This paper presents a case study about the applicability and usage of non blocking collective operations. These operations provide the ability to overlap communication with computa...
Torsten Hoefler, Peter Gottschling, Andrew Lumsdai...
The paper proposes a novel approach for optimizing performance of all-to-all collective communication by taking advantage of concurrency available in modern networks such as Infin...
Noncontiguous data access is a very common access pattern in many scientific applications. Using POSIX I/O to access many pieces of noncontiguous data segments will generate a lot...