Optimizing scientific software is a difficult task because codebases are often large and complex, and performance can depend upon several factors including the algorithm, its implementation, and hardware among others. Causes of poor performance can originate from disparate sources and be difficult to diagnose. Recent years have seen a multitude of work that use large language models (LLMs) to assist in software development tasks. However, these tools are trained to model the distribution of code as text, and are not specifically designed to understand performance aspects of code. In this work, we introduce a reinforcement learning based methodology to align the outputs of code LLMs with performance. This allows us to build upon the current code modeling capabilities of LLMs and extend them to generate better performing code. We demonstrate that our fine-tuned model improves the expected speedup of generated code over base models for a set of benchmark tasks from 0.9 to 1.6 for serial code and 1.9 to 4.5 for OpenMP parallel code.

We discuss the challenges and propose research directions for using AI to revolutionize the development of high-performance computing (HPC) software. AI technologies, in particular large language models, have transformed every aspect of software development. For its part, HPC software is recognized as a highly specialized scientific field of its own. We discuss the challenges associated with leveraging state-of-the-art AI technologies to develop such a unique and niche class of software and outline our research directions in the two US Department of Energy–funded projects for advancing HPC Software via AI: Ellora and Durban.

High-performance computing (HPC) systems and cloud data centers are converging, and containers are becoming the default method of portable software deployment. Yet, while containers simplify software management, they face significant performance challenges in HPC environments as they must sacrifice hardware-specific optimizations to achieve portability. Although HPC containers can use runtime hooks to access optimized MPI libraries and GPU devices, they are limited by application binary interface (ABI) compatibility and cannot overcome the effects of early-stage compilation decisions. Acceleration as a Service (XaaS) proposes a vision of performance-portable containers, where a containerized application should achieve peak performance across all HPC systems. We present a practical realization of this vision through Source and Intermediate Representation (IR) containers, where we delay performance-critical decisions until the target system specification is known. We analyze specialization mechanisms in HPC software and propose a new LLM-assisted method for automatic discovery of specializations. By examining the compilation pipeline, we develop a methodology to build containers optimized for target architectures at deployment time. Our prototype demonstrates that new XaaS containers combine the convenience of containerization with the performance benefits of system-specialized builds.

High performance computing (HPC) software ecosystems are inherently heterogeneous, comprising scientific applications that depend on hundreds of external packages, each with distinct build systems, options, and dependency constraints. Tools such as Spack automate dependency resolution and environment management, but their effectiveness relies on manually written build recipes. As these ecosystems grow, maintaining existing specifications and creating new ones becomes increasingly labor-intensive. While large language models (LLMs) have shown promise in code generation, automatically producing correct and maintainable Spack recipes remains a significant challenge. We present a systematic analysis of how LLMs and context-augmentation methods can assist in the generation of Spack recipes. To this end, we introduce SpackIt, an end-to-end framework that combines repository analysis, retrieval of relevant examples, and iterative refinement through diagnostic feedback. We apply SpackIt to a representative subset of 308 open-source HPC packages to assess its effectiveness and limitations. Our results show that SpackIt increases installation success from 20

Binary package managers install software quickly but they limit configurability due to rigid ABI requirements that ensure compatibility between binaries. Source package managers provide flexibility in building software, but compilation can be slow. For example, installing an HPC code with a new MPI implementation may result in a full rebuild. Spack, a widely deployed, HPC-focused package manager, can use source and pre-compiled binaries, but lacks a binary compatibility model, so it cannot mix binaries not built together. We present splicing, an extension to Spack that models binary compatibility between packages and allows seamless mixing of source and binary distributions. Splicing augments Spack's packaging language and dependency resolution engine to reuse compatible binaries but maintains the flexibility of source builds. It incurs minimal installation-time overhead and allows rapid installation from binaries, even for ABI-sensitive dependencies like MPI that would otherwise require many rebuilds.

