Details
-
Bug
-
Status: Closed
-
Major
-
Resolution: Fixed
-
4.1.3
-
None
-
gcc 4.1.2, Linux/x86_64
Description
According to my timings string::push_back() in stdcxx 4.1.3 is more than twice as slow than the same function in gcc 4.1.2 on Linux x86_64:
$ time ./push_back-stdcxx 100000000
real 0m2.175s
user 0m2.004s
sys 0m0.172s
$ time ./push_back-gcc 100000000
real 0m0.924s
user 0m0.760s
sys 0m0.164s
#include <cassert>
#include <cstdlib>
#include <string>
int main (int argc, char *argv[])
{
const int N = argc < 2 ? 1 : std::atoi (argv [1]);
std::string str;
for (int i = 0; i < N; ++i)
str.push_back ('x');
assert (str.size () == std::size_t (N));
}
Comparing the generated assembly, the gcc push_back() is mostly inline but the stdcxx push_back() is not:
stdcxx:
_Z8pushbackRSsc:
.LFB449:
movq (%rdi), %rax
movl %esi, %edx
movl $1, %ecx
movsbl %dl,%r8d
xorl %edx, %edx
movq -8(%rax), %rsi
jmp _ZNSs7replaceEmmmc
gcc:
_Z8pushbackRSsc:
.LFB904:
movq %rbp, -16(%rsp)
.LCFI0:
movq %r12, -8(%rsp)
.LCFI1:
movq %rdi, %rbp
movq %rbx, -24(%rsp)
.LCFI2:
subq $24, %rsp
.LCFI3:
movq (%rdi), %rax
movl %esi, %r12d
subq $24, %rax
movq (%rax), %rbx
addq $1, %rbx
cmpq 8(%rax), %rbx
ja .L2
movl 16(%rax), %eax
testl %eax, %eax
jg .L2
.L4:
movq (%rbp), %rdx
movq -24(%rdx), %rax
movb %r12b, (%rdx,%rax)
movq (%rbp), %rax
subq $24, %rax
movl $0, 16(%rax)
movq %rbx, (%rax)
movb $0, 24(%rax,%rbx)
movq (%rsp), %rbx
movq 8(%rsp), %rbp
movq 16(%rsp), %r12
addq $24, %rsp
ret
.p2align 4,,7
.L2:
movq %rbx, %rsi
movq %rbp, %rdi
call _ZNSs7reserveEm
jmp .L4
Attachments
Attachments
Issue Links
- relates to
-
STDCXX-492 std::string::operator+=() slow
- Resolved