Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Multiple processors”

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 379 records · Page 21

Parallel hybrid quantum-classical machine learning for kernelized time-series classification

Supervised time-series classification garners widespread interest because of its applicability throughout a broad application domain including finance, astronomy, biosensors, and many others. Here, in this work, we tackle this problem with hybrid quantum-classical machine learning, deducing pairwise temporal relationships between time-series instances using a timeseries Hamiltonian kernel (TSHK). A TSHK is constructed with a sum of inner products generated by quantum states evolved using a parameterized time evolution operator. This sum is then optimally weighted using techniques derived from multiple kernel learning. Because we treat the kernel weighting step as a differentiable convex optimization problem, our method can be regarded as an end-to-end learnable hybrid quantum-classical-convex neural network, or QCC-net, whose output is a data set-generalized kernel function suitable for use in any kernelized machine learning technique such as the support vector machine (SVM). Using our TSHK as input to a SVM, we classify univariate and multivariate time-series using quantum circuit simulators and demonstrate the efficient parallel deployment of the algorithm to 127-qubit superconducting quantum processors using quantum multi-programming.

97 MATHEMATICS AND COMPUTING↗

ML–Enabled FPGA Framework for Fast Quantum State Discrimination in Mid-Circuit Measurement Regimes

Accurate and low-latency quantum state discrimination is essential for protocols involving mid-circuit measurement (MCM) and conditional feed-forward. In superconducting quantum systems, conventional readout pipelines transfer measurement data to host processors for post-processing, introducing millisecond-scale delays that far exceed qubit coherence times. To overcome this bottleneck, we present an in-situ machine learning (ML) inference engine implemented on an FPGA for real-time quantum state discrimination. Our design performs inference directly on digitized readout signals with 40 ns latency, supports both qubit and qutrit readout, and enables conditional operations without host-side intervention. This capability is critical for MCM and for feedback-driven protocols such as quantum error correction. We validate the system on superconducting transmon hardware, demonstrating robust discrimination fidelity across multiple qubit and qutrit channels. We further demonstrate conditional qutrit logic driven by FPGA-resident classification, highlighting the potential of low-latency ML-on-FPGA control for NISQ applications and scalable fault-tolerant quantum computing.

Vora, Neel [Lawrence Berkeley National Laboratory ↗

EMPIRE-PIC: A Performance Portable Unstructured Particle-in-Cell Code

In this study we introduce EMPIRE-PIC, a finite element method particle-in-cell (FEM-PIC) application developed at Sandia National Laboratories. The code has been developed in C++ using the Trilinos library and the Kokkos Performance Portability Framework to enable running on multiple modern compute architectures while only requiring maintenance of a single codebase. EMPIRE-PIC is capable of solving both electrostatic and electromagnetic problems in two- and three-dimensions to second-order accuracy in space and time. In this paper we validate the code against three benchmark problems — a simple electron orbit, an electrostatic Langmuir wave, and a transverse electromagnetic wave propagating through a plasma. We demonstrate the performance of EMPIRE-PIC on four different architectures: Intel Haswell CPUs, Intel's Xeon Phi Knights Landing, ARM Thunder-X2 CPUs, and NVIDIA Tesla V100 GPUs attached to IBM POWER9 processors. This analysis demonstrates scalability of the code up to more than two thousand GPUs, and greater than one hundred thousand CPUs.