Automatic parameter tuning of parallel codes is ubiquitous in today's HPC environments where the performance portability of said codes is expected to keep pace with the perpetual release of new hardware. With changes in hardware, it is often the case that finding an optimal configuration of these codes is challenging and only further complicated by the high dimensionality or discontinuous topologies of the tuning spaces. Selecting a proper optimization strategy to automatically search these spaces is paramount to minimizing the energy and time spent on exploring sub-optimal configurations. Unfortunately, it is often the case that these optimizers have hyperparameters of their own, which are sensitive and can greatly affect the outcome of quickly converging to, or even finding an optimal code configuration. Much of the existing autotuning literature tends to use particular optimizers without describing their hyperparameter selection, leaving readers to figure out how to configure their optimizer for the best performance. In this work we compare and contrast the popular global optimization strategy of Bayesian Optimization (BO) to Iwo less popular strategies: Particle Swarm Optimization (PSO), and Covariance Matrix Adaptive Evolution Strategy (CMA-ES). We sweep the hyperparameters of these three optimizers in the context of tuning OpenMP hyperparameters of four classic OpenMP programs: BT, FT, HPCG, and Lulesh. Our study compares the long-term search behavior and average time-to-convergence between these three optimization strategies in tuning OpenMP codes. We contribute a detailed study of these strategies and provide deeper insights as to their sensitivities, noting the conditions where each performs well, and hinting at which optimizers require minimal tuning of their hyperparameters for desirable tuning results.

Software has become increasingly complex, with a typical application depending on tens or hundreds of packages. Finding compatible versions and build configurations of these packages is challenging. This paper presents a method to learn the likelihood of software build success, and techniques for leveraging this information to guide dependency solvers to better software configurations. We leverage the heavily parameterized package recipes from the Spack package manager to produce a training data set of builds, and we use Graph Neural Networks to learn whether a given package configuration will build successfully or not. We apply our tool to the U.S. Exascale Computing Project’s software stack. We demonstrate its effectiveness in predicting whether a given package will build successfully. We show that our technique can be used to improve the solutions generated by dependency solvers, reducing the need for developers to find working builds by trial and error.

At the IEEE/ACM International Conference for High-Performance Computing, Networking, Storage, and Analysis (SC23), held in Denver, experts discussed the convergence of high-performance computing and cloud computing. They explored how this integration could address current scientific computing limitations, enhance computational capabilities, and foster global collaboration while focusing on economic, security, technical, and community challenges and opportunities.

In this paper, we discuss the need for an integrated software stack that unites artificial intelligence (AI) and modeling and simulation (ModSim) tools to advance scientific discovery. The authors advocate for a unified AI/ModSim software ecosystem that ensures compatibility across a wide range of software on diverse high-performance computing systems, promoting ease of deployment, version management, and binary distribution. Key challenges highlighted include balancing the distinct needs of AI and ModSim, especially in terms of software build practices, dependency management, and compatibility. The document underscores the importance of continuous integration, community-driven stewardship, and collaboration with the Department of Energy (DOE) to develop a portable and cohesive scientific software ecosystem. Recommendations focus on supporting standardized environments through initiatives like the Extreme-scale Scientific Software Stack (E4S) and Spack to foster interdisciplinary innovation and facilitate new scientific advancements.

Modern scientific software in high performance computing is often complex, and many parallel applications and libraries depend on several other software or libraries. Developers and users of such complex software often use package managers for building them. Package managers depend on humans to codify package constraints (for dependency and version selection), and the dependency graph of a software package can often become large (hundreds of vertices). In addition, package constraints often become outdated and inconsistent over time since they are maintained by different people for different packages, which is a laborious task. This can result in package builds to fail for certain package configurations. In this paper, we propose a methodology that uses historical build results to assist a package manager in selecting the best versions of package dependencies with an aim to improve the likelihood of a successful build. We utilize a machine learning (ML) model to predict the probability of build outcomes of different configurations of packages in the Spack package manager. When evaluated on common scientific software stacks, this ML model-based approach is able to achieve a 13% higher success rate in building packages than the default version selection mechanism in Spack.

To manage the complex demands of modern high-performance computing (HPC), software applications increasingly depend on software developed by other teams, often at other institutions. An HPC software ecosystem approach is required to support dependencies on third-party scientific software. An ecosystem approach provides layers of activity above the individual software product level that promote interoperability, quality improvement, porting, testing and deployment. The U.S. Exascale Computing Project (ECP) developed its HPC software ecosystem using a three-pronged approach. First, ECP adopted and invested in Spack, a package manager designed to handle complex HPC package dependencies. Second, ECP created the Extreme Scale Scientific Software Stack (E4S), an effort that supports developing, deploying and running scientific applications on HPC platforms. Third, ECP supported software product communities, or Software Development Kits (SDKs) to develop and promote best practices, improve software interoperability, and other collaborative efforts. This paper describes ECP contributions to HPC software ecosystem challenges.

