Performance tuning to close Ninja gap for Accelerator Physics Emulation System (APES) on Intel Xeon Phi processors
Explore the source record for details and available documents.
43 PARTICLE ACCELERATORS↗
SEARCH · Engineering Papers
Results for “performance tuning”
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.
Conversion of CO2 on a highly active and stable Cu/FeOx/CeO2 catalyst: tuning catalytic performance by oxide-oxide interactions
Explore the source record for details and available documents.
99 GENERAL AND MISCELLANEOUS↗
Methodologies and Tools for Tuning Parallel Programs: Facts and Fantasies
The need for computing power has forced a migration from serial computation on a single processor to parallel processing on multiprocessors. However, without effective means to monitor (and analyze) program execution, tuning the performance of parallel programs becomes exponentially difficult as program complexity and machine size increase. The recent introduction of performance tuning tools from various supercomputer vendors (Intel's ParAide, TMC's PRISM, CRI's Apprentice, and Convex's CXtrace) seems to indicate the maturity of performance tool technologies and vendors'/customers' recognition of their importance. However, a few important questions remain: What kind of performance bottlenecks can these tools detect (or correct)? How time consuming is the performance tuning process? What are some important technical issues that remain to be tackled in this area? This workshop reviews the fundamental concepts involved in analyzing and improving the performance of parallel and heterogeneous message-passing programs. Several alternative strategies will be contrasted, and for each we will describe how currently available tuning tools (e.g. AIMS, ParAide, PRISM, Apprentice, CXtrace, ATExpert, Pablo, IPS-2) can be used to facilitate the process. We will characterize the effectiveness of the tools and methodologies based on actual user experiences at NASA Ames Research Center. Finally, we will discuss their limitations and outline recent approaches taken by vendors and the research community to address them.
Yan, Jerry C.↗
Methodologies and Tools for Tuning Parallel Programs: 80% Art, 20% Science, and 10% Luck
The need for computing power has forced a migration from serial computation on a single processor to parallel processing on multiprocessors. However, without effective means to monitor (and analyze) program execution, tuning the performance of parallel programs becomes exponentially difficult as program complexity and machine size increase. In the past few years, the ubiquitous introduction of performance tuning tools from various supercomputer vendors (Intel's ParAide, TMC's PRISM, CRI's Apprentice, and Convex's CXtrace) seems to indicate the maturity of performance instrumentation/monitor/tuning technologies and vendors'/customers' recognition of their importance. However, a few important questions remain: What kind of performance bottlenecks can these tools detect (or correct)? How time consuming is the performance tuning process? What are some important technical issues that remain to be tackled in this area? This workshop reviews the fundamental concepts involved in analyzing and improving the performance of parallel and heterogeneous message-passing programs. Several alternative strategies will be contrasted, and for each we will describe how currently available tuning tools (e.g. AIMS, ParAide, PRISM, Apprentice, CXtrace, ATExpert, Pablo, IPS-2) can be used to facilitate the process. We will characterize the effectiveness of the tools and methodologies based on actual user experiences at NASA Ames Research Center. Finally, we will discuss their limitations and outline recent approaches taken by vendors and the research community to address them.
Yan, Jerry C.↗
Parallelizing autotuning for HPC applications: Unveiling the potential of the speculation strategy in Bayesian optimization
In the exascale computing era, tuning High-Performance Computing (HPC) applications has become a significant computational challenge. Although Bayesian optimization (BO) has emerged as a promising tool for HPC performance tuning, the BO workflow is inherently sequential (i.e., one function evaluation at a time) and cannot leverage the huge amount of parallel resources present in modern supercomputers, resulting in a considerable underutilization of their computational capabilities. This paper explores the trade-off between search quality and parallelism in BO, investigating a diverse set of methods. Building upon both previous approaches from the literature and novel methodologies introduced in this work, our study provides a deep analysis to accelerate BO performance tuning. By examining a set of synthetic functions and practical HPC applications, our exploration analyzes the interaction among various BO methods for parallelization, the quantity of parallel resources, the runtime distribution of target HPC applications, and the costs associated with different search orchestration mechanisms that have been overlooked in previous studies. Compared to sequential BO, our novel methodology achieves comparable quality while demonstrating robust scalability in search time as the amount of parallel resources increases; it also outperforms a state-of-the-art tuner, which supports parallelization, achieving up to 3.67x faster search time. We provide high-value insights for practitioners seeking to leverage the power of parallel computing for efficient HPC application tuning. Additionally, to further assist researchers in accelerating the performance tuning of their HPC applications, we provide an extension of an existing open-source tuning framework that incorporates our methods.
