Martin Burtscher

Yineng Yan, William Ruys, Hochan Lee et al.

As the complexity and scale of modern parallel machines continue to grow, programmers increasingly rely on composition of software libraries to encapsulate and exploit parallelism. However, many libraries are not designed with composition in mind and assume they have exclusive access to all resources. Using such libraries concurrently can result in contention and degraded performance. Prior solutions involve modifying the libraries or the OS, which is often infeasible. We propose Virtual Library Contexts (VLCs), which are process subunits that encapsulate sets of libraries and associated resource allocations. VLCs control the resource utilization of these libraries without modifying library code. This enables the user to partition resources between libraries to prevent contention, or load multiple copies of the same library to allow parallel execution of otherwise thread-unsafe code within the same process. In this paper, we describe and evaluate C++ and Python prototypes of VLCs. Experiments show VLCs enable a speedup up to 2.85x on benchmarks including applications using OpenMP, OpenBLAS, and LibTorch. Source code of VLCs is available at https://github.com/pecos/Virtual-Library-Context.

Alex Fallin, Nathaniel Gorski, Tripti Agarwal et al.

Many scientific codes and instruments generate large amounts of floating-point data at high rates that must be compressed before they can be stored. Typically, only lossy compression algorithms deliver high-enough compression ratios. However, many of them provide only point-wise error bounds and do not preserve topological aspects of the data such as the relative magnitude of neighboring points. Even topology-preserving compressors tend to merely preserve some critical points and are generally slow. Our Local-Order-Preserving Compressor is the first to preserve the full local order (and thus all critical points), runs orders of magnitude faster than prior topology-preserving compressors, yields higher compression ratios than lossless compressors, and produces bit-for-bit the same output on CPUs and GPUs.

Saeed Taheri, Apan Qasem, Martin Burtscher

Future computing systems, from handhelds to supercomputers, will undoubtedly be more parallel and heterogeneous than todays systems to provide more performance and energy efficiency. Thus, GPUs are increasingly being used to accelerate general purpose applications, including applications with data dependent, irregular control flow and memory access patterns. However, the growing complexity, exposed memory hierarchy, incoherence, heterogeneity, and parallelism will make accelerator based systems progressively more difficult to program. In the foreseeable future, the vast majority of programmers will no longer be able to extract additional performance or energy savings from next generation systems be-cause the programming will be too difficult. Automatic performance analysis and optimization recommendation tools have the potential to avert this situation. They embody expert knowledge and make it available to software developers when needed. In this paper, we describe and evaluate such a tool.