97 MATHEMATICS AND COMPUTING↗

Snowflake: A Lightweight Portable Stencil DSL

Stencil computations are not well optimized by general-purpose production compilers and the increased use of multicore, manycore, and accelerator-based systems makes the optimization problem even more challenging. In this paper we present Snowflake, a Domain Specific Language (DSL) for stencils that uses a 'micro-compiler' approach, i.e., small, focused, domain-specific code generators. The approach is similar to that used in image processing stencils, but Snowflake handles the much more complex stencils that arise in scientific computing, including complex boundary conditions, higher-order operators (larger stencils), higher dimensions, variable coefficients, non-unit-stride iteration spaces, and multiple input or output meshes. Snowflake is embedded in the Python language, allowing it to interoperate with popular scientific tools like SciPy and iPython; it also takes advantage of built-in Python libraries for powerful dependence analysis as part of a just-in-time compiler. We demonstrate the power of the Snowflake language and the micro-compiler approach with a complex scientific benchmark, HPGMG, that exercises the generality of stencil support in Snowflake. By generating OpenMP comparable to, and OpenCL within a factor of 2x of hand-optimized HPGMG, Snowflake demonstrates that a micro-compiler can support diverse processor architectures and is performance-competitive whilst preserving a high-level Python implementation.

97 MATHEMATICS AND COMPUTING↗

MODAL FREQUENCY TRACKING: Performance Analysis on Noisy Experimental Ground Test Data

Mechanical devices operating in an environment contaminated by noise, uncertainties, and extraneous disturbances lead to low signal-to-noise-ratios creating an extremely challenging signal processing problem—especially for on-line, realtime, in-flight application. In this report, we discuss a model-based approach to incorporate physical device features into a dynamic structure that can be used to perform on-line tracking of modal frequencies. The approach we take, after pre-processing the raw measurement data, is to obtain a representation of the structural device under test that captures its underlying response to a suite of excitations and operating conditions. One approach is to apply modern system identification techniques based on stochastic subspace methods capable of both: (1) identifying the underlying black-box structure enabling the extraction of structural modes that can be used for analysis; and (2) modal tracking under continued vibrational excitation as in a real-time, in-flight like environment. The vibrational signature of the structural device is measured directly using a suite of tri-axial accelerometers characterizing a multiple input/multiple output (MIMO) dynamic system. In this analysis, we have 15 tri-axial accelerometer measurements or 45 total output channels along with a single excitation also measured with a tri-axial accelerometer providing a 3-input system for processing. We initially describe the experiment and then briefly develop the necessary background in stochastic subspace realization, discuss the algorithm and apply it to the isolated structural device, first, characterized by the set of noisy MIMO accelerometer measurements extracting the modal model from the data (subspace identification), extract the unique modal frequencies (modal coordinate transformation), track their evolution (real-time tracker) to evaluate the overall performance of the processor. Next we evaluate processor performance when the structural device is incorporated into a flight vehicle for further performance analysis. We summarize the results and predict performance.

42 ENGINEERING↗

Mode-multiplexed photonic integrated vector dot-product core from inverse design

Photonic computing has the potential to harness the full degrees of freedom (DOFs) of the light field, including the wavelength, spatial mode, spatial location, phase quadrature, and polarization, to achieve a higher level of computing parallelism and scalability than digital electronic processors. While multiplexing using the wavelength and other DOFs can be readily integrated on silicon photonics platforms with compact footprints, conventional mode-division multiplexed (MDM) photonic designs occupy areas exceeding tens to hundreds of microns for a few spatial modes, significantly limiting their scalability. Here, we utilize inverse design to demonstrate an ultracompact photonic computing core that calculates vector dot products based on MDM coherent mixing. Our dot-product core integrates the functionalities of two-mode multiplexers and one multimode coherent mixer within a nominal footprint of 5 μm x 3 μm . We have experimentally demonstrated computing examples on the fabricated dot-product core, including complex number multiplication and motion estimation using optical flow. The compact dot-product core design enables large-scale on-chip integration in a parallel photonic computing primitive cluster for high-throughput scientific computing and computer vision tasks.

