Geri Dön

Analysis of static and dynamic memory management schemes in embedded systems utilizing software-managed memory

Başlık çevirisi mevcut değil.

  1. Tez No: 402430
  2. Yazar: MÜBERRA NUR AKÇAMAN
  3. Danışmanlar: DR. HAKDURAN KOÇ
  4. Tez Türü: Yüksek Lisans
  5. Konular: Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol, Computer Engineering and Computer Science and Control
  6. Anahtar Kelimeler: Belirtilmemiş.
  7. Yıl: 2015
  8. Dil: İngilizce
  9. Üniversite: University of Houston–Clear Lake (UHCL)
  10. Enstitü: Yurtdışı Enstitü
  11. Ana Bilim Dalı: Bilgisayar Mühendisliği Ana Bilim Dalı
  12. Bilim Dalı: Belirtilmemiş.
  13. Sayfa Sayısı: 63

Özet

Özet yok.

Özet (Çeviri)

Software-managed memories like Scratchpad Memory (SPM) are widely used in embedded systems. SPM is preferred by embedded system designers due to its advantages over its hardware-controlled counterparts to optimize various design metrics such as performance, power consumption and memory space consumption. SPM management techniques have been investigated for both single-core and multi-core execution environments and are divided into two categories: static and dynamic management schemes. In static schemes, the initial data mapping to SPM is valid throughout the course of execution while the mapping is modified based on block access frequencies in dynamic management techniques. In this thesis, we investigate and compare the effect of static and dynamic memory management techniques for data-intensive applications running on both single and multi-core embedded architectures.The main difference between these two is the fact that, in static data allocation, the contents of on-chip software-managed memory components are fixed and do not change during the execution of the program; and, in dynamic data allocation method, the SPM contents are modified by transferring frequently-accessed data blocks at execution phase boundaries at run-time. The dynamic approach typically improves the performance of such applications by reducing the number of off-chip memory accesses. The proposed work targets at data-intensive applications which involve processing of large data arrays within loop nests. Such applications frequently occur in image/video processing domains. The target architectures used in this thesis are both single-core and multi-core embedded systems. In multi-core architecture, each core has a local SPM; and each core accesses other SPMs (remote SPM) and an on-chip shared L2 memory with higher memory access latencies. All on-chip memories are software-managed. Both architectures have off-chip memory which holds the entire dataset. After profiling the embedded application, the dataset is divided into blocks and the access frequencies to these blocks are determined. The data mapping is done to L1 SPMs, L2 SPM and off-chip memory based on the access frequencies of data blocks. This process is done once at compile time in static memory allocation while it is repeated at the beginning of each execution phase at run-time in dynamic data allocation. The experimental results collected using data-intensive benchmark programs are presented in single and multi-core embedded architectural setups.

Benzer Tezler

  1. Yeni bir hata değişik delta ağ maddeli arttırılmış delta ağı (ADA)

    Başlık çevirisi yok

    M.EBRU KOLUSAYIN

    Yüksek Lisans

    Türkçe

    Türkçe

    1998

    Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrolİstanbul Teknik Üniversitesi

    Kontrol ve Bilgisayar Mühendisliği Ana Bilim Dalı

    DOÇ. DR. MEHMET BÜLENT ÖRENCİK

  2. Reducing processor-memory performance gap and improving network-on-chip throughput

    İşlemci-bellek performans farkını azaltmak ve yonga-üstü-ağ verimini artırmak

    MUSTAFA NAVEED UL

    Doktora

    İngilizce

    İngilizce

    2019

    Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrolİhsan Doğramacı Bilkent Üniversitesi

    Bilgisayar Mühendisliği Ana Bilim Dalı

    PROF. DR. ÖZCAN ÖZTÜRK

  3. Kaynaklara dayalı yaklaşımın disipliner temelleri

    Disciplinary foundations of the resource based view

    MEHMET BAĞIŞ

    Doktora

    Türkçe

    Türkçe

    2018

    İşletmeSakarya Üniversitesi

    İşletme Ana Bilim Dalı

    DOÇ. DR. MAHMUT HIZIROĞLU

  4. Collective data forecasting indynamic transport networks

    Dinamik ulaştırma ağlarında kolektif veri tahminlemesi

    MEHMET GÜVERCİN

    Doktora

    İngilizce

    İngilizce

    2021

    Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrolİhsan Doğramacı Bilkent Üniversitesi

    Bilgisayar Mühendisliği Ana Bilim Dalı

    PROF. DR. İBRAHİM KÖRPEOĞLU

    DOÇ. DR. BUĞRA GEDİK

  5. Kural tabanlı optimizasyon ile ağ saldırılarının tespiti

    Detection of network attacks with rule-based optimization

    OĞUZ ÖZGER

    Yüksek Lisans

    Türkçe

    Türkçe

    2023

    Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve KontrolSakarya Uygulamalı Bilimler Üniversitesi

    Elektrik-Elektronik Mühendisliği Ana Bilim Dalı

    DOÇ. DR. HALİT ÖZTEKİN