Benchmarking Text to Vector conversion in Haskell

Main.hs

{-# LANGUAGE BangPatterns #-}
module Main (main) where

import Control.Monad
import Data.Maybe
import Data.String.Interpolate
import Data.Text as T
import qualified Data.Vector.Unboxed as VU
import Weigh


testFunc :: Int -> Text -> Weigh ()
testFunc inputSize text = wgroup [i|#{inputSize} characters|] $ do
  func' "VU.fromList" fromListMethod text
  func' "VU.fromListN" fromListNMethod text
  func' "generate" generateMethod text
  func' "unfoldr" unfoldrMethod text
  func' "unfoldrN" unfoldrNMethod text
  func' "unfoldrExactN" unfoldrExactNMethod text

fromListMethod :: Text -> VU.Vector Char
fromListMethod = VU.fromList . T.unpack

fromListNMethod :: Text -> VU.Vector Char
fromListNMethod t = VU.fromListN (T.length t) (T.unpack t)

-- | This one has great allocation but it's O(n^2) time!
generateMethod :: Text -> VU.Vector Char
generateMethod t = VU.generate (T.length t) (T.index t)

unfoldrMethod :: Text -> VU.Vector Char
unfoldrMethod = VU.unfoldr T.uncons

unfoldrNMethod :: Text -> VU.Vector Char
unfoldrNMethod t = VU.unfoldrN (T.length t) T.uncons t

unfoldrExactNMethod :: Text -> VU.Vector Char
unfoldrExactNMethod t = VU.unfoldrExactN (T.length t) (fromJust . T.uncons) t


main :: IO ()
main = mainWith $
  forM_ [10, 100, 1000, 10000, 100000] $ \n -> do
    let !text = T.replicate n "0"
    testFunc n text

Results

Benchmark myers-diff-weigh-text-to-vector: RUNNING...
                        
10 characters           
                        
  Case           Allocated  GCs
  VU.fromList        1,000    0
  VU.fromListN         888    0
  generate             104    0
  unfoldr              304    0
  unfoldrN             792    0
  unfoldrExactN        792    0
                        
100 characters          
                        
  Case           Allocated  GCs
  VU.fromList        8,424    0
  VU.fromListN       7,728    0
  generate             464    0
  unfoldr            1,248    0
  unfoldrN           7,632    0
  unfoldrExactN      7,632    0
                        
1000 characters         
                        
  Case           Allocated  GCs
  VU.fromList       80,440    0
  VU.fromListN      76,128    0
  generate           4,064    0
  unfoldr            8,464    0
  unfoldrN          76,032    0
  unfoldrExactN     76,032    0
                        
10000 characters        
                        
  Case           Allocated  GCs
  VU.fromList      851,384    0
  VU.fromListN     760,128    0
  generate          40,064    0
  unfoldr          131,408    0
  unfoldrN         760,032    0
  unfoldrExactN    760,032    0
                        
100000 characters       
                        
  Case           Allocated  GCs
  VU.fromList    8,248,936    1
  VU.fromListN   7,600,128    1
  generate         400,640    1
  unfoldr        1,048,960    0
  unfoldrN       7,600,032    1
  unfoldrExactN  7,600,032    1
Benchmark myers-diff-weigh-text-to-vector: FINISH
Completed 2 action(s).