Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “HPC applications”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 361 records · Page 20
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Improving Performance of M-to-N Processing and Data Redistribution in In Transit Analysis and Visualization

In an in transit setting, a parallel data producer, such as a numerical simulation, runs on one set of ranks M, while a data consumer, such as a parallel visualization application, runs on a different set of ranks N. One of the central challenges in this in transit setting is to determine the mapping of data from the set of M producer ranks to the set of N consumer ranks. This is a challenging problem for several reasons, such as the producer and consumer codes potentially having different scaling characteristics and different data models. The resulting mapping from M to N ranks can have a significant impact on aggregate application performance. In this work, we present an approach for performing this M-to-N mapping in a way that has broad applicability across a diversity of data producer and consumer applications. We evaluate its design and performance with a study that runs at high concurrency on a modern HPC platform. By leveraging design characteristics, which facilitate an “intelligent” mapping from M-to-N, we observe significant performance gains are possible in terms of several different metrics, including time-to-solution and amount of data moved.

Loring, Burlen↗
DOE OSTI2020

Improving Performance of M-to-N Processing and Data Redistribution in In Transit Analysis and Visualization

In an in transit setting, a parallel data producer, such as a numerical simulation, runs on one set of ranks M, while a data consumer, such as a parallel visualization application, runs on a different set of ranks N: One of the central challenges in this in transit setting is to determine the mapping of data from the set of M producer ranks to the set of N consumer ranks. This is a challenging problem for several reasons, such as the producer and consumer codes potentially having different scaling characteristics and different data models. The resulting mapping from M to N ranks can have a significant impact on aggregate application performance. In this work, we present an approach for performing this M-to-N mapping in a way that has broad applicability across a diversity of data producer and consumer applications. We evaluate its design and performance with a study that runs at high concurrency on a modern HPC platform. By leveraging design characteristics, which facilitate an ''intelligent'' mapping from M-to-N, we observe significant performance gains are possible in terms of several different metrics, including time-to-solution and amount of data moved.

Loring, Burlen↗
NASA NTRSDate not supplied

Particle Interaction Physics Model Formulation for Plume-Surface Interaction Erosion and Cratering

As part of the Game Changing Development (GCD) Program, funded by NASA’s Space Technology Mission Directorate (STMD), the development of simulation capability for the prediction of extra-terrestrial Plume Surface Interaction (PSI) environments has been undertaken by the Fluid Dynamics Branch at NASA/MSFC. The Predictive Simulation Capability (PSC) Element is focused on creating simulation capability for the reliable and accurate prediction of PSI in Martian (~650 Pa) and Lunar (vacuum) ambient environments. In addition to the predictive simulation capability, the GCD Program also contains a companion Ground Testing Element for development of focused datasets for validation of predictive capability as well as a Flight-focused Instrumentation Element. This paper will present the status of implementing and maturing particle-particle interaction constituent physics models essential in simulating the landing surface granular material flow under PSI effects. This gas-particle multi-phase interaction modeling of plume impingement flow on the extra-terrestrial soil material is performed with the Gas-Granular Flow Solver (GGFS) addressed in a companion paper. The response of regolith particle flow induced by lander PSI requires accurate representation of the regolith granular material fluidic behavior and gas-granular interactions. The lunar regolith, as the extreme example, is poorly sorted with broad particle size distributions and large fines content. It has significant cohesion, due to interlocking particle shapes for the very jagged particles. The combination of particle shape and size distribution has been identified as major drivers in the complex particle flow response and resulting crater shape characteristics of extraterrestrial granular material. Constituent models for spherical particles can be formulated directly from particle kinetics theory. Complex particle shapes can be modeled by gluing together elemental spherical shapes into composite particles, requiring a Discrete Element Model (DEM) particle kinetics modeling approach to extract data and formulate constituent models. Mixture constituent models for poly-disperse mixtures (i.e, containing distribution of particle sizes) have recently been developed. The required non-spherical particle mixture granular material response closure models are then obtained through small-scale unit physics DEM simulations for the range of particle shapes, mixtures and packing densities. The granular material response closure models are then implemented in the Eulerian granular flow formulation. This DEM-based constituent model extraction process and formulation of poly-disperse particle mixtures has been successfully developed by small business and academic partners in the development of the Gas-Granular Flow Solver (GGFS) simulation program simulation framework. The currently implemented capabilities have reached the capability level of modeling bi-disperse, non-spherical particle mixtures is being continuously extended towards computational modeling of full range irregular particle mixtures. Under the GCD project, this technology is being further developed, transferred to NASA analysts, and matured towards application readiness. The predictive simulation capability team under the GCD project has acquired the modeling tools and processes of the DEM based constituent model formulation from the GGFS development team and is developing the capability to replicate the existing process. This is the first important step towards the ability of the NASA team to independently perform such model development in a production setting. Further efforts are underway to migrate the DEM based model simulation process performed with the academic based tools to more capable Open Source, highly parallelized simulation tools for efficient operation on NASA HPC assets. Evaluation of the currently implemented (such as mono-disperse and bi-disperse spherical and irregular shape particle constituent model applications) and continuously evolving full-range particle physics models in the GGFS tool is performed by the NASA team to advance application readiness of the simulations. Application testing for complex PSI erosions and cratering scenarios such as the Apollo LM is performed for axi-symmetric and full 3D simulations to aid the tool developers in achieving practical application readiness for NASA projects. Important validation and application testing will further be performed against experimental data generated under the GCD PSI project experimental component.

