• Title/Summary/Keyword: Heterogeneous-Computing

Search Result 398, Processing Time 0.031 seconds

LADAR 영상의 실시간 신호 처리 (Real-time signal processing of LADAR image)

  • 하중림;남재두;김영길
    • 한국정보통신학회:학술대회논문집
    • /
    • 한국정보통신학회 2017년도 춘계학술대회
    • /
    • pp.387-390
    • /
    • 2017
  • 임베디드 분야에서 고해상도 센서의 등장으로 Heterogeneous 컴퓨팅에 대한 수요가 지속적으로 증가하고 있다. 로직모듈은 LADAR 시스템 구성품을 제어하고, 고속의 레이저 영상 데이터를 실시간 3차원 영상화하기 위한 임베디드 시스템이다. 본 논문에서는 로직모듈의 설계와 CPU-GPU Heterogeneous 컴퓨팅을 활용한 로직모듈의 신호처리에 대해 설명하려고 한다.

  • PDF

A Novel Smart Contract based Optimized Cloud Selection Framework for Efficient Multi-Party Computation

  • Haotian Chen;Abir EL Azzaoui;Sekione Reward Jeremiah;Jong Hyuk Park
    • Journal of Information Processing Systems
    • /
    • 제19권2호
    • /
    • pp.240-257
    • /
    • 2023
  • The industrial Internet of Things (IIoT) is characterized by intelligent connection, real-time data processing, collaborative monitoring, and automatic information processing. The heterogeneous IIoT devices require a high data rate, high reliability, high coverage, and low delay, thus posing a significant challenge to information security. High-performance edge and cloud servers are a good backup solution for IIoT devices with limited capabilities. However, privacy leakage and network attack cases may occur in heterogeneous IIoT environments. Cloud-based multi-party computing is a reliable privacy-protecting technology that encourages multiparty participation in joint computing without privacy disclosure. However, the default cloud selection method does not meet the heterogeneous IIoT requirements. The server can be dishonest, significantly increasing the probability of multi-party computation failure or inefficiency. This paper proposes a blockchain and smart contract-based optimized cloud node selection framework. Different participants choose the best server that meets their performance demands, considering the communication delay. Smart contracts provide a progressive request mechanism to increase participation. The simulation results show that our framework improves overall multi-party computing efficiency by up to 44.73%.

Efficient Process Network Implementation of Ray-Tracing Application on Heterogeneous Multi-Core Systems

  • Jung, Hyeonseok;Yang, Hoeseok
    • IEIE Transactions on Smart Processing and Computing
    • /
    • 제5권4호
    • /
    • pp.289-293
    • /
    • 2016
  • As more mobile devices are equipped with multi-core CPUs and are required to execute many compute-intensive multimedia applications, it is important to optimize the systems, considering the underlying parallel hardware architecture. In this paper, we implement and optimize ray-tracing application tailored to a given mobile computing platform with multiple heterogeneous processing elements. In this paper, a lightweight ray-tracing application is specified and implemented in Kahn process network (KPN) model-of-computation, which is known to be suitable for the description of real-time applications. We take an open-source C/C++ implementation of ray-tracing and adapt it to KPN description in the Distributed Application Layer framework. Then, several possible configurations are evaluated in the target mobile computing platform (Exynos 5422), where eight heterogeneous ARM cores are integrated. We derive the optimal degree of parallelism and a suitable distribution of the replicated tasks tailored to the target architecture.

분산 이기종 컴퓨팅 시스템에서 효율적인 리스트 스케줄링 알고리즘 (An Efficient List Scheduling Algorithm in Distributed Heterogeneous Computing System)

