Title :
MPEG video decoding with the UltraSPARC visual instruction set
Author :
Chang-Guo Zhou ; Ihtisham Kabir ; Leslie Kohn ; Aman Jabbi ; Rice, D. ; Xio-Ping Hu
Author_Institution :
Sun Microsyst. Inc., Mountain View, CA, USA
Abstract :
The UltraSPARC microprocessor is equipped with a rich "visual instruction set" (VIS) which can perform ALU and other operations on several pixels in parallel. Significant performance gains are possible in the areas of video compression and decompression, as well as other areas of image processing. In this paper, we present a computational complexity analysis of MPEG video decompression, and derive a quantitative performance bound for software MPEG decoders. Based on this estimate, we show that by combining VIS and a high superscalar instruction rate, UltraSPARC is capable of decoding MPEG digital video at 720/spl times/480/spl times/30 resolution entirely in software. A coding example for the YUV to RGB colorspace conversion is also presented.
Keywords :
computational complexity; data compression; decoding; image coding; image processing; instruction sets; microprocessor chips; video coding; ALU; MPEG digital video; MPEG video decoding; UltraSPARC microprocessor; UltraSPARC visual instruction set; coding example; computational complexity analysis; high superscalar instruction rate; image processing; performance gains; quantitative performance bound; software MPEG decoders; video compression; video decompression; Computational complexity; Decoding; Image coding; Image processing; Microprocessors; Performance analysis; Performance gain; Software performance; Transform coding; Video compression;
Conference_Titel :
Compcon '95.'Technologies for the Information Superhighway', Digest of Papers.
Conference_Location :
San Francisco, CA, USA
Print_ISBN :
0-8186-7029-0
DOI :
10.1109/CMPCON.1995.512424