Peter A Liever↗
DOE OSTI2024

Coatings for CSP Lifetime

The feasibility and performance of tower-technology-based concentrated solar power (CSP) is highly dependent on the efficiency of the energy transformation from sun to heat at the receiver. The higher the solar absorptivity of the receiver coating, the higher the efficiency of the plant as a whole. BrightSource Energy (BSE) has developed a series of High-Performance Coating (HPC) systems in order to achieve high absorptivity over the plant lifetime (25-35 years). This requires stable coatings that are easily applicable on the large receiver surface and will maintain their optical properties under intense solar flux and thousands of heating and cooling cycles in desert conditions. Different coating formulations are required according to the differing plant conditions: receiver materials, operating conditions (temperatures, daily cycles, etc.), and environmental conditions. BSE also developed a coating for the next generation of CSP receivers, such as those being under DOE’s CSP Gen3 program, which will be operated with high temperature heat transfer fluids at temperatures of up to 800°C, which is significantly hotter than the operating temperature of current systems. Once the coating is formulated, the next challenge is evaluating its lifetime properties. BSE has found several independent failure modes that impact HPC absorptivity degradation: • Decrease in HPC optical properties due to oxidation in the receiver tubes surface below the HPC; • HPC film deterioration due to cycling of temperatures and humidity due to daily operation startup and shutdown as well as changing ambient conditions; • Mechanical degradation due to erosion by sand and wind. Existing test methods examine various aspects independently, but do not provide a combined accelerated lifetime result. Creating such a combined test suite, with a way to interpret the results to predict the coating’s projected lifetime, was the ultimate goal of this project. The project was divided into three major workstreams: lab testing (individual failure mode tests and combined failure mode tests); developing a theoretical model for aging; and validation of the test apparatus via on-sun testing in near real-world conditions at CIEMAT-PSA. Developing a test apparatus that accurately controlled the temperature while also introducing the desired solar flux proved more challenging than expected. While in the end we did succeed in creating a test apparatus that can control temperature, solar flux, and humidity, the results did not appear to accelerate the lifetime of the samples as desired. We suspect that to properly accelerate the samples we must also subject the samples to increased amounts of oxygen. Similarly, while we successfully created a combined model that is publicly available, we were unable to validate it sufficiently to feel comfortable recommending it as a general guideline.

14 SOLAR ENERGY↗
DOE OSTI2022

Metall: A persistent memory allocator for data-centric analytics

Data analytics applications transform raw input data into analytics-specific data structures before performing analytics. Unfortunately, such data ingestion steps are often more expensive than analytics. In addition, various types of NVRAM devices are already used in many HPC systems today. Such devices will be useful for storing and reusing data structures beyond a single process life cycle. We developed Metall, a persistent memory allocator built on top of the memory-mapped file mechanism. Metall enables applications to transparently allocate custom C++ data structures into various types of persistent memories. Metall incorporates a concise and high-performance memory management algorithm inspired by Supermalloc and the rich C++ interface developed by Boost.Interprocess library. On a dynamic graph construction workload, Metall achieved up to 11.7x and 48.3x performance improvements over Boost.Interprocess and memkind (PMEM kind), respectively. We also demonstrate Metall’s high adaptability by integrating Metall into a graph processing framework, GraphBLAS Template Library. Here this study’s outcomes indicate that Metall will be a strong tool for accelerating future large-scale data analytics by allowing applications to leverage persistent memory efficiently.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Quantum Approximate Optimization Algorithm on Different Qubit Systems

