Cuda Chen

icon indicating a website link cuda-chen.github.io

icon company Seeking for opportunities icon location Taipei, Taiwan icon location Image Processing, Machine learning, Parallel Computing

Results 63 comments of Cuda Chen

[NEW] Accelerate CRC16 with SIMD

Hi @zuiderkwast , > Maybe a smaller LUT is the most promising idea for small payloads? For my current understanding, LUT is the most promising idea for fixed-length and small...

Optimize CRC16 using multi-byte LUT

Hi @zuiderkwast , I would like to share some benchmark results of this PR. If we are going to merge this PR, there are at least two works waiting for...

Optimize CRC16 using multi-byte LUT

Hi @zuiderkwast , > How much memory would the 2-byte reduction variant use? It will use 1 KB memory for LUT (256 entries * 2 bytes of each entry *...