Applied Mathematics Department Colloquium - Laura Grigori
| Event Description: , INRIA Paris - Rocquencourt Alpines group,Ìýjoint with Laboratoire J.L. Lions, UPMC An overview of fast and robust communication-avoiding algorithms In this talk I will discuss one of the main challenges in high performance computing: the increased cost of communication with respect to computation, where communication refers to data transferred either between processors or between different levels of memory hierarchy, including possibly NVMs (non-volatile memories).Ìý I will overview novel communication-avoiding numerical methods and algorithms that reduce the communication to a minimum for operations that are at the heart of many calculations, in particular numerical linear algebra algorithms.Ìý Those algorithms range from iterative methods (as used in numerical simulations) to low-rank matrix approximations for data analytics (based on LU/QR factorizations with column tournament pivoting).Ìý I will also discuss the algorithm/architecture matching of those algorithms |
| Location Information: ÌýÌý() 1111 Engineering DR Boulder, CO ¸é´Ç´Ç³¾:Ìý265 ÌýÌý() 1111 Engineering DR Boulder, CO Room:Ìý226: Applied Math Conference Room |
| Contact Information: Name: Ian Cunningham Phone: 303-492-4668 Email: amassist@colorado.edu |