Search NASA⌕ Search

SEARCH · Search NASA

Results for “Coprocessor”

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 73 records · Page 4

TH-AB-207A-07: Radiation Dose Simulation for a Newly Proposed Dynamic Bowtie Filters for CT Using Fast Monte Carlo Methods

Purpose: Dynamic bowtie filter is an innovative design capable of modulating the X-ray and balancing the flux in the detectors, and it introduces a new way of patient-specific CT scan optimizations. This study demonstrates the feasibility of performing fast Monte Carlo dose calculation for a type of dynamic bowtie filter for cone-beam CT (Liu et al. 2014 9(7) PloS one) using MIC coprocessors. Methods: The dynamic bowtie filter in question consists of a highly attenuating bowtie component (HB) and a weakly attenuating bowtie (WB). The HB is filled with CeCl3 solution and its surface is defined by a transcendental equation. The WB is an elliptical cylinder filled with air and immersed in the HB. As the scanner rotates, the orientation of WB remains the same with the static patient. In our Monte Carlo simulation, the HB was approximated by 576 boxes. The phantom was a voxelized elliptical cylinder composed of PMMA and surrounded by air (44cm×44cm×40cm, 1000×1000×1 voxels). The dose to the PMMA phantom was tallied with 0.15% statistical uncertainty under 100 kVp source. Two Monte Carlo codes ARCHER and MCNP-6.1 were compared. Both used double-precision. Compiler flags that may trade accuracy for speed were avoided. Results: The wall time of the simulation was 25.4 seconds by ARCHER on a 5110P MIC, 40 seconds on a X5650 CPU, and 523 seconds by the multithreaded MCNP on the same CPU. The high performance of ARCHER is attributed to the parameterized geometry and vectorization of the program hotspots. Conclusion: The dynamic bowtie filter modeled in this study is able to effectively reduce the dynamic range of the detected signals for the photon-counting detectors. With appropriate software optimization methods, the accelerator-based (MIC and GPU) Monte Carlo dose engines have shown good performance and can contribute to patient-specific CT scan optimizations.

60 APPLIED LIFE SCIENCES↗

WARP

WARP, which can stand for ``Weaving All the Random Particles,'' is a three-dimensional (3D) continuous energy Monte Carlo neutron transport code developed at UC Berkeley to efficiently execute on NVIDIA graphics processing unit (GPU) platforms. WARP accelerates Monte Carlo simulations while preserving the benefits of using the Monte Carlo method, namely, that very few physical and geometrical simplifications are applied. WARP is able to calculate multiplication factors, neutron flux distributions (in both space and energy), and fission source distributions for time-independent neutron transport problems. It can run in both criticality or fixed source modes, but fixed source mode is currently not robust, optimized, or maintained in the newest version. WARP can transport neutrons in unrestricted arrangements of parallelepipeds, hexagonal prisms, cylinders, and spheres. The goal of developing WARP is to investigate algorithms that can grow into a full-featured, continuous energy, Monte Carlo neutron transport code that is accelerated by running on GPUs. The crux of the effort is to make Monte Carlo calculations faster while producing accurate results. Modern supercomputers are commonly being built with GPU coprocessor cards in their nodes to increase their computational efficiency and performance. GPUs execute efficiently on data-parallel problems, but most CPU codes, including those for Monte Carlo neutral particle transport, are predominantly task-parallel. WARP uses a data-parallel neutron transport algorithm to take advantage of the computing power GPUs offer.

Bergmann, RyanM. [University of California - Berke↗

High-performance epistasis detection in quantitative trait GWAS

epiSNP is a program for identifying pairwise single nucleotide polymorphism (SNP) interactions (epistasis) in quantitative-trait genome-wide association studies (GWAS). A parallel MPI version (EPISNPmpi) was created in 2008 to address this computationally expensive analysis on large data sets with many quantitative traits and SNP markers. However, the falling cost of genotyping has led to an explosion of large-scale GWAS data sets that challenge EPISNPmpi’s ability to compute results in a reasonable amount of time. Therefore, we optimized epiSNP for modern multi-core and highly parallel many-core processors to efficiently handle these large data sets. This paper describes the serial optimizations, dynamic load balancing using MPI-3 RMA operations, and shared-memory parallelization with OpenMP to further enhance load balancing and allow execution on the Intel Xeon Phi coprocessor (MIC). For a large GWAS data set, our optimizations provided a 38.43× speedup over EPISNPmpi on 126 nodes using 2 MICs on TACC’s Stampede Supercomputer. We also describe a Coarray Fortran (CAF) version that demonstrates the suitability of PGAS languages for problems with this computational pattern. We show that the Coarray version performs competitively with the MPI version on the NERSC Edison Cray XC30 supercomputer. Finally, the performance benefits of hyper-threading for this application on Edison (average 1.35× speedup) are demonstrated.

