Search NASA⌕ Search

SEARCH · Search NASA

Results for “near memory computing”

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 55 records · Page 3

Exception Handling Controllers: An application of pushdown systems to discrete event control

Recent work by the author has extended the Supervisory Control Theory to include the class of control languages defined by pushdown machines. A pushdown machine is a finite state machine extended by an infinite stack memory. In this paper, we define a specific type of deterministic pushdown machine that is particularly useful as a discrete event controller. Checking controllability of pushdown machines requires computing the complement of the controller machine. We show that Exception Handling Controllers have the property that algorithms for taking their complements and determining their prefix closures are nearly identical to the algorithms available for finite state machines. Further, they exhibit an important property that makes checking for controllability extremely simple. Hence, they maintain the simplicity of the finite state machine, while providing the extra power associated with a pushdown stack memory. We provide an example of a useful control specification that cannot be implemented using a finite state machine, but can be implemented using an Exception Handling Controller.

42 ENGINEERING↗

Implementing efficient data compression and encryption in a persistent key-value store for HPC

Recently, persistent data structures, like key-value stores (KVSs), which are stored in a high-performance computing (HPC) system’s nonvolatile memory, provide an attractive solution for a number of emerging challenges like limited I/O performance. Data compression and encryption are two well-known techniques for improving several properties of such data-oriented systems. This article investigates how to efficiently integrate data compression and encryption into persistent KVSs for HPC with the ultimate goal of hiding their costs and complexity in terms of performance and ease of use. Our compression technique exploits deep memory hierarchy in an HPC system to achieve both storage reduction and performance improvement. Our encryption technique provides a practical level of security and enables sharing of sensitive data securely in complex scientific workflows with nearly imperceptible cost. We implement the proposed techniques on top of a distributed embedded KVS to evaluate the benefits and costs of incorporating these capabilities along different points in the dataflow path, illustrating differences in effective bandwidth, latency, and additional computational expense on Swiss National Supercomputing Centre’s Grand Tavé and National Energy Research Scientific Computing Center’s Cori.

97 MATHEMATICS AND COMPUTING↗

MetaStrider: Architectures for Scalable Memory-centric Reduction of Sparse Data Streams

Reduction is an operation performed on the values of two or more key-value pairs that share the same key. Reduction of sparse data streams finds application in a wide variety of domains such as data and graph analytics, cybersecurity, machine learning, and HPC applications. However, these applications exhibit low locality of reference, rendering traditional architectures and data representations inefficient. This article presents MetaStrider, a significant algorithmic and architectural enhancement to the state-of-the-art, SuperStrider. Furthermore, these enhancements enable a variety of parallel, memory-centric architectures that we propose, resulting in demonstrated performance that scales near-linearly with available memory-level parallelism.

97 MATHEMATICS AND COMPUTING↗

Reference guide to WPP version 2.0

WPP is a computer program for simulating seismic wave propagation on parallel machines. WPP solves the governing equations in second order formulation using a node-based finite difference approach. The basic numerical method is described in [9]. WPP implements substantial capabilities for 3-D seismic modeling, with a free surface condition on the top boundary, non-reflecting far-field boundary conditions on the other boundaries, point force and point moment tensor source terms with many predefined time dependencies, fully 3-D heterogeneous material model specification, output of synthetic seismograms in the SAC [4] format, output of GMT [11] scripts for laying out simulation information on a map, and output of 2-D slices of (derived quantites of) the solution field as well as the material model. Version 2.0 of WPP allows the free surface boundary condition to be imposed on a curved topography. For this purpose a curvilinear mesh is used near the free surface, extending into the computational domain down to a user specified level. The elastic wave equations and the free surface boundary conditions are discretized on the curvilinear mesh using the energy conserving technique described in [2]. A curvilinear mesh generator is built into WPP and the curvilinear mesh is automatically generated from the topography. Below the curvilinear grid, the elastic wave equation is discretized on Cartesian meshes, which leads to a more computationally efficient algorithm. In version 2.0 of WPP, Cartesian local mesh refinement can be used to make the computational mesh finer near the free surface, where more resolution often is needed to resolve short wave lenghts in the solution, for example in sedimentary basins. The mesh refinement is performed in the vertical direction and each Cartesian grid is constructed from user specified refinement levels. In this approach, the grid size in all three spatial directions is doubled across each mesh refinement interface, leading to substantial savings in memory and computational effort. The energy conserving mesh refinement coupling method described in [10] is used to handle the hanging nodes along the refinement interface. The examples subdirectory of the WPP source distribution contains several examples and validation tests. Many Matlab/octave scripts are provided in the tools directory.

