PPOPP

Migrating CPU code to the CUDA programming language has been a challenge for some time. While the code for many high-performance and massively data-parallel applications has been successfully ported to GPUs, this task has received comparatively less ...

We propose a framework for using static resource analysis to guide the automatic optimization of general-purpose GPU (GPGPU) kernels written in CUDA, NVIDIA's framework for GPGPU programming. In our proposed framework, optimizations are applied to the ...

Performance optimization continues to be a challenge in modern HPC software. Existing performance optimization techniques, including profiling-based and auto-tuning techniques, fail to indicate program modifications at the source level thus preventing ...

Memory and power constraints limit the current landscape of high-performance computing. Hardware specializations in clusters lead to heterogeneity, Non-Uniform Memory Architecture (NUMA) effects, and accelerator offloading. These increase the complexity ...

Many computational problems consider memory throughput a performance bottleneck. The problem becomes even more pronounced in the case of parallel platforms, where the ratio between computing elements and memory bandwidth shifts towards computing. ...

We present three novel parallel scan algorithms for multi-core CPUs which do not need to fix the number of available cores at the start, and have zero overhead compared to sequential scans when executed on a single core. These two properties are in ...