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 451 records · Page 25

Hydropower flexibility valuation tool for flow requirement evaluation

Timing of generation is becoming more and more valuable. This creates greater potential tension between environmental and power system objectives since both systems require their own flow patterns. Identifying win–win outcomes in this context requires being able to discuss the value of flexibility across stakeholder groups. This research proposes a two-stage optimization method to understand hydropower flexibility to meet both environmental and power system requirements. The tool simulates the two-settlement market process in the U.S. by maximizing revenues from both the day-ahead and real-time markets, subject to plant operational limits, regulatory flow and ramping requirements, and uncertainties associated with water availability and market prices. The model is formulated as linear programming problems and solved using IBM ILOG CPLEX optimizer. By examining a range of flow requirements, ramping constraints, and storage capacities, the proposed tool shows how to make more informed decisions to weigh the cost of specific flow requirements in the context of the overall license requirements. Results from the case study show that revenue is more sensitive to the ramping constraints than the minimum flow constraints. We also demonstrate that removing flow constraints in a dry month increases monthly revenue by up to 118%, as opposed to only 1% in a wet month. In addition, our results suggest that using a learning-based water flow forecast results in an increase of monthly revenue up to 6.4% compared with persistence forecast.

13 HYDRO ENERGY↗

SoK: What does it Mean to Benchmark Database Forensics?

Relational Database Management Systems are the backbone of modern enterprises and public-sector services, and are thus frequent targets of security incidents, insider threats, and thorough regulatory audits. Consequently, databases have become key sources of digital evidence, requiring investigators to reconstruct past activity from audit logs, transaction logs, and backups. Although benchmarking frameworks such as those developed by the Transaction Processing Performance Council (TPC) are widely used to evaluate database performance, they do not capture forensic requirements such as evidentiary completeness, tamper-evidence, chain of custody, or regulatory compliance under GDPR and CCPA. This survey examines the emerging domain of forensic database benchmarking. We gathered prior research on database forensics, secure logging, and tamper-evident data structures; we analyze modern forensic-ready features in commercial and open-source systems (SQL Server Ledger, Oracle Blockchain Tables, PostgreSQL pgAudit, Db2 Audit, Aurora Database Activity Streams, Oracle Real Application Security and IBM Guardium) and assess why existing benchmarks are insufficient. We propose forensic workloads, metrics, and methodologies that incorporate adversarial stressors, deleted-record recovery, and backup analysis. We also identify open research problems and call for a community-driven forensic benchmark suite. The result is an idea for evaluating not only database performance but also forensic soundness, bridging the gap between system engineering, compliance, and digital investigations.

Lenard, Ben↗

A performance comparison of current HPC systems: Blue Gene/Q, Cray XE6 and InfiniBand systems

We present here a performance analysis of three of current architectures that have become commonplace in the High Performance Computing world. Blue Gene/Q is the third generation of systems from IBM that use modestly performing cores but at large-scale in order to achieve high performance. The XE6 is the latest in a long line of Cray systems that use a 3-D topology but the first to use its Gemini interconnection network. InfiniBand provides the flexibility of using compute nodes from many vendors that can be connected in many possible topologies. The performance characteristics of each vary vastly, and the way in which nodes are allocated in each type of system can significantly impact on achieved performance. In this work we compare these three systems using a combination of micro-benchmarks and a set of production applications. In addition we also examine the differences in performance variability observed on each system and quantify the lost performance using a combination of both empirical measurements and performance models. Our results show that significant performance can be lost in normal production operation of the Cray XE6 and InfiniBand Clusters in comparison to Blue Gene/Q.

