lundi 27 juin 2016

GCC 5.1 Loop unrolling

Given the following code

#include <stdio.h>

int main(int argc, char **argv)
{
  int k = 0;
  for( k = 0; k < 20; ++k )
  {
    printf( "%dn", k ) ;
  }
}

Using GCC 5.1 or later with

-x c -std=c99 -O3 -funroll-all-loops --param max-completely-peeled-insns=1000 --param max-completely-peel-times=10000

does partially loop unrolling, it unrolls the loop ten times and then does a conditional jump.

.LC0:
        .string "%dn"
main:
        pushq   %rbx
        xorl    %ebx, %ebx
.L2:
        movl    %ebx, %esi
        movl    $.LC0, %edi
        xorl    %eax, %eax
        call    printf
        leal    1(%rbx), %esi
        movl    $.LC0, %edi
        xorl    %eax, %eax
        call    printf
        leal    2(%rbx), %esi
        movl    $.LC0, %edi
        xorl    %eax, %eax
        call    printf
        leal    3(%rbx), %esi
        movl    $.LC0, %edi
        xorl    %eax, %eax
        call    printf
        leal    4(%rbx), %esi
        movl    $.LC0, %edi
        xorl    %eax, %eax
        call    printf
        leal    5(%rbx), %esi
        movl    $.LC0, %edi
        xorl    %eax, %eax
        call    printf
        leal    6(%rbx), %esi
        movl    $.LC0, %edi
        xorl    %eax, %eax
        call    printf
        leal    7(%rbx), %esi
        movl    $.LC0, %edi
        xorl    %eax, %eax
        call    printf
        leal    8(%rbx), %esi
        movl    $.LC0, %edi
        xorl    %eax, %eax
        call    printf
        leal    9(%rbx), %esi
        xorl    %eax, %eax
        movl    $.LC0, %edi
        addl    $10, %ebx
        call    printf
        cmpl    $20, %ebx
        jne     .L2
        xorl    %eax, %eax
        popq    %rbx
        ret

But using older versions of GCC such as 4.9.2 creates the desired assemlby

.LC0:
    .string "%dn"
main:
    subq    $8, %rsp
    xorl    %edx, %edx
    movl    $.LC0, %esi
    movl    $1, %edi
    xorl    %eax, %eax
    call    __printf_chk
    movl    $1, %edx
    movl    $.LC0, %esi
    movl    $1, %edi
    xorl    %eax, %eax
    call    __printf_chk
    movl    $2, %edx
    movl    $.LC0, %esi
    movl    $1, %edi
    xorl    %eax, %eax
    call    __printf_chk
    movl    $3, %edx
    movl    $.LC0, %esi
    movl    $1, %edi
    xorl    %eax, %eax
    call    __printf_chk
    movl    $4, %edx
    movl    $.LC0, %esi
    movl    $1, %edi
    xorl    %eax, %eax
    call    __printf_chk
    movl    $5, %edx
    movl    $.LC0, %esi
    movl    $1, %edi
    xorl    %eax, %eax
    call    __printf_chk
    movl    $6, %edx
    movl    $.LC0, %esi
    movl    $1, %edi
    xorl    %eax, %eax
    call    __printf_chk
    movl    $7, %edx
    movl    $.LC0, %esi
    movl    $1, %edi
    xorl    %eax, %eax
    call    __printf_chk
    movl    $8, %edx
    movl    $.LC0, %esi
    movl    $1, %edi
    xorl    %eax, %eax
    call    __printf_chk
    movl    $9, %edx
    movl    $.LC0, %esi
    movl    $1, %edi
    xorl    %eax, %eax
    call    __printf_chk
    movl    $10, %edx
    movl    $.LC0, %esi
    movl    $1, %edi
    xorl    %eax, %eax
    call    __printf_chk
    movl    $11, %edx
    movl    $.LC0, %esi
    movl    $1, %edi
    xorl    %eax, %eax
    call    __printf_chk
    movl    $12, %edx
    movl    $.LC0, %esi
    movl    $1, %edi
    xorl    %eax, %eax
    call    __printf_chk
    movl    $13, %edx
    movl    $.LC0, %esi
    movl    $1, %edi
    xorl    %eax, %eax
    call    __printf_chk
    movl    $14, %edx
    movl    $.LC0, %esi
    movl    $1, %edi
    xorl    %eax, %eax
    call    __printf_chk
    movl    $15, %edx
    movl    $.LC0, %esi
    movl    $1, %edi
    xorl    %eax, %eax
    call    __printf_chk
    movl    $16, %edx
    movl    $.LC0, %esi
    movl    $1, %edi
    xorl    %eax, %eax
    call    __printf_chk
    movl    $17, %edx
    movl    $.LC0, %esi
    movl    $1, %edi
    xorl    %eax, %eax
    call    __printf_chk
    movl    $18, %edx
    movl    $.LC0, %esi
    movl    $1, %edi
    xorl    %eax, %eax
    call    __printf_chk
    movl    $19, %edx
    movl    $.LC0, %esi
    movl    $1, %edi
    xorl    %eax, %eax
    call    __printf_chk
    xorl    %eax, %eax
    addq    $8, %rsp
    ret

It there a way to force the later versions of GCC to produce the same output?

Using https://godbolt.org/g/D1AR6i to produce the assembly

EDIT: No duplicated question, since the problem to completly unroll loops with later versions of GCC has not yet been solved. Passing --param max-completely-peeled-insns=1000 --param max-completely-peel-times=10000 has not effects on the generated assembly using GCC >= 5.1

Aucun commentaire:

Enregistrer un commentaire