Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “IBM”

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 613 records · Page 34

Design and Evaluation of MPI File Domain Partitioning Methods under Extent-Based File Locking Protocol

MPI collective I/O has been an effective method for parallel shared-file access and maintaining the canonical orders of structured data in files. Its implementation commonly uses a two-phase I/O strategy that partitions a file into disjoint file domains, assigns each domain to a unique process, redistributes the I/O data based on their locations in the domains, and has each process perform I/O for the assigned domain. The partitioning quality determines the maximal performance achievable by the underlying file system, as the shared-file I/O has long been impeded by the cost of file system's data consistency control, particularly due to the conflicted locks. This paper proposes a few file domain partitioning methods designed to reduce lock conflicts under the extent-based file locking protocol. Experiments from four I/O benchmarks on the IBM GPFS and Lustre parallel file systems show that the partitioning method producing minimum lock conflicts wins the highest performance. The benefit of removing conflicted locks can be so significant that more than thirty times of write bandwidth differences are observed between the best and worst methods.

Computer Science↗

Enabling parallel simulation of large-scale HPC network systems

Here, with the increasing complexity of today’s high-performance computing (HPC) architectures, simulation has become an indispensable tool for exploring the design space of HPC systems—in particular, networks. In order to make effective design decisions, simulations of these systems must possess the following properties: (1) have high accuracy and fidelity, (2) produce results in a timely manner, and (3) be able to analyze a broad range of network workloads. Most state-of-the-art HPC network simulation frameworks, however, are constrained in one or more of these areas. In this work, we present a simulation framework for modeling two important classes of networks used in today’s IBM and Cray supercomputers: torus and dragonfly networks. We use the Co-Design of Multi-layer Exascale Storage Architecture (CODES) simulation framework to simulate these network topologies at a flit-level detail using the Rensselaer Optimistic Simulation System (ROSS) for parallel discrete-event simulation. Our simulation framework meets all the requirements of a practical network simulation and can assist network designers in design space exploration. First, it uses validated and detailed flit-level network models to provide an accurate and high-fidelity network simulation. Second, instead of relying on serial time-stepped or traditional conservative discrete-event simulations that limit simulation scalability and efficiency, we use the optimistic event-scheduling capability of ROSS to achieve efficient and scalable HPC network simulations on today’s high-performance cluster systems. Third, our models give network designers a choice in simulating a broad range of network workloads, including HPC application workloads using detailed network traces, an ability that is rarely offered in parallel with high-fidelity network simulations

97 MATHEMATICS AND COMPUTING↗

Symmetric Indefinite Linear Solver Using OpenMP Task on Multicore Architectures

Recently, the Open Multi-Processing (OpenMP) standard has incorporated task-based programming, where a function call with input and output data is treated as a task. At run time, OpenMP's superscalar scheduler tracks the data dependencies among the tasks and executes the tasks as their dependencies are resolved. On a shared-memory architecture with multiple cores, the independent tasks are executed on different cores in parallel, thereby enabling parallel execution of a seemingly sequential code. With the emergence of many-core architectures, this type of programming paradigm is gaining attention-not only because of its simplicity, but also because it breaks the artificial synchronization points of the program and improves its thread-level parallelization. In this paper, we use these new OpenMP features to develop a portable high-performance implementation of a dense symmetric indefinite linear solver. Obtaining high performance from this kind of solver is a challenge because the symmetric pivoting, which is required to maintain numerical stability, leads to data dependencies that prevent us from using some common performance-improving techniques. To fully utilize a large number of cores through tasking, while conforming to the OpenMP standard, we describe several techniques. Our performance results on current many-core architectures-including Intel's Broadwell, Intel's Knights Landing, IBM's Power8, and Arm's ARMv8-demonstrate the portable and superior performance of our implementation compared with the Linear Algebra PACKage (LAPACK). The resulting solver is now available as a part of the PLASMA software package.