58 GEOSCIENCES↗

Pausible bisynchronous FIFO

A system, method, and computer program product are provided for a pausible bisynchronous FIFO. Data is written synchronously with a first clock signal of a first clock domain to an entry of a dual-port memory array and an increment signal is generated in the first clock domain. The increment signal is determined to transition near an edge of a second dock signal, where the second clock signal is a pausible clock signal. A next edge of the second clock signal of the second clock domain is delayed and the increment signal to the second clock domain and is transmitted.

97 MATHEMATICS AND COMPUTING↗

Computational discovery of two-dimensional rare-earth iodides: promising ferrovalley materials for valleytronics

Two-dimensional Ferrovalley materials with intrinsic valley polarization are rare but highly promising for valley-based nonvolatile random access memory and valley filter devices. These ferromagnetic materials exhibit valleys at or near the Fermi level with intrinsic magnetism. The strong coupling between magnetism and spin–orbit coupling induces intrinsic valley polarization. Using Kinetically Limited Minimization, an unconstrained crystal structure prediction algorithm, and prototype sampling based on first-principles calculations, we have discovered new Ferrovalley materials, rare-earth iodides RI 2 , where R is a rare-earth element belonging to Sc, Y, or La-Lu, and I is Iodine. The rare-earth iodides are layered and demonstrate either 2H, 1T, or 1T d phase as the ground state in bulk, analogous to transition metal dichalcogenides (TMDCs). The calculated exfoliation energy of monolayers (MLs) is comparable to that of graphene and TMDCs, suggesting possible experimental synthesis. The MLs in the 2H phase exhibit ferromagnetism due to unpaired electrons in d and f orbitals. Throughout the rare-earth series, d bands have valley polarization at K and $\overline{K}$ points in the Brillouin zone in the vicinity of the Fermi level. Large intrinsic valley polarization in the range of 15–143 meV without external stimuli is observed in these Ferrovalley materials, which can be enhanced further by applying an in-plane bi-axial strain. These valleys can selectively be probed and manipulated for information storage and processing, potentially offering superior performance beyond conventional electronics and spintronics. Here we further show that the 2H ferromagnetic phase of RI 2 MLs possesses non-zero Berry curvature and exhibits anomalous valley Hall effect with considerable anomalous Hall conductivity. Our work will incite exploratory synthesis of the predicted Ferrovalley materials and their application in valleytronics and beyond.

2D materials↗

Two-level main memory co-design: Multi-threaded algorithmic primitives, analysis, and simulation

A challenge in computer architecture is that processors often cannot be fed data from DRAM as fast as CPUs can consume it. Therefore, many applications are memory-bandwidth bound. With this motivation and the realization that traditional architectures (with all DRAM reachable only via bus) are insufficient to feed groups of modern processing units, vendors have introduced a variety of non-DDR 3D memory technologies (Hybrid Memory Cube (HMC),Wide I/O 2, High Bandwidth Memory (HBM)). These offer higher bandwidth and lower power by stacking DRAM chips on the processor or nearby on a silicon interposer. We will call these solutions “near-memory,” and if user-addressable, “scratchpad.” High-performance systems on the market now offer two levels of main memory: near-memory on package and traditional DRAM further away. In the near term we expect the latencies near-memory and DRAM to be similar. Here, it is natural to think of near-memory as another module on the DRAM level of the memory hierarchy. Vendors are expected to offer modes in which the near memory is used as cache, but we believe that this will be inefficient.

97 MATHEMATICS AND COMPUTING↗

Design and performance of a scalable, parallel statistics toolkit.

Most statistical software packages implement a broad range of techniques but do so in an ad hoc fashion, leaving users who do not have a broad knowledge of statistics at a disadvantage since they may not understand all the implications of a given analysis or how to test the validity of results. These packages are also largely serial in nature, or target multicore architectures instead of distributed-memory systems, or provide only a small number of statistics in parallel. This paper surveys a collection of parallel implementations of statistics algorithm developed as part of a common framework over the last 3 years. The framework strategically groups modeling techniques with associated verification and validation techniques to make the underlying assumptions of the statistics more clear. Furthermore it employs a design pattern specifically targeted for distributed-memory parallelism, where architectural advances in large-scale high-performance computing have been focused. Moment-based statistics (which include descriptive, correlative, and multicorrelative statistics, principal component analysis (PCA), and k-means statistics) scale nearly linearly with the data set size and number of processes. Entropy-based statistics (which include order and contingency statistics) do not scale well when the data in question is continuous or quasi-diffuse but do scale well when the data is discrete and compact. We confirm and extend our earlier results by now establishing near-optimal scalability with up to 10,000 processes.

