Re: [C++] Returning objects from a function and performance

From: Alwyn (alwyn_at_blueyonder.co.uk)
Date: 02/21/05 

Date: Mon, 21 Feb 2005 19:33:22 +0000

On Mon, 21 Feb 2005 15:18:03 +0100, Spacen Jasset wrote:

> If I have a function that resturns a class object. i.e.
>
> ExtString mid( int start, int len )
> {
> ExtString result;
> ...
> return result;
> }
>
> Then the compiler must invoke the copy constructor of ExtString to make
> a copy and return it. Unless ofcourse it can be optimised.

There is something called Return Value Optimisation, which, if
implemented, would do away with the need to make a copy.

> But surpose the function is like this:
>
> ExtString mid( int start, int len )
> {
> ExtString result1;
> ExtString result2;
>
> if ( /* something )
> return result1;
> else
> return result2;
> }
>
> The compiler would have a harder time optimising that I suspect.

I'm not sure why.

> I ask this question becuase I've been told that this is all very
> inefficient and the 'mid' and other functions have been re-written in
> our library to take a refrence like this:
>
> void mid( ExtString &sub, int start, int len ) { ...
> }

Yes, you can do that, but I would only recommend such a style if it has
been shown (e.g. by means of a profiler) that it eliminates a real
bottleneck in performance. Producing results by side-effect is to be
avoided where possible.

> Is returning a potentially large object from a function as bad as it
> seems? I notice the std::string.substring() function also returns a
> string object. This looks like a popular thing to do in C++.

'std::string' is hardly what I would call a large object. I would say the
overhead here is probably the memory allocation.

> It's still traditional amoung C programmers to never return structures
> by value, despite being able to do so officialy since C89.

I didn't know that.

> Presumably
> there is a considerable performance problem for large objects in C++,
> but perhaps notso in C since there are no copy constructors, and the
> compiler can avoid any object copy on return.

The C++ standard insists on memberwise copy, though this too can be
optimised 'behind the scenes' to a straight memory copy in the case of
POD. And, as I said before, the overhead of creating a temporary object
can be avoided if the compiler is capable of return value optimisation. On
the whole, I believe in leaving micro-optimisation to the compiler until
it is shown that the impact on performance is such that it really does
need to be done by hand.

Alwyn

Relevant Pages

  • Re: RAD vs. performance
    ... abstractions that will be there, whereas my compiler can optimize them ... Usually this doesn't matter, though. ... I'd say the same thing about your premature optimisation ...
    (comp.lang.misc)
  • Re: simple increment operator question.
    ... The Real OS/2 Guy wrote: ... > compiler to make optimasions right. ... > optimisation ability will produce better code for ... If find it sadly ironic that someone so concerned with the readability ...
    (alt.comp.lang.learn.c-cpp)
  • Re: Coldfire MCF5475 performance question
    ... I find it is normally much easier to see what is happening at the assembly level with basic optimisation enabled. ... But too little optimisation can also make it difficult, since the compiler puts data on the stack and uses unnecessarily long, slow code sequences. ... I've since set the 3 bits in this register to turn each of the caches on, and the empty loop now takes 106us, a factor of 14 improvement. ... The easiest way to check your clock rate is if you have a decent scope, look at the clock output pin. ...
    (comp.arch.embedded)
  • Re: Debug optimised code
    ... DWARF2) and compiler optimizations. ... accurate results for higher optimization levels? ... optimisation levels mean very much. ... you have to start debugging optimised code. ...
    (comp.compilers)
  • Re: simple increment operator question.
    ... compiler to make optimasions right. ... optimisation ability will produce better code for ... I've never seen assember code for more than 15 years - ... language right when you have to write code in that language. ...
    (alt.comp.lang.learn.c-cpp)