gcc 的 asm volatile 是否等同于递归的 gfortran 默认设置?

However, I am a bit more specific and puzzled as the Fortran compiler seems to be doing what you can achieve with asm volatile in gcc. To give you some context let's consider the following recursive Fibonacci number implementation:

Fortran 代码:

module test
implicit none
private
public fib

contains

! Fibonacci function
integer recursive function fib(n) result(r)
    integer, intent(in) :: n
    if (n < 2) then
        r = n
    else
        r = fib(n-1) + fib(n-2)
    end if
end function  ! end of Fibonacci function
end module

program fibonacci
use test, only: fib
implicit none
integer :: r,i 
integer :: n = 1e09
real(8) :: start, finish, cum_time

cum_time=0
do i= 1,n 
    call cpu_time(start)
    r = fib(20)
    call cpu_time(finish) 
    cum_time = cum_time + (finish - start)
    if (cum_time >0.5) exit
enddo  

print*,i,'runs, average elapsed time is', cum_time/i/1e-06, 'us' 
end program

编译:

gfortran -O3 -march=native

C++ 代码:

#include <iostream>
#include <chrono>
using namespace std;

// Fib function
int fib(const int n)
{
    int r;
    if (n < 2)
        r = n;
    else
        r = fib(n-1) + fib(n-2);
    return r;
} // end of fib

template<typename T, typename ... Args>
double timeit(T (*func)(Args...), Args...args)
{
    double counter = 1.0;
    double mean_time = 0.0;
    for (auto iter=0; iter<1e09; ++iter){
        std::chrono::time_point<std::chrono::system_clock> start, end;
        start = std::chrono::system_clock::now();

        func(args...);

        end = std::chrono::system_clock::now();
        std::chrono::duration<double> elapsed_seconds = end-start;

        mean_time += elapsed_seconds.count();
        counter++;

        if (mean_time > 0.5){
            mean_time /= counter;
            std::cout << static_cast<long int>(counter)
            << " runs, average elapsed time is "
            << mean_time/1.0e-06 << " xC2xB5s" << std::endl; 
            break;
        }
    }
    return mean_time;
}

int main(){
    timeit(fib,20);
    return 0;
}

编译:

g++ -O3 -march=native

时间:

Fortran: 24991 runs, average elapsed time is 20.087 us
C++    : 12355 runs, average elapsed time is 40.471 μs

所以 gfortran 的速度是 gcc 的两倍.查看汇编代码，我得到了

.L28:
    cmpl    $1, %r13d
    jle .L29
    leal    -8(%rbx), %eax
    movl    %ecx, 12(%rsp)
    movl    %eax, 48(%rsp)
    leaq    48(%rsp), %rdi
    leal    -9(%rbx), %eax
    movl    %eax, 16(%rsp)
    call    __bench_MOD_fib
    leaq    16(%rsp), %rdi
    movl    %eax, %r13d
    call    __bench_MOD_fib
    movl    12(%rsp), %ecx
    addl    %eax, %r13d

.L28:
    movl    72(%rsp), %edx
    cmpl    $1, %edx
    movl    %edx, %eax
    jle .L33
    subl    $3, %eax
    movl    $0, 52(%rsp)
    movl    %eax, %esi
    movl    %eax, 96(%rsp)
    movl    92(%rsp), %eax
    shrl    %eax
    movl    %eax, 128(%rsp)
    addl    %eax, %eax
    subl    %eax, %esi
    movl    %edx, %eax
    subl    $1, %eax
    movl    %esi, 124(%rsp)
    movl    %eax, 76(%rsp)

// Fib function
int fib(const int n)
{
    int r;
    if (n < 2)
        r = n;
    else
        r = fib(n-1) + fib(n-2);
    asm("");
    return r;
} // end of fib

.L7:
    cmpl    $1, %edx
    jle .L17
    leal    -4(%rbx), %r13d
    leal    -5(%rbx), %edx
    cmpl    $1, %r13d
    jle .L19
    leal    -5(%rbx), %r14d
    cmpl    $1, %r14d
    jle .L55
    leal    -6(%rbx), %r13d
    movl    %r13d, %edi
    call    _Z3fibi
    leal    -7(%rbx), %edi
    movl    %eax, %r15d
    call    _Z3fibi
    movl    %r13d, %edi
    addl    %eax, %r15d

Fortran: 24991 runs, average elapsed time is 20.087 us
C++    : 25757 runs, average elapsed time is 19.412 μs

clang++ w/o asm    :  8846 runs, average elapsed time is 56.4555 μs
clang++ with asm   : 10427 runs, average elapsed time is 47.8991 μs 

int fib(const int n)
{
    if (n < 2)
        return n;
    else
        return fib(n-1) + fib(n-2);
}