|
|
|
|
|
|
by camel-cdr
257 days ago
|
|
|
Oh, this is cool, I wanted to look into using SIMD for huffman as well. For decode, do you use AVX512 to speedup the decode via caching the decode of small codewords? Do you decode serially or use the self syncronizing nature of huffman codes to decode the stream from multiple offsets in parallel? I haven't seen the later done in SIMD before. Are there any new SIMD instructions you'd like to see in future ISA extensions? OpenPower has proposed a scalar instruction to speedup prefix-code decoding: https://libre-soc.org/openpower/prefix_codes/ |
|
|