  • 윤완오;윤정희;이창호;김효기;최상방
    • 전자공학회논문지CI
    • /
    • 제46권3호
    • /
    • pp.86-95
    • /
    • 2009
  • 이기종 컴퓨팅 환경에서 방향성 비순환 그래프(directed acyclic graph DAG)의 효율적인 스케줄링은 시스템의 성능을 높게 만드는데 매우 중요한 역할을 한다. 이기종의 컴퓨팅 환경에서 DAG로 표현되는 프로그램의 최적 스케줄링 방법을 찾는 것은 잘 알려진 '정해진 시간 내에 해결하기 어려운 문제(NP-complete)' 이다. 본 논문은 분산 이기종 컴퓨팅 시스템에서 병렬로 실행 가능한 프로그램을 위한 새로운 리스트 스케줄링 알고리즘인 HRPS(Heterogeneous Rank-Path Scheduling)를 제안하였다. HRPS의 가장 궁극적인 목적은 프로그램의 실행시간을 최소화하는 것이다. 알고리즘의 성능을 위해 DAG 입력 그래프를 이용하여 기존에 제안되어진 CPOP, HCPT, FLB 알고리즘과 스케줄의 길이를 비교한 결과 성능 향상의 결과를 얻을 수 있었다.

Heterogeneous 멀티 코어 환경의 Thick Client에서 VDI 성능 최적화를 위한 혼합 병렬 처리 기법 연구 (VDI Performance Optimization with Hybrid Parallel Processing in Thick Client System under Heterogeneous Multi-Core Environment)

  • 김명섭;허의남
    • 한국통신학회논문지
    • /
    • 제38B권3호
    • /
    • pp.163-171
    • /
    • 2013
  • 최근 HD급 동영상이나 3D 어플리케이션과 같은 이전보다 저사양, 모바일 단말에서는 구동하기 힘든 프로그램들에 대한 이용 요구가 확대되면서 처리해야 할 콘텐츠 데이터들이 고용량화 되고 있다. 클라우드 기반의 VDI(Virtual Desktop Infrastructure) 서비스는 이를 처리하기 위해 효율적인 데이터 처리 능력이 필요해졌으며 QoE(Quality of Experience) 보장을 위한 성능 개선 연구가 이슈가 되고 있다. 본 논문에서는 H/W 성능이 향상되어 CPU와 GPU를 탑재한 Thick Client기반의 3가지 Thick-Thin간 VDI 자원 공유 및 위임이 가능한 VDI 서비스에 대해 제안하며, VDI 서비스 성능의 개선을 위해 CPU와 GPU가 혼합된 Heterogeneous 멀티코어 환경에서 CPU와 GPU 병렬 처리 기법인 OpenMP와 CUDA를 활용하여 VDI 서비스 최적화 방안을 제안하고 기존의 VDI와 비교한 성능을 거론한다.

Public Key Encryption with Equality Test for Heterogeneous Systems in Cloud Computing

  • Elhabob, Rashad;Zhao, Yanan;Sella, Iva;Xiong, Hu
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제13권9호
    • /
    • pp.4742-4770
    • /
    • 2019
  • Cloud computing provides a broad range of services like operating systems, hardware, software and resources. Availability of these services encourages data owners to outsource their intensive computations and massive data to the cloud. However, considering the untrusted nature of cloud server, it is essential to encrypt the data before outsourcing it to the cloud. Unfortunately, this leads to a challenge when it comes to providing search functionality for encrypted data located in the cloud. To address this challenge, this paper presents a public key encryption with equality test for heterogeneous systems (PKE-ET-HS). The PKE-ET-HS scheme simulates certificateless public encryption with equality test (CLE-ET) with the identity-based encryption with equality test (IBE-ET). This scheme provides the authorized cloud server the right to actuate the equivalence of two messages having their encryptions performed under heterogeneous systems. Basing on the random oracle model, we construct the security of our proposed scheme under the bilinear Diffie-Hellman (BDH) assumption. Eventually, we evaluate the size of storage, computation complexities, and properties with other related works and illustrations indicate good performance from our scheme.

