SEARCH · Engineering Papers

Results for “execution time”

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.

SourceResearch connectionFrom yearThrough year

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

At least 217 records · Page 12

All sources NASA NTRS DOE OSTI

NASA NTRS1979

Singular perturbation techniques for on-line optimal flight path control

This paper presents a partial evaluation on the use of singular perturbation methods for developing computer algorithms for on-line optimal control of aircraft. The evaluation is based on a study of the minimum time intercept problem using F-4 aerodynamic and propulsion data as a base line. The extensions over previous work on this subject are that aircraft turning dynamics (in addition to position and energy dynamics) are included in the analysis, the algorithm is developed for a moving end point and is adaptive to unpredictable target maneuvers, and short range maneuvers that do not have a cruise leg are included. Particular attention is given to identifying those quantities that can be precomputed and stored (as a function of aircraft total energy), thus greatly reducing the onboard computational load. Numerical results are given that illustrate the nature of the optimal intercept flight paths, and an estimate is given for the execution time and storage requirements of the control algorithm.

Calise, A. J.↗

NASA NTRS1975

Numerical computation of three-dimensional blunt body flow fields with an impinging shock

A time-marching finite-difference method was used to solve the compressible Navier-Stokes equations for the three-dimensional wing-leading-edge shock impingement problem. The bow shock was treated as a discontinuity across which the exact shock jump conditions were applied. All interior shock layer detail such as shear layers, shock waves, jets, and the wall boundary layer were automatically captured in the solution. The impinging shock was introduced by discontinuously changing the freestream conditions across the intersection line at the bow shock. A special storage-saving procedure for sweeping through the finite-difference mesh was developed which reduces the required amount of computer storage by at least a factor of two without sacrificing the execution time. Numerical results are presented for infinite cylinder blunt body cases as well as the three-dimensional shock impingement case. The numerical results are compared with existing experimental and theoretical results.

Holst, T. L.↗

NASA NTRS1991

Description of real-time Ada software implementation of a power system monitor for the Space Station Freedom PMAD DC testbed

The authors describe the Ada language software developed to perform the electrical power system monitoring functions for the NASA Lewis Research Center's Power Management and Distribution (PMAD) DC testbed. The results of the effort to implement this monitor are presented. The PMAD DC testbed is a reduced-scale prototype of the electric power system to be used in Space Station Freedom. The power is controlled by smart switches known as power control components (or switchgear). The power control components are currently coordinated by five Compaq 386/20e computers connected through an 802.4 local area network. The power system monitor algorithm comprises several functions, including periodic data acquisition, data smoothing, system performance analysis, and status reporting. Data are collected from the switchgear sensors every 100 ms, then passed through a 2-Hz digital filter. System performance analysis includes power interruption and overcurrent detection. The system monitor required a hardware timer interrupt to activate the data acquisition function. The execution time of the code was optimized by using an assembly language routine. The routine allows direct vectoring of the processor to Ada language procedures that perform periodic control activities.

Ludwig, Kimberly↗

NASA NTRS2012

State-Based Behavior Modeling of the Integrated SLS-MPCV System

In NASA's effort to foster a human spaceflight capability beyond Earth's orbit, two space systems are being developed - the Space Launch System (SLS) and the Multi-Purpose Crew Vehicle (MPCV). As of this time, the interactions between the two systems during launch are not fully detailed. To remedy this situation, a Systems Engineering approach utilizing models was developed to investigate the behavior of the integrated SLS-MPCV stack during ascent and abort situations. Specifically, this innovative approach combines aspects of Model-Based Systems Engineering (MBSE) and state analysis to simultaneously model the physical, functional, and behavioral aspects of systems. This approach focuses solely on the interactions between the systems, leaving much of the internal workings of either system at a logical level (i.e., black box). By utilizing this newly defined approach, a behavior model for the integrated SLS-MPCV stack was developed, emphasizing only the subset of interactions between the systems that impact behavior. Finally, analysis is performed within the model to investigate requirements gaps and examine the execution times of key behaviors related to various ascent phases and abort scenarios. The work described in this paper is merely a portion of the outlined effort being undertaken for this project; only a segment of the SLS-MPCV system behavior will be described.

