Learn how to use the roofline model to analyze the performance of GPU-Accelerated applications. We'll cover the basics of the model and explain how to use it to analyze application performance and track progress. We'll also explain how to use nvprof to automate data collection on GPU-Accelerated systems. Demonstrations will include DOE proxy applications in arithmetic intensity, memory stride, memory coalescing, and thread divergence/prediction, all of which can be captured within the roofline methodology.  Back

Learn how to optimize large complex-number reductions in material science code BerkeleyGW on NVIDIA GPUs. Our talk will showcase two BerkeleyGW kernels implemented with four frameworks CUDA, OpenACC, OpenMP 4.5, and Kokkos. We'll share optimization techniques used to achieve decent performance across all four implementations. We'll also report on the status of OpenACC and OpenMP 4.5 compilers and compare the performance portability capabilities of OpenACC, OpenMP 4.5, and Kokkos.  Back