Sarah Mazari

dblp:360/8140 · DBLP profile ↗
← Back
2ranked-venue papers
1as first author
2since 2021 · last 2024
0000-0002-7925-2547ORCID · corroborated

Domains — the database's venue-derived domains; a paper can count in several

Systems, architecture and hardware · 1 · 1 since 2021Graphics, computer vision, multimedia, augmented reality and games · 1 · 1 first-author · 1 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Software engineering, system software, and programming languages
1 paper
Operating systems · 100%
Computer architecture, parallel and distributed computing, and storage systems
1 paper
Memory systems · 77% Performance modeling and evaluation · 23%

Topics — the 4 heaviest of 4, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Operating systems › resource management › memory management
dynamic memory allocation
0.712023
VCMalloc: A Virtually Contiguous Memory Allocator · IEEE Trans. Computers 2023
Operating systems › resource management
memory management
0.712023
VCMalloc: A Virtually Contiguous Memory Allocator · IEEE Trans. Computers 2023
Memory systems › memory management
virtual memory
0.712023
VCMalloc: A Virtually Contiguous Memory Allocator · IEEE Trans. Computers 2023
Performance modeling and evaluation
benchmarking
0.212023
VCMalloc: A Virtually Contiguous Memory Allocator · IEEE Trans. Computers 2023

Methods — techniques the papers use, named apart from their topics

virtual contiguity preservation · 1.3control plane design · 1.3
YearPublicationVenuePosition
2024 Evaluating the effect of super-resolution for automatic plant disease detection: application to potato late blight detection
Sarah Mazari, Meddoudi Abdlemadjid, Benameur Sarah, Yacine Hadjadj, Miloud Chikr El-Mezouar
Multim. Tools Appl.1
2023 VCMalloc: A Virtually Contiguous Memory Allocator
abstract
This paper presents VCMalloc, a custom memory allocator based on a new dynamic memory management approach that keeps data allocated in a contiguous form in memory. It can preserve the virtual contiguity of data even after performing different memory operations like “Reallocation” and “Free” without consuming much system resources. A novel control plane that we call a “Memory Management System” is introduced with a set of algorithms for the physical-virtual memory mappings, assuring fast, efficient, and safe tracking of data and user pointers. The proposed allocator prioritizes virtual contiguity while it keeps the physical memory completely up to the operating system to manage. It was tested and compared with the current implementation of Malloc as well as a state-of-the-art memory allocator MIMalloc in the recent versions of the Microsoft Windows operating system. For the allocator itself, a considerable performance increase has been achieved in basic operations of up to 28% increase in allocation speed and 26% in reallocation speed. The data structures allocated by VCMalloc have shown remarkable performance increases of up to 31% faster for matrix multiplication. Furthermore, VCMalloc has also demonstrated its superiority in real-world SPEC CPU 2017 benchmark applications.
Yacine Hadjadj, Chakib Mustapha Anouar Zouaoui, Nasreddine Taleb, Sarah Mazari, Mohamed Elbahri, Miloud Chikr El-Mezouar
IEEE Trans. Computers4