APU Performance Evaluation for Accelerating Computationally Expensive Workloads

Ernesto Rivera-Alvarado; Francisco J. Torres-Rojas

doi:10.1016/j.entcs.2020.02.015

APU Performance Evaluation for Accelerating Computationally Expensive Workloads

Ernesto Rivera-Alvarado
, Francisco J. Torres-Rojas

Costa Rica Institute of Technology

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

APUs (Accelerated Processing Units) are widely available in personal computers as low-cost processors that have a CPU and an integrated GPU for displaying graphics, in the same die. Using a ray tracing algorithm as a computationally intensive workload and taking advantage of the APU specific characteristics, we compare the performance of this SoC against CPU and GPU solutions in the same price range.

Original language	English
Pages (from-to)	103-118
Number of pages	16
Journal	Electronic Notes in Theoretical Computer Science
Volume	349
DOIs	https://doi.org/10.1016/j.entcs.2020.02.015
State	Published - 1 Jun 2020

Keywords

accelerated processing unit
acceleration
computationally intensive workloads
CPU
GPU
ray tracing

Access to Document

10.1016/j.entcs.2020.02.015

Cite this

@article{030389d4ec2849379a2b20175dda8a38,

title = "APU Performance Evaluation for Accelerating Computationally Expensive Workloads",

abstract = "APUs (Accelerated Processing Units) are widely available in personal computers as low-cost processors that have a CPU and an integrated GPU for displaying graphics, in the same die. Using a ray tracing algorithm as a computationally intensive workload and taking advantage of the APU specific characteristics, we compare the performance of this SoC against CPU and GPU solutions in the same price range.",

keywords = "accelerated processing unit, acceleration, computationally intensive workloads, CPU, GPU, ray tracing",

author = "Ernesto Rivera-Alvarado and Torres-Rojas, \{Francisco J.\}",

note = "Publisher Copyright: {\textcopyright} 2020 The Author(s)",

year = "2020",

month = jun,

day = "1",

doi = "10.1016/j.entcs.2020.02.015",

language = "Ingl{\'e}s",

volume = "349",

pages = "103--118",

journal = "Electronic Notes in Theoretical Computer Science",

issn = "1571-0661",

}

TY - JOUR

T1 - APU Performance Evaluation for Accelerating Computationally Expensive Workloads

AU - Rivera-Alvarado, Ernesto

AU - Torres-Rojas, Francisco J.

PY - 2020/6/1

Y1 - 2020/6/1

N2 - APUs (Accelerated Processing Units) are widely available in personal computers as low-cost processors that have a CPU and an integrated GPU for displaying graphics, in the same die. Using a ray tracing algorithm as a computationally intensive workload and taking advantage of the APU specific characteristics, we compare the performance of this SoC against CPU and GPU solutions in the same price range.

AB - APUs (Accelerated Processing Units) are widely available in personal computers as low-cost processors that have a CPU and an integrated GPU for displaying graphics, in the same die. Using a ray tracing algorithm as a computationally intensive workload and taking advantage of the APU specific characteristics, we compare the performance of this SoC against CPU and GPU solutions in the same price range.

KW - accelerated processing unit

KW - acceleration

KW - computationally intensive workloads

KW - CPU

KW - GPU

KW - ray tracing

UR - https://www.scopus.com/pages/publications/85124192436

U2 - 10.1016/j.entcs.2020.02.015

DO - 10.1016/j.entcs.2020.02.015

M3 - Artículo

AN - SCOPUS:85124192436

SN - 1571-0661

VL - 349

SP - 103

EP - 118

JO - Electronic Notes in Theoretical Computer Science

JF - Electronic Notes in Theoretical Computer Science

ER -

APU Performance Evaluation for Accelerating Computationally Expensive Workloads

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this