Application analysis↗

Scaling Deep Learning workloads: NVIDIA DGX-1/Pascal and Intel Knights Landing

Deep Learning (DL) algorithms have become ubiquitous in data analytics. As a result, major computing vendors—including NVIDIA, Intel, AMD, and IBM—have architectural road maps influenced by DL workloads. Furthermore, several vendors have recently advertised new computing products as accelerating large DL workloads. Unfortunately, it is difficult for data scientists to quantify the potential of these different products. Here, this article provides a performance and power analysis of important DL workloads on two major parallel architectures: NVIDIA DGX-1 (eight Pascal P100 GPUs interconnected with NVLink) and Intel Knights Landing (KNL) CPUs interconnected with Intel Omni-Path or Cray Aries. Our evaluation consists of a cross section of convolutional neural net workloads: CifarNet, AlexNet, GoogLeNet, and ResNet50 topologies using the Cifar10 and ImageNet datasets. The workloads are vendor-optimized for each architecture. We use sequentially equivalent implementations to maintain iso-accuracy between parallel and sequential DL models. Our analysis indicates that although GPUs provide the highest overall performance, the gap can close for some convolutional networks; and the KNL can be competitive in performance/watt. We find that NVLink facilitates scaling efficiency on GPUs. However, its importance is heavily dependent on neural network architecture. Furthermore, for weak-scaling—sometimes encouraged by restricted GPU memory—NVLink is less important.

97 MATHEMATICS AND COMPUTING↗

Long-Term Bone Marrow Suppression During Postoperative Chemotherapy in Rectal Cancer Patients After Preoperative Chemoradiation Therapy

Purpose/Objective(s): To quantify ensuing bone marrow (BM) suppression during postoperative chemotherapy resulting from preoperative chemoradiation (CRT) therapy for rectal cancer. Methods and Materials: We retrospectively evaluated 35 patients treated with preoperative CRT followed by postoperative 5-Fluorouracil and oxaliplatin (OxF) chemotherapy for locally advanced rectal cancer. The pelvic bone marrow (PBM) was divided into ilium (IBM), lower pelvis (LPBM), and lumbosacrum (LSBM). Dose volume histograms (DVH) measured the mean doses and percentage of BM volume receiving between 5-40 Gy (i.e.: PBM-V5, LPBM-V5). The Wilcoxon signed rank tests evaluated the differences in absolute hematologic nadirs during neoadjuvant vs. adjuvant treatment. Logistic regressions evaluated the association between dosimetric parameters and ≥ grade 3 hematologic toxicity (HT3) and hematologic event (HE) defined as ≥ grade 2 HT and a dose reduction in OxF. Receiver Operator Characteristic (ROC) curves were constructed to determine optimal threshold values leading to HT3. Results: During OxF chemotherapy, 40.0% (n=14) and 48% (n=17) of rectal cancer patients experienced HT3 and HE, respectively. On multivariable logistic regression, increasing pelvic mean dose (PMD) and lower pelvis mean dose (LPMD) along with increasing PBM-V (25-40), LPBM-V25, and LPBM-V40 were significantly associated with HT3 and/or HE during postoperative chemotherapy. Exceeding ≥36.6 Gy to the PMD and ≥32.6 Gy to the LPMD strongly correlated with causing HT3 during postoperative chemotherapy. Conclusions: Neoadjuvant RT for rectal cancer has lasting effects on the pelvic BM, which are demonstrable during adjuvant OxF. Sparing of the BM during preoperative CRT can aid in reducing significant hematologic adverse events and aid in tolerance of postoperative chemotherapy.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Direct coupling of a genome-scale microbial in silico model and a groundwater reactive transport model

The activity of microorganisms often plays an important role in dynamic natural attenuation or engineered bioremediation of subsurface contaminants, such as chlorinated solvents, metals, and radionuclides. To evaluate and/or design bioremediated systems, quantitative reactive transport models are needed. State-of-the-art reactive transport models often ignore the microbial effects or simulate the microbial effects with static growth yield and constant reaction rate parameters over simulated conditions, while in reality microorganisms can dynamically modify their functionality (such as utilization of alternative respiratory pathways) in response to spatial and temporal variations in environmental conditions. Constraint-based genome-scale microbial in silico models, using genomic data and multiple-pathway reaction networks, have been shown to be able to simulate transient metabolism of some well studied microorganisms and identify growth rate, substrate uptake rates, and byproduct rates under different growth conditions. These rates can be identified and used to replace specific microbially-mediated reaction rates in a reactive transport model using local geochemical conditions as constraints. We previously demonstrated the potential utility of integrating a constraint based microbial metabolism model with a reactive transport simulator as applied to bioremediation of uranium in groundwater. However, that work relied on an indirect coupling approach that was effective for initial demonstration but may not be extensible to more complex problems that are of significant interest (e.g., communities of microbial species, multiple constraining variables). Here, we extend that work by presenting and demonstrating a method of directly integrating a reactive transport model (FORTRAN code) with constraint-based in silico models solved with IBM ILOG CPLEX linear optimizer base system (C library). The models were integrated with BABEL, a language interoperability tool. The modeling system is designed in such a way that constraint-based models targeting different microorganisms or competing organism communities can be easily plugged into the system. Constraint-based modeling is very costly given the size of a genome-scale reaction network. To save computation time, a binary tree is traversed to examine the concentration and solution pool generated during the simulation in order to decide whether the constraint-based model should be called. We also show preliminary results from the integrated model including a comparison of the direct and indirect coupling approaches.