Space Launch System (SLS)↗

DOE OSTI2023

Acceleration of the Parameterization of Unified Microphysics Across Scales (PUMAS) on the Graphics Processing Unit (GPU) With Directive-Based Methods

Cloud microphysics is one of the most time-consuming components in a climate model. In this study, we port the cloud microphysics parameterization in the Community Atmosphere Model (CAM), known as Parameterization of Unified Microphysics Across Scales (PUMAS), from CPU to GPU to seek a computational speedup. The directive-based methods (OpenACC and OpenMP target offload) are determined as the best fit specifically for our development practices, which enable a single version of source code to run either on the CPU or GPU, and yield a better portability and maintainability. Their performance is first examined in a PUMAS stand-alone kernel and the directive-based methods can outperform a CPU node as long as there is enough computational burden on the GPU. A consistent behavior is observed when we run PUMAS on the GPU in a practical CAM simulation. A 3.6× speedup of the PUMAS execution time, including data movement between CPU and GPU, is achieved at a coarse horizontal resolution (8 NVIDIA V100 GPUs against 36 Intel Skylake CPU cores). This speedup further increases up to 5.4× at a high resolution (24 NVIDIA V100 GPUs against 108 Intel Skylake CPU cores), which highlights the fact that GPU favors larger problem size. This study demonstrates that using GPU in a CAM simulation can save noticeable computational costs even with a small portion of code being GPU-enabled. Therefore, we are encouraged to port more parameterizations to GPU to take advantage of its computational benefit.

54 ENVIRONMENTAL SCIENCES↗

NASA NTRS2017

Open-Source RTOS Space Qualification: An RTEMS Case Study

NASA space-qualification of reusable off-the-shelf real-time operating systems (RTOSs) remains elusive due to several factors notably (1) The diverse nature of RTOSs utilized across NASA, (2) No single NASA space-qualification criteria, lack of verification and validation (V&V) analysis, or test beds, and (3) different RTOS heritages, specifically open-source RTOSs and closed vendor-provided RTOSs. As a leader in simulation test beds, the NASA IV&V Program is poised to help jump-start and lead the space-qualification effort of the open source Real-Time Executive for Multiprocessor Systems (RTEMS) RTOS. RTEMS, as a case-study, can be utilized as an example of how to qualify all RTOSs, particularly the reusable non-commercial (open-source) ones that are gaining usage and popularity across NASA. Qualification will improve the overall safety and mission assurance of RTOSs for NASA-agency wide usage. NASA's involvement in space-qualification of an open-source RTOS such as RTEMS will drive the RTOS industry toward a more qualified and mature open-source RTOS product.

Real-time operating system↗

NASA NTRS1978

Sorting on STAR

Timing comparisons are given for three sorting algorithms written for the CDC STAR computer. One algorithm is Hoare's (1962) Quicksort, which is the fastest or nearly the fastest sorting algorithm for most computers. A second algorithm is a vector version of Quicksort that takes advantage of the STAR's vector operations. The third algorithm is an adaptation of Batcher's (1968) sorting algorithm, which makes especially good use of vector operations but has a complexity of N(log N)-squared as compared with a complexity of N log N for the Quicksort algorithms. In spite of its worse complexity, Batcher's sorting algorithm is competitive with the serial version of Quicksort for vectors up to the largest that can be treated by STAR. Vector Quicksort outperforms the other two algorithms and is generally preferred. These results indicate that unusual instruction sets can introduce biases in program execution time that counter results predicted by worst-case asymptotic complexity analysis.

Stone, H. S.↗

DOE OSTI2022

Quantitative Performance Assessment of Proxy Apps and Parents (Report for ECP Proxy App Project Milestone ADCD-504-28)

The ECP Proxy Application Project has an annual milestone to assess the state of ECP proxy applications and their role in the overall ECP ecosystem. Our FY22 March/April milestone (ADCD- 504-28) proposed to: Assess the fidelity of proxy applications compared to their respective parents in terms of kernel and I/O behavior, and predictability. Similarity techniques will be applied for quantitative comparison of proxy/parent kernel behavior. MACSio evaluation will continue and support for OpenPMD backends will be explored. The execution time predictability of proxy apps with respect to their parents will be explored through a carefully designed scaling study and code comparisons. Note that in this FY, we also have quantitative assessment milestones that are due in September and are, therefore, not included in the description above or in this report. Another report on these deliverables will be generated and submitted upon completion of these milestones. To satisfy this milestone, the following specific tasks were completed: Study the ability of MACSio to represent I/O workloads of adaptive mesh codes. Re-define the performance counter groups for contemporary Intel and IBM platforms to better match specific hardware components and to better align across platforms (make cross-platform comparison more accurate). Perform cosine similarity study based on the new performance counter groups on the Intel and IBM P9 platforms. Perform detailed analysis of performance counter data to accurately average and align the data to maintain phases across all executions and develop methods to reduce the set of collected performance counters used in cosine similarity analysis. Apply a quantitative similarity comparison between proxy and parent CPU kernels. Perform scaling studies to understand the accuracy of predictability of the parent performance using its respective proxy application. This report presents highlights of these efforts.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1999

