! compile with
! as -xarch=v8plusa -o falign_test.o falign_test.s ; 
! ld -o falign_test falign_test.o

!     + Syscalls have number in %g1, options in %o0,%o1,...
!	Result returned in %o0
!	Linux syscall is called by "ta 0x10"

.equ SYSCALL_EXIT,1	
.equ SYSCALL_WRITE,4

.equ STDOUT,1

	.globl _start
_start:


!  
! print the source!
!

       set	source,%o1
       call	write_stdout
       nop

!
! copy the string
!

      set	source,%o1      
      set	destination,%o0


      alignaddr  %o1, %g0, %o3
 
      membar  #StoreStore|#LoadStore|#StoreLoad
      wr  %g0, 0xf0, %asi		       		! set block-copy asi
      nop
      
      ldda  [ %o1 ] %asi, %f0
      nop
      
      faligndata  %f0, %f2, %f16
      faligndata  %f2, %f4, %f18
      faligndata  %f4, %f6, %f20
      faligndata  %f6, %f8, %f22
      faligndata  %f8, %f10, %f24
      faligndata  %f10, %f12, %f26
      faligndata  %f12, %f14, %f28
      faligndata  %f14, %f16, %f30
after:      
      stda  %f16, [ %o0 ] %asi

      nop
      nop
       
      

!
! print the copy
!
       
      set	destination,%o1
      call	write_stdout
      nop


      ba 	exit
      nop


	#================================
	# WRITE_STDOUT
	#================================
	# %o1 has string

write_stdout:

	set	SYSCALL_WRITE,%g1	! Write syscall in %g1
	set	STDOUT,%o0		! 1 in %o0 (stdout)
	set	0,%o2			! 0 (count) in %o2

str_loop1:
	ldub	[%o1+%o2],%l0		! load byte
	cmp	%l0,%g0			! compare against zero
	bnz	str_loop1		! if not nul, repeat
	# BRANCH DELAY SLOT
	inc	%o2			! increment count

	dec	%o2			! correct count	
	ta	0x10			! run the syscall
	retl				! return
	nop

exit:		
        mov	0,%o0			! exit value
        mov	SYSCALL_EXIT,%g1        ! put the exit syscall number in g1
        ta      0x10			! and exit




!===========================================================================
.data
!===========================================================================

.balign 64    !(needs to be on 64-byte boundary)

              !           1         2         3         4
              ! 0123456789012345678901234567890123456789012345678
source: .ascii "The quick brown fox jumped over "
        .ascii  "the lazy dog! Need more fill!\n\0"

.lcomm destination,64