99 GENERAL AND MISCELLANEOUS↗

Efficient tree decomposition of high-rank tensors [Efficient decomposition of high-rank tensors]

Tensors are a natural way to express correlations among many physical variables, but storing tensors in a computer naively requires memory which scales exponentially in the rank of the tensor. This is not optimal, as the required memory is actually set not by the rank but by the mutual information amongst the variables in question. Representations such as the tensor tree perform near-optimally when the tree decomposition is chosen to reflect the correlation structure in question, but making such a choice is non-trivial and good heuristics remain highly context-specific. In this work I present two new algorithms for choosing efficient tree decompositions, independent of the physical context of the tensor. The first is a brute-force algorithm which in most cases produces optimal decompositions but is generally impractical for high-rank tensors, as the number of possible choices grows exponentially in rank. Here, the second is a greedy algorithm, and while it is not optimal it performs extremely well in numerical experiments while having runtime which makes it practical even for tensors of very high rank.

97 MATHEMATICS AND COMPUTING↗

Kokkos Programming Model and Library

High performance computing is in the midst of a many-core revolution driven by rapidly evolving microchips with diverse and heterogeneous architectures, increasing concurrency (thread count), and decreasing memory per thread. Our HPC applications face a major challenge to effectively use these microchips with a single code base that is performance portable across these evolving architectures. Kokkos was developed to enable on-chip concurrency and manage architecture-dependent constraints on memory access patterns. The goal is to maximize the amount of application code that is portable across diverse architectures and still obtain the same (or nearly) performance as a variant of that code written specifically for that architecture. The Kokkos team has ongoing R&D co-design collaborations with Sandia's and vendors' microchip and system engineers to rapidly incorporate evolving computer architecture features into Kokkos. The team is also providing leadership for DOE laboratories' participation on the ISO/C++ language standard committee to subsuming Kokkos features into a future standard.

97 MATHEMATICS AND COMPUTING↗

Analysis of GPU Data Access Patterns on Complex Geometries for the D3Q19 Lattice Boltzmann Algorithm

GPU performance of the lattice Boltzmann method (LBM) depends heavily on memory access patterns. When implemented with GPUs on complex domains, typically, geometric data is accessed indirectly and lattice data is accessed lexicographically. Although there are a variety of other options, no study has examined the relative efficacy between them. Here, we examine a suite of memory access schemes via empirical testing and performance modeling. We find strong evidence that semi-direct is often better suited than the more common indirect addressing, providing increased computational speed and reducing memory consumption. For the layout, we find that the Collected Structure of Arrays (CSoA) and bundling layouts outperform the common Structure of Array layout; on V100 and P100 devices, CSoA consistently outperforms bundling, however the relationship is more complicated on K40 devices. When compared to state-of-the-art practices, our recommendations lead to speedups of 10–40 percent and reduce memory consumption up to 17 percent. Using performance modeling and computational experimentation, we determine the mechanisms behind the accelerations. We demonstrate that our results hold across multiple GPUs on two leadership class systems, and present the first near-optimal strong results for LBM with arterial geometries run on GPUs.

42 ENGINEERING↗

Scaling the Ion Trap Quantum Processor

Trapped atomic ions are standards for quantum information processing, serving as quantum memories, hosts of quantum gates in quantum computers and simulators, and nodes of quantum communication networks. Quantum bits based on trapped ions enjoy a rare combination of attributes: They have exquisite coherence properties, they can be prepared and measured with nearly 100% efficiency, and they are readily entangled with each other through the Coulomb interaction or remote photonic interconnects. The outstanding challenge is the scaling of trapped ions to hundreds or thousands of qubits and beyond, at which scale quantum processors can outperform their classical counterparts in certain applications. We review the latest progress and prospects in that effort, with the promise of advanced architectures and new technologies, such as microfabricated ion traps and integrated photonics.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Computing NLTE Opacities -- Node Level Parallel Calculation

Presentation. The goal: to produce a robust library capable of computing reasonably accurate opacities inline with the assumption of LTE relaxed (non-LTE). Near term: demonstrate acceleration of non-LTE opacity computation. Far term (if funded): connect to application codes with in-line capability and compute opacities. Study science problems. Use efficient algorithms that expose many levels of parallelism and utilize good memory access patterns for use on advanced architectures. Portability to multiple types of hardware including multicore processors, manycore processors such as KNL, GPUs, etc. Easily coupled to radiation hydrodynamics and thermal radiative transfer codes.