Multidisciplinary Optimization Branch Experience Using iSIGHT Software

The Multidisciplinary Optimization (MDO) Branch at NASA Langley Research Center is investigating frameworks for supporting multidisciplinary analysis and optimization research. An optimization framework call improve the design process while reducing time and costs. A framework provides software and system services to integrate computational tasks and allows the researcher to concentrate more on the application and less on the programming details. A framework also provides a common working environment and a full range of optimization tools, and so increases the productivity of multidisciplinary research teams. Finally, a framework enables staff members to develop applications for use by disciplinary experts in other organizations. Since the release of version 4.0, the MDO Branch has gained experience with the iSIGHT framework developed by Engineous Software, Inc. This paper describes experiences with four aerospace applications: (1) reusable launch vehicle sizing, (2) aerospike nozzle design, (3) low-noise rotorcraft trajectories, and (4) acoustic liner design. All applications have been successfully tested using the iSIGHT framework, except for the aerospike nozzle problem, which is in progress. Brief overviews of each problem are provided. The problem descriptions include the number and type of disciplinary codes, as well as all estimate of the multidisciplinary analysis execution time. In addition, the optimization methods, objective functions, design variables, and design constraints are described for each problem. Discussions on the experience gained and lessons learned are provided for each problem. These discussions include the advantages and disadvantages of using the iSIGHT framework for each case as well as the ease of use of various advanced features. Potential areas of improvement are identified.

Padula, S. L.↗

NASA NTRS1995

Analysis of composite ablators using massively parallel computation

In this work, the feasibility of using massively parallel computation to study the response of ablative materials is investigated. Explicit and implicit finite difference methods are used on a massively parallel computer, the Thinking Machines CM-5. The governing equations are a set of nonlinear partial differential equations. The governing equations are developed for three sample problems: (1) transpiration cooling, (2) ablative composite plate, and (3) restrained thermal growth testing. The transpiration cooling problem is solved using a solution scheme based solely on the explicit finite difference method. The results are compared with available analytical steady-state through-thickness temperature and pressure distributions and good agreement between the numerical and analytical solutions is found. It is also found that a solution scheme based on the explicit finite difference method has the following advantages: incorporates complex physics easily, results in a simple algorithm, and is easily parallelizable. However, a solution scheme of this kind needs very small time steps to maintain stability. A solution scheme based on the implicit finite difference method has the advantage that it does not require very small times steps to maintain stability. However, this kind of solution scheme has the disadvantages that complex physics cannot be easily incorporated into the algorithm and that the solution scheme is difficult to parallelize. A hybrid solution scheme is then developed to combine the strengths of the explicit and implicit finite difference methods and minimize their weaknesses. This is achieved by identifying the critical time scale associated with the governing equations and applying the appropriate finite difference method according to this critical time scale. The hybrid solution scheme is then applied to the ablative composite plate and restrained thermal growth problems. The gas storage term is included in the explicit pressure calculation of both problems. Results from ablative composite plate problems are compared with previous numerical results which did not include the gas storage term. It is found that the through-thickness temperature distribution is not affected much by the gas storage term. However, the through-thickness pressure and stress distributions, and the extent of chemical reactions are different from the previous numerical results. Two types of chemical reaction models are used in the restrained thermal growth testing problem: (1) pressure-independent Arrhenius type rate equations and (2) pressure-dependent Arrhenius type rate equations. The numerical results are compared to experimental results and the pressure-dependent model is able to capture the trend better than the pressure-independent one. Finally, a performance study is done on the hybrid algorithm using the ablative composite plate problem. It is found that there is a good speedup of performance on the CM-5. For 32 CPU's, the speedup of performance is 20. The efficiency of the algorithm is found to be a function of the size and execution time of a given problem and the effective parallelization of the algorithm. It also seems that there is an optimum number of CPU's to use for a given problem.