Bayesian optimization↗
Tuning Catalytic Performance through a Single or Sequential Post-Synthesis Reaction(s) in a Gas Phase
Catalytic performance of a bimetallic catalyst is determined by geometric structure and electronic state of the surface or even the near-surface region of the catalyst. Here we report that single and sequential postsynthesis reactions of an as-synthesized bimetallic nanoparticle catalyst in one or more gas phases can tailor surface chemistry and structure of the catalyst in a gas phase, by which catalytic performance of this bimetallic catalyst can be tuned. Pt–Cu regular nanocube (Pt–Cu RNC) and concave nanocube (Pt–Cu CNC) are chosen as models of bimetallic catalysts. Surface chemistry and catalyst structure under different reaction conditions and during catalysis were explored in gas phase of one or two reactants with ambient-pressure X-ray photoelectron spectroscopy (AP-XPS) and extended X-ray absorption fine structure (EXAFS) spectroscopy. The newly formed surface structures of Pt–Cu RNC and Pt–Cu CNC catalysts strongly depend on the reactive gas(es) used in the postsynthesis reaction(s). A reaction of Pt–Cu RNC-as synthesized with H2 at 200 °C generates a near-surface alloy consisting of a Pt skin layer, a Cu-rich subsurface, and a Pt-rich deep layer. This near-surface alloy of Pt–Cu RNC-as synthesized-H2 exhibits a much higher catalytic activity in CO oxidation in terms of a low activation barrier of 39 ± 4 kJ/mol in contrast to 128 ± 7 kJ/mol of Pt–Cu RNC-as synthesized. Here the significant decrease of activation barrier demonstrates a method to tune catalytic performances of as-synthesized bimetallic catalysts. A further reaction of Pt–Cu RNC-as synthesized-H2 with CO forms a Pt–Cu alloy surface, which exhibits quite different catalytic performance in CO oxidation. It suggests the capability of generating a different surface by using another gas. The capability of tuning surface chemistry and structure of bimetallic catalysts was also demonstrated in restructuring of Pt–Cu CNC-as synthesized.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
Tuning Photovoltaic Performance of Perovskite Nickelates Heterostructures by Changing the A-Site Rare-Earth Element
Perovskite rare-earth nickelates (RNiO3) have attracted much attention because of their exotic physical properties and rich potential applications. Here, we report systematic tuning of the electronic structures of RNiO3 (R=Nd, Sm, Gd, and Lu) by isovalent A-site substitution. By integrating RNiO3 thin films with Nb-doped SrTiO3 (NSTO), p-n heterojunction photovoltaic cells have been prepared and their performance has been investigated. The open-circuit voltage increases monotonically with decreasing A-site cation radius of RNiO3. This change results in a downward shift of the Fermi level and induces the increase in the built-in potential at the RNiO3/NSTO heterojunction, with LuNiO3/NSTO showing the largest open-circuit voltage. At the same time, the short-circuit current initially increases upon changing the A-site element from Nd to Sm. However, the larger bandgaps of GdNiO3 and LuNiO3 reduces light absorption which in turn induces a decrease in the short-circuit current. A power conversion efficiency of 1.13% has been achieved by inserting an ultrathin insulating SrTiO3 layer at the SmNiO3/NSTO interface. Our study illustrates how changing the A-site cation is an effective strategy for tuning photovoltaic performance and increasing the applicability of nickelates in optoelectric devices.
Nickelates, Oxygen vacancy, photovoltaics, p-n het↗
Performance Engineering Research Institute SciDAC-2 Enabling Technologies Institute Final Report
Enhancing the performance of SciDAC applications on petascale systems has high priority within DOE SC. As we look to the future, achieving expected levels of performance on high-end com-puting (HEC) systems is growing ever more challenging due to enormous scale, increasing archi-tectural complexity, and increasing application complexity. To address these challenges, PERI has implemented a unified, tripartite research plan encompassing: (1) performance modeling and prediction; (2) automatic performance tuning; and (3) performance engineering of high profile applications. The PERI performance modeling and prediction activity is developing and refining performance models, significantly reducing the cost of collecting the data upon which the models are based, and increasing model fidelity, speed and generality. Our primary research activity is automatic tuning (autotuning) of scientific software. This activity is spurred by the strong user preference for automatic tools and is based on previous successful activities such as ATLAS, which has automatically tuned components of the LAPACK linear algebra library, and other re-cent work on autotuning domain-specific libraries. Our third major component is application en-gagement, to which we are devoting approximately 30% of our effort to work directly with Sci-DAC-2 applications. This last activity not only helps DOE scientists meet their near-term per-formance goals, but also helps keep PERI research focused on the real challenges facing DOE computational scientists as they enter the Petascale Era.