97 MATHEMATICS AND COMPUTING↗

Certified randomness using a trapped-ion quantum processor

Although quantum computers can perform a wide range of practically important tasks beyond the abilities of classical computers, realizing this potential remains a challenge. An example is to use an untrusted remote device to generate random bits that can be certified to contain a certain amount of entropy. Certified randomness has many applications but is impossible to achieve solely by classical computation. Here we demonstrate the generation of certifiably random bits using the 56-qubit Quantinuum H2-1 trapped-ion quantum computer accessed over the Internet. Our protocol leverages the classical hardness of recent random circuit sampling demonstrations: a client generates quantum ‘challenge’ circuits using a small randomness seed, sends them to an untrusted quantum server to execute and verifies the results of the server. We analyse the security of our protocol against a restricted class of realistic near-term adversaries. Using classical verification with measured combined sustained performance of 1.1 × 10 18 floating-point operations per second across multiple supercomputers, we certify 71,313 bits of entropy under this restricted adversary and additional assumptions. Our results demonstrate a step towards the practical applicability of present-day quantum computers.

computer science↗

MOCUM: A two-dimensional method of characteristics code based on unstructured meshing for general geometries

A transport theory code MOCUM based on the Method of Characteristics (MOC) as the flux solver with an advanced general geometry processor is developed for two-dimensional lattice and full core neutronics modeling. The core structure is represented by Constructive Solid Geometry (CSG) that uses Boolean operations to build complex geometries from simple polygons. Arbitrary-precision arithmetic is also used in the process of building CSG objects to eliminate the round-off error from the commonly used double precision numbers. Then, the constructed core frame will be decomposed and refined into a conforming Delaunay triangulation to ensure the quality of the meshes. The MOC solver kernel is fully paralleled using OpenMP and the developed numerical code is validated by several benchmarks representing various core geometries. For the cases modeled, the maximum percentage error for multiplication factor and the pin power compared to reference values are 0.1% and 0.7% respectively. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Development of MCNP Training Modules for Safeguards Practitioners [Abstract]

The Monte-Carlo N-Particle (MCNP) software developed at LANL is the most widely used neutron transport code in the world. It is an essential tool for a variety of applications including detector development and design, nuclear fuel burnup simulation, criticality safety, and nondestructive assay system optimization. For this reason, it is indispensable within the safeguards and materials control & accountability (MC&A) communities. Multiple MCNP training courses have been created and taught over the last several decades by the MCNP development team at LANL, however there are no existing courses that cover specialized topics considered fundamental to NDA and safeguards models. To fill this gap, the MCNP team and Safeguards Science and Technology group at LANL have co-created a set of training modules customized to meet the specialized needs of the safeguards and MC&A communities. The basic modules cover concepts such as NDA system optimization, He-specific and other capture tallies, and tools for improved theoretical understanding. An advanced module was also created to cover topics including variance reduction for active interrogation simulations, use of the LANL MCNPTools post-processor, PTRAC (particle tracking) and list-mode data simulations, and fuel burnup simulations. The training modules teach to the latest and most state-of-the-art MCNP features and tools released by the development team at LANL and are intended to be taught jointly by the developers and safeguards experts. Ultimately, we hope that creation of these modules will serve to capture and convey the safeguards modeling and MCNP expertise at LANL, and that we will be able to share the modules more broadly with the MC&A and safeguards communities.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Non-adiabatic Excited State Molecule Dynamics Modeling of Photochemistry and Photophysics of Materials

Understanding and controlling excited state dynamics lies at the heart of all our efforts to design photoactive materials with desired functionality. This tailor-design approach has become the standard for many technological applications (e.g., solar energy harvesting) including the design of organic conjugated electronic materials with applications in photovoltaic and light-emitting devices. Over the years, our team has developed efficient LANL-based codes to model the relevant photophysical processes following photoexcitation (spatial energy transfer, excitation localization/delocalization, and/or charge separation). The developed approach allows the non-radiative relaxation to be followed on up to ~10 ps timescales for large realistic molecules (hundreds of atoms in size) in the realistic solvent dielectric environment. The Collective Electronic Oscillator (CEO) code is used to compute electronic excited states, and the Non-adiabatic Excited State Molecular Dynamics (NA-ESMD) code is used to follow the non-adiabatic dynamics on multiple coupled Born-Oppenheimer potential energy surfaces. Our preliminary NA-ESMD simulations have revealed key photoinduced mechanisms controlling competing interactions and relaxation pathways in complex materials, including organic conjugated polymer materials, and have provided a detailed understanding of photochemical products and intermediates and the internal conversion process during the initiation of energetic materials. This project will be using LANL-based CEO and NA-ESMD codes to model nonradiative relaxation in organic and energetic materials. The NA-ESMD and CEO codes belong to a class of electronic structure/quantum chemistry codes that require large memory, “long-queue-few-core” distribution of resources in order to make useful progress. The NA-ESMD simulations are trivially parallelizable requiring ~300 processors for up to one week runtime to reach a meaningful restart point.

