|
Title:
|
HETEROGENEOUS CPU-GPU IMPLEMENTATION OF COLLISION DETECTION |
|
Author(s):
|
Mohid Tayyub and Gul N. Khan |
|
ISBN:
|
978-989-8533-95-1 |
|
Editors:
|
Hans Weghorn |
|
Year:
|
2019 |
|
Edition:
|
Single |
|
Keywords:
|
CPU-GPU Systems, Fast Collision Detection, Gaming and Animation, Heterogeneous Computing |
|
Type:
|
Full Paper |
|
First Page:
|
71 |
|
Last Page:
|
78 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
Collision detection is one of the key tasks employed for animation, simulation and gaming applications. A collision
detection algorithm must be efficient and work in real time as it executes multiple times over the course of its applications.
Parallel and/or GPU implementation have been employed to reduce the execution time for collision detection. In this paper,
we investigate, implement and analyze a parallel broad-phase part of collision detection for CPU-GPU implementation.
A crucial part of co-running any algorithm is determining the workload partition ratio. To this end this paper presents a
successive approximation approach to estimate an optimal partition ratio that is also applicable to other applications.
Proving its efficacy in a real-world benchmark by improving the efficiency of collision detection by employing
heterogeneous processing based on CPU-GPU platforms. Our CPU-GPU implementation allowed for an average 7.18%
execution time reduction across all the benchmarks. |
|
|
|
|
|
|