Solving optimization problems is critical across many research domains, but the high dimensionality of parameter spaces often poses significant challenges. The Quantum Approximate Optimization Algorithm (QAOA) has emerged as a promising approach for accelerating optimization in the Noisy Intermediate-Scale Quantum (NISQ) era by leveraging both classical and quantum computational resources. However, its performance can vary depending on the underlying quantum hardware architecture. In this work, we evaluate the performance of QAOA on different quantum hardware platforms, specifically, superconducting transmon qubits and trapped-ion qubits, targetting real-world optimization problems formulated as fully connected Quadratic Unconstrained Binary Optimization (QUBO) instances. We evaluate both the solution quality and time-to-solution using dense QUBO matrices. Furthermore, we show that large-scale problems, such as a 100-bit QUBO instance, can be effectively tackled by integrating quantum computing with high-performance computing (HPC) resources. This study provides practical insights into the strengths and limitations of different qubit technologies and advances the application of quantum computing in solving real-world optimization problems.

Kim, Seongmin [ORNL] (ORCID:0000000159063004)↗
DOE OSTI2022

Climbing the Summit and Pushing the Frontier of Mixed Precision Benchmarks at Extreme Scale

The rise of machine learning (ML) applications and their use of mixed precision to perform interesting science are driving forces behind AI for science on HPC. The convergence of ML and HPC with mixed precision offers the possibility of transformational changes in computational science. The HPL-AI benchmark is designed to measure the performance of mixed precision arithmetic as opposed to the HPL benchmark which measures double precision performance. Pushing the limits of systems at extreme scale is nontrivial -little public literature explores optimization of mixed precision computations at this scale. In this work, we demonstrate how to scale up the HPL-AI benchmark on the pre-exascale Summit and exascale Frontier systems at the Oak Ridge Leadership Computing Facility (OLCF) with a cross-platform design. We present the implementation, performance results, and a guideline of optimization strategies employed for delivering portable performance on both AMD and NVIDIA GPUs at extreme scale.

Lu, Hao↗
NASA NTRS2021

NASA High Efficiency, High OPR Capable Small Core Compressor

As future aircraft become lighter and more aerodynamically efficient, thrust requirements will decrease, reducing the core size of the engine. Furthermore, in the pursuit of improved fuel burn, engine overall pressure ratio and bypass ratio will increase, further driving down engine core size (core size being defined as high-pressure compressor [HPC] exit-corrected flow). These drivers together mean that the core size for future single-aisle aircraft applications will shrink below 3.0 lb/s. Traditionally, this small core compressor size is in the domain of axi-centrifugal designs, machines that are typically less efficient and limited to pressure ratios of ~25 due to stress and thermomechanical fatigue in the centrifugal impeller. In this light, NASA and Pratt & Whtiney (P&W) embarked upon a program to develop technologies to enable an all-axial high-pressure compressor with a core size below 3.0 lb/s and an overall pressure ratio greater than 50. The challenge with an all-axial high-pressure compressor at this core size is the small span at the rear of the compressor. As core size is scaled down, the rotor tip clearances, stator hub seal clearances, fillet sizes and leading edge thicknesses do not scale, leading to significant efficiency penalties. The goal of this program is to recover this lapse and realize the cycle benefits of small core size and high overall pressure ratio. The small core challenges described are mitigated through design optimization and technology insertion, enabling an estimated 5 to 10% fuel burn reduction relative to 2020 best-in-class. Three test rigs run at NASA Glenn Research Center evolved the small core design: a low-speed rig to vet technology and validate tools, and two high speeds rigs, the first to demonstrate an optimized meanline design and the second to validate technology to manage large rotor tip gaps. The efficiency improvement validated with these rigs has unlocked the small core design space, demonstrating that small core compressors can maintain a similar efficiency to current best-in-class large core size compressors. In addition to advancing the state-of-the-art of technology, the program has also advanced the modeling standards for multistage compressors with large clearance-to-span ratios. A best practice modeling standard was developed over the course of the program, incorporating learning from all three rig programs.

