623 Tflop/s HPCG run on Tianhe-2: Leveraging millions of hybrid cores
文献类型：期刊论文
| 作者 | Liu, YQ ; Yang, C ; Liu, FF ; Zhang, XY ; Lu, YT ; Du, YF ; Yang, CQ ; Xie, M ; Liao, XK |
| 刊名 | INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS
 |
| 出版日期 | 2016 |
| 卷号 | 30期号:1页码:39-54 |
| 关键词 | Tianhe-2 HPCG conjugate gradients MIC heterogeneous computing |
| ISSN号 | 1094-3420 |
| 中文摘要 | In this article, we present a new hybrid algorithm to enable and scale the high-performance conjugate gradients (HPCG) benchmark on large-scale heterogeneous systems such as the Tianhe-2. Based on an inner-outer subdomain partitioning strategy, the data distribution between host and device can be balanced adaptively. The overhead of data movement from both the MPI communication and the PCI-E transfer can be significantly reduced by carefully rearranging and fusing operations. A variety of parallelization and optimization techniques for performance-critical kernels are exploited and analyzed to maximize the performance gain on both host and device. We carry out experiments on both a small heterogeneous computer and the world's largest one, the Tianhe-2. On the small system, a thorough comparison and analysis has been presented to select from different optimization choices. On Tianhe-2, the optimized implementation scales to the full-system level of 3.12 million heterogeneous cores, with an aggregated performance of 623 Tflop/s and a parallel efficiency of 81.2%. |
| 英文摘要 | In this article, we present a new hybrid algorithm to enable and scale the high-performance conjugate gradients (HPCG) benchmark on large-scale heterogeneous systems such as the Tianhe-2. Based on an inner-outer subdomain partitioning strategy, the data distribution between host and device can be balanced adaptively. The overhead of data movement from both the MPI communication and the PCI-E transfer can be significantly reduced by carefully rearranging and fusing operations. A variety of parallelization and optimization techniques for performance-critical kernels are exploited and analyzed to maximize the performance gain on both host and device. We carry out experiments on both a small heterogeneous computer and the world's largest one, the Tianhe-2. On the small system, a thorough comparison and analysis has been presented to select from different optimization choices. On Tianhe-2, the optimized implementation scales to the full-system level of 3.12 million heterogeneous cores, with an aggregated performance of 623 Tflop/s and a parallel efficiency of 81.2%. |
| 收录类别 | SCI |
| 语种 | 英语 |
| WOS记录号 | WOS:000371326000004 |
| 公开日期 | 2016-12-09 |
| 源URL | [http://ir.iscas.ac.cn/handle/311060/17346]  |
| 专题 | 软件研究所_软件所图书馆_期刊论文 |
| 推荐引用方式 GB/T 7714 | Liu, YQ,Yang, C,Liu, FF,et al. 623 Tflop/s HPCG run on Tianhe-2: Leveraging millions of hybrid cores[J]. INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS,2016,30(1):39-54. |
| APA | Liu, YQ.,Yang, C.,Liu, FF.,Zhang, XY.,Lu, YT.,...&Liao, XK.(2016).623 Tflop/s HPCG run on Tianhe-2: Leveraging millions of hybrid cores.INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS,30(1),39-54. |
| MLA | Liu, YQ,et al."623 Tflop/s HPCG run on Tianhe-2: Leveraging millions of hybrid cores".INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS 30.1(2016):39-54. |
入库方式： OAI收割
来源：软件研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。