Created
February 25, 2018 01:15
-
-
Save quinnj/df388d2946503593c2124f9de1039a95 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
const BYTES = fill(false, 128) | |
BYTES[Int(',')] = true | |
BYTES[Int('\n')] = true | |
BYTES[Int('\r')] = true | |
const COMMA = UInt8(',') | |
const NEWLINE = UInt8('\n') | |
const RETURN = UInt8('\r') | |
function parse(file="/home/chronos/user/Downloads/.julia/v0.7/CSV/test/test_files/Fielding.csv") | |
m = Mmap.mmap(file) | |
bitmap = zeros(UInt8, fld1(length(m), 8)) | |
return parse(m, bitmap) | |
end | |
#TODO | |
# try perf on not unrolling inner loop | |
# check if actually simd | |
#• | |
function parse(m::Vector{UInt8}, bitmap::Vector{UInt8}) | |
i = 1 | |
j = 1 | |
len = length(m) | |
@simd for i = 1:8:len | |
@inbounds begin | |
b = m[i] | |
mask = ifelse(BYTES[b], 0b00000001, 0b00000000) | |
b = m[i+1] | |
mask |= ifelse(BYTES[b], 0b00000010, 0b00000000) | |
b = m[i+2] | |
mask |= ifelse(BYTES[b], 0b00000100, 0b00000000) | |
b = m[i+3] | |
mask |= ifelse(BYTES[b], 0b00001000, 0b00000000) | |
b = m[i+4] | |
mask |= ifelse(BYTES[b], 0b00010000, 0b00000000) | |
b = m[i+5] | |
mask |= ifelse(BYTES[b], 0b00100000, 0b00000000) | |
b = m[i+6] | |
mask |= ifelse(BYTES[b], 0b01000000, 0b00000000) | |
b = m[i+7] | |
mask |= ifelse(BYTES[b], 0b10000000, 0b00000000) | |
bitmap[j] = mask | |
end | |
j += 1 | |
end | |
return bitmap | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment