Performance Improvement of Multimedia Kernels by Alleviating Overhead Instructions on SIMD Devices

Authors:
Asadollah Shahbahrami;Ben Juurlink
Affiliations:
Computer Engineering Laboratory, Delft University of Technology, Delft, The Netherlands 2628 and Department of Computer Engineering, Faculty of Engineering, University of Guilan, Rasht, Iran;Computer Engineering Laboratory, Delft University of Technology, Delft, The Netherlands 2628
Venue:
APPT '09 Proceedings of the 8th International Symposium on Advanced Parallel Processing Technologies
Year:
2009

Citing 12
Cited 0

Performance of image and video processing with general-purpose processors and media ISA extensions

ISCA '99 Proceedings of the 26th annual international symposium on Computer architecture
Computer architecture: a quantitative approach

Computer architecture: a quantitative approach
Subword Extensions for Video Processing on Mobile Systems

IEEE Concurrency
SimpleScalar: An Infrastructure for Computer System Modeling

Computer
VIS Speeds New Media Processing

IEEE Micro
MMX Technology Extension to the Intel Architecture

IEEE Micro
Subword Parallelism with MAX-2

IEEE Micro
AltiVec Extension to PowerPC Accelerates Media Processing

IEEE Micro
Implementing Streaming SIMD Extensions on the Pentium III Processor

IEEE Micro
The Alpha 21164PC Microprocessor

COMPCON '97 Proceedings of the 42nd IEEE International Computer Conference
Hardware Support for Arithmetic Units of Processor with Multimedia Extension

MUE '07 Proceedings of the 2007 International Conference on Multimedia and Ubiquitous Engineering
Versatility of extended subwords and the matrix register file

ACM Transactions on Architecture and Code Optimization (TACO)

Quantified Score

Hi-index	0.00

Visualization

Abstract

SIMD extension is one of the most common and effective technique to exploit data-level parallelism in today's processor designs. However, the performance of SIMD architectures is limited by some constraints such as mismatch between the storage and the computational formats and using data permutation instructions during vectorization. In our previous work we have proposed two architectural modifications, the extended subwords and the Matrix Register File (MRF) to alleviate the limitations. The extended subwords, uses four extra bits for every byte in a media register and it provides additional parallelism. The MRF allows flexible row-wise as well as column-wise access to the register file and it eliminates data permutation instructions. We have validated the combination of the proposed techniques by studying the performance of some multimedia kernels. In this paper, we analysis each proposed technique separately. In other words, we answer the following questions in this paper. How much of the performance gain is a result of the additional parallelism? and how much is due to the elimination of data permutation instructions? The results show that employing the MRF and extended subwords separately obtains the speedup less than 1 and 1.15, respectively. In other words, our results indicate that using either extended subwords or the MRF techniques is insufficient to eliminate most pack/unpack and rearrangement overhead instructions on SIMD processors. The combination of both techniques, on the other hand, yields much more performance benefits than each technique.