Computer Science↗

Exploring Properties and Correlations of Fatal Events in a Large-Scale HPC System

In this study, we explore potential correlations of fatal system events for one of the most powerful supercomputers-IBM Blue Gene/Q Mira, which is deployed at Argonne National Laboratory, based on its 5-year reliability, availability, and serviceability (RAS) log. Our contribution is two-fold. (1) We design an efficient log analysis tool, namely LogAider, with a novel filtering method to effectively extract fatal events from masses of system messages that are heavily duplicated in the log. LogAider exhibits a very precise detection of temporal-correlation with a high similarity (up to 95 percent) to the ground-truth (i.e., compared to the failure records reported by the administrators). The total number of fatal events can be reduced to about 1,255 compared with originally 2.6 million duplicated fatal messages. (2) We analyze the 5-year RAS log of the MIRA system using LogAider, and summarize six important "takeaways" which can help system vendors and administrators better understand an extreme-scale system's fatal events. Specifically, we find that the distribution or proportion of the fatal system events follow a Pareto-like principle in general. The temporal correlation among fatal events is much stronger than that of warn messages and info messages, and the correlated events tend to constitute a few clusters. The mean time between fatal events (MTBFE) of the Mira system is about 1.3 days from the perspective of the system, and the MTTI is 2-4 days from the perspective of users. The most error-prone item value with respect to any key attribute appears likely in the log every 2-10 days. Weibull, Gamma, and Pearson6 are the three best-fit distributions for the fatal event intervals. The overall correlation of fatal events on the 5D torus network is not prominent, whereas the small-region locality correlation (e.g., the fatal events inside racks) is relatively strong. We believe our work will be interesting to large-scale HPC system administrators and vendors and to fault tolerance researchers, enabling them to better understand fatal events and mitigate such events accordingly.

97 MATHEMATICS AND COMPUTING↗

Geometric Mapping of Tasks to Processors on Parallel Computers with Mesh or Torus Networks

We present a new method for reducing parallel applications' communication time by mapping their MPI tasks to processors in a way that lowers the distance messages travel and the amount of congestion in the network. Assuming geometric proximity among the tasks is a good approximation of their communication interdependence, we use a geometric partitioning algorithm to order both the tasks and the processors, assigning task parts to the corresponding processor parts. In this way, interdependent tasks are assigned to “nearby” cores in the network. We also present a number of algorithmic optimizations that exploit specific features of the network or application to further improve the quality of the mapping. We specifically address the case of sparse node allocation, where the nodes assigned to a job are not necessarily located in a contiguous block nor within close proximity to each other in the network. Furthermore, our methods generalize to contiguous allocations as well, and results are shown for both contiguous and non-contiguous allocations. We show that, for the structured finite difference mini-application MiniGhost, our mapping methods reduced communication time up to 75% relative to MiniGhost's default mapping on 128K cores of a Cray XK7 with sparse allocation. For the atmospheric modeling code E3SM/HOMME, our methods reduced communication time up to 31% on 16K cores of an IBM BlueGene/Q with contiguous allocation.

97 MATHEMATICS AND COMPUTING↗

Noisy-Intermediate-Scale Quantum Electromagnetic Transients Program

Quantum-empowered electromagnetic transients program (QEMTP) is a promising paradigm for tackling EMTP's computational burdens. Nevertheless, no existing studies truly achieve a practical and scalable QEMTP operable on today's noisy-intermediate-scale quantum (NISQ) computers. The strong reliance on noise-free and fault-tolerant quantum devices--which appears to be decades away--hinder practical applications of current QEMTP methods. Here, we devise a NISQ-QEMTP methodology which for the first time transitions the QEMTP operations from ideal, noise-free quantum simulators to real, noisy quantum computers. The main contributions lie in: (1) a shallow-depth QEMTP quantum circuit for mitigating noises on NISQ quantum devices; (2) practical QEMTP linear solvers incorporating executable quantum state preparation and measurements for nodal voltage computations; (3) a noise-resilient QEMTP algorithm leveraging quantum resources logarithmically scaled with power system dimension; (4) a quantum shifted frequency analysis (QSFA) for accelerating QEMTP by exploiting dynamic phasor simulations with larger time steps; (5) a systematical analysis on QEMTPs performance under various noisy quantum environments. Extensive experiments systematically verify the accuracy, efficacy, universality and noise-resilience of QEMTP on both noise-free simulators and IBM real quantum computers.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

