http://gcc.gnu.org/bugzilla/show_bug.cgi?id=60889
Bug ID: 60889
Summary: -Os generate much bigger code
Product: gcc
Version: 4.10.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: middle-end
Assignee: unassigned at gcc dot gnu.org
Reporter: hjl.tools at gmail dot com
CC: mjambor at suse dot cz
On Linux/x86-64:
[hjl@gnu-6 gcc]$ cat /tmp/space.i
typedef float __v4sf __attribute__ ((__vector_size__ (16)));
typedef float __m128 __attribute__ ((__vector_size__ (16), __may_alias__));
struct S
{
__m128 a, b;
};
struct T
{
int a;
struct S s;
};
void foo (struct T *p, __m128 v)
{
struct S s;
s = p->s;
s.b = (__m128) __builtin_ia32_addps ((__v4sf)s.b, (__v4sf)v);
p->s = s;
}
[hjl@gnu-6 gcc]$ ./xgcc -B./ -S -O2 /tmp/space.i
[hjl@gnu-6 gcc]$ cat space.s
.file "space.i"
.section .text.unlikely,"ax",@progbits
.LCOLDB0:
.text
.LHOTB0:
.p2align 4,,15
.globl foo
.type foo, @function
foo:
.LFB0:
.cfi_startproc
addps 32(%rdi), %xmm0
movaps %xmm0, 32(%rdi)
ret
.cfi_endproc
.LFE0:
.size foo, .-foo
.section .text.unlikely
.LCOLDE0:
.text
.LHOTE0:
.ident "GCC: (GNU) 4.9.0 20140409 (experimental)"
.section .note.GNU-stack,"",@progbits
[hjl@gnu-6 gcc]$ ./xgcc -B./ -S -Os /tmp/space.i
[hjl@gnu-6 gcc]$ cat space.s
.file "space.i"
.section .text.unlikely,"ax",@progbits
.LCOLDB0:
.text
.LHOTB0:
.globl foo
.type foo, @function
foo:
.LFB0:
.cfi_startproc
movq %rdi, %rax
movl $8, %ecx
leaq -40(%rsp), %rdi
leaq 16(%rax), %rsi
rep movsl
addps 32(%rax), %xmm0
leaq 16(%rax), %rdi
leaq -40(%rsp), %rsi
movb $8, %cl
movaps %xmm0, -24(%rsp)
rep movsl
ret
.cfi_endproc
.LFE0:
.size foo, .-foo
.section .text.unlikely
.LCOLDE0:
.text
.LHOTE0:
.ident "GCC: (GNU) 4.9.0 20140409 (experimental)"
.section .note.GNU-stack,"",@progbits
[hjl@gnu-6 gcc]$
analyze_all_variable_accesses in tree-sra.c has
max_total_scalarization_size = UNITS_PER_WORD * BITS_PER_UNIT
* MOVE_RATIO (optimize_function_for_speed_p (cfun));
-Os sets MOVE_RATIO to 3. Should we have a different parameter
to control SRA?
