Abstract: This invention is a method of memory saving in compressed video decoding. For each group of pictures the method determines whether less than the maximum number N reference frames are needed for decoding. If so, then a memory is configuring for the needed number M reference frames less than N. If not, the memory is configured for N reference frames. The group of pictures is decoding the group of pictures using the configured number of reference frames.

Abstract: A novel algorithm is shown that allows efficient generation of Variable Length Codes using a Very Large Instruction Word processor with multiple execution units. The code generation is parallelized to take advantage of the multiple execution units, significantly reducing the cycle count and the execution time.

Abstract: A half sample and quarter sample pixel value interpolation calculation classifies a set of all possible half sample and quarter sample pixel value interpolation calculations into a plurality of interpolation types. A function kernel for each interpolation type includes a half sample pixel and all quarter sample pixels whose value calculation depend on a value of said half sample pixel value. The correct function kernel is called invoking the corresponding value interpolation calculation. The function kernels operate iteratively over a plurality of macroblocks of at least two macroblock sub-partition sizes. The calculation of dependent quarter sample pixel values preferably employs a packed average instruction.