To manage the complex demands of modern high-performance computing (HPC), software applications increasingly depend on software developed by other teams, often at other institutions. An HPC software ecosystem approach is required to support dependencies on third-party scientific software. An ecosystem approach provides layers of activity above the individual software product level that promote interoperability, quality improvement, porting, testing, and deployment. The U.S. Exascale Computing Project (ECP) developed its HPC software ecosystem using a three-pronged approach. First, the ECP adopted and invested in Spack, a package manager designed to handle complex HPC package dependencies. Second, the ECP created the Extreme Scale Scientific Software Stack, an effort that supports developing, deploying, and running scientific applications on HPC platforms. Third, the ECP supported software product communities, or software development kits, to develop and promote best practices, improve software interoperability, and other collaborative efforts. This article describes ECP contributions to HPC software ecosystem challenges.

The Exascale Computing Project (ECP) Software Technology and Co-Design teams addressed the growing complexities in high-performance computing (HPC) by developing scalable software libraries and tools that leverage exascale system capabilities. As we enter the exascale era, the need for reusable, optimized software solutions that can handle the unique challenges posed by these systems becomes increasingly important. The primary challenges the ECP teams faced were to create software libraries and tools that are performant on exascale architectures and portable and usable across diverse hardware platforms. Efforts addressed issues related to concurrent execution, memory management, and the integration of heterogeneous computing resources, such as GPUs from multiple vendors. The ECP’s strategy involved a structured development process encompassing the creation, optimization, and deployment of software in collaboration with industry, academia, and national laboratories. The project was organized into several technical areas: co-design of domain-specific suites with target applications, programming models and runtimes, development tools, mathematical libraries, data and visualization tools, and software ecosystem and delivery mechanisms. ECP has successfully developed a large portfolio of software libraries and tools that demonstrate significant improvements in performance and scalability on exascale systems. These products have been integrated into the Department of Energy’s computing facilities, supporting various scientific applications and ensuring robust performance across different hardware setups. ECP advancements in software development for exascale computing highlight the importance of a collaborative and adaptive approach to handling next-generation HPC systems complexities. The lessons learned emphasize the need for continuous engagement with end-users and vendors, and the importance of maintaining a balance between innovation and practical implementation. Future efforts will focus on ensuring scalability, keeping pace with rapid hardware advancements, and further enhancing the interoperability and usability of the software ecosystem. Subsequent articles in this special issue provide in-depth discussions and case studies into specific library and tool efforts.

Parallel programs in high performance computing (HPC) continue to grow in complexity and scale in the exascale era. The diversity in hardware and parallel programming models make developing, optimizing, and maintaining parallel software even more burdensome for developers. One way to alleviate some of these burdens is with automated development and analysis tools. Such tools can perform complex and/or remedial tasks for developers that increase their productivity and decrease the chance for error. Until recently, such tools for code development and performance analysis have been limited in the complexity of tasks they can perform, especially for parallel programs. However, with recent advancements in language modeling, and the availability of large amounts of open-source code related data, these tools have started to utilize predictive language models to automate more complex tasks. In this paper, we show how large language models (LLMs) can be applied to tasks specific to high performance and scientific codes. We introduce a new dataset of HPC and scientific codes and use it to fine-tune several pre-trained models. We compare several pre-trained LLMs on HPC-related tasks and introduce a new model, HPC-Coder, fine-tuned on parallel codes. In our experiments, we show that this model can auto-complete HPC functions where generic models cannot, decorate for loops with OpenMP pragmas, and model performance changes in scientific application repositories as well as programming competition solutions.

Heterogeneity has become a mainstream architecture design choice for building High Performance Computing systems. However, heterogeneity poses significant challenges for achieving performance portability of execution. Adapting a program to a new heterogeneous platform is laborious and requires developers to manually explore a vast space of execution parameters. To address those challenges, this paper proposes new extensions to OpenMP for autonomous, machine learning-driven adaptation. Our solution includes a set of novel language constructs, compiler transformations, and runtime support. We propose a producer-consumer pattern to flexibly define multiple, different variants of OpenMP code regions to enable adaptation. Those regions are transparently profiled at runtime to autonomously learn optimizing machine learning models that dynamically select the fastest variant. Our approach significantly reduces users' efforts of programming adaptive applications on heterogeneous architectures by leveraging machine learning techniques and code generation capabilities of OpenMP compilation. Using a complete reference implementation in Clang/LLVM we evaluate three use-cases of adaptive CPU-GPU execution. Experiments with HPC proxy applications and benchmarks demonstrate that the proposed adaptive OpenMP extensions automatically choose the best performing code variants for various adaptation possibilities, in several different heterogeneous platforms of CPUs and GPUs.