A Quantum-Classical Collaborative Training Architecture Based on Quantum State Fidelity

Recent advancements have highlighted the limitations of current quantum systems, particularly the restricted number of qubits available on near-term quantum devices. This constraint greatly inhibits the range of applications that can leverage quantum computers. Moreover, as the available qubits increase, the computational complexity grows exponentially, posing additional challenges. Consequently, there is an urgent need to use qubits efficiently and mitigate both present limitations and future complexities. To address this, existing quantum applications attempt to integrate classical and quantum systems in a hybrid framework. In this study, we concentrate on quantum deep learning and introduce a collaborative classical-quantum architecture called co-TenQu. The classical component employs a tensor network for compression and feature extraction, enabling higher-dimensional data to be encoded onto logical quantum circuits with limited qubits. On the quantum side, we propose a quantum-state-fidelity-based evaluation function to iteratively train the network through a feedback loop between the two sides. co-TenQu has been implemented and evaluated with both simulators and the IBM-Q platform. Compared to state-of-the-art approaches, co-TenQu enhances a classical deep neural network by up to 41.72% in a fair setting. Additionally, it outperforms other quantum-based methods by up to 1.9 times and achieves similar accuracy while utilizing 70.59% fewer qubits.

42 ENGINEERING↗

Robust Design Under Uncertainty in Quantum Error Mitigation

Error mitigation techniques are crucial to achieving near-term quantum advantage. Classical postprocessing of quantum computation outcomes is a popular approach for error mitigation, which includes methods, such as zero noise extrapolation, virtual distillation, and learning-based error mitigation. However, these techniques have limitations due to the propagation of uncertainty resulting from the finite shot number of a quantum measurement. In this work, we introduce general and unbiased methods for quantifying the uncertainty and error of error-mitigated observables based on the strategic sampling of error mitigation outcomes. We then extend our approach to demonstrate the optimization of performance and robustness of error mitigation under uncertainty. To illustrate our methods, we apply them to zero noise extrapolation and Clifford date regression in the ground state of the XY model simulated using depolarizing and International Business Machines Corporation (IBM) Toronto noise models, respectively. In particular, we optimize the choice of noise levels and the allocation of shots for zero noise extrapolation and the distribution of the training circuits for Clifford data regression. While our methods are readily applicable to any postprocessing-based error mitigation approach, in practice they must not be prohibitively expensive—even though they perform optimizations of the error mitigation hyperparameters requiring sampling of a statistical distribution of error mitigation outcomes. By leveraging surrogate-based optimization, we show that our methods can efficiently perform optimal design for a zero noise extrapolation implementation. We then further demonstrate the transferability of learned zero noise extrapolation hyperparameters to other similar circuits.

97 MATHEMATICS AND COMPUTING↗

Development of a Stiffness-Based Chemistry Load Balancing Scheme, and Optimization of Input/Output and Communication, to Enable Massively Parallel High-Fidelity Internal Combustion Engine Simulations

A closed-cycle gasoline compression ignition engine simulation near top dead center (TDC) was used to profile the performance of a parallel commercial engine computational fluid dynamics code, as it was scaled on up to 4096 cores of an IBM Blue Gene/Q supercomputer. The test case has 9 million cells near TDC, with a fixed mesh size of 0.15 mm, and was run on configurations ranging from 128 to 4096 cores. Profiling was done for a small duration of 0.11 crank angle degrees near TDC during ignition. Optimization of input/output performance resulted in a significant speedup in reading restart files, and in an over 100-times speedup in writing restart files and files for post-processing. Improvements to communication resulted in a 1400-times speedup in the mesh load balancing operation during initialization, on 4096 cores. An improved, “stiffness-based” algorithm for load balancing chemical kinetics calculations was developed, which results in an over 3-times faster run-time near ignition on 4096 cores relative to the original load balancing scheme. With this improvement to load balancing, the code achieves over 78% scaling efficiency on 2048 cores, and over 65% scaling efficiency on 4096 cores, relative to 256 cores.