54 ENVIRONMENTAL SCIENCES↗

Performance of a parallel algebraic multilevel preconditioner for stabilized finite element semiconductor device modeling

In this study results are presented for the large-scale parallel performance of an algebraic multilevel preconditioner for solution of the drift-diffusion model for semiconductor devices. The preconditioner is the key numerical procedure determining the robustness, efficiency and scalability of the fully-coupled Newton-Krylov based, nonlinear solution method that is employed for this system of equations. The coupled system is comprised of a source term dominated Poisson equation for the electric potential, and two convection-diffusion-reaction type equations for the electron and hole concentration. The governing PDEs are discretized in space by a stabilized finite element method. Solution of the discrete system is obtained through a fully-implicit time integrator, a fully-coupled Newton-based nonlinear solver, and a restarted GMRES Krylov linear system solver. The algebraic multilevel preconditioner is based on an aggressive coarsening graph partitioning of the nonzero block structure of the Jacobian matrix. Representative performance results are presented for various choices of multigrid V-cycles and W-cycles and parameter variations for smoothers based on incomplete factorizations. Parallel scalability results are presented for solution of up to 10{sup 8} unknowns on 4096 processors of a Cray XT3/4 and an IBM POWER eServer system.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Towards oscillation-free implementation of the immersed boundary method with spectral-like methods

Highlights: {yields} A radial basis function based smoothing technique is introduced. {yields} It is more general and easier to implement compared to other techniques. {yields} With this technique, a combined immersed boundary and spectral method is developed. {yields} It is shown that the proposed method works better in terms of reducing the non-physical Gibbs oscillation. - Abstract: It is known that, when the immersed boundary method (IBM) is implemented within spectral-like methods, the Gibbs oscillation seriously deteriorates the calculation of derivatives near the body surface. In this paper, a radial basis function (RBF) based smoothing technique is proposed with the intention of eliminating or efficiently reducing the Gibbs oscillation without affecting the flow field outside the body. Based on this technique, a combined IBM/spectral scheme is developed to solve the incompressible Navier-Stokes equations. Numerical simulations of flow through a periodic lattice of cylinders of various cross sections are performed. The results demonstrate that the proposed methodology is able to give accurate and nearly oscillation-free numerical solutions of incompressible viscous flows.

97 MATHEMATICS AND COMPUTING↗

Surface fluctuating hydrodynamics methods for the drift-diffusion dynamics of particles and microstructures within curved fluid interfaces

Here we introduce fluctuating hydrodynamics approaches on surfaces for capturing the drift-diffusion dynamics of particles and microstructures immersed within curved fluid interfaces of spherical shape. We take into account the interfacial hydrodynamic coupling, traction coupling with the surrounding bulk fluid, and thermal fluctuations. For fluid-structure interactions, we introduce Immersed Boundary Methods (IBM) and related Stochastic Eulerian-Lagrangian Methods (SELM) for curved surfaces. We use these approaches to investigate the statistics of surface fluctuating hydrodynamics and microstructures. For velocity autocorrelations, we find characteristic power-law scalings $τ^{-1}, τ^{-2}$, and plateaus can emerge. This depends on the physical regime associated with the geometry, surface viscosity, and bulk viscosity. This differs from the characteristic $τ^{-3/2}$ scaling for bulk three dimensional fluids. We develop theory explaining these observed power-laws associated with time-scales for dissipation within the fluid interface and coupling to the surrounding fluid. We then use our introduced methods to investigate a few example systems and roles of hydrodynamic coupling and thermal fluctuations including for the kinetics of passive particles and active microswimmers in curved fluid interfaces.

