We present Realm, an event-based runtime system for heterogeneous, distributed memory
machines. Realm is fully asynchronous: all runtime actions are non-blocking. Realm …

We present Bamboo, a custom source-to-source translator that transforms MPI C source into
a data-driven form that automatically overlaps communication with available computation …

In the current practice, scientific programmer and HPC users are required to develop code
that exposes a high degree of parallelism, exhibits high locality, dynamically adapts to the …

Hiding communication behind useful computation is an important performance programming
technique but remains an inscrutable programming exercise even for the expert. We present …

Most collaborative systems assume that users have access to workspaces through which
they can access the entire collaborative context. This is often not the case with mobile users …

Reformulating an algorithm to mask communication delays is crucial in maintaining
scalability, but traditional solutions embed the overlap strategy into the application. We …

Scientific applications strive for increased memory and computing performance, requiring
massive amounts of data and time to produce results. Applications utilize large-scale …

We present MATE, a model for developing communication-tolerant scientific applications.
MATE employs a combination of mechanisms to reduce or hide the cost of network and intra …

We discuss our experience in optimizing a stencil method on an Intel Xeon Phi-based
cluster. We describe our solutions to three challenges: tolerating the high cost of inter-node …

A novel feature extraction method based on parallel coordinate plots was presented.
Observing the parallel coordinate plots, discovered that using the distance of one point to …