97 MATHEMATICS AND COMPUTING↗

An efficient MPI/OpenMP parallelization of the Hartree–Fock–Roothaan method for the first generation of Intel® Xeon Phi™ processor architecture

The Hartree-Fock (HF) method in the quantum chemistry package GAMESS represents one of the most irregular algorithms in computation today. Major steps in the calculation are the irregular computation of electron repulsion integrals (ERIs) and the building of the Fock matrix. These are the central components of the main Self Consistent Field (SCF) loop, the key hotspot in Electronic Structure (ES) codes. By threading the MPI ranks in the official release of the GAMESS code, we not only speed up the main SCF loop (4x to 6x for large systems), but also achieve a significant (>2x) reduction in the overall memory footprint. These improvements are a direct consequence of memory access optimizations within the MPI ranks. We benchmark our implementation against the official release of the GAMESS code on the Intel R Xeon PhiTM supercomputer. Here, scaling numbers are reported on up to 7,680 cores on Intel Xeon Phi coprocessors.

97 MATHEMATICS AND COMPUTING↗

LANL SDAV Visualization Update [Slides]

Xeon Phi (MIC) on Stampede: •To demonstrate the portability of our algorithms, the same code was compiled to the Thrust OpenMP backend (including our own OpenMP implementation of scan) and run on a 2563 particle data set on an Intel Xeon Phi SE10P (MIC) Coprocessor on a single node of Stampede at TACC • PISTON version scales to more cores than running the existing serial algorithms with multiple MPI processes. Titan: • This test problem has ~90 million particles per process. • Due to memory constraints on the GPUs, we utilize a hybrid approach, in which the halos are computed on the CPU but the centers on the GPU. • The PISTON MBP center finding algorithm requires much less memory than the halo finding algorithm but provides the large majority of the speed-up, since MBP center finding takes much longer than FOF halo finding with the original CPU code. In-situ Integration in HACC: • Successfully ran 500 time-step, 512 3 particle simulation on Moonlight using our GPU halo and center finders integrated with HACC in-situ • Completed prototype integration with CosmoTools

97 MATHEMATICS AND COMPUTING↗

GPU/MIC Acceleration of the LHC High Level Trigger to Extend the Physics Reach at the LHC

The quest for rare new physics phenomena leads the PI to propose evaluation of coprocessors based on Graphics Processing Units (GPUs) and the Intel Many Integrated Core (MIC) architecture for integration into the trigger system at LHC. This will require development of a new massively parallel implementation of the well known Combinatorial Track Finder which uses the Kalman Filter to accelerate processing of data from the silicon pixel and microstrip detectors and reconstruct the trajectory of all charged particles down to momentums of 100 MeV. It is expected to run at least one order of magnitude faster than an equivalent algorithm on a quad core CPU for extreme pileup scenarios of 100 interactions per bunch crossing. The new tracking algorithms will be developed and optimized separately on the GPU and Intel MIC and then evaluated against each other for performance and power efficiency. The results will be used to project the cost of the proposed hardware architectures for the HLT server farm, taking into account the long term projections of the main vendors in the market (AMD, Intel, and NVIDIA) over the next 10 years. Extensive experience and familiarity of the PI with the LHC tracker and trigger requirements led to the development of a complementary tracking algorithm that is described in [arxiv: 1305.4855], [arxiv: 1309.6275] and preliminary results accepted to JINST.