Axial Compressors↗
DOE OSTI2026

Frontier Job-Centric Telemetry Dataset

Comprehensive analysis of high-performance computing (HPC) systems requires linking workload execution to system behavior. This kind of analysis is vital for diagnosing performance issues, managing capacity, detecting anomalous workloads, and understanding how applications interact with system hardware. This job-centric telemetry dataset unifies scheduler job records with node-level measurements, enabling direct association between workloads and their corresponding power, thermal, and performance characteristics. It contains sanitized, scheduler related metadata for 152,400 individual jobs that ran on the Frontier supercomputer and ended on selected days throughout 2024 and 2025, a subpopulation of ~6.8% of the total number of allocated jobs with non-zero run time on the system over that same period. Each is linked with files that contain telemetry time series records of the power utilization and temperature behavior of its allocated nodes and their processors during the run time of the job. Where available, a portion of the job files also contain network performance time series. Jobs are sampled from select days that reflect normal levels of user activity and possess job size distributions with large numbers of leadership class jobs (>20% of Frontier nodes). Jobs in this dataset attempt to best represent successful user workflows.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2021

Visual HPC Workflows for the Analysis of System Dynamics Models

Visual analytics supported by high performance computing (HPC) accelerates and enhances the discovery, exploration, and analysis of causal patterns in complex system dynamics (SD) models. We present a suite of visualization-assisted ensemble-based techniques for hypothesis generation and testing, and for sensitivity analysis. By employing HPC to provide parallel, on-demand simulation of SD models, one can “steer” an ensemble of simulated scenarios in real time as one first formulates and then informally tests those hypotheses: this provides rapid feedback for analysts to refine their understanding of the causal relationships emergent from a model. Such understandings can be followed and augmented by rigorous application of statistical methods, namely global variance-based sensitivity analysis, Monte-Carlo filtering, adaptive regional sensitivity analysis, and self-organized maps: here timely computation relies on HPC, while effective presentation emphasizes high-dimensional multivariate data visualization. Immersive visualization in virtual 3D environments provides an excellent adjunct to the traditional 2D graphics typically used for SD models, as it generates an embodied understanding of model behavior and facilitates an active, collaborative critique of model structure and output. Finally, we summarize prospects for HPC-enabled visual analytics applied to SD modeling.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2020

UNITY: Unified Memory and Storage Space

UNITY is a 36-month project focused on providing design and evaluate a new distributed storage paradigm that unifies the traditionally distinct application views of memory- and file-based data storage into a single scalable and resilient environment. The project is a collaboration among Oak Ridge National Laboratory (ORNL, Lead institution), Los Alamos National Labs (LANL), and Georgia Tech (GT). The main contributions of the GT team have been around development of low level systems software for best leveraging the capabilities of new types of persistent memory technologies, and for development of methods for intelligent data management across memory/storage substrates with heterogeneous components. GT contributed the Phoenix library for optimized checkpoint/restart for HPC I/O for systems with non-volatile memory (NVM), the NVStream library for NVM-specialized streaming I/O for HPC workflows, the CoMerge, Mnemo and Kleio solutions for intelligent data management on NVM-based systems. These contributions result in significant improvements in both application performance and system efficiency.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

CLAS12 remote data-stream processing using ERSAP framework

Implementing a physics data processing application is relatively straightforward with the use of current containerization technologies and container image runtime services, which are prevalent in most high-performance computing (HPC) environments. However, the process is complicated by the challenges associated with data provisioning and migration, impacting the ease of workflow migration and deployment. Transitioning from traditional file-based batch processing to data-stream processing workflows is suggested as a method to streamline these workflows. This transition not only simplifies file provisioning and migration but also significantly reduces the necessity for extensive disk space. Data-stream processing is particularly effective for real-time processing during data acquisition, thereby enhancing data quality assurance. This paper introduces the integration of the JLAB CLAS12 event reconstruction application within the ERSAP data-stream processing framework that facilitates the execution of streaming event reconstruction at a remote data center and enables the return streaming of reconstructed events to JLAB while circumventing the need for temporary data storage throughout the process.

