Proceedings of the 13th International Conference on Supercomputing 1999
DOI: 10.1145/305138.305150
|View full text |Cite
|
Sign up to set email alerts
|

Exploiting SIMD parallelism in DSP and multimedia algorithms using the AltiVec technology

Abstract: AltiVec technology is Motorola's high-per$ormance vector parallel processing extension to the PowerPC"' RISC microprocessor. It is designed to improve the performance of algorithms and applications that can exploit data parallelism such as those in digital signal processing (DSP) and multimedia. In this paper, we investigate the behavior of the AltiVec technology on a set of common DSP and multimedia algorithms. These algorithms include digital $lters, fast Fourier transforms, inverse discrete cosine transform… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
26
0

Year Published

2001
2001
2018
2018

Publication Types

Select...
4
3
3

Relationship

0
10

Authors

Journals

citations
Cited by 64 publications
(27 citation statements)
references
References 3 publications
1
26
0
Order By: Relevance
“…With recent releases of G4 PowerPC processors with AltiVec and the AltiVec enabled C compiler, we can confirm the evaluations assessed with various simulators [7].…”
Section: Proposed Implementationsupporting
confidence: 64%
“…With recent releases of G4 PowerPC processors with AltiVec and the AltiVec enabled C compiler, we can confirm the evaluations assessed with various simulators [7].…”
Section: Proposed Implementationsupporting
confidence: 64%
“…Matrix multiplication is a common function used in DSP and multimedia applications [15]. To illustrate how attributes such as SoO and interconnection affect algorithm mapping, matrix multiplication of two 4x4 matrices was mapped to the CGRA-A, CGRA-B and CGRA-C architectures.…”
Section: Application Mappingmentioning
confidence: 99%
“…Harnessing data parallelism using short vector or SIMD architectures is a popular approach [20,1]. This technique has been shown to improve performance by up to an order of magnitude on DSP style algorithms and even on some small speech processing codes [13].…”
Section: Related Workmentioning
confidence: 99%