Astronomy & Astrophysics(79)↗

HiPACE++: A portable, 3D quasi-static particle-in-cell code

Modeling plasma accelerators is a computationally challenging task and the quasi-static particle-in-cell algorithm is a method of choice in a wide range of situations. In this work, we present the first performance-portable, quasi-static, three-dimensional particle-in-cell code HiPACE++. By decomposing all the computation of a 3D domain in successive 2D transverse operations and choosing appropriate memory management, HiPACE++ demonstrates orders-of-magnitude speedups on modern scientific GPUs over CPU-only implementations. The 2D transverse operations are performed on a single GPU, avoiding time-consuming communications. The longitudinal parallelization is done through temporal domain decomposition, enabling near-optimal strong scaling from 1 to 512 GPUs. HiPACE++ is a modular, open-source code enabling efficient modeling of plasma accelerators from laptops to state-of-the-art supercomputers.

97 MATHEMATICS AND COMPUTING↗

Virtualized Logical Qubits: A 2.5D Architecture for Error-Corrected Quantum Computing

Current, near-term quantum devices have shown great progress in the last several years culminating recently with a demonstration of quantum supremacy. In the medium-term, however, quantum machines will need to transition to greater reliability through error correction, likely through promising techniques like surface codes which are well suited for near-term devices with limited qubit connectivity. We discover quantum memory, particularly resonant cavities with transmon qubits arranged in a 2.5D architecture, can efficiently implement surface codes with substantial hardware savings and performance/fidelity gains. Specifically, we virtualize logical qubits by storing them in layers of qubit memories connected to each transmon. Surprisingly, distributing each logical qubit across many memories has a minimal impact on fault tolerance and results in substantially more efficient operations. Our design permits fast transversal application of CNOT operations between logical qubits sharing the same physical address (same set of cavities) which are 6x faster than standard lattice surgery CNOTs. We develop a novel embedding which saves approximately 10x in transmons with another 2x savings from an additional optimization for compactness. Although qubit virtualization pays a 10x penalty in serialization, advantages in the transversal CNOT and in area efficiency result in fault-tolerance and performance comparable to conventional 2D transmon-only architectures. Our simulations show our system can achieve fault tolerance comparable to conventional two-dimensional grids while saving substantial hardware. Furthermore, our architecture can produce magic states at 1.22x the baseline rate given a fixed number of transmon qubits. Here, this is a critical benchmark for future fault-tolerant quantum computers as magic states are essential and machines will spend the majority of their resources continuously producing them. This architecture substantially reduces the hardware requirements for fault-tolerant quantum computing and puts within reach a proof-of-concept experimental demonstration of around 10 logical qubits, requiring only 11 transmons and 9 attached cavities in total.