CFD, Mira, Supercomputing, High Performance Comput↗

Dose-shaping using targeted sparse optimization

Purpose: Dose volume histograms (DVHs) are common tools in radiation therapy treatment planning to characterize plan quality. As statistical metrics, DVHs provide a compact summary of the underlying plan at the cost of losing spatial information: the same or similar dose-volume histograms can arise from substantially different spatial dose maps. This is exactly the reason why physicians and physicists scrutinize dose maps even after they satisfy all DVH endpoints numerically. However, up to this point, little has been done to control spatial phenomena, such as the spatial distribution of hot spots, which has significant clinical implications. To this end, the authors propose a novel objective function that enables a more direct tradeoff between target coverage, organ-sparing, and planning target volume (PTV) homogeneity, and presents our findings from four prostate cases, a pancreas case, and a head-and-neck case to illustrate the advantages and general applicability of our method.Methods: In designing the energy minimization objective (E{sub tot}{sup sparse}), the authors utilized the following robust cost functions: (1) an asymmetric linear well function to allow differential penalties for underdose, relaxation of prescription dose, and overdose in the PTV; (2) a two-piece linear function to heavily penalize high dose and mildly penalize low and intermediate dose in organs-at risk (OARs); and (3) a total variation energy, i.e., the L{sub 1} norm applied to the first-order approximation of the dose gradient in the PTV. By minimizing a weighted sum of these robust costs, general conformity to dose prescription and dose-gradient prescription is achieved while encouraging prescription violations to follow a Laplace distribution. In contrast, conventional quadratic objectives are associated with a Gaussian distribution of violations, which is less forgiving to large violations of prescription than the Laplace distribution. As a result, the proposed objective E{sub tot}{sup sparse} improves tradeoff between planning goals by 'sacrificing' voxels that have already been violated to improve PTV coverage, PTV homogeneity, and/or OAR-sparing. In doing so, overall plan quality is increased since these large violations only arise if a net reduction in E{sub tot}{sup sparse} occurs as a result. For example, large violations to dose prescription in the PTV in E{sub tot}{sup sparse}-optimized plans will naturally localize to voxels in and around PTV-OAR overlaps where OAR-sparing may be increased without compromising target coverage. The authors compared the results of our method and the corresponding clinical plans using analyses of DVH plots, dose maps, and two quantitative metrics that quantify PTV homogeneity and overdose. These metrics do not penalize underdose since E{sub tot}{sup sparse}-optimized plans were planned such that their target coverage was similar or better than that of the clinical plans. Finally, plan deliverability was assessed with the 2D modulation index.Results: The proposed method was implemented using IBM's CPLEX optimization package (ILOG CPLEX, Sunnyvale, CA) and required 1-4 min to solve with a 12-core Intel i7 processor. In the testing procedure, the authors optimized for several points on the Pareto surface of four 7-field 6MV prostate cases that were optimized for different levels of PTV homogeneity and OAR-sparing. The generated results were compared against each other and the clinical plan by analyzing their DVH plots and dose maps. After developing intuition by planning the four prostate cases, which had relatively few tradeoffs, the authors applied our method to a 7-field 6 MV pancreas case and a 9-field 6MV head-and-neck case to test the potential impact of our method on more challenging cases. The authors found that our formulation: (1) provided excellent flexibility for balancing OAR-sparing with PTV homogeneity; and (2) permitted the dose planner more control over the evolution of the PTV's spatial dose distribution than conventional objective functions. In particular, E{sub tot}{sup sparse}-optimized plans for the pancreas case and head-and-neck case exhibited substantially improved sparing of the spinal cord and parotid glands, respectively, while maintaining or improving sparing for other OARs and markedly improving PTV homogeneity. Plan deliverability for E{sub tot}{sup sparse}-optimized plans was shown to be better than their associated clinical plans, according to the two-dimensional modulation index.Conclusions: These results suggest that our formulation may be used to improve dose-shaping and OAR-sparing for complicated disease sites, such as the pancreas or head and neck. Furthermore, our objective function and constraints are linear and constitute a linear program, which converges to the global minimum quickly, and can be easily implemented in treatment planning software. Thus, the authors expect fast translation of our method to the clinic where it may have a positive impact on plan quality for challenging disease sites.