97 MATHEMATICS AND COMPUTING↗
Critical Points Based Register-Concurrency Autotuning for GPUs
The unprecedented prevalence of GPGPU is largely attributed to its abundant on-chip register resources, which allow massively concurrent threads and extremely fast context switch. However, due to internal memory capacity constraints, there is a tradeoff between the per-thread register usage and the overall concurrency. This becomes a design problem in terms of performance tuning, since the performance “sweet spot” which can be significantly affected by these two factors is generally unknown beforehand. In this paper, we propose an effective autotuning solution to quickly and efficiently select the optimal number of registers perthread for delivering the best GPU performance. Experiments on three generations of GPUs (Nvidia Fermi, Kepler and Maxwell) demonstrate that our simple strategy can achieve an average of 10% performance improvement while a max of 50% over the original version without modifying the user program. Additionally, to reduce local cache misses due to register spilling and further improve performance, we explore three optimization schemes (i.e. bypass L1 for global memory access, enlarge local L1 cache and spill into shared memory) and discuss their impact on performance on a Kepler GPU.
auto-tuning↗
Tuning the Performance of Single-Atom Electrocatalysts: Support-Induced Structural Reconstruction
We present that creating active and stable electrocatalysts remains a highly desirable and critical goal in the fields of catalysis and clean energy conversion. Single-atom catalyst (SAC), as a new research frontier in heterogeneous catalysis, has demonstrated emerging prospects for many electrocatalytic reactions. Support assisted pyrolysis approaches are widely used in the synthesis of single-atom electrocatalysts. While extensive efforts have been devoted to increase the loading of the atomically dispersed metal sites, the role of the support in creating these active metal sites remains largely unexplored. Herein, we compare catalysts created by support-free and support-assisted pyrolysis of vitamin B12 and cobalt tetramethoxyphenylporphyrin, respectively, and demonstrate an important effect of support-induced structural reconstruction that directly controls the activation of SAC. Electrochemical studies show support-free catalysts are inactive for oxygen reduction reaction whereas the support-assisted pyrolysis yields highly active catalysts using the same molecular precursors. X-ray absorption spectroscopy experiments reveal that both the metal-nitrogen coordination and the type of nitrogen species are different in these two types of samples, which leads to a difference in the d-band of the cobalt metal center and ultimately controls the catalytic activity and stability. In conclusion, this new insight provides a unique perspective on how to tune the electrocatalytic performances of SAC at the molecular level.
30 DIRECT ENERGY CONVERSION↗
Antenna Linear-Quadratic-Gaussian (LQG) Ccontrollers: Properties, Limits of Performance, and Tuning
The LQG controllers significantly improve antenna tracking precision, but their tuning is a trial-and-error process. A control engineer has two tools to tune an LQG controller: the choice of coordinate system of the controller, and the selection of weights of the LQG performance index. The paper selects the coordinates of the open-loop model that simplify the shaping of the closed-loop performance. and analyzes the impact of thc weights on the antenna closed-loop bandwidth, disturbance rejection properties, and antenna acceleration. Finally, it presents the LQG controller tuning procedure that rationally shapes the closed-loop performance.
control technology↗
Antenna LQG Controllers: Properties, Limits of Performance, and Tuning Procedure
The LQG controllers significantly improve antenna tracking precision, but their tuning is a trial-and-error process. A control engineer has two tools to tune an LQG controller: the choice of coordinate system of the controller, and the selection of weights of the LQG performance index. The paper selects the coordinates of the open-loop model that simplify the shaping of the closed-loop performance and analyzes the impact of the weights on the antenna closed-loop bandwidth, disturbance rejection properties, and antenna acceleration. Finally, it presents the LQG controller tuning procedure that rationally shapes the closed-loop performance.
