On 28.05.2013 12:35, Ondřej Bílka wrote:
Did you tried if following gets optimized out?
(((long)atpr)%16 != 0) abort();
No, it is not, it generates:
406eb0: a8 0f test $0xf,%al
406eb2: 48 89 44 24 58 mov%rax,0x58(%rsp) // unrelated
406eb7
On 28.05.2013 12:19, Marc Glisse wrote:
On Tue, 28 May 2013, Anton Titov wrote:
I'm trying to force gcc to trust me that my memory allocation
function is returning aligned memory. So far I tried everything I
found with no luck.
Did you try using __builtin_assume_aligned?
I've tr
%es:(%rdi)" code for memset without the
checks for alignment?
Best,
Anton Titov
Hello,
I've set up a new gcc mirror in Sofia, Bulgaria
ftp://mirrors.host.bg/gnu/ftp/gnu/gcc/
http://mirrors.host.bg/gnu/ftp/gnu/gcc/
Regards,
Anton Titov
Host.bg