quantum computing↗

Adaptive and Efficient Computing for Subsurface Simulation within ParFlow

This project is concerned with the PF.WRF model as a means to enable more accurate predictions of wind fluctuations and subsurface storage. As developed at LLNL, PF.WRF couples a groundwater (subsurface) and surface water flow model (ParFlow) to a mesoscale atmospheric model (WRF, Weather Research and Forecasting Model). It was developed as a unique tool to address coupled water balance and wind energy questions that occur across traditionally separated research regimes of the atmosphere, land surface, and subsurface. PF.WRF is capable of simulating fluid, mass, and energy transport processes in groundwater, vadose zone, root zone, and land surface systems, including overland flow, and allows for the WRF model to both directly drive and respond to surface and subsurface hydrologic processes and conditions. The current PF.WRF model is constrained to have uniform spatial gridding below the land surface and matching areal grids with the WRF model at the land surface. There are often cases where it is advantageous for land surface, overland flow and subsurface models to have finer gridding than their atmospheric counterparts. Finer vertical discretization is also advantageous near the land surface (to properly capture feedbacks) yet many applications have a large vertical extent. However, the surface flow is strongly dependent on topography leading to a need for greater lateral resolution in some regions and the subsurface flow is tightly coupled to the atmospheric model near the surface leading to a need for finer vertical resolution. In addition, the interactions (e.g. rain) will be highly variable in space and time across the problem domain so an adaptive scheme is preferred to a static strategy to efficiently use computing and memory resources. As a result, this project focussed on algorithmic research required for development of an adaptive simulation capability in the PF.WRF system and its subsequent use in an application problem in the Central Valley of California. This report documents schemes of use for a future implementation of an adaptive grid capability within the ParFlow subsurface flow simulator in PF.WRF. The methods describe specific handling of the coarse/fine boundaries within a cell-centered discretization of the nonlinear parabolic Richards equation model for variable saturated flow. In addition, we describe development of a spline fit and table lookup method implemented within ParFlow to enhance computational efficiency of variably saturated flow calculations.

97 MATHEMATICS AND COMPUTING↗

Monte Carlo Explicitly Correlated Second-Order Many-Body Green’s Function Calculations of Semiconductor Band Gaps

A systematically converging series of ab initio, post-density-functional, size-consistent, electron-correlated approximations is desired for predictive computing of felectronic band structures of insulating, semiconducting, and metallic solids. A series that meets all of these desiderata (except the applicability to metals) is ab initio many-body Green's function theory based on Gaussian-type-orbital (GTO) basis sets. Here, its leading-order approximation, the second-order Green's function (GF2) method in the diagonal and frequency-independent approximations with the aug-cc-pVDZ basis set, is applied to the fundamental band gaps of three semiconductors (diamond, silicon, and silicon carbide in the zincblende structure) using cluster models. Corrections are made to the basis-set-incompleteness errors by the explicit-correlation (F12) ansatz (GF2-F12) for the valence band edges. The crystals are modeled as surface-passivated clusters of increasing sizes, whose wave functions are expanded by up to 2709 GTO basis functions. Immense computational costs of these calculations are overcome by the highly scalable stochastic algorithm of the Monte Carlo GF2-F12 method, whose operation cost per state increases only as a cubic power of system size, which has a tiny memory footprint and easily achieves near-perfect parallel efficiency on thousands of CPUs or on hundreds of GPUs. The correlated, F12-corrected highest-occupied and lowest-unoccupied molecular-orbital energy (HOMO-LUMO) gap is 5.78 ± 0.07 eV for C 87 H 76 as compared with the experimental value of the fundamental (indirect) band gap of bulk diamond at 5.48 eV. The correlated, F12-corrected HOMO-LUMO gaps for Si 75 H 76 and Si 32 C 43 H 76 are 2.56 ± 0.15 eV and 3.50 ± 0.12 eV, respectively, which are expected to decrease further with increasing cluster sizes. As a result, the experimental fundamental (indirect) band gaps of bulk silicon and silicon carbide are 1.17 eV and 2.42 eV, respectively.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Toward Large-Scale Image Segmentation on Summit

Semantic segmentation of images is an important computer vision task that emerges in a variety of application domains such as medical imaging, robotic vision and autonomous vehicles to name a few. While these domain-specific image analysis tasks involve relatively small image sizes (~ 10 2 × 10 2 ), there are many applications that need to train machine learning models on image data with extents that are orders of magnitude larger (~10 4 × 10 4 ). Training deep neural network (DNN) models on large extent images is extremely memory-intensive and often exceeds the memory limitations of a single graphical processing unit, a hardware accelerator of choice for computer vision workloads. Here, an efficient, sample parallel approach to train U-Net models on large extent image data sets is presented. Its advantages and limitations are analyzed and near-linear strong-scaling speedup demonstrated on 256 nodes (1536 GPUs) of the Summit supercomputer. Using a single node of the Summit supercomputer, an early evaluation of a recently released model parallel framework called GPipe is demonstrated to deliver ~ 2X speedup in executing a U-Net model with an order of magnitude larger number of trainable parameters than reported before. Performance bottlenecks for pipelined training of U-Net models are identified and mitigation strategies to improve the speedups are discussed. Together, these results open up the possibility of combining both approaches into a unified scalable pipelined and data parallel algorithm to efficiently train U-Net models with very large receptive fields on data sets of ultra-large extent images.

Seal, Sudip↗