antennas↗
Antenna Linear-Quadratic-Gaussian (LQG) Controllers: Properties, Limits of Performance, and Tuning Procedure
Wind gusts are the main disturbances that depreciate tracking precision of microwave antennas and radiotelescopes. The linear-quadratic-Gaussian (LQG) controllers - as compared with the proportional-and-integral (PI) controllers significantly improve the tracking precision in wind disturbances. However, their properties have not been satisfactorily understood; consequently, their tuning is a trial-and-error process. A control engineer has two tools to tune an LQG controller: the choice of coordinate system of the controller model and the selection of weights of the LQG performance index. This article analyzes properties of an open- and closed-loop antenna. It shows that the proper choice of coordinates of the open-loop model simplifies the shaping of the closed-loop performance. The closed-loop properties are influenced by the LQG weights. The article shows the impact of the weights on the antenna closed-loop bandwidth, disturbance rejection properties, and antenna acceleration. The bandwidth and the disturbance rejection characterize the antenna performance, while the acceleration represents the performance limit set by the antenna hardware (motors). The article presents the controller tuning procedure, based on the coordinate selection and the weight properties. The procedure rationally shapes the closed-loop performance, as an alternative to the trial-and-error approach.
Gawronski, W.↗
CMS HGCAL ECON-D ASIC : Impact of CMOS fabrication process tuning on performance and radiation tolerance
The CMS experiment’s High Granularity Calorimeter (HGCAL) upgrade will replace CMS’s existing endcap calorimeters in preparation for the High Luminosity LHC. To effectively use over 6 million channels of this “imaging”calorimeter, CMS has developed two novel Endcap Concentrator (ECON) ASICs to perform data compression/selection on detector. The ECON-D ASIC operates on the 750kHz data path, and the ECON-T ASIC on the 40MHz trigger path. These 65 nm CMOS ASICs are radiation tolerant to 200 Mrad and low power, operating at less than 2.5 mW/channel. The first full-functionality prototype ECONs were produced and characterized in 2021-23, and an initial engineering run was performed in 2024. ECON-D radiation testing for the engineering run revealed that the chip’s internal SRAMs produce intermittent read errors for a non-negligible fraction of chips. Further investigation indicated that the SRAM performance is highly sensitive to the exact parameters of the CMOS fabrication process. To both study this process sensitivity and mitigate SRAM performance issues, twenty ECON wafers were produced in 2025 with a range of doping concentrations designed to tune the underlying transistor threshold voltage by 0%, 5%, 10%, and 15% from nominal. This talk will present first measurements of ECON-D performance, power consumption, and radiation tolerance for these four variations of CMOS process.
Syal, Chinar [Fermilab]↗
Boosting the Oxygen Reduction Performance via Tuning the Synergy between Metal Core and Oxide Shell of Metal−Organic Frameworks‐Derived Co@CoO x
Abstract Co core@Co oxide shell (Co@CoO x ) catalysts represent a large family with promising oxygen reduction reaction (ORR) catalytic activity. However, inadequate understanding of Co@CoO x synergy prohibits further pursuit of catalytic performance enhancement. Herein, a Co zeolitic−imidazolate framework was converted into metallic Co, followed by controlled air treatment to form Co@CoO x . The composition and structure evolution as a function of air treatment temperature were studied thoroughly through conventional and synchrotron (both ex‐situ and in‐situ) characterizations, confirming the coexistence of CoO and Co 3 O 4 in the shell. The optimal catalyst showed an ORR half‐wave potential of 0.87 V (vs. RHE) in an alkaline half‐cell and delivered high discharge capacity in an aprotic Li−O 2 battery (7,124 mAh g Cat+C −1 ) and an aqueous Zn−air battery (694 mAh g Zn −1 ) with good performance retention after durability test. Modeling simulation and density functional theory calculation confirmed the charge donation from metal core to oxide shell and shed light on new insights of how metal@metal oxide synergy impacted the ORR via tuning the charge conductivity, oxygen affinity and intermediate transfer pathway. This work opens up a venue to boost ORR catalytic activity from an interfacial synergy perspective.
