Modular scaleable processing engine for accelerating variable length coding

A content-adaptive variable length coder, comprising:

• a plurality of variable length coding engines for performing variable length coding operations on a like plurality of sub-blocks of residual data in parallel to produce a like plurality of variable length output data sets;
• a like plurality of buffers coupled to the variable length coding engines, each one of the buffers storing one of the plurality of variable length output data sets;
• an assembler circuit coupled to the plurality of buffers to retrieve the plurality of variable length output data sets one set at a time and in a pre-determined order that is prioritized at least in part based on data stored in the buffers;
• and
• an output buffer coupled to the assembler circuit, wherein the assembler circuit stores the variable length output data sets in the output buffer one data set at a time in the pre-determined order.