Jared O'Neal

Heterogeneity is the prevalent trend in the rapidly evolving high-performance computing (HPC) landscape in both hardware and application software. The diversity in hardware platforms, currently comprising various accelerators and a future possibility of specializable chiplets, poses a significant challenge for scientific software developers aiming to harness optimal performance across different computing platforms while maintaining the quality of solutions when their applications are simultaneously growing more complex. Code synthesis and code generation can provide mechanisms to mitigate this challenge. We have developed a divide and conquer approach where different aspects of performance are handled by different stand-alone tools that are interfaced with the application through generated code. This portability system, ORCHA, enables users to configure and orchestrate their computations among available resources on a platform by specifying a high-level recipe, thereby permitting a many-to-many paradigm where each recipe results in a different variant of the application. The core design goal is to let users decide the application’s hardware mapping and orchestration by editing only the high-level recipe—without modifying the maintained source code or binding the application to a particular runtime system. Tools in ORCHA distribution are: CG-Kit for translating the recipe into an execution graph; Milhoja to execute the graph by orchestrating data and task movement among hardware resources; and Macroprocessor that enables users to define their own code-shorthand for higher composability and easier management of code variants. Additionally, the design of ORCHA permits tools to work in a plug-and-play mode where the application can build and run without CG-Kit and Milhoja, and either tool can be swapped out for other tools with similar capabilities by modifying the code generation portion of ORCHA. In this paper, we describe the design of ORCHA and the role that code-generation plays in isolating applications from tools. We demonstrate the breadth of configurations ORCHA enables with a case study in which an application configuration is realized on three distinct hardware mappings—a GPU-centric, a CPU/GPU balanced, and a CPU/GPU concurrent layouts by using different recipes.

The Fayans energy density functional (EDF) has been very successful in describing global nuclear properties (binding energies, charge radii, and especially differences of radii) within nuclear density functional theory. In a recent study, supervised machine learning methods were used to calibrate the Fayans EDF. Building on this experience, in this work we explore the effect of adding isovector pairing terms, which are responsible for different proton and neutron pairing fields, by comparing a 13D model without the isovector pairing term against the extended 14D model. At the heart of the calibration is a carefully selected heterogeneous dataset of experimental observables representing ground-state properties of spherical even–even nuclei. To quantify the impact of the calibration dataset on model parameters and the importance of the new terms, we carry out advanced sensitivity and correlation analysis on both models. The extension to 14D improves the overall quality of the model by about 30%. The enhanced degrees of freedom of the 14D model reduce correlations between model parameters and enhance sensitivity.

CG-Kit is a new code generation toolkit that we propose as a solution for portability and maintainability for scientific computing applications. The development of CG-Kit is rooted in the urgent need created by the shifting landscape of high-performance computing platforms and the algorithmic complexities of a particular large-scale multiphysics application: Flash-X. This combination leads to unique challenges including handling an existing large code base in Fortran and/or C/C++, subdivision of code into a great variety of units supporting a wide range of physics and numerical methods, different parallelization techniques for distributed- and shared-memory systems and accelerator devices, and heterogeneity of computing platforms requiring coexisting variants of parallel algorithms. The challenges demand that developers determine custom abstractions and granularity for code generation. CG-Kit tackles this with standalone tools that can be combined into highly specific and, we argue, highly effective portability and maintainability tool chains. Here we present the design of our new tools: parametrized source trees, control flow graphs, and recipes. The tools are implemented in Python. Although the tools are agnostic to the programming language of the source code, we focus on C/C++ and Fortran. Code generation experiments demonstrate the generation of variants of parallel algorithms: first, multithreaded variants of the basic AXPY operation (scalar-vector addition and vector-vector multiplication) to introduce the application of CG-Kit tool chains; and second, variants of parallel algorithms within a hydrodynamics solver, called Spark, from Flash-X that operates on block-structured adaptive meshes. In summary, code generated by CG-Kit achieves a reduction by over 60% of the original C/C++/Fortran source code.

Computational science relies on scientific software as its primary instrument for scientific discovery. Therefore, similar to the use of other types of scientific instruments, correct software and the correct operation of the software is necessary for executing rigorous scientific investigations. Scientific software verification can be especially difficult, as users typically need to modify the software as part of a scientific study. Systematic methodologies for building test suites for scientific software are rare in the literature. Here, we describe a methodology that we have developed for Flash-X, a community simulation software for multiple scientific domains, that has composable components that can be permuted and combined in a multitude of ways to generate a wide range of applications. Ensuring sufficient code coverage by a test suite is particularly challenging due to this composability. Our methodology includes a consideration of trade-offs between meeting software quality goals, developer productivity, and meeting the scientific goals of the Flash-X user community.

We address the calibration of a computationally expensive nuclear physics model for which derivative information with respect to the fit parameters is not readily available. Of particular interest is the performance of optimization-based training algorithms when dozens, rather than millions or more, of training data are available and when the expense of the model places limitations on the number of concurrent model evaluations that can be performed. As a case study, we consider the Fayans energy density functional model, which has characteristics similar to many model fitting and calibration problems in nuclear physics. We analyze hyperparameter tuning considerations and variability associated with stochastic optimization algorithms and illustrate considerations for tuning in different computational settings.

FLASH is a multiphysics software package that was created in 1998 by combining three preexisting packages and has undergone three major revisions. Software design and engineering practices were integrated early in the development and maintenance processes of FLASH, and these processes have evolved strongly at each of the revisions. As high-performance computing enters the age of exascale, challenges along the orthogonal axes of node-level hardware and solver heterogeneity force developers of complex multiphysics software to consider a software architecture overhaul. Because of the nature and scope of necessary changes, an effort to refactor and grow the architecture of the FLASH code has been launched as a separate software project. For this project to succeed, its development team must evaluate, improve, and modernize software processes and policies to meet the unique challenges posed by the exascale era. We describe here our experiences, lessons we have learned, and the methods that we have developed as part of this ongoing project. Within the context of the challenges posed by exascale, we review the FLASH design approach as well as some of the main software engineering processes and tools that have been implemented or updated throughout the lifetime of FLASH. Modernization applied to these processes and tools is also detailed. Reviewing and reevaluating the FLASH experience of establishing and updating software design and engineering practices have been helpful in understanding the needs of the project as it transitions to exascale and in planning the transition. We find that our historical design methodology is still important and relevant. We also believe that using a mixture of plan-based and agile methods is still the best for our project and is in accord with the guidance found in the literature. We present a section on inferences and lessons learned related to software design and engineering practices.