the cognitive architecture approach claims for massively parallel data structures and processes. However, none of these models fully address the integration of emotion generation and its effects in the context of cogn...
详细信息
the proceedings contain 36 papers. the topics discussed include: mixed-order Sugeno model to predict the resultant force in the milling process for honeycomb sandwich;stoichiometry control of the two gas reactive sput...
ISBN:
(纸本)9781728156255
the proceedings contain 36 papers. the topics discussed include: mixed-order Sugeno model to predict the resultant force in the milling process for honeycomb sandwich;stoichiometry control of the two gas reactive sputtering process;demand side management electric energy consumption data processingarchitectures within internet of things context;development of an LQ regulator for longitudinal vehicle control of an automated vehicle;parking lot exploration strategy;a semi-automated generation of entity relationship diagram based on morphosyntactic tagging from the requirements written in a Serbian natural language;data analytics for health-care risk predictions based on ensemble classifiers and subjective projection;and data analytics for health-care risk predictions based on ensemble classifiers and subjective projection.
Tomography reconstruction is the process of quickly reconstructing the original image form the projection obtained by X-ray radiation. At present, the high-resolution detector of the Shanghai Synchrotron Radiation Fac...
详细信息
ISBN:
(数字)9781728165509
ISBN:
(纸本)9781728165516
Tomography reconstruction is the process of quickly reconstructing the original image form the projection obtained by X-ray radiation. At present, the high-resolution detector of the Shanghai Synchrotron Radiation Facility (SSRF) can scan more than 4GB of tomographic data every 1.5 seconds, and the transmission speed is increased to more than 100GB s -1 . Withthe upgrade of high-resolution detectors and the increase of data transmission volume, the reconstruction computation on cloud has become a bottleneck in improving the speed of tomography reconstruction even if the fastest Gridrec algorithm is adopted. In this paper, we propose an improved serial Gridrec algorithm and a parallel Gridrec algorithm by improving the convolution kernel to optimize the speed of existing image reconstruction algorithms on low cost GPUs for edge computing. On these GPUs, the multi-threaded tomography reconstruction algorithm not only guarantees high-quality results, but also improves the reconstruction speed over original Gridrec algorithm by more than 11x, and over the classic FBP algorithm by more than 234x. Besides the significant speedup, our work would be the first parallel implementation of Gridrec algorithm on GPU for edge computing.
the low-level data processing of the Cherenkov Telescope Array (CTA) and indeed all other existing Cherenkov Telescopes can be broken into four general steps: 1) the processing of air-shower event image time-series, 2...
详细信息
the low-level data processing of the Cherenkov Telescope Array (CTA) and indeed all other existing Cherenkov Telescopes can be broken into four general steps: 1) the processing of air-shower event image time-series, 2) the stereo reconstruction of the incident air showers, and 3) the discrimination of gamma-ray induced showers from those from cosmic rays 4) the determination of the overall system response. the final output for science users is a list of reconstructed gamma-ray-like events and their associated parameters, along with a set of instrumental response functions needed for doing astrophysics. We present a python-based framework, ctapipe, for writing the algorithms required for these processing steps along with a reference prototype pipeline. the code is written with a focus on simplicity and usability by developers with a diverse range of skill sets, and leverages existing code from the science community (AstroPy, SciPy/NumPy, SciKit-Learn, etc). this concept is intended to be a prototype for the final CTA low-level data processing pipeline, allowing physicists to quickly explore low-level Cherenkov telescope data and develop new algorithms. thanks to the framework modularity, computer engineers and data scientists will be able to simultaneously optimize the algorithms and parallelize them using modern computing and big-data architectures to support the high data volumes of CTA.
Radar signal processing is currently done digitally with DSP (digital signal processor) or FPGA (field-programmable gate array) devices. Implementation of radar signal processing at the software level can provide high...
详细信息
ISBN:
(纸本)9781728124186
Radar signal processing is currently done digitally with DSP (digital signal processor) or FPGA (field-programmable gate array) devices. Implementation of radar signal processing at the software level can provide high scalability, but existing research still has poor performance when implemented on the CPU. Meanwhile, the development of graphics processing unit (GPU) technology provides an opportunity to perform processing of radar signals with high performance as well as scaling. this paper focus on processing radar signals using GPUs with case studies of dual polarization FMCW (frequency-modulated continuous wave) weather radar signal processing. In this research has been done the implementation of weather radar signal processing algorithm on 2 platforms, which are serialized using CPU and in parallel using GPU. the results of performance measurements on both platforms show that GPU implementations deliver performance more than 2 times faster than implementations on the CPU.
this paper investigates design and implementation of the signal processing unit for the relay node in a two-way relay multiple-input multiple-output spatial division multiplexing (MIMO-SDM) system using physical-layer...
