Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “multithreaded architecture”

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 19 records
All sourcesNASA NTRSDOE OSTI
NASA NTRS1998

The Tera Multithreaded Architecture and Unstructured Meshes

The Tera Multithreaded Architecture (MTA) is a new parallel supercomputer currently being installed at San Diego Supercomputing Center (SDSC). This machine has an architecture quite different from contemporary parallel machines. The computational processor is a custom design and the machine uses hardware to support very fine grained multithreading. The main memory is shared, hardware randomized and flat. These features make the machine highly suited to the execution of unstructured mesh problems, which are difficult to parallelize on other architectures. We report the results of a study carried out during July-August 1998 to evaluate the execution of EUL3D, a code that solves the Euler equations on an unstructured mesh, on the 2 processor Tera MTA at SDSC. Our investigation shows that parallelization of an unstructured code is extremely easy on the Tera. We were able to get an existing parallel code (designed for a shared memory machine), running on the Tera by changing only the compiler directives. Furthermore, a serial version of this code was compiled to run in parallel on the Tera by judicious use of directives to invoke the "full/empty" tag bits of the machine to obtain synchronization. This version achieves 212 and 406 Mflop/s on one and two processors respectively, and requires no attention to partitioning or placement of data issues that would be of paramount importance in other parallel architectures.

Bokhari, Shahid H.↗
DOE OSTI2015

Codesign Lessons Learned from Implementing Graph Matching on Multithreaded Architectures

Co-design of algorithms and architectures is an effective way to address the performance of irregular applications on multithreaded architectures. We explore the interplay between algorithm design and architectural features using graph matching as a case study. We present the key lessons that we have learnt as a means to influence co-design of algorithms and architecture for execution of data-intensive irregular workloads.

matching, graph algorithms, multithreaded architec↗
DOE OSTI2017

Parallel k-means++

A parallelization of the k-means++ seed selection algorithm on three distinct hardware platforms: GPU, multicore CPU, and multithreaded architecture. K-means++ was developed by David Arthur and Sergei Vassilvitskii in 2007 as an extension of the k-means data clustering technique. These algorithms allow people to cluster multidimensional data, by attempting to minimize the mean distance of data points within a cluster. K-means++ improved upon traditional k-means by using a more intelligent approach to selecting the initial seeds for the clustering process. While k-means++ has become a popular alternative to traditional k-means clustering, little work has been done to parallelize this technique. We have developed original C++ code for parallelizing the algorithm on three unique hardware architectures: GPU using NVidia's CUDA/Thrust framework, multicore CPU using OpenMP, and the Cray XMT multithreaded architecture. By parallelizing the process for these platforms, we are able to perform k-means++ clustering much more quickly than it could be done before.

Source record↗
DOE OSTI2016

A fast band–Krylov eigensolver for macromolecular functional motion simulation on multicore architectures and graphics processors

We introduce a new iterative Krylov subspace-based eigensolver for the simulation of macromolecular motions on desktop multithreaded platforms equipped with multicore processors and, possibly, a graphics accelerator (GPU). The method consists of two stages, with the original problem first reduced into a simpler band-structured form by means of a high-performance compute-intensive procedure. This is followed by a memory-intensive but low-cost Krylov iteration, which is off-loaded to be computed on the GPU by means of an efficient data-parallel kernel. The experimental results reveal the performance of the new eigensolver. Concretely, when applied to the simulation of macromolecules with a few thousands degrees of freedom and the number of eigenpairs to be computed is small to moderate, the new solver outperforms other methods implemented as part of high-performance numerical linear algebra packages for multithreaded architectures.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2014

New Effective Multithreaded Matching Algorithms

Matching is an important combinatorial problem with a number of applications in areas such as community detection, sparse linear algebra, and network alignment. Since computing optimal matchings can be very time consuming, several fast approximation algorithms, both sequential and parallel, have been suggested. Common to the algorithms giving the best solutions is that they tend to be sequential by nature, while algorithms more suitable for parallel computation give solutions of less quality. We present a new simple 1 2 -approximation algorithm for the weighted matching problem. This algorithm is both faster than any other suggested sequential 1 2 -approximation algorithm on almost all inputs and also scales better than previous multithreaded algorithms. We further extend this to a general scalable multithreaded algorithm that computes matchings of weight comparable with the best sequential algorithms. The performance of the suggested algorithms is documented through extensive experiments on different multithreaded architectures.

