[Flang] Assignments for variables of a derived type 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
end module

subroutine ddsnnn004(lhs,rhs)
  use d
  type(mytype1) :: rhs
  type(mytype1) :: lhs
  lhs = rhs
end subroutine

• main.f90

use d
implicit none

integer, parameter :: count = 40000
integer :: i,j,k
type(mytype1) :: t1,t2
real :: start_t, end_t
interface
  subroutine ddsnnn004(lhs,rhs)
    use d
    type(mytype1) :: rhs
    type(mytype1) :: lhs
  end subroutine
end interface

call cpu_time(start_t)
do i=1,count
  do j=1,count
    call ddsnnn004(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	15.933074	3.21280599
Grace	2.9103858	0.975975990
Xeon	3.3161151	1.50089002