- Byte/Nibble transpose/shuffle for improving compression of binary data (ex. floating point data)<p>- Scalar/SIMD Transpose/Shuffle 8,16,32,64,... bits
Dynamic CPU detection and JIT scalar/sse/avx2 switching<p>- 100% C (C++ headers), usage as simple as memcpy<p>- Ready and simple to use library, no hassless dependencies<p>+ Byte Transpose<p>- Fastest byte transpose<p>+ Nibble Transpose<p>- nearly as fast as byte transpose<p>- more efficient in most binary data files, up to 6 times faster than Bitshuffle<p>- more robust worst case scenario than bitshuffle