详细信息
ISBN:
(纸本)9781728102733
this paper investigates design and implementation of the signal processing unit for the relay node in a two-way relay multiple-input multiple-output spatial division multiplexing (MIMO-SDM) system using physical-layer network coding (PNC), reffered to as MIMO-SDM-PNC. Based on Field-programmable gate array (FPGA) platform, two processingarchitectures for zero-forcing (ZF) and minimum mean square error (MMSE) detector are proposed for the relay node. Using the standard pipe-lining and the parallel computing methodologies, a novel architecture is developed in order to achieve low latency and low-area occupation for FPGA implementation. the proposed architecture has been composed in Verilog language and synthesized on the ISE tool for Xilinx FPGA Virtex 7. Experimental results demonstrate that the proposed design offers high performance in terms of low latency and high throughput.
this paper investigates parallel random sampling from a potentially-unending data stream whose elements are revealed in a series of element sequences (minibatches). While sampling from a stream was extensively studied...
详细信息
ISBN:
(纸本)9783030294007;9783030293994
this paper investigates parallel random sampling from a potentially-unending data stream whose elements are revealed in a series of element sequences (minibatches). While sampling from a stream was extensively studied sequentially, not much has been explored in the parallel context, with prior parallel random-sampling algorithms focusing on the static batch model. We present parallelalgorithms for minibatch-stream sampling in two settings: (1) sliding window, which draws samples from a prespecified number of most-recently observed elements, and (2) infinite window, which draws samples from all the elements received. Our algorithms are computationally and memory efficient: their work matches the fastest sequential counterpart, their parallel depth is small (polylogarithmic), and their memory usage matches the best known.
the proceedings contain 18 papers. the special focus in this conference is on High Performance Computing in Computational Science. the topics include: A Scheduling theory Framework for GPU Tasks Efficient Execution;A ...
ISBN:
(纸本)9783030159955
the proceedings contain 18 papers. the special focus in this conference is on High Performance Computing in Computational Science. the topics include: A Scheduling theory Framework for GPU Tasks Efficient Execution;A Timer-Augmented Cost Function for Load Balanced DSMC;Accelerating Scientific Applications on Heterogeneous Systems with HybridOMP;a New parallel Benchmark for Performance Evaluation and Energy Consumption;bigger Buffer k-d Trees on Multi-Many-Core Systems;a parallel Generator of Non-Hermitian Matrices Computed from Given Spectra;LRMalloc: A Modern and Competitive Lock-Free Dynamic Memory Allocator;towards a Strategy for Performance Prediction on Heterogeneous architectures;Dynamic Configuration of CUDA Runtime Variables for CDP-Based Divide-and-Conquer algorithms;Design, Implementation and Performance Analysis of a CFD Task-Based Application for Heterogeneous CPU/GPU Resources;Optimizing Packed String Matching on AVX2 Platform;A GPU-Based Metaheuristic for Workflow Scheduling on Clouds;a Systematic Mapping on High-Performance Computing for Protein Structure Prediction;performance Evaluation of Deep Learning Frameworks over Different architectures;non-uniform Domain Decomposition for Heterogeneous Accelerated processing Units;performance Evaluation of Two Load Balancing algorithms for Hybrid Clusters.
Sketches are probabilistic data structures that can provide approximate results within mathematically proven error bounds while using orders of magnitude less memory than traditional approaches. they are tailored for ...
详细信息
ISBN:
(纸本)9783030294007;9783030293994
Sketches are probabilistic data structures that can provide approximate results within mathematically proven error bounds while using orders of magnitude less memory than traditional approaches. they are tailored for streaming data analysis on architectures even with limited memory such as single-board computers that are widely exploited for IoT and edge computing. Since these devices offer multiple cores, with efficient parallel sketching schemes, they are able to manage high volumes of data streams. However, since their caches are relatively small, a careful parallelization is required. In this work, we focus on the frequency estimation problem and evaluate the performance of a high-end server, a 4-core Raspberry Pi and an 8-core Odroid. As a sketch, we employed the widely used Count-Min Sketch. To hash the stream in parallel and in a cache-friendly way, we applied a novel tabulation approach and rearranged the auxiliary tables into a single one. To parallelize the process with performance, we modified the workflow and applied a form of buffering between hash computations and sketch updates. Today, many single-board computers have heterogeneous processors in which slow and fast cores are equipped together. To utilize all these cores to their full potential, we proposed a dynamic load-balancing mechanism which significantly increased the performance of frequency estimation.
this paper proposes a wavelength-division multiplexing fiber laser acoustic emission sensing technique based on 3x3 coupler type interrogation method and a FPGA parallelprocessing algorithm. Narrow- linewidth (about ...
详细信息
ISBN:
(数字)9781510631601
ISBN:
(纸本)9781510631601
this paper proposes a wavelength-division multiplexing fiber laser acoustic emission sensing technique based on 3x3 coupler type interrogation method and a FPGA parallelprocessing algorithm. Narrow- linewidth (about 3 kHz) single-frequency distributed feedback fiber lasers are used for acoustic emission probes. A NI FlexRIO device is used to acquire the original signals from the photodetectors. A symmetric demodulation algorithm is executed in the FPGA using parallel data processing structure. the acoustic emission sensing system with four parallel channels and 2 MHz sampling rate achieves a wavelength resolution of 2 x10(-7) pm/vHz @ 100 kHz.
暂无评论