G++ 4.0.3 - NRVO (named return value optimization) does not work if destructor/copy ctor is implicit

[Michael Kilburn]

Hi,

I have got a problem with GCC 4.0.3 -- if class does not have both
explicit dtor and cctor, NRVO does not work for it. I suspect this
problem applies to other GCC versions. This (of course) adversely
affects compiled code performance.
I can not explain why it happens and looking for:
- an explanation how implicit cctor/dtor affect NRVO-related decisions
made by compiler
- some kind of fix/workaround

Thanks!

(Btw, I checked this in MSVC 2005 -- everything is fine there)


Here is test code (uncomment either 1. or 2. or both and first test
will become as fast as second one):

-------- code start -------

#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#include <string.h>


struct TestX
{
    /************* TEST **************/
    // if you add any of these we get fast:

    // 1.
    //TestX() {}
    //TestX(const TestX& rhs) { memcpy(data, rhs.data, sizeof
(data)); }

    // 2.
    //~TestX() {}
    /************ END TEST **************/

    unsigned data[1000];

    void run_test()
    {
        memset(data, 0, sizeof(data));
    }
};


class RVO_Test
{
public:
    TestX fill(unsigned i)
    {
        TestX data;
        data.run_test();
        return data;
    }

    void fill(unsigned i, TestX &data)
    {
        data.run_test();
    }
};

int main()
{
    const unsigned MAX = 500000;

    // test #1
    {
        printf("Running Option 1\n");
        clock_t start = clock();

        for(int k = 0; k < 10; k++)
        {
            // slow or fast depending on cc.h TEST changes
            unsigned count = 0;
            RVO_Test a;
            for ( unsigned i = 0; i < MAX; ++i ) {
                TestX x = a.fill( MAX );
                count += x.data[5];
            }
            printf("Count: %i\n", count);
        }

        printf("Time: %f\n", double(clock() - start)/CLOCKS_PER_SEC);
    }

    // test #2
    {
        printf("Running Option 2\n");
        clock_t start = clock();

        for(int k = 0; k < 10; k++)
        {
            // fast
            unsigned count = 0;
            RVO_Test a;
            for ( unsigned i = 0; i < MAX; ++i ) {
                TestX x;
                a.fill( MAX, x );
                count += x.data[5];
            }
            printf("Count: %i\n", count);
        }

        printf("Time: %f\n", double(clock() - start)/CLOCKS_PER_SEC);
    }

    return 0;
}

-------- code end -------


Sincerely yours,
Michael.