Gyurjyan, Vardan↗
DOE OSTI2024

PeleMP: The Multiphysics Solver for the Combustion Pele Adaptive Mesh Refinement Code Suite

Combustion encompasses multiscale, multiphase reacting flow physics spanning a wide range of scales from the molecular scales, where chemical reactions occur, to the device scales, where the turbulent flow is affected by the geometry of the combustor. This scale disparity and the limited measurement capabilities from experiments make modeling combustion a significant challenge. Recent advancements in high-performance computing (HPC), particularly with the Department of Energy's Exascale Computing Project (ECP), have enabled high-fidelity simulations of practical applications to be performed. The major physics submodels, including chemical reactions, turbulence, sprays, soot, and thermal radiation, exhibit distinctive computational characteristics that need to be examined separately to ensure efficient utilization of computational resources. This paper presents the multiphysics solver for the Pele code suite, called PeleMP, which consists of models for spray, soot, and thermal radiation. Here, the mathematical and algorithmic aspects of the model implementations are described in detail as well as the verification process. The computational performance of these models is benchmarked on multiple supercomputers, including Frontier, an exascale machine. Results are presented from production simulations of a turbulent sooting ethylene flame and a bluff-body swirl stabilized spray flame with sustainable aviation fuels to demonstrate the capability of the Pele codes for modeling practical combustion problems with multiphysics. This work is an important step toward the exascale computing era for high-fidelity combustion simulations providing physical insights and data for predictive modeling of real-world devices.

42 ENGINEERING↗
DOE OSTI2025

Using a Large Language Model as a Building Block to Generate Usable Validation and Verification Suite for OpenMP

In the HPC area, both hardware and software move quickly. Often new hardware is developed and deployed, the corresponding software stack, including compilers and other tools, are under active development while leading edge software developers are working to port and tune their applications, all at the same time. While the software ecosystem is in flux, one of the key challenges for users is obtaining insight into the state of implementation of key features in the programming languages and models their applications are using – whether they have been implemented, and whether the implementation conforms to the specification, especially for newly implemented features (less tested by widespread use). OpenMP is one of the most prominent shared memory programming models used for on-node programming in HPC. With the shift towards accelerators (such as GPUs and FPGAs) and heterogeneous programming OpenMP features are getting more complex. It is natural to ask whether generative AI approaches, and large language models (LLMs) in particular, can help in producing validation and verification test suites to allow users better and faster insights into the availability and correctness of OpenMP features of interest. In this work, we explore the use of ChatGPT-4 to generate a suite of tests for OpenMP features. We have chosen a set of directives and clauses, a total of 78 combinations, which first appeared in OpenMP 3.0 (released in May 2008) but are also relevant for accelerators. We prompted ChatGPT to generate tests in the C and Fortran languages, for both host (CPU) and device (accelerator). On the Summit super-computer using the GNU implementation, we found that, of the 78 generated tests 67 C tests and 43 Fortran tests compiled successfully and fewer than those executed to completion. On further analysis we show that not all generated tests are valid. We document the process, results, and provide detailed analysis regarding the quality of tests generated. With the aim of providing input to a production quality validation and verification suite, we manually implement the corrections required to make the tests valid according to the current OpenMP specification. We quantify this effort as small, medium, or large, and record the lines of code changed to correct the invalid tests. With the corrected tests we validate recent implementations from HPE, AMD, and GNU on the Frontier supercomputer. Our experiment and subsequent analysis show that although LLMs are capable of producing HPC specific codes, they are limited by their understanding of the deeper semantics and restrictions of programming models such as OpenMP. Unsurprisingly more commonly used features have better support, while some OpenMP 3.0 directives such as sections and tasking are not universally supported on accelerators. We demonstrate that successful compilation and execution to completion are inadequate metrics for evaluating generated code and that, at this time, commodity LLMs require expert intervention for code verification. This points to gaps in the training data that is currently available for HPC. We demonstrate that with "small" effort 37% of generated invalid C tests and 63% of generated invalid Fortran tests could be corrected. This improves productivity of test generation as we circumvent writing from scratch and the common programming errors associated with it.

