scholarly journals Exploiting Fine-Grain Thread Parallelism on Multicore Architectures

2009 ◽  
Vol 17 (4) ◽  
pp. 309-323 ◽  
Author(s):  
P.E. Hadjidoukas ◽  
G.Ch. Philos ◽  
V.V. Dimakopoulos

In this work we present a runtime threading system which provides an efficient substrate for fine-grain parallelism, suitable for deployment in multicore platforms. Its architecture encompasses a number of optimizations that make it particularly effective in managing a large number of threads and with low overheads. The runtime system has been integrated into an OpenMP implementation to allow for transparent usage under a high level programming paradigm. We evaluate our implementation on two multicore systems using synthetic microbenchmarks and a real-time face detection application.

Author(s):  
Khalil Khattab ◽  
Philippe Brunet ◽  
Julien Dubois ◽  
Johel Miter
Keyword(s):  

2019 ◽  
Author(s):  
Marcelo Cogo Miletto ◽  
Lucas Schnorr

Directed Acyclic Graph (DAG) is a high-level abstraction to describe the activities of parallel applications. A DAG contains tasks (nodes) and dependencies (edges) in the task-based programming paradigm. Application performance depends on the choices of the runtime system. Our work intends to evaluate and compare the performance of three different runtime systems, GCC/libgomp, LLVM/libomp, and StarPU for a task-based dense block QR factorization. The obtained results show that while GCC/libgomp achieves up to 5.4% better performance in the best case, it has scalability problems for finegrain problems with large DAGs. LLVM/libomp and StarPU are more scalable, and StarPU is much faster in task creation and submission than the other runtimes.


Computers ◽  
2020 ◽  
Vol 9 (3) ◽  
pp. 71
Author(s):  
Brandon Woolley ◽  
Susan Mengel ◽  
Atila Ertas

The aerospace and defense industry is facing an end-of-life production issue with legacy embedded uniprocessor systems. Most, if not all, embedded processor manufacturers have already moved towards system-on-a-chip multicore architectures. Current scheduling arrangements do not consider schedules related to safety and security. The methods are also inefficient because they arbitrarily assign larger-than-necessary windows of execution. This research creates a hierarchical scheduling framework as a model for real-time multicore systems to integrate the scheduling for safe and secure systems. This provides a more efficient approach which automates the migration of embedded systems’ real-time software tasks to multicore architectures. A novel genetic algorithm with a unique objective function and encoding scheme was created and compared to classical bin-packing algorithms. The simulation results show the genetic algorithm had 1.8–2.5 times less error (a 56–71% difference), outperforming its counterparts in uniformity in utilization. This research provides an efficient, automated method for commercial, private and defense industries to use a genetic algorithm to create a feasible two-level hierarchical schedule for real-time embedded multicore systems that address safety and security constraints.


2008 ◽  
Vol 2008 (1) ◽  
pp. 938256 ◽  
Author(s):  
Nicolas Farrugia ◽  
Franck Mamalet ◽  
Sébastien Roux ◽  
Fan Yang ◽  
Michel Paindavoine

Buildings ◽  
2019 ◽  
Vol 9 (3) ◽  
pp. 68
Author(s):  
Mankyu Sung

This paper proposes a graph-based algorithm for constructing 3D Korean traditional houses automatically using a computer graphics technique. In particular, we target designing the most popular traditional house type, a giwa house, whose roof is covered with a set of Korean traditional roof tiles called giwa. In our approach, we divided the whole design processes into two different parts. At a high level, we propose a special data structure called ‘modeling graphs’. A modeling graph consists of a set of nodes and edges. A node represents a particular component of the house and an edge represents the connection between two components with all associated parameters, including an offset vector between components. Users can easily add/ delete nodes and make them connect by an edge through a few mouse clicks. Once a modeling graph is built, then it is interpreted and rendered on a component-by-component basis by traversing nodes in a procedural way. At a low level, we came up with all the required parameters for constructing the components. Among all the components, the most beautiful but complicated part is the gently curved roof structures. In order to represent the sophisticated roof style, we introduce a spline curve-based modeling technique that is able to create curvy silhouettes of three different roof styles. In this process, rather than just applying a simple texture image onto the roof, which is widely used in commercial software, we actually laid out 3D giwa tiles on the roof seamlessly, which generated more realistic looks. Through many experiments, we verified that the proposed algorithm can model and render the giwa house at a real time rate.


Sensors ◽  
2021 ◽  
Vol 21 (12) ◽  
pp. 3956
Author(s):  
Youngsun Kong ◽  
Hugo F. Posada-Quintero ◽  
Ki H. Chon

The subjectiveness of pain can lead to inaccurate prescribing of pain medication, which can exacerbate drug addiction and overdose. Given that pain is often experienced in patients’ homes, there is an urgent need for ambulatory devices that can quantify pain in real-time. We implemented three time- and frequency-domain electrodermal activity (EDA) indices in our smartphone application that collects EDA signals using a wrist-worn device. We then evaluated our computational algorithms using thermal grill data from ten subjects. The thermal grill delivered a level of pain that was calibrated for each subject to be 8 out of 10 on a visual analog scale (VAS). Furthermore, we simulated the real-time processing of the smartphone application using a dataset pre-collected from another group of fifteen subjects who underwent pain stimulation using electrical pulses, which elicited a VAS pain score level 7 out of 10. All EDA features showed significant difference between painless and pain segments, termed for the 5-s segments before and after each pain stimulus. Random forest showed the highest accuracy in detecting pain, 81.5%, with 78.9% sensitivity and 84.2% specificity with leave-one-subject-out cross-validation approach. Our results show the potential of a smartphone application to provide near real-time objective pain detection.


Sign in / Sign up

Export Citation Format

Share Document