97 MATHEMATICS AND COMPUTING↗

Analysis of Vector Particle-In-Cell (VPIC) memory usage optimizations on cutting-edge computer architectures

Vector Particle-In-Cell (VPIC) is one of the fastest plasma simulation codes in the world, with particle numbers ranging from one trillion on the first petascale system, Roadrunner, to ten trillion particles on the more recent Blue Waters supercomputer. As supercomputers continue to grow rapidly in size, so too does the gap between computing capability and memory capability. Current memory systems limit VPIC simulations greatly as the maximum number of particles that can be simulated directly depends on the available memory. In this study, we present a suite of VPIC memory optimizations (i.e., particle weight, half-precision, and fixed-point optimizations) that enable a significant increase in the number of particles in VPIC simulations. Here, we assess the optimizations’ impact on memory and runtime performance for a suite of cutting-edge computer architectures such has the NVIDIA V100 GPU, the IBM Power9, and the Fujitsu A64FX architectures. Our optimizations enable a 31.25% reduction in memory usage and up to 40% increase in the number of particles. This paper extends our work on developing particle storage format optimizations Tan et al.

97 MATHEMATICS AND COMPUTING↗

Cross-scale efficient tensor contractions for coupled cluster computations through multiple programming model backends

Coupled-cluster methods provide highly accurate models of molecular structure through explicit numerical calculation of tensors representing the correlation between electrons. These calculations are dominated by a sequence of tensor contractions, motivating the development of numerical libraries for such operations. While based on matrix–matrix multiplication, these libraries are specialized to exploit symmetries in the molecular structure and in electronic interactions, and thus reduce the size of the tensor representation and the complexity of contractions. The resulting algorithms are irregular and their parallelization has been previously achieved via the use of dynamic scheduling or specialized data decompositions. We introduce our efforts to extend the Libtensor framework to work in the distributed memory environment in a scalable and energy-efficient manner. We achieve up to 240× speedup compared with the optimized shared memory implementation of Libtensor. We attain scalability to hundreds of thousands of compute cores on three distributed-memory architectures (Cray XC30 and XC40, and IBM Blue Gene/Q), and on a heterogeneous GPU-CPU system (Cray XK7). As the bottlenecks shift from being compute-bound DGEMM's to communication-bound collectives as the size of the molecular system scales, we adopt two radically different parallelization approaches for handling load-imbalance, tasking and bulk synchronous models. Nevertheless, we preserve a unified interface to both programming models to maintain the productivity of computational quantum chemists.

97 MATHEMATICS AND COMPUTING↗

A 15GSa/s, 1.5GHz bandwidth waveform digitizing ASIC

The PSEC4 custom integrated circuit was designed for the recording of fast waveforms for use in large-area time-of-flight detector systems. The ASIC has been fabricated using the IBM-8RF 0.13 micron CMOS process. On each of 6 analog channels, PSEC4 employs a switched capacitor array (SCA) 256 samples deep, a ramp-compare ADC with 10.5 bits of DC dynamic range, and a serial data readout with the capability of region-of-interest windowing to reduce dead time. The sampling rate can be adjusted between 4 and 15 Gigasamples/second [GSa/s] on all channels and is servo-controlled on-chip with a low-jitter delay-locked loop (DLL). The input signals are passively coupled on-chip with a -3 dB analog bandwidth of 1.5 GHz. The power consumption in quiescent sampling mode is less than 50 mW/chip; at a sustained trigger and readout rate of 50 kHz the chip draws 100 mW. After fixed-pattern pedestal subtraction, the uncorrected integral non-linearity is 0.15% over an 750 mV dynamic range. With a linearity correction, a full 1 V signal voltage range is available.The sampling timebase has a fixed-pattern non-linearity with an RMS of 13%, which can be corrected for precision waveform feature extraction and timing.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Interface tracking simulations of bubbly flows in PWR relevant geometries