matching, parallel algorithms↗
DOE OSTI2016

A survey of techniques for architecting and managing GPU register file

To support their massively-multithreaded architecture, GPUs use very large register file (RF) which has a capacity higher than even L1 and L2 caches. In total contrast, traditional CPUs use tiny RF and much larger caches to optimize latency. Due to these differences, along with the crucial impact of RF in determining GPU performance, novel and intelligent techniques are required for managing GPU RF. In this paper, we survey the techniques for designing and managing GPU RF. We discuss techniques related to performance, energy and reliability aspects of RF. To emphasize the similarities and differences between the techniques, we classify them along several parameters. Lastly, the aim of this paper is to synthesize the state-of-art developments in RF management and also stimulate further research in this area.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
NASA NTRS1992

A simple modern correctness condition for a space-based high-performance multiprocessor

A number of U.S. national programs, including space-based detection of ballistic missile launches, envisage putting significant computing power into space. Given sufficient progress in low-power VLSI, multichip-module packaging and liquid-cooling technologies, we will see design of high-performance multiprocessors for individual satellites. In very high speed implementations, performance depends critically on tolerating large latencies in interprocessor communication; without latency tolerance, performance is limited by the vastly differing time scales in processor and data-memory modules, including interconnect times. The modern approach to tolerating remote-communication cost in scalable, shared-memory multiprocessors is to use a multithreaded architecture, and alter the semantics of shared memory slightly, at the price of forcing the programmer either to reason about program correctness in a relaxed consistency model or to agree to program in a constrained style. The literature on multiprocessor correctness conditions has become increasingly complex, and sometimes confusing, which may hinder its practical application. We propose a simple modern correctness condition for a high-performance, shared-memory multiprocessor; the correctness condition is based on a simple interface between the multiprocessor architecture and a high-performance, shared-memory multiprocessor; the correctness condition is based on a simple interface between the multiprocessor architecture and the parallel programming system.

Probst, David K.↗
DOE OSTI2016

Parallel k-means++ for Multiple Shared-Memory Architectures

In recent years k-means++ has become a popular initialization technique for improved k-means clustering. To date, most of the work done to improve its performance has involved parallelizing algorithms that are only approximations of k-means++. In this paper we present a parallelization of the exact k-means++ algorithm, with a proof of its correctness. We develop implementations for three distinct shared-memory architectures: multicore CPU, high performance GPU, and the massively multithreaded Cray XMT platform. We demonstrate the scalability of the algorithm on each platform. In addition we present a visual approach for showing which platform performed k-means++ the fastest for varying data sizes.

data clustering↗
NASA NTRS2000

HTMT-class Latency Tolerant Parallel Architecture for Petaflops Scale Computation

Computational Aero Sciences and other numeric intensive computation disciplines demand computing throughputs substantially greater than the Teraflops scale systems only now becoming available. The related fields of fluids, structures, thermal, combustion, and dynamic controls are among the interdisciplinary areas that in combination with sufficient resolution and advanced adaptive techniques may force performance requirements towards Petaflops. This will be especially true for compute intensive models such as Navier-Stokes are or when such system models are only part of a larger design optimization computation involving many design points. Yet recent experience with conventional MPP configurations comprising commodity processing and memory components has shown that larger scale frequently results in higher programming difficulty and lower system efficiency. While important advances in system software and algorithms techniques have had some impact on efficiency and programmability for certain classes of problems, in general it is unlikely that software alone will resolve the challenges to higher scalability. As in the past, future generations of high-end computers may require a combination of hardware architecture and system software advances to enable efficient operation at a Petaflops level. The NASA led HTMT project has engaged the talents of a broad interdisciplinary team to develop a new strategy in high-end system architecture to deliver petaflops scale computing in the 2004/5 timeframe. The Hybrid-Technology, MultiThreaded parallel computer architecture incorporates several advanced technologies in combination with an innovative dynamic adaptive scheduling mechanism to provide unprecedented performance and efficiency within practical constraints of cost, complexity, and power consumption. The emerging superconductor Rapid Single Flux Quantum electronics can operate at 100 GHz (the record is 770 GHz) and one percent of the power required by convention semiconductor logic. Wave Division Multiplexing optical communications can approach a peak per fiber bandwidth of 1 Tbps and the new Data Vortex network topology employing this technology can connect tens of thousands of ports providing a bi-section bandwidth on the order of a Petabyte per second with latencies well below 100 nanoseconds, even under heavy loads. Processor-in-Memory (PIM) technology combines logic and memory on the same chip exposing the internal bandwidth of the memory row buffers at low latency. And holographic storage photorefractive storage technologies provide high-density memory with access a thousand times faster than conventional disk technologies. Together these technologies enable a new class of shared memory system architecture with a peak performance in the range of a Petaflops but size and power requirements comparable to today's largest Teraflops scale systems. To achieve high-sustained performance, HTMT combines an advanced multithreading processor architecture with a memory-driven coarse-grained latency management strategy called "percolation", yielding high efficiency while reducing the much of the parallel programming burden. This paper will present the basic system architecture characteristics made possible through this series of advanced technologies and then give a detailed description of the new percolation approach to runtime latency management.