Pophale, Swaroop [ORNL] (ORCID:0000000185446367)↗
DOE OSTI2021

Enabling discovery data science through cross-facility workflows

Experimental and observational instruments for scientific research (such as light sources, genome sequencers, accelerators, telescopes and electron microscopes) increasingly require High Performance Computing (HPC) scale capabilities for data analysis and workflow processing. Next-generation instruments are being deployed with higher resolutions and faster data capture rates, creating a big data crunch that cannot be handled by modest institutional computing resources. Often these big data analysis pipelines also require near real-time computing and have higher resilience requirements than the simulation and modeling workloads more traditionally seen at HPC centers. While some facilities have enabled workflows to run at a single HPC facility, there is a growing need to integrate capabilities across HPC facilities to enable cross-facility workflows, either to provide resilience to an experiment, increase analysis throughput capabilities, or to better match a workflow to a particular architecture. In this paper we describe the barriers to executing complex data analysis workflows across HPC facilities and propose an architectural design pattern for enabling scientific discovery using cross-facility workflows that includes orchestration services, application programming interfaces (APIs), data access and co-scheduling.

Antypas, Katerina B.↗
DOE OSTI2023

Autonomy Loops for Monitoring, Operational Data Analytics, Feedback, and Response in HPC Operations

Many High Performance Computing (HPC) facilities have developed and deployed frameworks in support of continuous monitoring and operational data analytics (MODA) to help improve efficiency and throughput. Because of the complexity and scale of systems and workflows and the need for low-latency response to address dynamic circumstances, automated feedback and response have the potential to be more effective than current human-in-the-loop approaches which are laborious and error prone. Progress has been limited, however, by factors such as the lack of infrastructure and feedback hooks, and successful deployment is often site- and case-specific. In this position paper we report on the outcomes and plans from a recent Dagstuhl Seminar, seeking to carve a path for community progress in the development of autonomous feedback loops for MODA, based on the established formalism of similar (MAPE-K) loops in autonomous computing and self-adaptive systems. By defining and developing such loops for significant cases experienced across HPC sites, we seek to extract commonalities and develop conventions that will facilitate interoperability and interchangeability with system hardware, software, and applications across different sites, and will motivate vendors and others to provide telemetry interfaces and feedback hooks to enable community development and pervasive deployment of MODA autonomy loops.

autonomy loops↗
DOE OSTI2026

Toward Energy-Efficient HPC: Insights from Power Profiling a Cloud-Resolving Earth System Model

Power is a fundamental constraint as supercomputing advances to exascale. Efficient operation within strict power budgets requires application-aware power management based on a detailed understanding of application-level power behavior. This work analyzes the Energy Exascale Earth System Model (E3SM) atmosphere component, SCREAM, on Perlmutter (NERSC) and Frontier (OLCF). We characterize power variation across inputs, concurrency levels, and power caps, evaluate the energy impact of code optimizations, and attribute energy within the code using a newly developed GPU energy model. Results show that SCREAM’s peak power remains stable during its core execution phase and decreases gradually as concurrency increases. Power capping experiments reveal a performance–energy "sweet spot". On Perlmutter, limiting GPU power to 50% of thermal design power (TDP) achieves up to 15% energy savings with a 7% performance penalty. On Frontier, a 40% TDP cap yields up to 10% energy savings with less than 10% performance loss. Code optimizations reduce SCREAM energy by shortening run time without increasing power. Modeling reveals a critical insight: data movement accounts for approximately 70% of SCREAM’s GPU energy. This fundamentally shifts the optimization focus from FLOPS to data transfer reduction for this class of applications, offering the most impactful strategy for improving energy efficiency. This work establishes a foundation for practical, application-aware power management at exascale.

Zhao, Zhengji [Lawrence Berkeley National Laborato↗
DOE OSTI2024

AutoCheck: Automatically Identifying Variables for Checkpointing by Data Dependency Analysis

Checkpoint/Restart (C/R) has been widely deployed in numerous HPC systems, Clouds, and industrial data centers, which are typically operated by system engineers. Nevertheless, there is no existing approach that helps system engineers without domain expertise and domain scientists without system fault tolerance knowledge identify those critical variables accounted for correct application execution restoration in a failure for C/R. To address this problem, we propose an analytical model and a tool (AutoCheck) that can automatically identify critical variables to checkpoint for C/R. AutoCheck relies on first, analytically tracking and optimizing data dependency between variables and other application execution state, and second, a set of heuristics that identify critical variables for checkpointing from the refined data dependency graph (DDG). AutoCheck allows programmers to pinpoint critical variables to checkpoint quickly within a few minutes. We evaluate AutoCheck on 13 representative HPC benchmarks, demonstrating that AutoCheck can efficiently identify correct critical variables to checkpoint.

HPC↗