Re: [Caml-list] Native compilation for today's MIPS

[rixed@happyleptic.org]

I managed to spot a problem with this small piece of code, which is
the last function of unison's fileinfo module :

let unchanged fspath path info =
  (* The call to [Util.time] must be before the call to [get] *)
  let t0 = Util.time () in
  let info' = get true fspath path in
  let dataUnchanged =
    Props.same_time info.desc info'.desc
      &&
    stamp info = stamp info'
      &&
    if Props.time info'.desc = t0 then begin
	 	prerr_endline ("infotime="^(string_of_float (Props.time info'.desc))^" et t0="^(string_of_float t0)); (* THIS POOR STYLE LINE IS FROM ME *)
      Unix.sleep 1;
      false
    end else
      true
  in ...

As is, the generated code does not work as intended : although
Props.time infos'.desc and t0 are two distinct floats, the = test
behave like the values were equal and this function loop while it
shouldn't.

The corresponding code is :

1004b608 <camlFileinfo__unchanged_109>:
1004b608:	27bdffe0 	addiu	sp,sp,-32
1004b60c:	afbf001c 	sw	ra,28(sp)
1004b610:	afbc0018 	sw	gp,24(sp)
1004b614:	3c180011 	lui	t8,0x11
1004b618:	27187eb8 	addiu	t8,t8,32440
1004b61c:	0338e02d 	daddu	gp,t9,t8

1004b620 <$180>:
1004b620:	afa80000 	sw	a4,0(sp)
1004b624:	afa90004 	sw	a5,4(sp)
1004b628:	afaa0008 	sw	a6,8(sp)
1004b62c:	0c01c5a5 	jal	10071694 <camlUtil__time_308>
1004b630:	24080001 	li	a4,1

1004b634 <$181>:
1004b634:	afa2000c 	sw	v0,12(sp)
1004b638:	24080003 	li	a4,3
1004b63c:	8fa90000 	lw	a5,0(sp)
1004b640:	0c012c9e 	jal	1004b278 <camlFileinfo__get_78>
1004b644:	8faa0004 	lw	a6,4(sp)

1004b648 <$182>:
1004b648:	afa20004 	sw	v0,4(sp)
1004b64c:	8c52000c 	lw	s2,12(v0)
1004b650:	8fae0008 	lw	t2,8(sp)
1004b654:	8dd1000c 	lw	s1,12(t2)
1004b658:	3c101015 	lui	s0,0x1015
1004b65c:	8e10f0a4 	lw	s0,-3932(s0)
1004b660:	8e0a002c 	lw	a6,44(s0)
1004b664:	8e49000c 	lw	a5,12(s2)
1004b668:	0c013889 	jal	1004e224 <camlProps__same_368>
1004b66c:	8e28000c 	lw	a4,12(s1)

1004b670 <$183>:
1004b670:	24010001 	li	at,1
1004b674:	10410051 	beq	v0,at,1004b7bc <$173>
1004b678:	00000000 	nop
1004b67c:	0c012d44 	jal	1004b510 <camlFileinfo__stamp_105>
1004b680:	8fa80004 	lw	a4,4(sp)

1004b684 <$184>:
1004b684:	afa20000 	sw	v0,0(sp)
1004b688:	0c012d44 	jal	1004b510 <camlFileinfo__stamp_105>
1004b68c:	8fa80008 	lw	a4,8(sp)

1004b690 <$185>:
1004b690:	0040202d 	move	a0,v0
1004b694:	8fa50000 	lw	a1,0(sp)
1004b698:	3c18100c 	lui	t8,0x100c
1004b69c:	0c033a96 	jal	100cea58 <caml_c_call>
1004b6a0:	271808a4 	addiu	t8,t8,2212

1004b6a4 <$186>:
1004b6a4:	24010001 	li	at,1
1004b6a8:	10410041 	beq	v0,at,1004b7b0 <$174>
1004b6ac:	00000000 	nop
1004b6b0:	8faa0004 	lw	a6,4(sp)
1004b6b4:	8d48000c 	lw	a4,12(a6)
1004b6b8:	8d07000c 	lw	a3,12(a4)
1004b6bc:	90e6fffc 	lbu	a2,-4(a3)
1004b6c0:	10c00007 	beqz	a2,1004b6e0 <$179>
1004b6c4:	00000000 	nop
1004b6c8:	8ce50000 	lw	a1,0(a3)
1004b6cc:	68b80000 	ldl	t8,0(a1)
1004b6d0:	6cb80007 	ldr	t8,7(a1)
1004b6d4:	44b80800 	dmtc1	t8,$f1
1004b6d8:	10000005 	b	1004b6f0 <$178>
1004b6dc:	00000000 	nop

