Search NASA⌕ Search

SEARCH · Search NASA

Results for “memory efficiency”

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 37 records · Page 2

Memory efficient solution of the primitive equations for numerical weather prediction on the CYBER 205

Numerical Weather Prediction (NWP), for both operational and research purposes, requires only fast computational speed but also large memory. A technique for solving the Primitive Equations for atmospheric motion on the CYBER 205, as implemented in the Mesoscale Atmospheric Simulation System, which is fully vectorized and requires substantially less memory than other techniques such as the Leapfrog or Adams-Bashforth Schemes is discussed. The technique presented uses the Euler-Backard time marching scheme. Also discussed are several techniques for reducing computational time of the model by replacing slow intrinsic routines by faster algorithms which use only hardware vector instructions.

Tuccillo, J. J.↗

Memory-efficient nonsmooth dynamic optimization using adaptive randomized compression

Dynamic optimization problems arise in many applications including flow control, full waveform inversion, and medical imaging. These problems are plagued by significant computational challenges. One such challenge — and the focus of this work — is the memory limitation induced by the size of the underlying dynamical system. In particular, the entire dynamic trajectory is required for derivative computation and therefore must be stored or recomputed using, e.g., checkpointing. Although recent work demonstrated the use of adaptive randomized sketching to overcome the memory challenge, that work only applies to smooth unconstrained problems, prohibiting its use for nonsmooth regularized and constrained problems. The inclusion of nonsmooth regularizers and constraints is critical as they often arise in an attempt to preserve certain physical properties or to promote sparsity. To solve these problems, we introduce a trust-region algorithm for minimizing the sum of a smooth nonconvex function and a nonsmooth convex function that leverages randomized sketching to compress the dynamical system trajectories and adaptively adjust the sketch rank to satisfy a gradient inexactness condition. We prove convergence of this algorithm and demonstrate that it achieves substantial memory reduction on three discretized PDE-constrained optimization applications.

97 MATHEMATICS AND COMPUTING↗

A Memory Efficient Lock-Free Circular Queue

Hardware queues are import in many applications, such as data transfer, synchronization of concurrent modules with the need of mutual exclusion constructs. State of the art bounded (of a fixed size) lock free circular queues are implemented either by read/write atomic operations, or barrier conditions, or by separating dequeue and enqueue operations. However, these queues always require an unused element at all the times to safe-guard the front and rear pointers of the queue, so as to avoid data race conditions, which leads to the waste of memory. The waste of memory is especially disadvantageous in applications such as I/O data transfer, and image transfer between processing filters, when large element size is needed, We propose a lock-free solution of the bounded circular queue through read/write atomic operations, but without the need of an extra element in the queue. The proposed solution is implemented and verified in both Verilog and ’C’ languages. We also demonstrate its effectiveness by comparing its area and delay metrics with the implementations of other existing designs of queue.

Miniskar, Narasinga Rao↗

Memory-efficient emulation of physical tabular data using quadtree decomposition

Computationally expensive functions are sometimes replaced in simulations with an emulator that approx-imates the true function (e.g., equations of state, wavelength-dependent opacity, or composition-dependent materials properties). For functions that have a constrained domain of interest, this can be done by discretizing the domain and performing a local interpolation on the tabulated function values of each local domain. For these so-called tabular data methods, the method of discretizing the domain and mapping the input space to each subdomain can drastically influence the memory and computational costs of the emulator. This is especially true for functions that vary drastically in different regions. We present a method for domain discretization and mapping that utilizes quadtrees, which results in significant reductions in the size of the emulator with minimal increases to computational costs or loss of global accuracy. We apply our method to the electron-positron Helmholtz free energy equation of state and show over an order of magnitude reduction in memory costs for reasonable levels of numerical accuracy.