97 MATHEMATICS AND COMPUTING↗

Beyond Moore’s Law: Exploring the Future of Computation

Conclusions: Emerging computational hardware may fundamentally change optimization algorithm development; Ising Coprocessors are like ALUs or GPUs for optimization!; Based on initial benchmarking efforts D-Wave hardware is not outperforming state-of-the-art alternatives, but seems competitive

97 MATHEMATICS AND COMPUTING↗

FPGAs as a Service to Accelerate Machine Learning Inference [PowerPoint]

Large-scale particle physics experiments face challenging demands for high-throughput computing resources both now and in the future. New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in particle physics for simulation, reconstruction, and analysis are naturally deployed on such platforms. We demonstrate that the acceleration of machine learning inference as a web service represents a heterogeneous computing solution for particle physics experiments that requires minimal modification to the current computing model. As examples, we retrain the ResNet-50 convolutional neural network to demonstrate state-of-the-art performance for top quark jet tagging at the LHC, and apply a ResNet-50 model with transfer learning for neutrino event classification. Using Project Brainwave b y Microsoft to accelerate the ResNet-50 image classification model, we achieve average inference times of 60 (10) milliseconds with our experimental physics software framework using Brainwave as a cloud (edge or on-premises) service, representing an improvement by a factor of approximately 30 (175) in model inference latency over traditional CPU inference in current experimental hardware. A single FPGA service accessed by many CPUs achieves a throughput of 600--700 inferences per second using an image batch of one, comparable to large batch-size GPU throughput and significantly better than small batch-size GPU throughput. Deployed as an edge or cloud service for the particle physics computing model, coprocessor accelerators can have a higher duty cycle and are potentially much more cost-effective.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Introduction to Graphics Processing Units [Slides]

Graphics Processing Units are designed for fast graphics processing. Graphics are a form of arithemetic and have gradually evolved a design that is also usefule for non-graphics computing. They are not standalone, but work alongside a CPU(host)-coprocessor.

97 MATHEMATICS AND COMPUTING↗

CompF2: Theoretical Calculations and Simulation Topical Group Report

This report summarizes the work of the Computational Frontier topical group on theoretical calculations and simulation for Snowmass 2021. We discuss the challenges, potential solutions, and needs facing six diverse but related topical areas that span the subject of theoretical calculations and simulation in high energy physics (HEP): cosmic calculations, particle accelerator modeling, detector simulation, event generators, perturbative calculations, and lattice QCD (quantum chromodynamics). The challenges arise from the next generations of HEP experiments, which will include more complex instruments, provide larger data volumes, and perform more precise measurements. Calculations and simulations will need to keep up with these increased requirements. The other aspect of the challenge is the evolution of computing landscape away from general-purpose computing on CPUs and toward special-purpose accelerators and coprocessors such as GPUs and FPGAs. These newer devices can provide substantial improvements for certain categories of algorithms, at the expense of more specialized programming and memory and data access patterns.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Searching for Strongly Coupled Dark Sectors with Unsupervised and Generative Learning

Recipient of the URA Early Career Award for groundbreaking searches for dark matter arising from strongly coupled dark sectors with the CMS detector, pioneering work in ML-based model-independent anomaly detection for collider and astrophysics experiments, and leadership in the development of new AI/ML techniques to improve event reconstruction and detector simulation in particle physics, as well as novel strategies to accelerate AI inference and throughput with heterogeneous computing using coprocessors as a service.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

A floating-point/multiple-precision processor for airborne applications

A compact input output (I/O) numerical processor capable of performing floating-point, multiple precision and other arithmetic functions at execution times which are at least 100 times faster than comparable software emulation is described. The I/O device is a microcomputer system containing a 16 bit microprocessor, a numerical coprocessor with eight 80 bit registers running at a 5 MHz clock rate, 18K random access memory (RAM) and 16K electrically programmable read only memory (EPROM). The processor acts as an intelligent slave to the host computer and can be programmed in high order languages such as FORTRAN and PL/M-86.

