Optimizing OpenCL Kernels for Iterative Statistical Applications on GPUs

Download Now
Provided by: Indiana University
Topic: Hardware
Format: PDF
The authors present a study of three important kernels that occur frequently in iterative statistical applications: k-means, Multi-Dimensional Scaling (MDS), and PageRank. They implemented each kernel using OpenCL and evaluated their performance on an NVIDIA Tesla GPGPU card. By examining the underlying algorithms and empirically measuring the performance of various components of the kernel they explored the optimization of these kernels by four main techniques: caching invariant data in GPU memory across iterations, selectively placing data in different memory levels, rearranging data in memory and dividing the work between the GPU and the CPU.
Download Now

Find By Topic