61 RADIATION PROTECTION AND DOSIMETRY↗

Toward perturbation theory methods on a quantum computer

Perturbation theory, used in a wide range of fields, is a powerful tool for approximate solutions to complex problems, starting from the exact solution of a related, simpler problem. Advances in quantum computing, especially over the past several years, provide opportunities for alternatives to classical methods. Here, we present a general quantum circuit estimating both the energy and eigenstates corrections that is far superior to the classical version when estimating second-order energy corrections. We demonstrate our approach as applied to the two-site extended Hubbard model. In addition to numerical simulations based on qiskit, results on IBM’s quantum hardware are also presented. Our work offers a general approach to studying complex systems with quantum devices, with no training or optimization process needed to obtain the perturbative terms, which can be generalized to other Hamiltonian systems both in chemistry and physics.

97 MATHEMATICS AND COMPUTING↗

The Effect of the Deformation Parameter on the Cross Sections for Reactions: {sup 110}Pd(d,n){sup 111}Ag and {sup 110}Pd(d, 2n){sup 110m}Ag

In this study, we focused on the effects of the deformation parameter on the cross sections. First, the deformation parameters of target nucleus {sup 110}Pd was determined within the interacting boson model (IBM). Later this parameter was used in the TALYS-1.8 code to calculate the cross sections of the {sup 110}Pd(d,n){sup 111}Ag and {sup 110}Pd(d, 2n){sup 110m}Ag reactions. Moreover, other deformation parameters obtained RIPL-3 and TALYS default were used for the cross section calculation. The calculated results were compared with the experimental nuclear reaction data from EXFOR.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Demonstration of the rodeo algorithm on a quantum computer

The rodeo algorithm is an efficient algorithm for eigenstate preparation and eigenvalue estimation for any observable on a quantum computer. This makes it a promising tool for studying the spectrum and structure of atomic nuclei as well as other fields of quantum many-body physics. The only requirement is that the initial state has sufficient overlap probability with the desired eigenstate. While it is exponentially faster than well-known algorithms such as phase estimation and adiabatic evolution for eigenstate preparation, it has yet to be implemented on an actual quantum device. In this work, we apply the rodeo algorithm to determine the energy levels of a random one-qubit Hamiltonian, resulting in a relative error of 0.08% using mid-circuit measurements on the IBM Q device Casablanca. This surpasses the accuracy of directly-prepared eigenvector expectation values using the same quantum device. We take advantage of the high-accuracy energy determination and use the Hellmann-Feynman theorem to compute eigenvector expectation values for a different random one-qubit observable. For the Hellmann-Feynman calculations, we find a relative error of 0.7%. Here, we conclude by discussing possible future applications of the rodeo algorithm for multi-qubit Hamiltonians.

algorithm↗

Controlled gate networks: theory and application to eigenvalue estimation

We introduce a new scheme for quantum circuit design called controlled gate networks. Rather than trying to reduce the complexity of individual unitary operations, the new strategy is to toggle between all of the unitary operations needed with the fewest number of gates. We present the general theory of controlled gate networks and show that, under quite general conditions, it can significantly reduce the number of two-qubit gates needed to produce linear combinations of unitary operators. The first example we consider is a variational subspace calculation for a two-qubit system. The second example is estimating the eigenvalues of a two-qubit Hamiltonian via the rodeo algorithm (Choi et al. in Phys Rev Lett 127(4):040505, 2021. https://doi.org/10.1103/PhysRevLett.127.040505) using operators that we call controlled reversal gates. We use the Quantinuum H1-2 and IBM Perth devices to realize the quantum circuits. The third example is the application of controlled gate networks to the controlled time evolution of a free nucleon on a three-dimensional lattice. For all of the examples, we show very substantial reductions in the number of two-qubit gates required. Our work demonstrates that controlled gate networks are a useful tool for reducing gate complexity in quantum algorithms for quantum many-body problems such as those relevant to nuclear physics.

