See below: two register->register moves which
are not needed.
# cat byteorder.c
typedef unsigned long long u64;
typedef unsigned u32;
static inline u64 swab64(u64 val) {
union {
struct { u32 a,b; } s;
u64 u;
} v;
v.u = val;
asm("bswapl %0 ; bswapl %1"
: "=r" (v.s.b), "=r" (v.s.a)
: "0" (v.s.a), "1" (v.s.b));
return v.u;
}
extern u64 w;
void f() {
w = swab64(w);
}
# gcc -O3 byteorder.c -S
# cat byteorder.s
.file "byteorder.c"
.text
.p2align 2,,3
.globl f
.type f, @function
f:
pushl %ebp
movl %esp, %ebp
pushl %esi
pushl %ebx
movl w, %esi
movl w+4, %edx
movl %esi, %ebx
movl %edx, %esi
#APP
bswapl %ebx ; bswapl %esi
#NO_APP
movl %ebx, w+4
popl %ebx
movl %esi, w
popl %esi
leave
ret
.size f, .-f
.section .note.GNU-stack,"",@progbits
.ident "GCC: (GNU) 3.4.3"
# gcc -O3 byteorder.c -S; cat byteorder.s; gcc -v
.file "byteorder.c"
.text
.p2align 2,,3
.globl f
.type f, @function
f:
pushl %ebp
movl %esp, %ebp
pushl %esi
pushl %ebx
movl w, %eax
movl w+4, %edx
movl %eax, %ebx
movl %edx, %esi
#APP
bswapl %ebx ; bswapl %esi
#NO_APP
movl %esi, w
movl %ebx, w+4
popl %ebx
popl %esi
leave
ret
.size f, .-f
.ident "GCC: (GNU) 4.0.0"
.section .note.GNU-stack,"",@progbits
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
--
Summary: Extra register moves generated
Product: gcc
Version: 4.0.0
Status: UNCONFIRMED
Severity: normal
Priority: P2
Component: rtl-optimization
AssignedTo: unassigned at gcc dot gnu dot org
ReportedBy: vda at port dot imtp dot ilyichevsk dot odessa dot ua
CC: gcc-bugs at gcc dot gnu dot org
GCC build triplet: i386-pc-linux-gnu
GCC host triplet: i386-pc-linux-gnu
GCC target triplet: i386-pc-linux-gnu
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=21202