Package managers such as NPM have become essential for software development. The NPM repository hosts over 2 million packages and serves over 43 billion downloads every week. Unfortunately, the NPM dependency solver has several shortcomings. 1) NPM is greedy and often fails to install the newest versions of dependencies; 2) NPM's algorithm leads to duplicated dependencies and bloated code, which is particularly bad for web applications that need to minimize code size; 3) NPM's vulnerability fixing algorithm is also greedy, and can even introduce new vulnerabilities; and 4) NPM's ability to duplicate dependencies can break stateful frameworks and requires a lot of care to workaround. Although existing tools try to address these problems they are either brittle, rely on post hoc changes to the dependency tree, do not guarantee optimality, or are not composable. We present PacSolve, a unifying framework and implementation for dependency solving which allows for customizable constraints and optimization goals. We use PacSolve to build MaxNPM, a complete, drop-in replacement for NPM, which empowers developers to combine multiple objectives when installing dependencies. We evaluate MaxNPM with a large sample of packages from the NPM ecosystem and show that it can: 1) reduce more vulnerabilities in dependencies than NPM's auditing tool in 33% of cases; 2) chooses newer dependencies than NPM in 14% of cases; and 3) chooses fewer dependencies than NPM in 21% of cases. All our code and data is open and available.

Parallel software codes in high performance computing (HPC) continue to grow in complexity and scale as we enter the exascale era. A diverse set of emerging hardware and programming paradigms make developing, optimizing, and maintaining parallel software burdensome for developers. One way to alleviate some of these burdens is with automated development and analysis tools. Such tools can perform complex and/or remedial tasks for developers that increase their productivity and decrease the chance for error. So far, such tools for code development and performance analysis have been limited in the complexity of tasks they can perform. However, with recent advancements in language modeling, and the wealth of code related data that is now available online, these tools have started to utilize predictive language models to automate more complex tasks. In this paper, we show how large language models (LLMs) can be applied to tasks specific to high performance and scientific codes. We train LLMs using code and performance data that is specific to parallel codes. We compare several recent LLMs on HPC related tasks and introduce a new model, HPC-Coder, trained on parallel code. In our experiments we show that this model can auto-complete HPC functions where general models cannot, decorate for loops with OpenMP pragmas, and model performance changes in two scientific application repositories.

Optimizing the performance of large-scale parallel codes is critical for efficient utilization of computing resources. Code developers often explore various execution parameters, such as hardware configurations, system software choices, and application parameters, and are interested in detecting and understanding bottlenecks in different executions. They often collect hierarchical performance profiles represented as call graphs, which combine performance metrics with their execution contexts. The crucial task of exploring multiple call graphs together is tedious and challenging because of the many structural differences in the execution contexts and significant variability in the collected performance metrics (e.g., execution runtime). In this paper, we present Ensemble CallFlow to support the exploration of ensembles of call graphs using new types of visualizations, analysis, graph operations, and features. We introduce ensemble-Sankey , a new visual design that combines the strengths of resource-flow (Sankey) and box-plot visualization techniques. Whereas the resource-flow visualization can easily and intuitively describe the graphical nature of the call graph, the box plots overlaid on the nodes of Sankey convey the performance variability within the ensemble. Our interactive visual interface provides linked views to help explore ensembles of call graphs, e.g., by facilitating the analysis of structural differences, and identifying similar or distinct call graphs. We demonstrate the effectiveness and usefulness of our design through case studies on large-scale parallel codes.

Increasingly diverse mission needs, the emergence of AI and cloud, and increasing hardware diversity are driving HPC software to be more complex. Modern codes are built from hundreds of small, complex components, and much of the software development process involves integrating these components rather than developing new components from scratch. The goal of the BUILD project was to ease the task of software integration for developers across LLNL’s programs. The project focused on (1) modeling software compatibility, (2) modeling ABI compatibility with binary analysis, (3) developing solver techniques to reason about compatibility, and (4) developing AI/ML models to fill gaps in our understanding of software compatibility. The project has developed several key technologies that help developers—by accelerating development workflows, removing the need for rebuilds, and enabling faster, automatic, and less error-prone code sharing. These technologies are used in LLNL codes and will be ready for the new El Capitan Exascale system in Livermore Computing. Many of these technologies have been hardened and integrated with LLNL’s Spack package manager, and they are already in use by production code teams. Results of BUILD have laid the groundwork for future advances in software integration—the ML and binary modification techniques developed in this project still need to be operationalized but have great potential to further speed up software integration.