97 MATHEMATICS AND COMPUTING↗

Efficient Memory Access with NumPy Global Arrays using Local Memory Access

This paper discusses the work completed working with Global Arrays of data on distributed multi-computer systems and improving their performance. The tasks completed were done at Pacific Northwest National Laboratory in the Science Undergrad Laboratory Internship program in the summer of 2013 for the Data Intensive Computing Group in the Fundamental and Computational Sciences DIrectorate. This work was done on the Global Arrays Toolkit developed by this group. This toolkit is an interface for programmers to more easily create arrays of data on networks of computers. This is useful because scientific computation is often done on large amounts of data sometimes so large that individual computers cannot hold all of it. This data is held in array form and can best be processed on supercomputers which often consist of a network of individual computers doing their computation in parallel. One major challenge for this sort of programming is that operations on arrays on multiple computers is very complex and an interface is needed so that these arrays seem like they are on a single computer. This is what global arrays does. The work done here is to use more efficient operations on that data that requires less copying of data to be completed. This saves a lot of time because copying data on many different computers is time intensive. The way this challenge was solved is when data to be operated on with binary operations are on the same computer, they are not copied when they are accessed. When they are on separate computers, only one set is copied when accessed. This saves time because of less copying done although more data access operations were done.

Daily, Jeffrey A.↗

Memory-Efficient Onboard Rock Segmentation

Rockster-MER is an autonomous perception capability that was uploaded to the Mars Exploration Rover Opportunity in December 2009. This software provides the vision front end for a larger software system known as AEGIS (Autonomous Exploration for Gathering Increased Science), which was recently named 2011 NASA Software of the Year. As the first step in AEGIS, Rockster-MER analyzes an image captured by the rover, and detects and automatically identifies the boundary contours of rocks and regions of outcrop present in the scene. This initial segmentation step reduces the data volume from millions of pixels into hundreds (or fewer) of rock contours. Subsequent stages of AEGIS then prioritize the best rocks according to scientist- defined preferences and take high-resolution, follow-up observations. Rockster-MER has performed robustly from the outset on the Mars surface under challenging conditions. Rockster-MER is a specially adapted, embedded version of the original Rockster algorithm ("Rock Segmentation Through Edge Regrouping," (NPO- 44417) Software Tech Briefs, September 2008, p. 25). Although the new version performs the same basic task as the original code, the software has been (1) significantly upgraded to overcome the severe onboard re source limitations (CPU, memory, power, time) and (2) "bulletproofed" through code reviews and extensive testing and profiling to avoid the occurrence of faults. Because of the limited computational power of the RAD6000 flight processor on Opportunity (roughly two orders of magnitude slower than a modern workstation), the algorithm was heavily tuned to improve its speed. Several functional elements of the original algorithm were removed as a result of an extensive cost/benefit analysis conducted on a large set of archived rover images. The algorithm was also required to operate below a stringent 4MB high-water memory ceiling; hence, numerous tricks and strategies were introduced to reduce the memory footprint. Local filtering operations were re-coded to operate on horizontal data stripes across the image. Data types were reduced to smaller sizes where possible. Binary- valued intermediate results were squeezed into a more compact, one-bit-per-pixel representation through bit packing and bit manipulation macros. An estimated 16-fold reduction in memory footprint relative to the original Rockster algorithm was achieved. The resulting memory footprint is less than four times the base image size. Also, memory allocation calls were modified to draw from a static pool and consolidated to reduce memory management overhead and fragmentation. Rockster-MER has now been run onboard Opportunity numerous times as part of AEGIS with exceptional performance. Sample results are available on the AEGIS website at http://aegis.jpl.nasa.gov.

Burl, Michael C.↗

Memory-efficient optimization of Gyrokinetic particle-to-grid interpolation for multicore processors

We present multicore parallelization strategies for the particle-to-grid interpolation step in the Gyrokinetic Toroidal Code (GTC), a 3D particle-in-cell (PIC) application to study turbulent transport in magnetic-confinement fusion devices. Particle-grid interpolation is a known performance bottleneck in several PIC applications. In GTC, this step involves particles depositing charges to a 3D toroidal mesh, and multiple particles may contribute to the charge at a grid point. We design new parallel algorithms for the GTC charge deposition kernel, and analyze their performance on three leading multicore platforms. We implement thirteen different variants for this kernel and identify the best-performing ones given typical PIC parameters such as the grid size, number of particles per cell, and the GTC-specific particle Larmor radius variation. We find that our best strategies can be 2x faster than the reference optimized MPI implementation, and our analysis provides insight into desirable architectural features for high-performance PIC simulation codes.