[en] Highlights: • Simulations were performed for turbulent bubbly flows in PWR subchannel geometry. • Liquid turbulence is fully resolved by direct numerical simulation approach. • Bubble behavior is captured using level-set interface tracking method. • Time-averaged single- and two-phase turbulent flow statistical quantities are obtained. - Abstract: The advances in high performance computing (HPC) have allowed direct numerical simulation (DNS) approach coupled with interface tracking methods (ITM) to perform high fidelity simulations of turbulent bubbly flows in various complex geometries. In this work, we have chosen the geometry of the pressurized water reactor (PWR) core subchannel to perform a set of interface tracking simulations (ITS) with fully resolved liquid turbulence. The presented research utilizes a massively parallel finite-element based code, PHASTA, for the subchannel geometry simulations of bubbly flow turbulence. The main objective for this research is to demonstrate the ITS capabilities in gaining new insight into bubble/turbulence interactions and assisting the development of improved closure laws for multiphase computational fluid dynamics (M-CFD). Both single- and two-phase turbulent flows were studied within a single PWR subchannel. The analysis of numerical results includes the mean gas and liquid velocity profiles, void fraction distribution and turbulent kinetic energy profiles. Two sets of flow rates and bubble sizes were used in the simulations. The chosen flow rates corresponded to the Reynolds numbers of 29,079 and 80,775 based on channel hydraulic diameter (D_h) and mean velocity. The finite element unstructured grids utilized for these simulations include 53.8 million and 1.11 billion elements, respectively. This has allowed to fully resolve all the turbulence scales and the deformable interfaces of individual bubbles. For the two-phase flow simulations, a 1% bubble volume fraction was used which resulted in 17 bubbles in the smaller case and 262 bubbles in the larger case. In the larger simulation case the size of the resolved bubbles is 0.65 mm in diameter, and the bulk mesh cell size is about 30 microns. Those large-scale simulations provide new level of details previously unavailable and were enabled by the excellent scaling performance of our two-phase flow solver and access to the state-of-the-art supercomputing resources. The presented simulations used up to 256 thousand processing threads on the IBM BG/Q supercomputer “Mira” (Argonne National Laboratory).

Nuclear Science & Technology↗

Tuning collective communication for Partitioned Global Address Space programming models

Partitioned Global Address Space (PGAS) languages offer programmers the convenience of a shared memory programming style combined with locality control necessary to run on large-scale distributed memory systems. Even within a PGAS language programmers often need to perform global communication operations such as broadcasts or reductions, which are best performed as collective operations in which a group of threads work together to perform the operation. In this study we consider the problem of implementing collective communication within PGAS languages and explore some of the design trade-offs in both the interface and implementation. In particular, PGAS collectives have semantic issues that are different than in send–receive style message passing programs, and different implementation approaches that take advantage of the one-sided communication style in these languages. We present an implementation framework for PGAS collectives as part of the GASNet communication layer, which supports shared memory, distributed memory and hybrids. The framework supports a broad set of algorithms for each collective, over which the implementation may be automatically tuned. In conclusion, we demonstrate the benefit of optimized GASNet collectives using application benchmarks written in UPC, and demonstrate that the GASNet collectives can deliver scalable performance on a variety of state-of-the-art parallel machines including a Cray XT4, an IBM BlueGene/P, and a Sun Constellation system with InfiniBand interconnect.

97 MATHEMATICS AND COMPUTING↗

A scalable infrastructure for the performance analysis of passive target synchronization

Partitioned global address space (PGAS) languages combine the convenient abstraction of shared memory with the notion of affinity, extending multi-threaded programming to large-scale systems with physically distributed memory. However, in spite of their obvious advantages, PGAS languages still lack appropriate tool support for performance analysis, one of the reasons why their adoption is still in its infancy. Some of the performance problems for which tool support is needed occur at the level of the underlying one-sided communication substrate, such as the Aggregate Remote Memory Copy Interface (ARMCI). One such example is the waiting time in situations where asynchronous data transfers cannot be completed without software in- tervention at the target side. This is not uncommon on systems with reduced operating-system kernels such as IBM Blue Gene/P where the use of progress threads would double the number of cores necessary to run an application. In this paper, we present an extension of the Scalasca trace-analysis infrastructure aimed at the identification and quantification of progress-related waiting times at larger scales. We demonstrate its utility and scalability using a benchmark running with up to 32,768 processes.

