Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Ivy bridge”

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.

8 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2017

A Locality-Based Threading Algorithm for the Configuration-Interaction Method

The Configuration Interaction (CI) method has been widely used to solve the non-relativistic many-body Schrodinger equation. One great challenge to implementing it efficiently on manycore architectures is its immense memory and data movement requirements. To address this issue, within each node, we exploit a hybrid MPI+OpenMP programming model in lieu of the traditional flat MPI programming model. Here in this paper, we develop optimizations that partition the workloads among OpenMP threads based on data locality,-which is essential in ensuring applications with complex data access patterns scale well on manycore architectures. The new algorithm scales to 256 threadson the 64-core Intel Knights Landing (KNL) manycore processor and 24 threads on dual-socket Ivy Bridge (Xeon) nodes. Compared with the original implementation, the performance has been improved by up to 7× on theKnights Landing processor and 3× on the dual-socket Ivy Bridge node.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2014

Characterization of UMT2013 Performance on Advanced Architectures

This paper presents part of a larger effort to make detailed assessments of several proxy applications on various advanced architectures, with the eventual goal of extending these assessments to codes of programmatic interest running more realistic simulations. The focus here is on UMT2013, a proxy implementation of deterministic transport for unstructured meshes. I present weak and strong MPI scaling results and studies of OpenMP efficiency on the Sequoia BG/Q system at LLNL, with comparison against similar tests on an Intel Sandy Bridge TLCC2 system. The hardware counters on BG/Q provide detailed information on many aspects of on-node performance, while information from the mpiP tool gives insight into the reasons for the differing scaling behavior on these two different architectures. Preliminary tests that exploit NVRAM as extended memory on an Ivy Bridge machine designed for “Big Data” applications are also included.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2014

MIC-SVM: Designing A Highly Efficient Support Vector Machine For Advanced Modern Multi-Core and Many-Core Architectures

Support Vector Machine (SVM) has been widely used in data-mining and Big Data applications as modern commercial databases start to attach an increasing importance to the analytic capabilities. In recent years, SVM was adapted to the field of High Performance Computing for power/performance prediction, auto-tuning, and runtime scheduling. However, even at the risk of losing prediction accuracy due to insufficient runtime information, researchers can only afford to apply offline model training to avoid significant runtime training overhead. To address the challenges above, we designed and implemented MICSVM, a highly efficient parallel SVM for x86 based multi-core and many core architectures, such as the Intel Ivy Bridge CPUs and Intel Xeon Phi coprocessor (MIC).

42 ENGINEERING↗
DOE OSTI2017

A Work-Efficient Parallel Sparse Matrix-Sparse Vector Multiplication Algorithm

We design and develop a work-efficient multithreaded algorithm for sparse matrix-sparse vector multiplication (SpMSpV) where the matrix, the input vector, and the output vector are all sparse. SpMSpV is an important primitive in the emerging GraphBLAS standard and is the workhorse of many graph algorithms including breadth-first search, bipartite graph matching, and maximal independent set. As thread counts increase, existing multithreaded SpMSpV algorithms can spend more time accessing the sparse matrix data structure than doing arithmetic. Our shared-memory parallel SpMSpV algorithm is work efficient in the sense that its total work is proportional to the number of arithmetic operations required. The key insight is to avoid each thread individually scan the list of matrix columns. Our algorithm is simple to implement and operates on existing column-based sparse matrix formats. It performs well on diverse matrices and vectors with heterogeneous sparsity patterns. A high-performance implementation of the algorithm attains up to 15x speedup on a 24-core Intel Ivy Bridge processor and up to 49x speedup on a 64-core Intel KNL manycore processor. In contrast to implementations of existing algorithms, the performance of our algorithm is sustained on a variety of different input types include matrices representing scale-free and high-diameter graphs.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2015

Parallel Application Performance on Two Generations of Intel Xeon HPC Platforms

Two next-generation node configurations hosting the Haswell microarchitecture were tested with a suite of microbenchmarks and application examples, and compared with a current Ivy Bridge production node on NREL" tm s Peregrine high-performance computing cluster. A primary conclusion from this study is that the additional cores are of little value to individual task performance--limitations to application parallelism, or resource contention among concurrently running but independent tasks, limits effective utilization of these added cores. Hyperthreading generally impacts throughput negatively, but can improve performance in the absence of detailed attention to runtime workflow configuration. The observations offer some guidance to procurement of future HPC systems at NREL. First, raw core count must be balanced with available resources, particularly memory bandwidth. Balance-of-system will determine value more than processor capability alone. Second, hyperthreading continues to be largely irrelevant to the workloads that are commonly seen, and were tested here, at NREL. Finally, perhaps the most impactful enhancement to productivity might occur through enabling multiple concurrent jobs per node. Given the right type and size of workload, more may be achieved by doing many slow things at once, than fast things in order.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