36 MATERIALS SCIENCE↗

Understanding HPC Benchmark Performance on Intel Broadwell and Cascade Lake Processors

Hardware platforms in high performance computing are constantly getting more complex to handle even when considering multicore CPUs alone. Numerous features and configuration options in the hardware and the software environment that are relevant for performance are not even known to most application users or developers. Microbenchmarks, i.e., simple codes that fathom a particular aspect of the hardware, can help to shed light on such issues, but only if they are well understood and if the results can be reconciled with known facts or performance models. The insight gained from microbenchmarks may then be applied to real applications for performance analysis or optimization. In this paper we investigate two modern Intel x86 server CPU architectures in depth: Broadwell EP and Cascade Lake SP. We highlight relevant hardware configuration settings that can have a decisive impact on code performance and show how to properly measure on-chip and off-chip data transfer bandwidths. The new victim L3 cache of Cascade Lake and its advanced replacement policy receive due attention. Finally we use DGEMM, sparse matrix-vector multiplication, and the HPCG benchmark to make a connection to relevant application scenarios.

97 MATHEMATICS AND COMPUTING↗

Accelerating Binarized Neural Networks via Bit-Tensor-Cores in Turing GPUs

Despite foreseeing tremendous speedups over conventional deep neural networks, the performance advantage of binarized neural networks (BNNs) has merely been showcased on general-purpose processors such as CPUs and GPUs. In fact, due to being unable to leverage bit-level-parallelism with a word-based architecture, GPUs have been criticized for extremely low utilization (1%) when executing BNNs. Consequently, the latest tensorcores in NVIDIA Turing GPUs start to experimentally support bit computation. In this work, we look into this brand new bit computation capability and characterize its unique features. We show that the stride of memory access can significantly affect performance delivery and a data-format co-design is highly desired to support the tensorcores for achieving superior performance than existing software solutions without tensorcores. We realize the tensorcore-accelerated BNN design, particularly the major functions for fully-connect and convolution layers — bit matrix multiplication and bit convolution. Evaluations on two NVIDIA Turing GPUs show that, with ResNet-18, our BTC-BNN design can process ImageNet at a rate of 5.6K images per second, 77% faster than state-of-the-art. Our BNN approach is released on https://github.com/pnnl/TCBNN.

Li, Ang↗

Improving efficiency of semi‐direct møller–plesset second‐order perturbation methods through oversubscription on multiple nodes

The purpose of this work is to evaluate the efficacy of oversubscription, at the 1 n , 2 n , and 3 n levels for n physical cores, on semi‐direct MP2 methods within NWChem when using two and three Intel nodes. Semi‐direct MP2 energy and gradient calculations were performed on chemical systems ranging from 824 to 1626 basis functions using the cc‐pVDZ basis set. Wall times for semi‐direct MP2 energies were reduced by as much as 36% using two nodes and 44% using three nodes compared to no oversubscription. Total energy consumed by the CPU and DRAM was also reduced by as much as 12% using two nodes and as much as 20% using three nodes when oversubscribing. MP2 gradient wall times improved by as much as 16% using two nodes and 18% using three nodes compared to execution at the 1 n level; however, energy savings were insignificant. Intel performance‐counter data show a strong correlation between total wall time saved and less time spent in the idle state, indicating a more efficient use of the processors when oversubscribing. © 2019 Wiley Periodicals, Inc.

