Search Results for "distributed computing"

...Unfortunately, glpk does not support any multithreading and there is no feature to distribute problems via network connections. Today, this is a pitiable sight, because modern computer systems are coupled by networks and support multi threading. We create a distributed system with Apache thrift and the C-API of glpk. Now, it is possible to use as many cores in a network as you want. With a focus on the MILP methods we implement a load balancing and speed up the solving process in a multiplicative way. Sometimes we have super-linear speedup with a small set of hardware. With a splitting of problems, parallel computing and distributing the actual best solution to all running processes we solve CBP much faster than a sequential processing can do.

Workflow of Heterogeneous Computing. Our aim is to offer a software layer that would leverage the full potential of a network (heterogeneous cpu/gpu/hybrid) by attempting to allocate resources according to application (OpenCL) needs.

REX: Remote EXecution Distributed Computing Services for Linux and Solaris, providing C and C++ APIs, librex library and "rexd" daemon software to implement Load Balancing Process Migration : Dump + Restore, Remote File and Resource Management.