97 MATHEMATICS AND COMPUTING↗

Memory-efficient decoding of LDPC codes

We present a low-complexity quantization scheme for the implementation of regular (3,6) LDPC codes. The quantization parameters are optimized to maximize the mutual information between the source and the quantized messages. Using this non-uniform quantized belief propagation algorithm, we have simulated that an optimized 3-bit quantizer operates with 0.2dB implementation loss relative to a floating point decoder, and an optimized 4-bit quantizer operates less than 0.1dB quantization loss.

Low-Density-Parity-Check (LDPC)↗

Efficient Machine Learning Approach for Optimizing Scientific Computing Applications on Emerging HPC Architectures

Efficient parallel implementations of scientific applications on multi-core CPUs with accelerators such as GPUs and Xeon Phis is challenging. This requires - exploiting the data parallel architecture of the accelerator along with the vector pipelines of modern x86 CPU architectures, load balancing, and efficient memory transfer between different devices. It is relatively easy to meet these requirements for highly structured scientific applications. In contrast, a number of scientific and engineering applications are unstructured. Getting performance on accelerators for these applications is extremely challenging because many of these applications employ irregular algorithms which exhibit data-dependent control-ow and irregular memory accesses. Furthermore, these applications are often iterative with dependency between steps, and thus making it hard to parallelize across steps. As a result, parallelism in these applications is often limited to a single step. Numerical simulation of charged particles beam dynamics is one such application where the distribution of work and memory access pattern at each time step is irregular. Applications with these properties tend to present significant branch and memory divergence, load imbalance between different processor cores, and poor compute and memory utilization. Prior research on parallelizing such irregular applications have been focused around optimizing the irregular, data-dependent memory accesses and control-ow during a single step of the application independent of the other steps, with the assumption that these patterns are completely unpredictable. We observed that the structure of computation leading to control-ow divergence and irregular memory accesses in one step is similar to that in the next step. It is possible to predict this structure in the current step by observing the computation structure of previous steps. In this dissertation, we present novel machine learning based optimization techniques to address the parallel implementation challenges of such irregular applications on different HPC architectures. In particular, we use supervised learning to predict the computation structure and use it to address the control-ow and memory access irregularities in the parallel implementation of such applications on GPUs, Xeon Phis, and heterogeneous architectures composed of multi-core CPUs with GPUs or Xeon Phis. We use numerical simulation of charged particles beam dynamics simulation as a motivating example throughout the dissertation to present our new approach, though they should be equally applicable to a wide range of irregular applications. The machine learning approach presented here use predictive analytics and forecasting techniques to adaptively model and track the irregular memory access pattern at each time step of the simulation to anticipate the future memory access pattern. Access pattern forecasts can then be used to formulate optimization decisions during application execution which improves the performance of the application at a future time step based on the observations from earlier time steps. In heterogeneous architectures, forecasts can also be used to improve the memory performance and resource utilization of all the processing units to deliver a good aggregate performance. We used these optimization techniques and anticipation strategy to design a cache-aware, memory efficient parallel algorithm to address the irregularities in the parallel implementation of charged particles beam dynamics simulation on different HPC architectures. Experimental result using a diverse mix of HPC architectures shows that our approach in using anticipation strategy is effective in maximizing data reuse, ensuring workload balance, minimizing branch and memory divergence, and in improving resource utilization.

Arumugam, Kamesh↗

Efficient multimode quantum memory based on photon echo in an optimal QED cavity

Effective multimode photon echo quantum memory on multiatomic ensemble in the QED cavity is proposed. We obtain the analytical solution for the quantum memory efficiency that can be equal to unity when optimal conditions for the cavity and atomic parameters are held. Detailed analysis of the optimal conditions is performed. Numerical estimation for realistic atomic and cavity parameters demonstrates the high efficiency of the quantum memory for an optically thin resonant atomic system that opens a door for real applications.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