Yee, R.↗

A real-time, portable, microcomputer-based jet engine simulator

Modern piloted flight simulators require detailed models of many aircraft components, such as the airframe, propulsion system, flight deck controls and instrumentation, as well as motion drive and visual display systems. The amount of computing power necessary to implement these systems can exceed that offered by dedicated mainframe computers. One approach to this problem is through the use of distributed computing, where parts of the simulation are assigned to computing subsystems, such as microcomputers. One such subsystem, such as microcomputers. One such subsystem, a real-time, portable, microcomputer-based jet engine simulator, is described in this paper. The simulator will be used at the NASA Ames Vertical Motion Simulator facility to perform calculations previously done on the facility's mainframe computer. The mainframe will continue to do all other system calculations and will interface to the engine simulator through analog I/0. The engine simulator hardware includes a 16-bit microcomputer and floating-point coprocessor. There is an 8 channel analog input board and an 8 channel analog output board. A model of a small turboshaft engine/control is coded in floating-point FORTRAN. The FORTRAN code and a data monitoring program run under the control of an assembly language real-time executive. The monitoring program allows the user to isplay and/or modify simulator variables on-line through a data terminal. A dual disk drive system is used for mass storage of programs and data. The CP/M-86 operating system provides file management and overall system control. The frame time for the simulator is 30 milliseconds, which includes all analog I/0 operations.

Blech, R. A.↗

Floating-point function generation routines for 16-bit microcomputers

Several computer subroutines have been developed that interpolate three types of nonanalytic functions: univariate, bivariate, and map. The routines use data in floating-point form. However, because they are written for use on a 16-bit Intel 8086 system with an 8087 mathematical coprocessor, they execute as fast as routines using data in scaled integer form. Although all of the routines are written in assembly language, they have been implemented in a modular fashion so as to facilitate their use with high-level languages.

Mackin, M. A.↗

A SLAM II simulation model for analyzing space station mission processing requirements

Space station mission processing is modeled via the SLAM 2 simulation language on an IBM 4381 mainframe and an IBM PC microcomputer with 620K RAM, two double-sided disk drives and an 8087 coprocessor chip. Using a time phased mission (payload) schedule and parameters associated with the mission, orbiter (space shuttle) and ground facility databases, estimates for ground facility utilization are computed. Simulation output associated with the science and applications database is used to assess alternative mission schedules.

Linton, D. G.↗

Concurrent system-level error detection using a watchdog processor

This paper describes the design of a watchdog coprocessor for detecting hardware and software errors. The watchdog executes assertions about the process running on the main computer. Both general purpose an special purpose (used to check systems such as digital signal processors, telephone switching systems, or digital flight controllers) watchdog designs are described. The improvement of error coverage by adding control flow checking facilities is discussed. The implementation of the watchdog as a software process is presented.

Mahmood, A.↗

Hardware requirements: A new generation partial reflection radar for studies of the equatorial mesosphere

A new partial reflection (PR) radar is being developed for operation at the proposed Equatorial Observatory. The system is being designed to make maximum use of recent advances in solid-state technology in order to minimize the power requirements. In particular, it is planned to use a solid-state transmitter in place of the tube transmitters previously used in PR systems. Solid-state transmitters have the advantages that they do not need high voltage supplies, they do not require cathode heaters with a corresponding saving in power consumption and parts are readily available and inexpensive. It should be possible to achieve 15 kW peak powers with recently announced fast switching transistors. Since high mean powers are desirable for obtaining good signal-to-noise ratios, it is also planned to phase code the transmitted pulses and decode after coherent integration. All decoding and signal processing will be carried out in dedicated microprocessors before the signals are passed to a microcomputer for on-line analysis. Recent tests have shown that an Olivetti M24 micro (an IBM compatible) running an 8-MHz clock with a 8087 coprocessor can analyze data at least as fast as the minicomputers presently being used with the Adelaide PR rad ar and at a significantly lower cost. The processed winds data will be stored in nonvolatile CMOS RAM modules; about 0.5 to 1 Mbyte is required to store one week's information.

Vincent, R. A.↗

Communication and control in an integrated manufacturing system

Typically, components in a manufacturing system are all centrally controlled. Due to possible communication bottlenecking, unreliability, and inflexibility caused by using a centralized controller, a new concept of system integration called an Integrated Multi-Robot System (IMRS) was developed. The IMRS can be viewed as a distributed real time system. Some of the current research issues being examined to extend the framework of the IMRS to meet its performance goals are presented. These issues include the use of communication coprocessors to enhance performance, the distribution of tasks and the methods of providing fault tolerance in the IMRS. An application example of real time collision detection, as it relates to the IMRS concept, is also presented and discussed.

Shin, Kang G.↗