Shia, David↗

DOE OSTI2025

Implementation of the D1S Methodology for Shutdown Dose Rate Calculations in the OpenMC Monte Carlo Particle Transport Code

We present an implementation of the direct one-step (D1S) methodology for shutdown dose rate (SDR) calculations in the OpenMC Monte Carlo particle transport code. In addition to being the first fully open-source D1S implementation, it is also the first to require no ad hoc source code or nuclear data library modifications. The code can seamlessly switch between production of prompt and decay photons based on a user input parameter, and the decay data needed for decay photon generation are made available through a depletion chain file, which is already used for OpenMC’s built-in depletion/activation solver. A set of Python functions significantly eases the burden of computing and applying time correction factors needed to properly account for the time dependence of radionuclide activity. To assess the accuracy of the D1S implementation, SDR calculations have been carried out for three problems: a prism of iron irradiated by 14-MeV neutrons, the ITER port plug computational benchmark, and the Frascati Neutron Generator (FNG) ITER dose rate benchmark problem from the Shielding INtegral Benchmark Archive and Database (SINBAD). For each of these problems, comparisons were made to calculations using the rigorous two-step (R2S) method. The results on the iron prism problem illustrate how the D1S method achieves superior spatial resolution compared to the R2S method without the need for spatial discretization of the activation regions. The D1S and R2S results for the ITER port plug benchmark agree well with previously reported results in the literature. While the D1S results are 10% to 15% lower than the R2S results, this may be due to stochastic uncertainty and/or spatial discretization in the R2S calculations. On the FNG dose rate benchmark problem, the D1S method produces dose rate estimates that are within 4% of the dose rates predicted using a cell-based R2S workflow. The D1S estimates of the SDR are also in reasonable agreement with the experimental measurements and show the same basic trends that have been observed in previous works. A qualitative analysis of the execution time and uncertainty for the R2S and D1S workflows suggests that the D1S method would attain a higher figure of merit.

D1S method↗

DOE OSTI2022

Towards Enhancing Coding Productivity for GPU Programming Using Static Graphs

The main contribution of this work is to increase the coding productivity of GPU programming by using the concept of Static Graphs. GPU capabilities have been increasing significantly in terms of performance and memory capacity. However, there are still some problems in terms of scalability and limitations to the amount of work that a GPU can perform at a time. To minimize the overhead associated with the launch of GPU kernels, as well as to maximize the use of GPU capacity, we have combined the new CUDA Graph API with the CUDA programming model (including CUDA math libraries) and the OpenACC programming model. We use as test cases two different, well-known and widely used problems in HPC and AI: the Conjugate Gradient method and the Particle Swarm Optimization. In the first test case (Conjugate Gradient) we focus on the integration of Static Graphs with CUDA. In this case, we are able to significantly outperform the NVIDIA reference code, reaching an acceleration of up to 11x thanks to a better implementation, which can benefit from the new CUDA Graph capabilities. In the second test case (Particle Swarm Optimization), we complement the OpenACC functionality with the use of CUDA Graph, achieving again accelerations of up to one order of magnitude, with average speedups ranging from 2x to 4x, and performance very close to a reference and optimized CUDA code. Our main target is to achieve a higher coding productivity model for GPU programming by using Static Graphs, which provides, in a very transparent way, a better exploitation of the GPU capacity. The combination of using Static Graphs with two of the current most important GPU programming models (CUDA and OpenACC) is able to reduce considerably the execution time w.r.t. the use of CUDA and OpenACC only, achieving accelerations of up to more than one order of magnitude. Finally, we propose an interface to incorporate the concept of Static Graphs into the OpenACC Specifications.

