A SIMD lookup algorithm validates UTF-8 in under one instruction per byte and runs more than 10 times faster than common library implementations.
Data-parallel Finite-state Machines
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DB 1years
2020 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Validating UTF-8 In Less Than One Instruction Per Byte
A SIMD lookup algorithm validates UTF-8 in under one instruction per byte and runs more than 10 times faster than common library implementations.