------- Comment #14 from rguenth at gcc dot gnu dot org 2008-01-03 17:06
-------
With optimization we now avoid the error, but unoptimized code is still wrong:
_Z10InitializeP16SQLU_DICT_INFO_0:
.LFB3:
pushq %rbp
.LCFI2:
movq %rsp, %rbp
.LCFI3:
pushq %rbx
.LCFI4:
subq $8, %rsp
.LCFI5:
movq %rdi, -16(%rbp)
movq -16(%rbp), %rax
movb $0, 8(%rax)
movq -16(%rbp), %rax
movb $0, 9(%rax)
movq -16(%rbp), %rbx
call _Z17INIT_6_BYTES_ZEROv
movzbl %al, %ecx
movzbl 10(%rbx), %edx
andl $0, %edx
orl %ecx, %edx
movb %dl, 10(%rbx)
movzbl %ah, %edx
mov %edx, %ecx
movq 10(%rbx), %rdx
^^^^^^^^^^^^^ here
movb %cl, %dh
movq %rdx, 10(%rbx)
^^^^^^^^^^^^^ and here
movq %rax, %rdx
shrq $16, %rdx
movzbq %dl,%rcx
movzbl 12(%rbx), %edx
andl $0, %edx
orl %ecx, %edx
movb %dl, 12(%rbx)
movq %rax, %rdx
shrq $24, %rdx
movzbq %dl,%rcx
movzbl 13(%rbx), %edx
andl $0, %edx
orl %ecx, %edx
movb %dl, 13(%rbx)
movq %rax, %rdx
shrq $32, %rdx
movzbq %dl,%rcx
movzbl 14(%rbx), %edx
andl $0, %edx
orl %ecx, %edx
movb %dl, 14(%rbx)
shrq $40, %rax
movzbq %al,%rdx
movzbl 15(%rbx), %eax
andl $0, %eax
orl %edx, %eax
movb %al, 15(%rbx)
addq $8, %rsp
popq %rbx
leave
ret
without inlining we do optimize this to
_Z10InitializeP16SQLU_DICT_INFO_0:
.LFB3:
pushq %rbx
.LCFI0:
movq %rdi, %rbx
movb $0, 8(%rdi)
movb $0, 9(%rdi)
call _Z17INIT_6_BYTES_ZEROv
movb %al, 10(%rbx)
movzbl %ah, %edx
movb %dl, 11(%rbx)
movq %rax, %rdx
shrq $16, %rdx
movb %dl, 12(%rbx)
movq %rax, %rdx
shrq $24, %rdx
movb %dl, 13(%rbx)
movq %rax, %rdx
shrq $32, %rdx
movb %dl, 14(%rbx)
shrq $40, %rax
movb %al, 15(%rbx)
popq %rbx
ret
which doesn't have the 8 byte move any more. 4.2, even when optimizing
retains the 8 byte move.
--
rguenth at gcc dot gnu dot org changed:
What |Removed |Added
----------------------------------------------------------------------------
Last reconfirmed|2007-03-22 10:03:14 |2008-01-03 17:06:20
date| |
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=31309
