Modern parallel microprocessors deliver high performance on applications that expose
substantial fine-grained data parallelism. Although data parallelism is widely available in …

With the rapid development of deep learning, a variety of neural network models emerge in
endlessly, which leads to a huge demand for computing resources. For the intensive …

GPUs are increasingly being used used to speed up Python applications in the scientific
computing and machine learning domains. Currently, the two common approaches to …

In this paper we introduce Bohrium, a runtimesystem for map** array-operations onto a
number of different hardware platforms, from multi-core systems to clusters and GPU …

While graphics processing units (GPUs) provide low-cost and efficient platforms for
accelerating high performance computations, the tedious process of performance tuning …

This paper describes the development and integration of augmented reality content with
traditional Engineering Design Graphics materials, and presents the results of a preliminary …

The introduction of clock skew at an edge-triggered ipop has an e ect that is similar to the
movement of the ip-op across combinational logic module boundaries, and these are …

In this paper we introduce, Bohrium, a runtime-system for map** vector operations onto a
number of different hardware platforms, from simple multi-core systems to clusters and GPU …

To facilitate a broad range of experimental research on novel protocols and application
concepts, we consider an indoor wireless testbed to emulate the performance of real-world …

Data-parallel languages feature fine-grained parallel primitives that can be supported by
compilers targeting modern many-core architectures where data parallelism must be …