelism, redundant computations, or increased control ow overhead incompatible with efficient GPU execution. We explore a new path to maximize the effectivness of time-tiling on iterative stencil computations. Our approach is particularly well suited for GPUs. It does not require any redundant computations, it favors coalesced global-memory access and data reuse in shared-memory/cache, avoids thread divergence, and extracts a high degree of parallelism. We introduce hybrid hexagonal tiling, combining hexagonal tile shapes along the time (sequential) dimension and one spatial dimension, with classical tiling for other spatial dimensions. An hexagonal tile shape simultaneously enable parallel tile execution and reuse along the time dimension. Experimental results demonstrate significant performance improvements over existing stencil compilers. |
| File Format | |
| Publisher Date | 2013-01-01 |
| Access Restriction | Open |
| Subject Keyword | Hybrid Hexagonal Classical Tiling Spatial Dimension Data Reuse Hexagonal Tile Shape Redundant Computation Iterative Stencil Computation Efficient Execution Shared-memory Cache Unbalanced Parallelism Several Prior Effort Control Ow High Degree Time Dimension Efficient Gpu Execution Technique Trade New Path Positive Negative Dependence Distance Hybrid Hexagonal Tiling Enable Parallel Tile Execution Stencil Compiler Usual Hyper-rectangular Tile Global-memory Access Classical Tiling |
| Content Type | Text |