Bee-Lindgren, Max [Georgia Institute of Technology↗

MPI on millions of cores

Petascale parallel computers with more than a million processing cores are expected to be available in a couple of years. Although MPI is the dominant programming interface today for large-scale systems that at the highest end already have close to 300,000 processors, a challenging question to both researchers and users is whether MPI will scale to processor and core counts in the millions. In this paper, we examine the issue of scalability of MPI to very large systems. We first examine the MPI specification itself and discuss areas with scalability concerns and how they can be overcome. We then investigate issues that an MPI implementation must address in order to be scalable. To illustrate the issues, we ran a number of simple experiments to measure MPI memory consumption at scale up to 131,072 processes, or 80%, of the IBM Blue Gene/P system at Argonne National Laboratory. Based on the results, we identified nonscalable aspects of the MPI implementation and found ways to tune it to reduce its memory footprint. We also briefly discuss issues in application scalability to large process counts and features of MPI that enable the use of other techniques to alleviate scalability limitations in applications.

97 MATHEMATICS AND COMPUTING↗

Gyrokinetic toroidal simulations on leading multi- and manycore HPC systems

The gyrokinetic Particle-in-Cell (PIC) method is a critical computational tool enabling petascale fusion simulation re-search. In this work, we present novel multi- and manycore-centric optimizations to enhance performance of GTC, a PIC-based production code for studying plasma microtur-bulence in tokamak devices. Our optimizations encompass all six GTC sub-routines and include multi-level particle and grid decompositions designed to improve multi-node parallel scaling, particle binning for improved load balance, GPU acceleration of key subroutines, and memory-centric optimizations to improve single-node scaling and reduce memory utilization. The new hybrid MPI-OpenMP and MPI-OpenMP-CUDA GTC versions achieve up to a 2× speedup over the production Fortran code on four parallel systems - clusters based on the AMD Magny-Cours, Intel Nehalem-EP, IBM BlueGene/P, and NVIDIA Fermi architectures. Finally, strong scaling experiments provide insight into parallel scalability, memory utilization, and programmability trade-offs for large-scale gyrokinetic PIC simulations, while attaining a 1.6× speedup on 49,152 XE6 cores.

97 MATHEMATICS AND COMPUTING↗

Making Data Prefetch Smarter: Adaptive Prefetching on POWER7

Hardware data prefetch engines are integral parts of many general purpose server-class microprocessors in the eld to- day. Some prefetch engines allow the user to change some of their parameters. The prefetcher, however, is usually enabled in a default conguration during system bring-up and dynamic reconguration of the prefetch engine is not an autonomic feature of current machines. Conceptually, however, it is easy to infer that commonly used prefetch algorithms, when applied in a xed mode will not help per- formance in many cases. In fact, they may actually de- grade performance due to useless bus bandwidth consump- tion and cache pollution. In this paper, we present an adap- tive prefetch scheme that dynamically modies the prefetch settings in order to adapt to the workload requirements. We implement and evaluate adaptive prefetching in the con- text of an existing, commercial processor, namely the IBM POWER7. Our adaptive prefetch mechanism improves per- formance with respect to the default prefetch setting up to 2.7X and 30% for single-threaded and multiprogrammed workloads, respectively. Categories

Jimenez, Victor↗

Kinetic turbulence simulations at extreme scale on leadership-class systems

Reliable predictive simulation capability addressing confinement properties in magnetically confined fusion plasmas is critically-important for ITER, a 20 billion dollar international burning plasma device under construction in France. The complex study of kinetic turbulence, which can severely limit the energy confinement and impact the economic viability of fusion systems, requires simulations at extreme scale for such an unprecedented device size. Our newly optimized, global, ab initio particle-in-cell code solving the nonlinear equations underlying gyrokinetic theory achieves excellent performance with respect to "time to solution" at the full capacity of the IBM Blue Gene/Q on 786,432 cores of Mira at ALCF and recently of the 1,572,864 cores of Sequoia at LLNL. Recent multithreading and domain decomposition optimizations in the new GTC-P code represent critically important software advances for modern, low memory per core systems by enabling routine simulations at unprecedented size (130 million grid points ITER-scale) and resolution (65 billion particles).

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