Fought, Ellie L.↗

End-System Network Interface Controller for 100 Gb/s Wide Area Networks: Final Report

In recent years, network bandwidth requirements have scaled multiple folds, pushing the need for the development of data exchange mechanisms at 100 Gb/s and beyond. High performance computing, climate modeling, large-scale storage, and collaborative scientific research are examples of applications that can greatly benefit by leveraging high bandwidth capabilities of the order of 100 Gb/s. Such requirements and advances in IEEE Ethernet standards, Optical Transport Unit4 (OTU4), and host-system interconnects demand a network infrastructure supporting throughput rates of the order of 100 Gb/s with a single wavelength. To address such a demand Acadia Optronics in collaboration with the University of New Mexico, proposed and developed a end-system Network Interface Controller (NIC) for the 100Gbps WANs. Acadia’s 100G NIC employs an FPGA based system with a high-performance processor interconnect (PCIe 3.0) and a high capacity optical transmission link (CXP) to provide data transmission at the rate of 100 Gbps.

100 Gb/s network interface controller↗

iHarmonizer: improving the disk efficiency of I/O-intensive multithreaded codes

Challenged by serious power and thermal constraints, and limited by available instruction-level parallelism, processor designs have evolved to multi-core architectures. These architectures, many augmented with native simultaneous multithreading, are driving software developers to use multithreaded programs to exploit thread-level parallelism. While multithreading is well-known to introduce concerns of data dependency and CPU load balance, less known is that the uncertainty of relative progress of thread execution can cause patterns of I/O requests, issued by different threads, to be effectively random and so significantly degrade hard-disk efficiency. This effect can severely offset the performance gains from parallel execution, especially for I/O-intensive programs. Retaining the benefits of multithreading while not reducing I/O efficiency is an urgent and challenging problem. We propose a user-level scheme, iHarmonizer, to streamline the servicing of I/O requests from multiple threads in OpenMP programs. Specifically, we use the compiler to insert code into OpenMP programs so that data usage can be transmitted at run time to a supporting run-time library; this library in turn prefetches data in a disk-friendly way and coordinates threads execution according to the availability of their requested data. Transparently to the programmer, iHarmonizer makes a multithreaded program I/O efficient while maintaining the benefits of parallelism. Our experiments show that iHarmonizer can significantly speed up the execution of a representative set of I/O-intensive scientific benchmarks.

97 MATHEMATICS AND COMPUTING↗

Iterative map-making with two-level preconditioning for polarized cosmic microwave background data sets: A worked example for ground-based experiments

Context. An estimation of the sky signal from streams of time ordered data (TOD) acquired by the cosmic microwave background (CMB) experiments is one of the most important steps in the context of CMB data analysis referred to as the map-making problem. The continuously growing CMB data sets render the CMB map-making problem progressively more challenging in terms of computational cost and memory in particular in the context of ground-based experiments with their operational limitations as well as the presence of contaminants. Aims. We study a recently proposed, novel class of the Preconditioned Conjugate Gradient (PCG) solvers which invoke two-level preconditioners in the context of the ground-based CMB experiments. We compare them against the PCG solvers commonly used in the map-making context considering their precision and time-to-solution. Methods. We compare these new methods on realistic, simulated data sets reflecting the characteristics of current and forthcoming CMB ground-based experiments. We develop a divide-and-conquer implementation of the approach where each processor performs a sequential map-making for a subset of the TOD. Results. We find that considering the map level residuals, the new class of solvers permits us to achieve a tolerance that is better than the standard approach by up to three orders of magnitude, where the residual level often saturates before convergence is reached. This often corresponds to an important improvement in the precision of the recovered power spectra in particular on the largest angular scales. The new method also typically requires fewer iterations to reach a required precision and therefore shorter run times are required for a single map-making solution. However, the construction of an appropriate two-level preconditioner can be as costly as a single standard map-making run. Nevertheless, if the same problem needs to be solved multiple times, for example, as in Monte Carlo simulations, this cost is incurred only once, and the method should be competitive, not only as far as its precision is concerned but also its performance.

