Base64 encoding and decoding advances are characterized. Some embodiments rely on only a single bit shifting operation; some have no reliance on bit-shifting. Some access data source bytes with multi-byte reads, and use those data source bytes as indexes into an encoding lookup table. Some use a table with four quadrants, each of which contains a copy of the same 64 encoding values. Some use a negative value as both a counter and an index. Some exclude BSWAP instructions even with a little-endian processor. Some partition a data source into N partitions, which are then encoded or decoded concurrently. In some, partition length is based on expected processor performance. Unrolled loops, exemplary assembly language code and coding choices, division using MagicNumber multiplication, terminal null addition, encoding/decoding applications, and other examples are also presented.