[erlang-questions] clarify: why bit syntax so slow + benchmark code

[Mateusz Berezecki]

Hello,

I have attached a benchmark at the end of this e-mail.
It is a complete mystery to me why it performs so poorly.

Could please anyone share some ideas what is the
background behind this behavior?

Example test results;

24.1486134 seconds / 100 Mb (extracting 1 byte)
12.8946602 seconds / 100 Mb (extracting 2 bytes)
6.37089217 seconds / 100 Mb (extracting 4 bytes)
3.19605309 seconds / 100 Mb (extracting 8 bytes)
1.57278535 seconds / 100 Mb (extracting 16 bytes)

The code was compiled without +native flag.
I don't understand why it performs so poorly .

The C code can do 600mb in 24 seconds while performing IO from disk
while erlang code needs 24 seconds for 100mb while reading it from memory.

The million dollar questions is - Why ?


regards,
Mateusz Berezecki

P.S.
Benchmark code

-module (benchmark).
-export([bitsyntax/1, test1/1, test2/1, test4/1, test8/1, test16/1]).

test1(<<>>) -> done;
test1(Bin) when is_binary(Bin) ->
        <<A:1/binary, Rest/binary>> = Bin,
        <<_A1:8>> = A,
        test1(Rest).

test2(<<>>) -> done;
test2(Bin) when is_binary(Bin) ->
        <<A:2/binary, Rest/binary>> = Bin,
        <<_A1:8, _A2:8>> = A,
        test2(Rest).

test4(<<>>) -> done;
test4(Bin) when is_binary(Bin) ->
        <<A:4/binary, Rest/binary>> = Bin,
        <<_A1:8,_A2:8,_A3:8,_A4:8>> = A,
        test4(Rest).

test8(<<>>) -> done;
test8(Bin) when is_binary(Bin) ->
        <<A:8/binary, Rest/binary>> = Bin,
        <<_A1:8,_A2:8,_A3:8,_A4:8, _A5:8, _A6:8, _A7:8, _A8:8>> = A,
        test8(Rest).

test16(<<>>) -> done;
test16(Bin) when is_binary(Bin) ->
        <<A:16/binary, Rest/binary>> = Bin,
        <<_A1:8,_A2:8,_A3:8,_A4:8, _A5:8, _A6:8, _A7:8, _A8:8, _A9:8, _A10:8,
_A11:8,_A12:8, _A13:8, _A14:8, _A15:8, _A16:8>> = A,
        test16(Rest).

bitsyntax(N) when is_integer(N), N > 0 ->
        K = lists:seq(1, N * 16),
        Bin = list_to_binary(lists:map(fun(X) -> <<X:8>> end, K)),

        io:format("Running tests for N = ~p.~n", [N * 16]),
        {T1, _} = timer:tc(?MODULE, test1, [Bin]),
        {T2, _} = timer:tc(?MODULE, test2, [Bin]),
        {T3, _} = timer:tc(?MODULE, test4, [Bin]),
        {T4, _} = timer:tc(?MODULE, test8, [Bin]),
        {T5, _} = timer:tc(?MODULE, test16, [Bin]),

        io:format("T1 = ~p.~n", [T1]),
        io:format("T2 = ~p.~n", [T2]),
        io:format("T3 = ~p.~n", [T3]),
        io:format("T4 = ~p.~n", [T4]),
        io:format("T5 = ~p.~n", [T5]).


-- 
Mateusz Berezecki
http://www.meme.pl