| Both sides previous revision
Previous revision
Next revision
|
Previous revision
|
melange:papers:summer2015 [2015/07/02 16:22] waruna |
melange:papers:summer2015 [2015/07/02 16:30] (current) waruna |
| address = {New York, NY, USA}, | address = {New York, NY, USA}, |
| keywords = {inspector/executor, loop transformations, non-affine, polyhedral model, sparse matrices}, | keywords = {inspector/executor, loop transformations, non-affine, polyhedral model, sparse matrices}, |
| | } |
| | |
| | |
| | @article{Xipeng2013, |
| | year={2013}, |
| | issn={0885-7458}, |
| | journal={International Journal of Parallel Programming}, |
| | volume={41}, |
| | number={6}, |
| | doi={10.1007/s10766-012-0236-3}, |
| | title={An Infrastructure for Tackling Input-Sensitivity of GPU Program Optimizations}, |
| | url={http://dx.doi.org/10.1007/s10766-012-0236-3}, |
| | publisher={Springer US}, |
| | keywords={GPU; Program Optimizations; Empirical Search; CUDA; G-ADAPT; Cross-input Adaptation}, |
| | author={Shen, Xipeng and Liu, Yixun and Zhang, EddyZ. and Bhamidipati, Poornima}, |
| | pages={855-869}, |
| | language={English} |
| | } |
| | |
| | @inproceedings{Bertolacci:2015:PDT:2751205.2751226, |
| | author = {Bertolacci, Ian J. and Olschanowsky, Catherine and Harshbarger, Ben and Chamberlain, Bradford L. and Wonnacott, David G. and Strout, Michelle Mills}, |
| | title = {Parameterized Diamond Tiling for Stencil Computations with Chapel Parallel Iterators}, |
| | booktitle = {Proceedings of the 29th ACM on International Conference on Supercomputing}, |
| | series = {ICS '15}, |
| | year = {2015}, |
| | isbn = {978-1-4503-3559-1}, |
| | location = {Newport Beach, California, USA}, |
| | pages = {197--206}, |
| | numpages = {10}, |
| | url = {http://doi.acm.org/10.1145/2751205.2751226}, |
| | doi = {10.1145/2751205.2751226}, |
| | acmid = {2751226}, |
| | publisher = {ACM}, |
| | address = {New York, NY, USA}, |
| | keywords = {chapel, diamond tiling, parallel iterators, separation of concerns, stencil computations}, |
| | } |
| | |
| | |
| | @inproceedings{Wu:2015:EEF:2751205.2751213, |
| | author = {Wu, Bo and Chen, Guoyang and Li, Dong and Shen, Xipeng and Vetter, Jeffrey}, |
| | title = {Enabling and Exploiting Flexible Task Assignment on GPU Through SM-Centric Program Transformations}, |
| | booktitle = {Proceedings of the 29th ACM on International Conference on Supercomputing}, |
| | series = {ICS '15}, |
| | year = {2015}, |
| | isbn = {978-1-4503-3559-1}, |
| | location = {Newport Beach, California, USA}, |
| | pages = {119--130}, |
| | numpages = {12}, |
| | url = {http://doi.acm.org/10.1145/2751205.2751213}, |
| | doi = {10.1145/2751205.2751213}, |
| | acmid = {2751213}, |
| | publisher = {ACM}, |
| | address = {New York, NY, USA}, |
| | keywords = {compiler transformation, data affinity, gpgpu, program co-run, scheduling}, |
| | } |
| | |
| | @inproceedings{Aga:2015:ZDC:2751205.2751211, |
| | author = {Aga, Shaizeen and Singh, Abhayendra and Narayanasamy, Satish}, |
| | title = {zFENCE: Data-less Coherence for Efficient Fences}, |
| | booktitle = {Proceedings of the 29th ACM on International Conference on Supercomputing}, |
| | series = {ICS '15}, |
| | year = {2015}, |
| | isbn = {978-1-4503-3559-1}, |
| | location = {Newport Beach, California, USA}, |
| | pages = {295--305}, |
| | numpages = {11}, |
| | url = {http://doi.acm.org/10.1145/2751205.2751211}, |
| | doi = {10.1145/2751205.2751211}, |
| | acmid = {2751211}, |
| | publisher = {ACM}, |
| | address = {New York, NY, USA}, |
| | keywords = {data less coherence, fences, memory consistency, parallel programming, sequential consistency}, |
| | } |
| | |
| | @inproceedings{Grosser:2015:ODP:2751205.2751248, |
| | author = {Grosser, Tobias and Pop, Sebastian and Pouchet, Louis-Noel and Sadayappan, P. and Pop, Sebastian}, |
| | title = {Optimistic Delinearization of Parametrically Sized Arrays}, |
| | booktitle = {Proceedings of the 29th ACM on International Conference on Supercomputing}, |
| | series = {ICS '15}, |
| | year = {2015}, |
| | isbn = {978-1-4503-3559-1}, |
| | location = {Newport Beach, California, USA}, |
| | pages = {351--360}, |
| | numpages = {10}, |
| | url = {http://doi.acm.org/10.1145/2751205.2751248}, |
| | doi = {10.1145/2751205.2751248}, |
| | acmid = {2751248}, |
| | publisher = {ACM}, |
| | address = {New York, NY, USA}, |
| | keywords = {linear memory layout, multi-dimensional arrays, polyhedral analysis}, |
| | } |
| | |
| | @inproceedings{Zandifar:2015:CAS:2751205.2751241, |
| | author = {Zandifar, Mani and Abdul Jabbar, Mustafa and Majidi, Alireza and Keyes, David and Amato, Nancy M. and Rauchwerger, Lawrence}, |
| | title = {Composing Algorithmic Skeletons to Express High-Performance Scientific Applications}, |
| | booktitle = {Proceedings of the 29th ACM on International Conference on Supercomputing}, |
| | series = {ICS '15}, |
| | year = {2015}, |
| | isbn = {978-1-4503-3559-1}, |
| | location = {Newport Beach, California, USA}, |
| | pages = {415--424}, |
| | numpages = {10}, |
| | url = {http://doi.acm.org/10.1145/2751205.2751241}, |
| | doi = {10.1145/2751205.2751241}, |
| | acmid = {2751241}, |
| | publisher = {ACM}, |
| | address = {New York, NY, USA}, |
| | keywords = {algorithmic skeletons, data flow programming, distributed systems, high-performance computing, patterns}, |
| } | } |