1004b6e0 <$179>:
1004b6e0:	8ce40000 	lw	a0,0(a3)
1004b6e4:	68980000 	ldl	t8,0(a0)
1004b6e8:	6c980007 	ldr	t8,7(a0)
1004b6ec:	44b80800 	dmtc1	t8,$f1

1004b6f0 <$178>:
1004b6f0:	8fa8000c 	lw	a4,12(sp)
1004b6f4:	69180000 	ldl	t8,0(a4)
1004b6f8:	6d180007 	ldr	t8,7(a4)
1004b6fc:	44b80000 	dmtc1	t8,$f0
1004b700:	00000000 	nop
1004b704:	46200832 	c.eq.d	$f1,$f0
1004b708:	00000000 	nop
1004b70c:	45000025 	bc1f	1004b7a4 <$175>
1004b710:	00000000 	nop
1004b714:	0c020d9d 	jal	10083674 <camlPervasives__string_of_float_164>
1004b718:	00000000 	nop

1004b71c <$187>:
1004b71c:	0040482d 	move	a5,v0
1004b720:	3c081015 	lui	a4,0x1015
1004b724:	0c020cde 	jal	10083378 <camlPervasives__$5e_136>
1004b728:	2508ef1c 	addiu	a4,a4,-4324

1004b72c <$188>:
1004b72c:	afa20000 	sw	v0,0(sp)
1004b730:	8fa80004 	lw	a4,4(sp)
1004b734:	8d14000c 	lw	s4,12(a4)
1004b738:	8e93000c 	lw	s3,12(s4)
1004b73c:	9272fffc 	lbu	s2,-4(s3)
1004b740:	12400004 	beqz	s2,1004b754 <$177>
1004b744:	00000000 	nop
1004b748:	8e710000 	lw	s1,0(s3)
1004b74c:	10000003 	b	1004b75c <$176>
1004b750:	0220402d 	move	a4,s1

1004b754 <$177>:
1004b754:	8e700000 	lw	s0,0(s3)
1004b758:	0200402d 	move	a4,s0

1004b75c <$176>:
1004b75c:	0c020d9d 	jal	10083674 <camlPervasives__string_of_float_164>
1004b760:	00000000 	nop

1004b764 <$189>:
1004b764:	0040402d 	move	a4,v0
1004b768:	0c020cde 	jal	10083378 <camlPervasives__$5e_136>
1004b76c:	8fa90000 	lw	a5,0(sp)

1004b770 <$190>:
1004b770:	3c081015 	lui	a4,0x1015
1004b774:	2508ef0c 	addiu	a4,a4,-4340
1004b778:	0c020cde 	jal	10083378 <camlPervasives__$5e_136>
1004b77c:	0040482d 	move	a5,v0

1004b780 <$191>:
1004b780:	0c021067 	jal	1008419c <camlPervasives__prerr_endline_309>
1004b784:	0040402d 	move	a4,v0

1004b788 <$192>:
1004b788:	24040003 	li	a0,3
1004b78c:	3c18100b 	lui	t8,0x100b
1004b790:	0c033a96 	jal	100cea58 <caml_c_call>
1004b794:	27186e10 	addiu	t8,t8,28176

1004b798 <$193>:
1004b798:	240b0001 	li	a7,1
1004b79c:	10000009 	b	1004b7c4 <$172>
1004b7a0:	afab0000 	sw	a7,0(sp)

1004b7a4 <$175>:
1004b7a4:	240b0003 	li	a7,3
1004b7a8:	10000006 	b	1004b7c4 <$172>
1004b7ac:	afab0000 	sw	a7,0(sp)


This last caml_c_call being for the Unix.sleep if Im not mistaken.
Notice how floating point registers $f0 and $f1 are used and compared
together for equality, jumping if they are not equal to <$175> (which
sets a7 to true and leaves this part of the code. I'm googling for
mips instructions while reading so I migh be wrong, but the test
looks OK to me. So certainly f0 and/or f1 are wrong, despite the correct
values being displayed by prerr_endline.

