Accelerating High-Throughput Computing through OpenCL
Part of book or chapter of book
- Publisher: The Emerging Technology (EMiT) Conference
acm: ComputingMethodologies_COMPUTERGRAPHICS | Software_PROGRAMMINGTECHNIQUES
This paper presents the implementation of a HTCondor pool with GPU execution capabilities through OpenCL. Implementation is discussed from both the system setup and the software design standpoint. The GPU landscape is investigated and the efficiency of the system is evaluated via Fast- Fourier Transform computations. Experimental results show that HTCondor GPU performance matches a dedicated GPU cluster.