Sterling, Thomas↗
NASA NTRS2002

Gilgamesh: A Multithreaded Processor-In-Memory Architecture for Petaflops Computing

Processor-in-Memory (PIM) architectures avoid the von Neumann bottleneck in conventional machines by integrating high-density DRAM and CMOS logic on the same chip. Parallel systems based on this new technology are expected to provide higher scalability, adaptability, robustness, fault tolerance and lower power consumption than current MPPs or commodity clusters. In this paper we describe the design of Gilgamesh, a PIM-based massively parallel architecture, and elements of its execution model. Gilgamesh extends existing PIM capabilities by incorporating advanced mechanisms for virtualizing tasks and data and providing adaptive resource management for load balancing and latency tolerance. The Gilgamesh execution model is based on macroservers, a middleware layer which supports object-based runtime management of data and threads allowing explicit and dynamic control of locality and load balancing. The paper concludes with a discussion of related research activities and an outlook to future work.

management locality load balance↗
DOE OSTI2016

SMT-Aware Instantaneous Footprint Optimization

Modern architectures employ simultaneous multithreading (SMT) to increase thread-level parallelism. SMT threads share many functional units and the whole memory hierarchy of a physical core. Without a careful code design, SMT threads can easily contend with each other for these shared resources, causing severe performance degradation. Minimizing SMT thread contention for HPC applications running on dedicated platforms is very challenging, because they usually spawn threads within Single Program Multiple Data (SPMD) models. To address this important issue, we introduce a simple scheme for SMT-aware code optimization, which aims to reduce the memory contention across SMT threads.

Instantaneous Footprint↗
DOE OSTI2018

The Ongoing Evolution of OpenMP

Here, this paper presents an overview of the past, present and future of the OpenMP application programming interface (API). While the API originally specified a small set of directives that guided shared memory fork-join parallelization of loops and program sections, OpenMP now provides a richer set of directives that capture a wide range of parallelization strategies that are not strictly limited to shared memory. As we look toward the future of OpenMP, we immediately see further evolution of the support for that range of parallelization strategies and the addition of direct support for debugging and performance analysis tools. Looking beyond the next major release of the specification of the OpenMP API, we expect the specification eventually to include support for more parallelization strategies and to embrace closer integration into its Fortran, C and, in particular, C++ base languages, which will likely require the API to adopt additional programming abstractions.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2018

System Architecture Directions for Post-SoC/32-bit Networked Sensors

The emergence of low-power 32-bit Systems-on-Chip (SoCs), which integrate a 32-bit MCU, radio, and flash, presents an opportunity to re-examine design points and trade-offs at all levels of the system architecture of networked sensors. To this end, we develop a post-SoC/32-bit design point called Hamilton, showing that using integrated components enables a ~$7 core and shifts hardware modularity to design time. We study the interaction between hardware and embedded operating systems, identifying that (1) post-SoC motes provide lower idle current (5.9 μA) than traditional 16-bit motes, (2) 32-bit MCUs are a major energy consumer (e.g., tick increases idle current >50 times), comparable to radios, and (3) thread-based concurrency is viable, requiring only 8.3 μs of context switch time. We design a system architecture, based on a tickless multithreading operating system, with cooperative/adaptive clocking, advanced sensor abstraction, and preemptive packet processing. Its efficient MCU control improves concurrency with ~30% less energy consumption. Together, these developments set the system architecture for networked sensors in a new direction.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
NASA NTRS2006