79 ASTRONOMY AND ASTROPHYSICS↗

NMIS with Imaging and Gamma Ray Spectrometry for Pu, HEU, HE and Other Materials

The Nuclear Material Identification System (NMIS) has been under development at ORNL and the National Nuclear Security Administration (NNSA) Y-12 National Security Complex since 1984. In the mid-1990s, what is now the US Department of Energy (DOE) Office of Nuclear Verification (ONV) realized that it was a useful technology for future arms control treaty applications and supported further development of the system. In 2004, fast-neutron imaging was incorporated into the system. In 2007, the ONV decided to develop a fieldable version of the system, designated as FNMIS, for potential use in future treaties. The FNMIS is being developed to be compatible with the eventual incorporation of gamma-ray spectrometry and an information barrier. This report addresses how and what attributes could be determined by the FNMIS system with gamma-ray spectrometry. The NMIS is a time-dependent coincidence system that incorporates tomographic imaging (including mapping of the fission sites) and gamma-ray spectrometry. It utilizes a small, lightweight (30 lb), portable deuterium-tritium (DT) neutron (14.1 MeV) generator (4 x 10 7 neutrons/second) for active interrogation and can also perform passive interrogation. A high-purity germanium (HPGe) gamma-ray detector with multichannel analysis can be utilized in conjunction with the source for active interrogation or passively. The system uses proton recoil scintillators: 32 small 2.5 x 2.5 x 10.2-cm-thick plastic scintillators for imaging and at least two 2 x 2 arrays of 27 x 27 x 10-cm-thick plastic scintillators that detect induced fission radiation. The DT generator contains an alpha detector that time and directionally tags a fan beam of some of the neutrons emitted and subdivides it into pixels. A fast (1 GHz) time correlation processor measures the time-dependent coincidence among all detectors in the system. A computer-controlled scanner moves the small detectors and the source appropriately for scanning a target object for imaging. The system is based on detection of transmitted 14.1 MeV neutrons, fission neutrons, and gamma rays from spontaneous, inherent source fission of the target, fission neutrons and gamma rays induced by the external DT source, gamma rays from natural emissions of uranium and plutonium, and induced gamma-ray emission by the interaction of the 14.1 MeV neutrons from the DT source. The NMIS can and has been used with a time-tagged californium spontaneous fission source. It has also been used with pulsed interrogation sources such as LINACs, DT, and deuterium-deuterium (DD) sources. This system is uniquely suited for detection of shielded highly enriched uranium (HEU), plutonium, and other special nuclear materials and detection of high explosives (HE) and chemical agents. The NMIS will be adapted to utilize a trusted processor that incorporates information barrier and authentication techniques using open software and then be useful in some international applications for materials whose characteristics may be classified. The proposed information barrier version of the NMIS system would consist of detectors and cables, the red (classified side) computer system, which processes the data, and the black (unclassified side) computer, which handles the computer interface. The system could use the 'IB wrapper' concept proposed by Los Alamos National Laboratory and the software integrity (digital signatures) system proposed by Sandia. Since it is based entirely on commercially available components, the entire system, including NMIS data acquisition boards, can be built with commercial off-the-shelf components. This system is being developed into a fieldable system (FNMIS) for potential arms control treaties by the ONV. The system will be modularly constructed with the RF shielded modules connected to the processor by appropriate control and signal cable in metal conduit. The FNMIS is presently being designed for eventual incorporation of gamma-ray spectrometry and an information barrier to protect classified information. The system hardware and software can be configured to obtain the following: plutonium presence, plutonium mass, Pu-240/239 ratio, plutonium geometry, plutonium metal vs non-metallic (absence of metal), time (age) since processing for plutonium (or last purification), uranium presence, uranium mass, uranium enrichment, uranium geometry, uranium metal vs non-metallic compound (absence of metal), beryllium presence and mass, tritium and deuterium gas bottle presence, HE, and chemical weapons. A matrix of the quantities determined, the method of determination, whether active (external neutron source) or passive, and the measurement equipment involved is given in the Tables 1-4. Some of these attributes can be obtained by multiple data analysis methods. The gamma-ray spectrometry methods for HEU, plutonium, and HE have been developed by other laboratories, are well known, and will be incorporated.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