lkml.org 
[lkml]   [2005]   [Aug]   [15]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRe: [-mm patch] make kcalloc() a static inline
Date
On Monday 15 August 2005 12:41, Arjan van de Ven wrote:
> On Mon, 2005-08-15 at 12:33 +0300, Denis Vlasenko wrote:
>
> > gcc can optimize that away with non-const n?! I don't think so.
>
> due to the wonders of "value range propagation" it actually can, if the
> check is done sufficiently before...
>
> gcc keeps track of the range a variable can have at each point, so if
> the check is done before, the "possible range" will be such that the
> divide should be optimizable.
>
> (Note: this is a relatively new feature in gcc though)

# gcc -v
Using built-in specs.
Target: i386-pc-linux-gnu
Configured with: ../gcc-4.0.0.src/configure --prefix=/usr/app/gcc-4.0.0 --exec-prefix=/usr/app/gcc-4.0.0 --bindir=/usr/bin --sbindir=/usr/sbin --libexecdir=/usr/app/gcc-4.0.0/libexec --datadir=/usr/app/gcc-4.0.0/share --sysconfdir=/etc --sharedstatedir=/usr/app/gcc-4.0.0/var/com --localstatedir=/usr/app/gcc-4.0.0/var --libdir=/usr/lib --includedir=/usr/include --infodir=/usr/info --mandir=/usr/man --with-slibdir=/usr/app/gcc-4.0.0/lib --with-local-prefix=/usr/local --with-gxx-include-dir=/usr/app/gcc-4.0.0/include/g++-v3 --enable-languages=c,c++ --with-system-zlib --disable-nls --enable-threads=posix i386-pc-linux-gnu
Thread model: posix
gcc version 4.0.0
# cat t.c
#include <stdlib.h>
#include <limits.h>

void *kzalloc(size_t size, unsigned int flags);

static inline void *kcalloc(size_t n, size_t size, unsigned int flags)
{
if (n != 0 && size > INT_MAX / n)
return NULL;
return kzalloc(n * size, flags);
}

void* f(int n, int sz)
{
if (sz<1000) return kcalloc(n, sz, 1);
return NULL;
}
# gcc -O2 -S -mcpu=i386 t.c
`-mcpu=' is deprecated. Use `-mtune=' or '-march=' instead.
# cat t.s
.file "t.c"
.text
.p2align 2,,3
.globl f
.type f, @function
f:
pushl %ebp
movl %esp, %ebp
pushl %ebx
movl 8(%ebp), %ebx
movl 12(%ebp), %ecx
cmpl $999, %ecx
jg .L2
testl %ebx, %ebx
jne .L9
.L4:
movl $1, 12(%ebp)
imull %ebx, %ecx
movl %ecx, 8(%ebp)
popl %ebx
leave
jmp kzalloc
.p2align 2,,3
.L9:
movl $2147483647, %eax
xorl %edx, %edx
divl %ebx
cmpl %eax, %ecx
jbe .L4
.p2align 2,,3
.L2:
xorl %eax, %eax
popl %ebx
leave
ret
.size f, .-f
.ident "GCC: (GNU) 4.0.0"
.section .note.GNU-stack,"",@progbits


Seems like that optimization is not helping.
Do you have better example?
--
vda

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2005-08-15 14:21    [W:0.062 / U:5.740 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site