First-Principles Dissociation Pathways of BCl 3 on the Si(100)-2 × 1 Surface

BCl 3 is a promising acceptor precursor for atomic-precision δ-doping of silicon, as it has been observed to rapidly dissociate into boron doped into the silicon surface and surface chlorine, which can be removed upon annealing. The chemical pathway and the resulting kinetics, through which BCl 3 adsorbs and dissociates on silicon, however, have only been partially explained. Here, in this work, we use density functional theory to expand the dissociation reactions of BCl 3 to include reactions that take place across multiple silicon dimer rows and reactions which end in a bare B atom either at the surface, substituted for a surface silicon, or in a subsurface position. We further simulate the resulting scanning tunneling microscopy images for each of these BCl x dissociation fragments, demonstrating that they often display distinct features that may allow for relatively confident experimental identification. Finally, we input the full dissociation pathway for BCl 3 into a kinetic Monte Carlo model, which simulates realistic reaction pathways as a function of environmental conditions, such as the pressure and temperature of dosing. We find that BCl 2 is broadly dominant at low temperatures, while high temperatures and ample space on the silicon surface for dissociation encourage the formation of bridging BCl fragments and B substitutions on the surface. This work provides the chemical mechanisms for understanding atomic-precision doping of Si with B, enabling a number of relevant quantum applications, such as bipolar nanoelectronics, acceptor-based qubits, and superconducting Si.

Campbell, Quinn T. [Sandia National Laboratories (↗
DOE OSTI2025

High-Resolution Model Intercomparison Project phase 2 (HighResMIP2) towards CMIP7

Abstract. Robust projections and predictions of climate variability and change, particularly at regional scales, rely on the driving processes being represented with fidelity in model simulations. Consequently, the role of enhanced horizontal resolution in improved process representation in all components of the climate system continues to be of great interest. Recent simulations suggest the possibility of significant changes in both large-scale aspects of the ocean and atmospheric circulations and in the regional responses to climate change, as well as improvements in representations of small-scale processes and extremes, when resolution is enhanced. The first phase of the High-Resolution Model Intercomparison Project (HighResMIP1) was successful at producing a baseline multi-model assessment of global simulations with model grid spacings of 25–50 km in the atmosphere and 10–25 km in the ocean, a significant increase when compared to models with standard resolutions on the order of 1° that are typically used as part of the Coupled Model Intercomparison Project (CMIP) experiments. In addition to over 250 peer-reviewed manuscripts using the published HighResMIP1 datasets, the results were widely cited in the Intergovernmental Panel on Climate Change report and were the basis of a variety of derived datasets, including tracked cyclones (both tropical and extratropical), river discharge, storm surge, and impact studies. There were also suggestions from the few ocean eddy-rich coupled simulations that aspects of climate variability and change might be significantly influenced by improved process representation in such models. The compromises that HighResMIP1 made should now be revisited, given the recent major advances in modelling and computing resources. Aspects that will be reconsidered include experimental design and simulation length, complexity, and resolution. In addition, larger ensemble sizes and a wider range of future scenarios would enhance the applicability of HighResMIP. Therefore, we propose the High-Resolution Model Intercomparison Project phase 2 (HighResMIP2) to improve and extend the previous work, to address new science questions, and to further advance our understanding of the role of horizontal resolution (and hence process representation) in state-of-the-art climate simulations. With further increases in high-performance computing resources and modelling advances, along with the ability to take full advantage of these computational resources, an enhanced investigation of the drivers and consequences of variability and change in both large- and synoptic-scale weather and climate is now possible. With the arrival of global cloud-resolving models (currently run for relatively short timescales), there is also an opportunity to improve links between such models and more traditional CMIP models, with HighResMIP providing a bridge to link understanding between these domains. HighResMIP also aims to link to other CMIP projects and international efforts such as the World Climate Research Program lighthouse activities and various digital twin initiatives. It also has the potential to be used as training and validation data for the fast-evolving machine learning climate models.

54 ENVIRONMENTAL SCIENCES↗