im Juli wird Erik Zenker versuchen uns von den Vorzügen von "Alpaka" zu begeistern.
The Last Programming Model for Parallel Kernel Acceleration You Will Ever Need
Abstract:
This talk will dive deep into the library for parallel kernel acceleration Alpaka that provide an uniform abstract C++ interface to a range of parallel programming models such as CUDA and OpenMP. We will show how Alpaka can achieve platform and performance portability across various types of architectures by exploiting parallelism and memory hierarchies at all levels available in current hardware.
Alpaka has demonstrated platform and performance portability in academic (daxpy, dgemm) and real world applications (PIConGPU, HASEonGPU) on various architectures such as CPUs and GPUs. However, the Alpaka C++ template interface allows for straightforward extension of the library to support other and upcoming architectures and specialization of its internals for optimization.
Ich bin schon sehr gespannt, was diese neue Bibliothek zu bieten hat.
Termin: Donnerstag, 14. Juli 2016
Beginn: 20:00 Uhr
Ende: offen
Ort: Studentenclub Wu5, August-Bebel-Straße 12, 01219 Dresden
Bitte weiter leiten und alle einladen die sich für das Thema interessieren.
Keine Kommentare:
Kommentar veröffentlichen