[Flang] Defined assignments are slower than GFortran

[yus3710-fj]

The execution of the following codes is slower than GFortran.

• test.f90

module d
  type mytype1
    integer :: x,y,z
  end type
  type mytype2
    integer :: x,y
    type(mytype1) :: t
  end type
  interface assignment(=)
    module procedure :: swap
  end interface

contains
  pure subroutine swap(lhs,rhs)
    type(mytype2), intent(in) :: rhs
    type(mytype2), intent(out) :: lhs
    lhs%x = rhs%y
    lhs%y = rhs%x
    lhs%t = rhs%t
  end subroutine
end module

subroutine ddsnnn005(lhs,rhs)
  use d
  type(mytype2) :: rhs
  type(mytype2) :: lhs
  lhs = rhs
end subroutine

• main.f90

use d
implicit none

integer, parameter :: count = 10000
integer :: i,j,k
type(mytype2) :: t1,t2
real :: start_t, end_t
interface
  subroutine ddsnnn005(lhs,rhs)
    use d
    type(mytype2) :: rhs
    type(mytype2) :: lhs
  end subroutine
end interface

call cpu_time(start_t)
do i=1,count
  do j=1,count
    call ddsnnn005(t1,t2)
  end do
end do
call cpu_time(end_t)

print *, end_t - start_t
end

• commands

$ flang -Ofast -mcpu=native test.f90 main.f90 && ./a.out # for A64FX/Grace
$ flang -Ofast -march=native test.f90 main.f90 && ./a.out # for Xeon

	Flang [s]	GFortran [s]
A64FX	60.1938	0.327012002
Grace	8.52184	0.0610399991
Xeon	16.20353	0.0939439982