Now, lets change a little how the test is done :

let unchanged fspath path info =
  (* The call to [Util.time] must be before the call to [get] *)
  let t0 = Util.time () in
  let info' = get true fspath path in
  let are_the_same a b = a = b in  (* I ADDED THIS MASTERPIECE *)
  let dataUnchanged =
    Props.same_time info.desc info'.desc
      &&
    stamp info = stamp info'
      &&
    if are_the_same (Props.time info'.desc) t0 then begin
	 	prerr_endline ("infotime="^(string_of_float (Props.time info'.desc))^" et t0="^(string_of_float t0));
      Unix.sleep 1;
      false
    end else
      true
  in

With the addition if this gratuitous complication of the code, unison
works (at least it does no longer loop forever here and do copy some files).
The generated code is here and, abracadabra!, all the floating point code is
gone :


1004b644 <camlFileinfo__unchanged_109>:
1004b644:	27bdffe0 	addiu	sp,sp,-32
1004b648:	afbf001c 	sw	ra,28(sp)
1004b64c:	afbc0018 	sw	gp,24(sp)
1004b650:	3c180011 	lui	t8,0x11
1004b654:	27187e8c 	addiu	t8,t8,32396
1004b658:	0338e02d 	daddu	gp,t9,t8

1004b65c <$182>:
1004b65c:	afa80000 	sw	a4,0(sp)
1004b660:	afa90004 	sw	a5,4(sp)
1004b664:	afaa0008 	sw	a6,8(sp)
1004b668:	0c01c5ad 	jal	100716b4 <camlUtil__time_308>
1004b66c:	24080001 	li	a4,1

1004b670 <$183>:
1004b670:	afa2000c 	sw	v0,12(sp)
1004b674:	24080003 	li	a4,3
1004b678:	8fa90000 	lw	a5,0(sp)
1004b67c:	0c012cad 	jal	1004b2b4 <camlFileinfo__get_78>
1004b680:	8faa0004 	lw	a6,4(sp)

# LOOK AT THESE TWO NEW INSTRUCTIONS HERE (lui and addiu)
# TO CHANGE v1. WHAT IS IN v1 ?
1004b684 <$184>:
1004b684:	afa20004 	sw	v0,4(sp)
1004b688:	3c031015 	lui	v1,0x1015
1004b68c:	2463ecc4 	addiu	v1,v1,-4924
1004b690:	8c55000c 	lw	s5,12(v0)
1004b694:	8faf0008 	lw	t3,8(sp)
1004b698:	8df4000c 	lw	s4,12(t3)
1004b69c:	3c131015 	lui	s3,0x1015
1004b6a0:	8e73f0b4 	lw	s3,-3916(s3)
1004b6a4:	8e6a002c 	lw	a6,44(s3)
1004b6a8:	8ea9000c 	lw	a5,12(s5)
1004b6ac:	0c013891 	jal	1004e244 <camlProps__same_368>
1004b6b0:	8e88000c 	lw	a4,12(s4)

1004b6b4 <$185>:
1004b6b4:	24010001 	li	at,1
1004b6b8:	10410048 	beq	v0,at,1004b7dc <$175>
1004b6bc:	00000000 	nop
1004b6c0:	0c012d53 	jal	1004b54c <camlFileinfo__stamp_105>
1004b6c4:	8fa80004 	lw	a4,4(sp)

1004b6c8 <$186>:
1004b6c8:	afa20000 	sw	v0,0(sp)
1004b6cc:	0c012d53 	jal	1004b54c <camlFileinfo__stamp_105>
1004b6d0:	8fa80008 	lw	a4,8(sp)

1004b6d4 <$187>:
1004b6d4:	0040202d 	move	a0,v0
1004b6d8:	8fa50000 	lw	a1,0(sp)
1004b6dc:	3c18100c 	lui	t8,0x100c
1004b6e0:	0c033a9e 	jal	100cea78 <caml_c_call>
1004b6e4:	271808c4 	addiu	t8,t8,2244