NAAL: 뉴로모픽 아키텍처 추상화 기반 이기종 IoT 기기 제어용 소프트웨어 (NAAL: Software for controlling heterogeneous IoT devices based on neuromorphic architecture abstraction)

  • 조진성;김봉재
    • 스마트미디어저널
    • /
    • 제11권3호
    • /
    • pp.18-25
    • /
    • 2022
  • 뉴로모픽 컴퓨팅은 일반적으로 CPU와 GPU를 이용하여 신경망 연산을 하는 것보다 전력, 면적, 속도 측면에서 매우 뛰어난 성능을 보여준다. 이러한 특성은 에너지 사용량이 중요시되는 자원 제약적인 IoT 환경에 매우 적합하다. 하지만 뉴로모픽 컴퓨팅을 지원하는 이기종 IoT 기기에 따라 환경설정 및 응용 프로그램 동작을 위한 소스코드의 수정이 필요하다는 문제점을 가지고 있다. 이러한 문제점을 해결하고자 본 논문에서는 NAAL을 제안하고 구현하였다. NAAL은 공통의 API를 기반으로 다양한 이기종 IoT 기기 환경에서 IoT 기기의 제어와 뉴로모픽 아키텍처의 추상화 및 추론 모델 동작에 필요한 기능을 제공한다. NAAL은 향후 새로운 이기종 IoT 기기 및 뉴로모픽 아키텍처와 컴퓨팅 장치의 추가적인 지원이 가능하다는 장점을 가진다.

이종 멀티코어 시스템의 전력 및 성능 분석을 위한 프레임워크 설계 및 구현 (A Systematic Power and Performance Analysis Framework for Heterogeneous Multiprocessor System)

  • 김형준;경주현;임성수
    • 대한임베디드공학회논문지
    • /
    • 제9권6호
    • /
    • pp.315-321
    • /
    • 2014
  • Mobile computing devices such as smartphones, tablet computers have become the dominant personal computing platforms. Energy efficiency is a prime design requirement for smart devices. In order to reduce the energy consumption of the smart devices, analysis of performance and energy consumption has become important. However, so far, there is no framework for the analysis and systematic approach to improve the power consumption of the heterogeneous multi-core system. In this paper, we describe a new framework for the analysis of heterogeneous multi-core systems. Also, by use of an analysis tool, can be provide reliability and productivity of development results.

Energy-efficient Scheduling of Periodic Real-time Tasks on Heterogeneous Grid Computing Systems

  • Lee, Wan Yeon;Choi, Yun-Seok
    • International Journal of Internet, Broadcasting and Communication
    • /
    • 제9권2호
    • /
    • pp.78-86
    • /
    • 2017
  • In this paper, we propose an energy-efficient scheduling scheme for real-time periodic tasks on a heterogeneous Grid computing system. The Grid system consists of heterogeneous processors providing the DVFS mechanism with a finite set of discrete clock frequencies. In order to save energy consumption, the proposed scheduling scheme assigns each real-time task to a processor with the least energy increment. Also the scheme activates a part of all available processors with unused processors powered off. Evaluation shows that the proposed scheme saves up to 70% energy consumption of the previous method.

이동 이질 멀티데이타베이스 시스텐을 위한 이동 유연 트랜잭션의 실행 제어 알고리즘 (An Execution Control Algorithm for Mobile Flex Transactions in Mobile Heterogeneous Multidatabase Systems)

  • 구경이;김유성
    • 한국정보처리학회논문지
    • /
    • 제6권11호
    • /
    • pp.2845-2862
    • /
    • 1999
  • As the technical advances in portable computers and wireless communication technologies, mobile computing environment has been rapidly expanded. The mobile users on mobile host can access information via wireless communication from the distributed heterogeneous multidatabase system in which pre-existing independent local information systems are integrated into one logical system to support mobile applications. Hence, mobile transaction model should include not only the features for heterogeneous multidatabase systems but also the ones for mobile computing environment. In this paper, we proposed a mobile flex transaction model which extends the flexible transaction model that previously proposed for heterogeneous multidatabase systems is extended to support the requirements of mobile heterogeneous multidatabase systems. We also presented the execution control mechanism of the mobile flex transaction model. The proposed mobile flex transaction model allows the definition of location-dependent subtransactions, the effective support of hand-over, and the flexibility of transaction executions. Hence, the proposed mobile flex transaction model can be suit to mobile heterogeneous multidatabase systems that have low power capability, low bandwidth, and high communication failure possibility.

  • PDF