This is the mail archive of the
gcc-bugs@gcc.gnu.org
mailing list for the GCC project.
[Bug tree-optimization/26944] [4.1/4.2 Regression] -ftree-ch generates worse code
- From: "steven at gcc dot gnu dot org" <gcc-bugzilla at gcc dot gnu dot org>
- To: gcc-bugs at gcc dot gnu dot org
- Date: 2 May 2006 17:38:08 -0000
- Subject: [Bug tree-optimization/26944] [4.1/4.2 Regression] -ftree-ch generates worse code
- References: <bug-26944-1008@http.gcc.gnu.org/bugzilla/>
- Reply-to: gcc-bugzilla at gcc dot gnu dot org
------- Comment #4 from steven at gcc dot gnu dot org 2006-05-02 17:38 -------
The inner loop in the .cunroll, .ivopts and .final_cleanup with GVN-PRE
disabled look like this:
# Int_Index_37 = PHI <Int_Index_58(5), Int_Loc_3(3)>;
<L0>:;
(*D.1561_56)[Int_Index_37] = Int_Loc_3;
Int_Index_58 = Int_Index_37 + 1;
if (D.1563_41 >= Int_Index_58) goto <L8>; else goto <L2>;
<L8>:;
goto <bb 4> (<L0>);
and
# ivtmp.34_26 = PHI <ivtmp.34_19(5), ivtmp.34_1(3)>;
# Int_Index_37 = PHI <Int_Index_58(5), Int_Loc_3(3)>;
<L0>:;
D.1613_59 = (int *) ivtmp.34_26;
MEM[base: D.1613_59, offset: 20B] = Int_Loc_3;
Int_Index_58 = Int_Index_37 + 1;
ivtmp.34_19 = ivtmp.34_26 + 4B;
if (D.1563_41 >= Int_Index_58) goto <L8>; else goto <L2>;
<L8>:;
goto <bb 4> (<L0>);
and
<L0>:;
MEM[base: (int *) ivtmp.34, offset: 20B] = Int_Loc;
Int_Index = Int_Index + 1;
ivtmp.34 = ivtmp.34 + 4B;
if (D.1563 >= Int_Index) goto <L0>; else goto <L2>;
which compiles to:
.L4:
addl $1, %eax
movl %ecx, 20(%edx)
addl $4, %edx
cmpl %eax, %ebx
jge .L4
With PRE enabled, we get this:
# Int_Index_37 = PHI <Int_Index_58(6), Int_Loc_3(4)>;
<L0>:;
D.1559_54 = pretmp.27_59;
D.1560_55 = pretmp.28_45;
D.1561_56 = pretmp.28_49;
(*pretmp.28_49)[Int_Index_37] = Int_Loc_3;
Int_Index_58 = Int_Index_37 + 1;
if (D.1563_41 >= Int_Index_58) goto <L8>; else goto <L9>;
<L8>:;
goto <bb 5> (<L0>);
and
# ivtmp.38_26 = PHI <ivtmp.38_35(6), 0(4)>;
<L0>:;
D.1559_54 = pretmp.27_59;
D.1560_55 = pretmp.28_45;
D.1561_56 = pretmp.28_49;
D.1622_34 = (int *) pretmp.28_49;
D.1623_33 = (int *) Int_1_Par_Val_2;
D.1624_22 = (int *) ivtmp.38_26;
D.1625_21 = D.1623_33 + D.1624_22;
MEM[base: D.1622_34, index: D.1625_21, step: 4B, offset: 20B] = Int_Loc_3;
ivtmp.38_35 = ivtmp.38_26 + 1;
D.1626_20 = (unsigned int) Int_1_Par_Val_2;
D.1627_17 = D.1626_20 + ivtmp.38_35;
D.1628_16 = D.1627_17 + 5;
Int_Index_15 = (One_Fifty) D.1628_16;
if (D.1563_41 >= Int_Index_15) goto <L8>; else goto <L9>;
<L8>:;
goto <bb 5> (<L0>);
and
<L0>:;
MEM[base: (int *) prephitmp.33, index: (int *) Int_1_Par_Val + (int *)
ivtmp.38, step: 4B, offset: 20B] = Int_Loc;
ivtmp.38 = ivtmp.38 + 1;
if ((One_Fifty) ((unsigned int) Int_1_Par_Val + 5 + ivtmp.38) <= D.1563) goto
<L0>; else goto <L2>;
and from there:
.L5:
leal (%edi,%edx), %eax
addl $1, %edx
movl %ecx, 20(%ebx,%eax,4)
leal (%ecx,%edx), %eax
cmpl %esi, %eax
jle .L5
So it's a mix of PRE and IVOPTs that gives this strange code.
BTW regarding "Its strange that tree-ch messes up", please next time don't
blame random passes if you don't fully analyze the problem.
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=26944