CaLRS: A Critical-Aware Shared LLC Request Scheduling Algorithm on GPGPU
Ultra high thread-level parallelism in modern GPUs usually introduces numerous memory requests simultaneously. So there are always plenty of memory requests waiting at each bank of the shared LLC (L2 in this paper) and global memory. For global memory, various schedulers have already been developed...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2015-01-01
|
| Series: | The Scientific World Journal |
| Online Access: | http://dx.doi.org/10.1155/2015/848416 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832568035696705536 |
|---|---|
| author | Jianliang Ma Jinglei Meng Tianzhou Chen Minghui Wu |
| author_facet | Jianliang Ma Jinglei Meng Tianzhou Chen Minghui Wu |
| author_sort | Jianliang Ma |
| collection | DOAJ |
| description | Ultra high thread-level parallelism in modern GPUs usually introduces numerous memory requests simultaneously. So there are always plenty of memory requests waiting at each bank of the shared LLC (L2 in this paper) and global memory. For global memory, various schedulers have already been developed to adjust the request sequence. But we find few work has ever focused on the service sequence on the shared LLC. We measured that a big number of GPU applications always queue at LLC bank for services, which provide opportunity to optimize the service order on LLC. Through adjusting the GPU memory request service order, we can improve the schedulability of SM. So we proposed a critical-aware shared LLC request scheduling algorithm (CaLRS) in this paper. The priority representative of memory request is critical for CaLRS. We use the number of memory requests that originate from the same warp but have not been serviced when they arrive at the shared LLC bank to represent the criticality of each warp. Experiments show that the proposed scheme can boost the SM schedulability effectively by promoting the scheduling priority of the memory requests with high criticality and improves the performance of GPU indirectly. |
| format | Article |
| id | doaj-art-da226da647b54108a97ab4f9395c6db7 |
| institution | Kabale University |
| issn | 2356-6140 1537-744X |
| language | English |
| publishDate | 2015-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | The Scientific World Journal |
| spelling | doaj-art-da226da647b54108a97ab4f9395c6db72025-02-03T00:59:57ZengWileyThe Scientific World Journal2356-61401537-744X2015-01-01201510.1155/2015/848416848416CaLRS: A Critical-Aware Shared LLC Request Scheduling Algorithm on GPGPUJianliang Ma0Jinglei Meng1Tianzhou Chen2Minghui Wu3College of Computer Science, Zhejiang University, Zheda Road No. 38, Hangzhou 310013, ChinaCollege of Computer Science, Zhejiang University, Zheda Road No. 38, Hangzhou 310013, ChinaCollege of Computer Science, Zhejiang University, Zheda Road No. 38, Hangzhou 310013, ChinaZhejiang University City College, Huzhou Road No. 51, Hangzhou 310015, ChinaUltra high thread-level parallelism in modern GPUs usually introduces numerous memory requests simultaneously. So there are always plenty of memory requests waiting at each bank of the shared LLC (L2 in this paper) and global memory. For global memory, various schedulers have already been developed to adjust the request sequence. But we find few work has ever focused on the service sequence on the shared LLC. We measured that a big number of GPU applications always queue at LLC bank for services, which provide opportunity to optimize the service order on LLC. Through adjusting the GPU memory request service order, we can improve the schedulability of SM. So we proposed a critical-aware shared LLC request scheduling algorithm (CaLRS) in this paper. The priority representative of memory request is critical for CaLRS. We use the number of memory requests that originate from the same warp but have not been serviced when they arrive at the shared LLC bank to represent the criticality of each warp. Experiments show that the proposed scheme can boost the SM schedulability effectively by promoting the scheduling priority of the memory requests with high criticality and improves the performance of GPU indirectly.http://dx.doi.org/10.1155/2015/848416 |
| spellingShingle | Jianliang Ma Jinglei Meng Tianzhou Chen Minghui Wu CaLRS: A Critical-Aware Shared LLC Request Scheduling Algorithm on GPGPU The Scientific World Journal |
| title | CaLRS: A Critical-Aware Shared LLC Request Scheduling Algorithm on GPGPU |
| title_full | CaLRS: A Critical-Aware Shared LLC Request Scheduling Algorithm on GPGPU |
| title_fullStr | CaLRS: A Critical-Aware Shared LLC Request Scheduling Algorithm on GPGPU |
| title_full_unstemmed | CaLRS: A Critical-Aware Shared LLC Request Scheduling Algorithm on GPGPU |
| title_short | CaLRS: A Critical-Aware Shared LLC Request Scheduling Algorithm on GPGPU |
| title_sort | calrs a critical aware shared llc request scheduling algorithm on gpgpu |
| url | http://dx.doi.org/10.1155/2015/848416 |
| work_keys_str_mv | AT jianliangma calrsacriticalawaresharedllcrequestschedulingalgorithmongpgpu AT jingleimeng calrsacriticalawaresharedllcrequestschedulingalgorithmongpgpu AT tianzhouchen calrsacriticalawaresharedllcrequestschedulingalgorithmongpgpu AT minghuiwu calrsacriticalawaresharedllcrequestschedulingalgorithmongpgpu |