58 GEOSCIENCES↗

NASA NTRS1992

Fortran for the nineties

Fortran has largely enjoyed prominence for the past few decades as the computer programming language of choice for numerically intensive scientific, engineering, and process control applications. Fortran's well understood static language syntax has allowed resulting parsers and compiler optimizing technologies to often generate among the most efficient and fastest run-time executables, particularly on high-end scalar and vector supercomputers. Computing architectures and paradigms have changed considerably since the last ANSI/ISO Fortran release in 1978, and while FORTRAN 77 has more than survived, it's aged features provide only partial functionality for today's demanding computing environments. The simple block procedural languages have been necessarily evolving, or giving way, to specialized supercomputing, network resource, and object-oriented paradigms. To address these new computing demands, ANSI has worked for the last 12-years with three international public reviews to deliver Fortran 90. Fortran 90 has superseded and replaced ISO FORTRAN 77 internationally as the sole Fortran standard; while in the US, Fortran 90 is expected to be adopted as the ANSI standard this summer, coexisting with ANSI FORTRAN 77 until at least 1996. The development path and current state of Fortran will be briefly described highlighting the many new Fortran 90 syntactic and semantic additions which support (among others): free form source; array syntax; new control structures; modules and interfaces; pointers; derived data types; dynamic memory; enhanced I/O; operator overloading; data abstraction; user optional arguments; new intrinsics for array, bit manipulation, and system inquiry; and enhanced portability through better generic control of underlying system arithmetic models. Examples from dynamical astronomy, signal and image processing will attempt to illustrate Fortran 90's applicability to today's general scalar, vector, and parallel scientific and engineering requirements and object oriented programming paradigms. Time permitting, current work proceeding on the future development of Fortran 2000 and collateral standards will be introduced.

Himer, J. T.↗

DOE OSTI2021

Autotuning PolyBench benchmarks with LLVM Clang/Polly loop optimization pragmas using Bayesian optimization

Here, we develop a ytopt autotuning framework that leverages Bayesian optimization to explore the parameter space search and compare four different supervised learning methods within Bayesian optimization and evaluate their effectiveness. We select six of the most complex PolyBench benchmarks and apply the newly developed LLVM Clang/Polly loop optimization pragmas to the benchmarks to optimize them. We then use the autotuning framework to optimize the pragma parameters to improve their performance. The experimental results show that our autotuning approach outperforms the other compiling methods to provide the smallest execution time for the benchmarks syr2k, 3mm, heat-3d, lu, and covariance with two large datasets in 200 code evaluations for effectively searching the parameter spaces with up to 170,368 different configurations. We find that the Floyd-Warshall benchmark did not benefit from autotuning. To cope with this issue, we provide some compiler option solutions to improve the performance. Then we present loop autotuning without a user's knowledge using a simple mctree autotuning framework to further improve the performance of the Floyd-Warshall benchmark. We also extend the ytopt autotuning framework to tune a deep learning application.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2025

Results of a Geant4 benchmarking study for bio‐medical applications, performed with the G4‐Med system

Geant4, a Monte Carlo Simulation Toolkit extensively used in bio-medical physics, is in continuous evolution to include newest research findings to improve its accuracy and to respond to the evolving needs of a very diverse user community. In 2014, the G4-Med benchmarking system was born from the effort of the Geant4 Medical Simulation Benchmarking Group, to benchmark and monitor the evolution of Geant4 for medical physics applications. The G4-Med system was first described in our Medical Physics Special Report published in 2021. Results of the tests were reported for Geant4 10.5. Purpose In this work, we describe the evolution of the G4-Med benchmarking system. Methods The G4-Med benchmarking suite currently includes 23 tests, which benchmark Geant4 from the calculation of basic physical quantities to the simulation of more clinically relevant set-ups. New tests concern the benchmarking of Geant4-DNA physics and chemistry components for regression testing purposes, dosimetry for brachytherapy with a 125 I source, dosimetry for external x-ray and electron FLASH radiotherapy, experimental microdosimetry for proton therapy, and in vivo PET for carbon and oxygen beams. Regression testing has been performed between Geant4 10.5 and 11.1. Finally, a simple Geant4 simulation has been developed and used to compare Geant4 EM physics constructors and physics lists in terms of execution times. Results In summary, our EM tests show that the parameters of the multiple scattering in the Geant4 EM constructor G4EmStandardPhysics_option3 in Geant4 11.1, while improving the modeling of the electron backscattering in high atomic number targets, are not adequate for dosimetry for clinical x-ray and electron beams. Therefore, these parameters have been reverted back to those of Geant4 10.5 in Geant4 11.2.1. The x-ray radiotherapy test shows significant differences in the modeling of the bremsstrahlung process, especially between G4EmPenelopePhysics and the other constructors under study (G4EmLivermorePhysics, G4EmStandardPhysics_option3, and G4EmStandardPhysics_option4). These differences will be studied in an in-depth investigation within our Group. Improvement in Geant4 11.1 has been observed for the modeling of the proton and carbon ion Bragg peak with energies of clinical interest, thanks to the adoption of ICRU90 to calculate the low energy proton stopping powers in water and of the Linhard–Sorensen ion model, available in Geant4 since version 11.0. Nuclear fragmentation tests of interest for carbon ion therapy show differences between Geant4 10.5 and 11.1 in terms of fragment yields. In particular, a higher production of boron fragments is observed with Geant4 11.1, leading to a better agreement with reference data for this fragment. Conclusions Based on the overall results of our tests, we recommend to use G4EmStandardPhysics_option4 as EM constructor and QGSP_BIC_HP with G4EmStandardPhysics_option4, for hadrontherapy applications. The Geant4-DNA physics lists report differences in modeling electron interactions in water, however, the tests have a pure regression testing purpose so no recommendation can be formulated.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