1004b6e8 <$188>:
1004b6e8:	24010001 	li	at,1
1004b6ec:	10410038 	beq	v0,at,1004b7d0 <$176>
1004b6f0:	00000000 	nop
1004b6f4:	8fab0004 	lw	a7,4(sp)
1004b6f8:	8d6b000c 	lw	a7,12(a7)
1004b6fc:	8d6a000c 	lw	a6,12(a7)
1004b700:	9149fffc 	lbu	a5,-4(a6)
1004b704:	11200003 	beqz	a5,1004b714 <$181>
1004b708:	00000000 	nop
1004b70c:	10000002 	b	1004b718 <$180>
1004b710:	8d440000 	lw	a0,0(a6)

1004b714 <$181>:
1004b714:	8d440000 	lw	a0,0(a6)

# HERE IT'S COMPLETELY DIFFERENT FROM ABOVE
# THE FP CODE IS GONE ??
1004b718 <$180>:
1004b718:	8fa5000c 	lw	a1,12(sp)
1004b71c:	3c18100c 	lui	t8,0x100c
1004b720:	0c033a9e 	jal	100cea78 <caml_c_call>
1004b724:	271808c4 	addiu	t8,t8,2244

1004b728 <$189>:
1004b728:	24010001 	li	at,1
1004b72c:	10410025 	beq	v0,at,1004b7c4 <$177>
1004b730:	00000000 	nop
1004b734:	0c020da5 	jal	10083694 <camlPervasives__string_of_float_164>
1004b738:	8fa8000c 	lw	a4,12(sp)

1004b73c <$190>:
1004b73c:	0040482d 	move	a5,v0
1004b740:	3c081015 	lui	a4,0x1015
1004b744:	0c020ce6 	jal	10083398 <camlPervasives__$5e_136>
1004b748:	2508ef2c 	addiu	a4,a4,-4308

1004b74c <$191>:
1004b74c:	afa20000 	sw	v0,0(sp)
1004b750:	8fa80004 	lw	a4,4(sp)
1004b754:	8d15000c 	lw	s5,12(a4)
1004b758:	8eb4000c 	lw	s4,12(s5)
1004b75c:	9293fffc 	lbu	s3,-4(s4)
1004b760:	12600004 	beqz	s3,1004b774 <$179>
1004b764:	00000000 	nop
1004b768:	8e920000 	lw	s2,0(s4)
1004b76c:	10000003 	b	1004b77c <$178>
1004b770:	0240402d 	move	a4,s2

1004b774 <$179>:
1004b774:	8e910000 	lw	s1,0(s4)
1004b778:	0220402d 	move	a4,s1

1004b77c <$178>:
1004b77c:	0c020da5 	jal	10083694 <camlPervasives__string_of_float_164>
1004b780:	00000000 	nop

1004b784 <$192>:
1004b784:	0040402d 	move	a4,v0
1004b788:	0c020ce6 	jal	10083398 <camlPervasives__$5e_136>
1004b78c:	8fa90000 	lw	a5,0(sp)

1004b790 <$193>:
1004b790:	3c081015 	lui	a4,0x1015
1004b794:	2508ef1c 	addiu	a4,a4,-4324
1004b798:	0c020ce6 	jal	10083398 <camlPervasives__$5e_136>
1004b79c:	0040482d 	move	a5,v0

1004b7a0 <$194>:
1004b7a0:	0c02106f 	jal	100841bc <camlPervasives__prerr_endline_309>
1004b7a4:	0040402d 	move	a4,v0

1004b7a8 <$195>:
1004b7a8:	24040003 	li	a0,3
1004b7ac:	3c18100b 	lui	t8,0x100b
1004b7b0:	0c033a9e 	jal	100cea78 <caml_c_call>
1004b7b4:	27186e30 	addiu	t8,t8,28208

1004b7b8 <$196>:
1004b7b8:	240b0001 	li	a7,1
1004b7bc:	10000009 	b	1004b7e4 <$174>
1004b7c0:	afab0000 	sw	a7,0(sp)

1004b7c4 <$177>:
1004b7c4:	240b0003 	li	a7,3
1004b7c8:	10000006 	b	1004b7e4 <$174>
1004b7cc:	afab0000 	sw	a7,0(sp)


So what's happening there ? Why no more FP registers ?

I'm still in the dark but I wanted to share these questions with the
list in the hope that a Mips guru would see this and recognize at first
sight the stupid mistake I did and point me in the right direction.

If all the gurus are in hollidays, well, it's fun anyway :)
Sory to waste the bandwidth.