performance analysis, event tracing, one-sided com↗

I/O-aware bandwidth allocation for petascale computing systems

In the Big Data era, the gap between the storage performance and an appli- cation's I/O requirement is increasing. I/O congestion caused by concurrent storage accesses from multiple applications is inevitable and severely harms the performance. Conventional approaches either focus on optimizing an ap- plication's access pattern individually or handle I/O requests on a low-level storage layer without any knowledge from the upper-level applications. In this paper, we present a novel I/O-aware bandwidth allocation framework to coordinate ongoing I/O requests on petascale computing systems. The motivation behind this innovation is that the resource management system has a holistic view of both the system state and jobs' activities and can dy- namically control the jobs' status or allocate resource on the y during their execution. We treat a job's I/O requests as periodical subjobs within its lifecycle and transform the I/O congestion issue into a classical scheduling problem. Based on this model, we propose a bandwidth management mech- anism as an extension to the existing scheduling system. We design several bandwidth allocation policies with different optimization objectives either on user-oriented metrics or system performance. We conduct extensive trace- based simulations using real job traces and I/O traces from a production IBM Blue Gene/Q system at Argonne National Laboratory. Experimental results demonstrate that our new design can improve job performance by more than 30%, as well as increasing system performance.

I/O congestion↗

Asynchronous Two-Level Checkpointing Scheme for Large-Scale Adjoints in the Spectral-Element Solver Nek5000

Adjoints are an important computational tool for large-scale sensitivity evaluation, uncertainty quantification, and derivative-based optimization. An essential component of their performance is the storage/recomputation balance in which efficient checkpointing methods play a key role. We introduce a novel asynchronous two-level adjoint checkpointing scheme for multistep numerical time discretizations targeted at large-scale numerical simulations. The checkpointing scheme combines bandwidth-limited disk checkpointing and binomial memory checkpointing. Based on assumptions about the target petascale systems, which we later demonstrate to be realistic on the IBM Blue Gene/Q system Mira, we create a model of the expected performance of our checkpointing approach and validate it using the highly scalable Navier-Stokes spectralelement solver Nek5000 on small to moderate subsystems of the Mira supercomputer. In turn, this allows us to predict optimal algorithmic choices when using all of Mira. We also demonstrate that two-level checkpointing is significantly superior to single-level checkpointing when adjoining a large number of time integration steps. To our knowledge, this is the first time two-level checkpointing had been designed, implemented, tuned, and demonstrated on fluid dynamics codes at large scale of 50k+ cores.

Adjoints↗

Longitudinal analysis of risk factors for dementia based on Mild Cognitive Impairment Screen results and questionnaire responses from healthy Japanese individuals registered in an online database

Abstract Introduction Despite an urgent need for developing remedial measures against dementia, no disease‐modifying drugs have been developed. Efficient protocols for participant recruitment need to be established for conducting clinical trials. To meet this need, a large‐scale online registry system, the Integrated Registry of Orange Plan (IROOP ® ), was created for healthy individuals. Although the risk factors for dementia have been discussed in our previous studies for a short interval of 6 months, some factors remain controversial. The present study aimed to explore factors affecting longitudinal changes in cognitive function for a longer interval of 18 months using the IROOP ® data. Methods This study assessed the longitudinal changes in the collated data for predicting the risk of dementia and included 473 individuals (175 men and 298 women; mean age 59.6 ± 10.1 years) registered in the IROOP ® between July 5, 2016 and January 15, 2018 who completed the initial questionnaire and brief assessment of cognitive function (Mild Cognitive Impairment Screen) at baseline and the regular questionnaire and the Mild Cognitive Impairment Screen at least once after baseline. Statistical analyses were performed using IBM SPSS, version 23.0, for Windows for demographic data and the MIXED procedure in SAS, version 9.4, for the linear mixed‐effect model. In each analysis, the statistical significance level was set at P < .05. Results Mood, sleep, quality of life, and medical histories including cognition were found to influence longitudinal changes in cognitive function. Discussion Given the multifactorial etiology of dementia, preventive measures targeting multiple domains are required for maintaining cognitive function, instead of focusing on one lifestyle factor.

Ogawa, Masayo↗