DOE OSTI2023

Pairwise‐Parallel Entangling Gates on Orthogonal Modes in a Trapped‐Ion Chain

Abstract Parallel operations are important for both near‐term quantum computers and larger‐scale fault‐tolerant machines because they reduce execution time and qubit idling. This study proposes and implements a pairwise‐parallel gate scheme on a trapped‐ion quantum computer. The gates are driven simultaneously on different sets of orthogonal motional modes of a trapped‐ion chain. This work demonstrates the utility of this scheme by creating a Greenberger‐Horne‐Zeilinger (GHZ) state in one step using parallel gates with one overlapping qubit. It also shows its advantage for circuits by implementing a digital quantum simulation of the dynamics of an interacting spin system, the transverse‐field Ising model. This method effectively extends the available gate depth by up to two times with no overhead when no overlapping qubit is involved, apart from additional initial cooling. This scheme can be easily applied to different trapped‐ion qubits and gate schemes, broadly enhancing the capabilities of trapped‐ion quantum computers.

Optics↗

DOE OSTI2018

Evaluating Performance Portability of Accelerator Programming Models using SPEC ACCEL 1.2 Benchmarks

As heterogeneous architectures are becoming mainstream for HPC systems, application programmers are looking for programming model implementations that offer both performance and portability across platforms. Two directive-based programming models for accelerator programming that aim at doing this are OpenMP 4/4.5 and OpenACC. Many users want to know the difference between these two programming models, the state of their implementations, how to use them, and evaluate how suitable they are for their applications.The Standard Performance Evaluation Corporation (SPEC) ACCEL benchmarks, developed by the SPEC High Performance Group (HPG), recently released SPEC ACCEL 1.2 benchmark suite to help the evaluation of OpenCL, OpenMP 4.5 and OpenACC on different platforms. Inthis paper we present our preliminary results that evaluates OpenMP4.5 and OpenACC on a variety of accelerator-based systems: POWER9with NVIDIA V100 GPUs (Summit), Intel Xeon Phi 7230 (Percival), and AMD Bulldozer Opteron with NVIDIA K20x (Titan). Comparing these benchmarks on different systems gives us insight into the support for OpenMP and OpenACC and their execution times provide insights about their quality of implementations provided by different vendors. We also compare best of OpenMP and OpenACC to see if a particular programming model favors a particular type of benchmark kernel.

Boehm, Swen↗

DOE OSTI2020

3D Coded SUMMA: Communication-Efficient and Robust Parallel Matrix Multiplication

In this paper, we propose a novel fault-tolerant parallel matrix multiplication algorithm called 3D Coded SUMMA that achieves higher failure-tolerance than replication-based schemes for the same amount of redundancy. This work bridges the gap between recent developments in coded computing and fault-tolerance in high-performance computing (HPC). The core idea of coded computing is the same as algorithm-based fault-tolerance (ABFT), which is weaving redundancy in the computation using error-correcting codes. In particular, we show that MatDot codes, an innovative code construction for parallel matrix multiplications, can be integrated into three-dimensional SUMMA (Scalable Universal Matrix Multiplication Algorithm [30]) in a communication-avoiding manner. To tolerate any two node failures, the proposed 3D Coded SUMMA requires ~50% less redundancy than replication, while the overhead in execution time is only about 5–10%.

97 MATHEMATICS AND COMPUTING↗