Wang, Hao↗
Proactive Data Containers for Scientific Storage (Final Report)
Emerging HPC systems are expected to be deployed with an unprecedented level of complexity, due to a deep system memory/storage hierarchy and heterogeneity of the storage hardware. This hierarchy is expected to range from CPU cache through several levels of volatile memory to nonvolatile memory, traditional hard disks, and tape. Simple and efficient methods of data management and movement through this hierarchy is critical for scientific applications using exascale systems. Existing storage system and I/O (SSIO) technologies face severe challenges in dealing with these requirements. POSIX and MPI I/O standards that are the basis for existing I/O libraries and parallel file systems present fundamental challenges in the areas of scalable metadata operations, semantics-based data movement performance tuning, asynchronous operation, and support for scalable consistency of distributed operations. Moving toward new paradigms for SSIO in the extreme-scale era, we have proposed to investigate novel object-based data abstractions and storage mechanisms that take advantage of the deep storage hierarchy and enable proactive automated performance tuning. In order to achieve these overarching goals, we initiated an effort to develop a fundamental new data abstraction, called Proactive Data Containers (PDC). A PDC is a container within a locus of storage (memory, NVRAM, disk, etc.) that stores science data in an object-centric manner. Managing data as objects enables powerful optimization opportunities for data movement and transformations. The R&D focus of this project are: 1) formulation of object-oriented PDCs and their mapping in different levels of the exascale storage hierarchy; 2) efficient strategies for moving data in deep storage hierarchies using PDCs; 3) techniques for transforming and reorganizing data based on application requirements; and 4) novel analysis paradigms for enabling data transformations and user-defined analysis on data in PDCs. Toward achieving these overarching goals, we designed an object-centric application programing interface (API) for HPC, scalable metadata management for object-centric storage systems, and data movement optimizations such as Data Elevator for moving data between two levels of storage devices and TAPIOCA for efficient aggregation of data on compute nodes. We then implemented several components of the PDC system. They include metadata management, data placement services, remote procedure calls, data aggregation, etc. We have put them together into the overall PDC framework.
97 MATHEMATICS AND COMPUTING↗
A Measurement and Simulation Based Methodology for Cache Performance Modeling and Tuning
We present a cache performance modeling methodology that facilitates the tuning of uniprocessor cache performance for applications executing on shared memory multiprocessors by accurately predicting the effects of source code level modifications. Measurements on a single processor are initially used for identifying parts of code where cache utilization improvements may significantly impact the overall performance. Cache simulation based on trace-driven techniques can be carried out without gathering detailed address traces. Minimal runtime information for modeling cache performance of a selected code block includes: base virtual addresses of arrays, virtual addresses of variables, and loop bounds for that code block. Rest of the information is obtained from the source code. We show that the cache performance predictions are as reliable as those obtained through trace-driven simulations. This technique is particularly helpful to the exploration of various "what-if' scenarios regarding the cache performance impact for alternative code structures. We explain and validate this methodology using a simple matrix-matrix multiplication program. We then apply this methodology to predict and tune the cache performance of two realistic scientific applications taken from the Computational Fluid Dynamics (CFD) domain.
Waheed, Abdul↗
Interplay of molten salt and dopants in tuning the performance of single-crystalline LiNiO 2
Single-crystalline layered oxide cathodes have seen great research interest in recent years. Adoption of single-crystal morphology improves mechanical robustness and eliminates intergranular boundaries, improving the chemical stability of the cathode. Furthermore, single-crystal cathodes also suffer from worsened lithium-diffusion kinetics stemming from the significantly increased diffusion path lengths. Sluggish lithiation kinetics induce concentration gradients within the cathode particle during cell operation, resulting in the accumulation of lattice strain, which deteriorates cell performance. Foreign dopants have been shown to greatly improve ion diffusion in many high-Ni layered oxide cathode systems. In particular, we identify Ti and Te as promising dopants to ameliorate the slow diffusion kinetics. We find that doping 1 mol.% Te into single crystal LiNiO 2 greatly improves Li + diffusivity, as determined through galvanostatic intermittent titration technique. Further incorporating 2 mol.% Al and pairing with lithium-metal anode in a localized high concentration electrolyte (LHCE) delivers 206 mA h g -1 at C/3 rate and retains 94% capacity after 100 cycles in Li metal half cells. By addressing kinetically mediated degradation with Te doping, and surface-based degradation with Al and LHCE, the cathode experiences very little polarization and overpotential growth, enabling stable cycling with high accessible capacity.
25 ENERGY STORAGE↗