High-performance collective communication among GPUs in modern supercomputers is crucial for enabling many applications. Complex hierarchical interconnects between GPU devices necessitate collective algorithms that can effectively leverage the underlying network topology. We present parameterized algorithms for two GPU-to-GPU collectives, Allgather and Allreduce, as well as an optimized permutation kernel used to further enhance GPU collective communication. By employing a LogGP-based model calibrated with real machine measurements, we can efficiently simulate various parameter choices to identify optimal settings for specific device allocations and message sizes. Our comprehensive evaluation on NCSA Delta and Argonne Polaris supercomputers demonstrates that our parameterized algorithms can achieve, on average, a $20 \%$ speedup over their non-parameterized counterparts, with our parameter selection process capturing $98 \%$ of the potential speedup.

Modern programming languages offer abstractions that simplify software development and allow hardware to reach its full potential. These abstractions range from the well-established OpenMP language extensions to newer C++ features like smart pointers. To properly use these abstractions in an existing codebase, programmers must determine how a given source code region interacts with Program State Elements (PSEs) (i.e., the program's variables and memory locations). We call this process Program State Element Characterization (PSEC). Without tool support for PSEC, a programmer's only option is to manually study the entire codebase. We propose a profile-based approach that automates PSEC and provides abstraction recommendations to programmers. Because a profile-based approach incurs an impractical overhead, we introduce the Compiler and Runtime Memory Observation Tool (CARMOT), a PSEC-specific compiler co-designed with a parallel runtime. CARMOT reduces the overhead of PSEC by two orders of magnitude, making PSEC practical. We show that CARMOT's recommendations achieve the same speedup as hand-tuned OpenMP directives and avoid memory leaks with C++ smart pointers. From this, we argue that PSEC tools, such as CARMOT, can provide support for the rich ecosystem of modern programming language abstractions.

High-level parallel languages (HLPLs) make it easier to write correct parallel programs. Disciplined memory usage in these languages enables new optimizations for hardware bottlenecks, such as cache coherence. In this work, we show how to reduce the costs of cache coherence by integrating the hardware coherence protocol directly with the programming language; no programmer effort or static analysis is required.

Exascale supercomputers have renewed the exigence of improving distributed communication, specifically MPI collectives. Previous works accelerated collectives for specific scenarios by changing the radix of the collective algorithms. However, these approaches fail to explore the interplay between modern hardware features, such as multi-port networks, and software features, such as message size. In this paper, we present a novel approach that uses system-agnostic, generalized (i.e., variableradix) algorithms to capture relevant features and provide broad speedups for upcoming exascale-class supercomputers.We identify hardware commonalities found on announced exascale systems and three omnipresent communication kernels (binomial tree, ring, and recursive doubling) that can be generalized to better leverage these features, creating 10 total implementations. For each kernel, we develop analytical models to intuit algorithm performance with varying radix values.Experiments on the world’s first exascale supercomputer (Frontier at ORNL) and a pre-exascale system (Polaris at ANL) show that our generalized algorithms outperform the baseline open-source and proprietary vendor MPI implementations by a significant margin, up to over 4.5x. We empirically determine optimal algorithms and parameter values, identifying where the analytical models are accurate and where hardware features directly determine performance. Most notably, we show how a single, system-agnostic implementation of a generalized algorithm can optimize for multiple hardware/software features across multiple systems.

MPI collective communication is an omnipresent communication model for high-performance computing (HPC) systems. The performance of a collective operation depends strongly on the algorithm used to implement it. MPI libraries use inaccurate heuristics to select these algorithms, causing applications to suffer unnecessary slowdowns. Machine learning (ML)-based autotuners are a promising alternative. ML autotuners can intelligently select algorithms for individual jobs, resulting in near-optimal performance. However, these approaches currently spend more time training than they save by accelerating applications, rendering them impractical. We make the case that ML-based collective algorithm selection autotuners can be made practical and accelerate production applications on large-scale supercomputers. We identify multiple impracticalities in the existing work, such as inefficient training point selection and ignoring non-power-of-two feature values. We address these issues through variance-based point selection and model testing alongside topology-aware benchmark paral-lelization. Our approach minimizes training time by eliminating unnecessary training points and maximizing machine utilization. We incorporate our improvements in a prototype active learning system, ACCLAiM (Advancing Collective Communication (L) Autotuning using Machine Learning). We show that each of ACCLAiM's advancements significantly reduces training time compared with the best existing machine learning approach. Then we apply ACCLAiM on a leadership-class supercomputer and demonstrate the conditions where ACCLAiM can accelerate HPC applications, proving the advantage of ML autotuners in a production setting for the first time.