| Zhang Xiuxia (张秀霞),Tan Guangming,Chen Mingyu,Yao Erlin.[J].高技术通讯(英文),2017,23(2):185~190 |
|
| A case study of 3D RTM-TTI algorithm on multicore and many-core platforms |
| |
| DOI：10.3772/j.issn.1006-6748.2017.02.010 |
| 中文关键词: |
| 英文关键词: 3D RTM-TTI, Intel Xeon Phi, NVIDIA K20 GPU, stencil computing, many-core, multicore, seismic imaging |
| 基金项目: |
| Author Name | Affiliation | | Zhang Xiuxia (张秀霞) | | | Tan Guangming | | | Chen Mingyu | | | Yao Erlin | |
|
| Hits: 1257 |
| Download times: 1080 |
| 中文摘要: |
| |
| 英文摘要: |
| 3D reverse time migration in tiled transversly isotropic (3D RTM-TTI) is the most precise model for complex seismic imaging. However, vast computing time of 3D RTM-TTI prevents it from being widely used, which is addressed by providing parallel solutions for 3D RTM-TTI on multicores and many-cores. After data parallelism and memory optimization, the hot spot function of 3D RTM-TTI gains 35.99X speedup on two Intel Xeon CPUs, 89.75X speedup on one Intel Xeon Phi, 89.92X speedup on one NVIDIA K20 GPU compared with serial CPU baseline. This study makes RTM-TTI practical in industry. Since the computation pattern in RTM is stencil, the approaches also benefit a wide range of stencil-based applications. |
|
View Full Text
View/Add Comment Download reader |
| Close |
|
|
|