SALT: The Simulator for the Analysis of LWP Timing

With the emergence of new processor architectures that are highly multithreaded, and support features such as full/empty memory semantics and split-phase memory transactions, the need for a processor simulator to handle these features becomes apparent. This paper describes such a simulator, called SALT.

simulation↗
DOE OSTI2018

Multithreaded sparse matrix-matrix multiplication for many-core and GPU architectures

Sparse matrix-matrix multiplication is a key kernel that has applications in several domains such as scientific computing and graph analysis. Several algorithms have been studied in the past for this foundational kernel. In this work, we develop parallel algorithms for sparse matrix-matrix multiplication with a focus on performance portability across different high performance computing architectures. The performance of these algorithms depend on the data structures used in them. We compare different types of accumulators in these algorithms and demonstrate the performance difference between these data structures. Furthermore, we develop a meta-algorithm, kkSpGEMM, to choose the right algorithm and data structure based on the characteristics of the problem. We show performance comparisons on three architectures and demonstrate the need for the community to develop two phase sparse matrix-matrix multiplication implementations for efficient reuse of the data structures involved.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Optimizing the hypre solver for manycore and GPU architectures

The solution of large-scale combustion problems with codes such as Uintah on modern computer architectures requires the use of multithreading and GPUs to achieve performance. Uintah uses a low-Mach number approximation that requires iteratively solving a large system of linear equations. The Hypre iterative solver has solved such systems in a scalable way for Uintah, but the use of OpenMP with Hypre leads to at least slowdown due to OpenMP overheads. The proposed solution uses the MPI Endpoints within Hypre, where each team of threads acts as a different MPI rank. This approach minimizes OpenMP synchronization overhead and performs as fast or (up to 1.44) faster than Hypre's MPI-only version, and allows the rest of Uintah to be optimized using OpenMP. The profiling of the GPU version of Hypre shows the bottleneck to be the launch overhead of thousands of micro-kernels. The GPU performance was improved by fusing these micro-kernels and was further optimized by using Cuda-aware MPI, resulting in an overall speedup of 1.16—1.44 compared to the baseline GPU implementation. The above optimization strategies were published in the International Conference on Computational Science 2020 [1]. This work extends the previously published research by carrying out the second phase of communication-centered optimizations in Hypre to improve its scalability on large-scale supercomputers. Additionally, this includes an efficient non-blocking inter-thread communication scheme, communication-reducing patch assignment, and expression of logical communication parallelism to a new version of the MPICH library that utilizes the underlying network parallelism [2]. The above optimizations avoid communication bottlenecks previously observed during strong scaling and improve performance by up to 2 on 256 nodes of Intel Knight's Landing processor.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2011

DAQ: Software Architecture for Data Acquisition in Sounding Rockets

A multithreaded software application was developed by Jet Propulsion Lab (JPL) to collect a set of correlated imagery, Inertial Measurement Unit (IMU) and GPS data for a Wallops Flight Facility (WFF) sounding rocket flight. The data set will be used to advance Terrain Relative Navigation (TRN) technology algorithms being researched at JPL. This paper describes the software architecture and the tests used to meet the timing and data rate requirements for the software used to collect the dataset. Also discussed are the challenges of using commercial off the shelf (COTS) flight hardware and open source software. This includes multiple Camera Link (C-link) based cameras, a Pentium-M based computer, and Linux Fedora 11 operating system. Additionally, the paper talks about the history of the software architecture's usage in other JPL projects and its applicability for future missions, such as cubesats, UAVs, and research planes/balloons. Also talked about will be the human aspect of project especially JPL's Phaeton program and the results of the launch.

Ahmad, Mohammad↗
DOE OSTI2014

Performance Tuning of Fock Matrix and Two-Electron Integral Calculations for NWChem on Leading HPC Platforms

Attaining performance in the evaluation of two-electron repulsion integrals and constructing the Fock matrix is of considerable importance to the computational chemistry community. Due to its numerical complexity improving the performance behavior across a variety of leading supercomputing platforms is an increasing challenge due to the significant diversity in high-performance computing architectures. In this paper, we present our successful tuning methodology for these important numerical methods on the Cray XE6, the Cray XC30, the IBM BG/Q, as well as the Intel Xeon Phi. Our optimization schemes leverage key architectural features including vectorization and simultaneous multithreading, and results in speedups of up to 2.5x compared with the original implementation.

Shan, Hongzhan↗