Release v0.2.0

The release includes the first couple of the predefined workflows. These are the wait all and the wait first workflows, which apply a Singular computation to a tuple of input tokens and wait until all computations finish resp. until one computation finishes. The computations can be administered in a convinient way completely from Singular.

Release v0.1.2

Minor updates in the installation docu. Last version before significant additions (wait-all and wait-first).

Release v0.1.1

Bugfixes, improvements of the user interface, in particular, with regard to the logging of computations using the GPI-Space monitor, and other minor changes.

Release v0.1.0

We provide access from Singular to GPI-Space to call again libSingular to support massively parallel computations in computer algebra. We use GPI-Space for the coordination of the computation and Singular as the frontend and the computational backend. We implement a sample application in form of a massively parallel algorithm to test smoothness of algebraic varieties, which is based on a Hironaka type approach branching into a tree of charts. The implementation creates a Singular library and accompanying dynamical module for Singular. Configuration of the whole system can easily be done by using a so-called configuration token in Singular and specifying a nodefile file (with one hostname per line), which contains the names of the computation nodes to be used.