引言

 

先从一小段代码说起：

#include <stdio.h>

int main()
{
    int sum = 0;
    for (int i = 0; i < 100; i++) {
        sum += i;
    }
    printf("sum = %d\n", sum);

    return 0;
}

将代码以-O2选项编译后，查看目标程序中的汇率指令：

gcc test.c -O2
objdump -d a.out

发现main函数汇编代码的第二行，是将立即数0x1356(十进制：4950)移入esi寄存器中。也就是说，程序没有按原有的逻辑去执行循环累加，而直接返回了计算结果。相对没有加-O2的汇编代码，精简了许多操作，而这些细微的差异如果不注意，会违背开发者的初衷，甚至影响程序预期结果。

 

那么-O2到底包含了哪些编译选项？

# gcc选项解释
# -Q：使编译器在编译每个函数时输出函数名, 并在每个编译阶段结束时输出一些统计信息。
#     当出现在--help选项之前时, --help的输出内容会有所改变:
#     不再显示编译选项的通用描述, 而是显示该选项在当前的编译命令中是否开启。
#     对于有具体设置的值的选项, 会显示该选项被设置的具体值。
# --help=optimizers：显示所有的优化编译选项

[root@localhost ~]# gcc -Q -O2 --help=optimizers | grep "启用" | wc -l
129
[root@localhost ~]# gcc -Q -O2 --help=optimizers | grep "启用"
  -faggressive-loop-optimizations       [启用]
  -falign-labels                        [启用]
  -fasynchronous-unwind-tables          [启用]
  -fauto-inc-dec                        [启用]
  -fbranch-count-reg                    [启用]
  -fcaller-saves                        [启用]
  -fcode-hoisting                       [启用]
  -fcombine-stack-adjustments           [启用]
  -fcompare-elim                        [启用]
  -fcprop-registers                     [启用]
  -fcrossjumping                        [启用]
  -fcse-follow-jumps                    [启用]
  -fdce                                 [启用]
  -fdefer-pop                           [启用]
  -fdelete-null-pointer-checks          [启用]
  -fdevirtualize                        [启用]
  -fdevirtualize-speculatively          [启用]
  -fdse                                 [启用]
  -fearly-inlining                      [启用]
  -fexpensive-optimizations             [启用]
  -fforward-propagate                   [启用]
  -ffp-int-builtin-inexact              [启用]
  -ffunction-cse                        [启用]
  -fgcse                                [启用]
  -fgcse-lm                             [启用]
  -fguess-branch-probability            [启用]
  -fhoist-adjacent-loads                [启用]
  -fif-conversion                       [启用]
  -fif-conversion2                      [启用]
  -findirect-inlining                   [启用]
  -finline                              [启用]
  -finline-atomics                      [启用]
  -finline-functions-called-once        [启用]
  -finline-small-functions              [启用]
  -fipa-bit-cp                          [启用]
  -fipa-cp                              [启用]
  -fipa-icf                             [启用]
  -fipa-icf-functions                   [启用]
  -fipa-icf-variables                   [启用]
  -fipa-profile                         [启用]
  -fipa-pure-const                      [启用]
  -fipa-ra                              [启用]
  -fipa-reference                       [启用]
  -fipa-sra                             [启用]
  -fipa-vrp                             [启用]
  -fira-hoist-pressure                  [启用]
  -fira-share-save-slots                [启用]
  -fira-share-spill-slots               [启用]
  -fisolate-erroneous-paths-dereference         [启用]
  -fivopts                              [启用]
  -fjump-tables                         [启用]
  -flifetime-dse                        [启用]
  -flra-remat                           [启用]
  -fmath-errno                          [启用]
  -fmove-loop-invariants                [启用]
  -fomit-frame-pointer                  [启用]
  -foptimize-sibling-calls              [启用]
  -foptimize-strlen                     [启用]
  -fpartial-inlining                    [启用]
  -fpeephole                            [启用]
  -fpeephole2                           [启用]
  -fplt                                 [启用]
  -fprefetch-loop-arrays                [启用]
  -fprintf-return-value                 [启用]
  -freg-struct-return                   [启用]
  -frename-registers                    [启用]
  -freorder-blocks                      [启用]
  -freorder-blocks-and-partition        [启用]
  -freorder-functions                   [启用]
  -frerun-cse-after-loop                [启用]
  -frtti                                [启用]
  -fsched-critical-path-heuristic       [启用]
  -fsched-dep-count-heuristic           [启用]
  -fsched-group-heuristic               [启用]
  -fsched-interblock                    [启用]
  -fsched-last-insn-heuristic           [启用]
  -fsched-rank-heuristic                [启用]
  -fsched-spec                          [启用]
  -fsched-spec-insn-heuristic           [启用]
  -fsched-stalled-insns-dep             [启用]
  -fschedule-fusion                     [启用]
  -fschedule-insns2                     [启用]
  -fshort-enums                         [启用]
  -fshrink-wrap                         [启用]
  -fshrink-wrap-separate                [启用]
  -fsigned-zeros                        [启用]
  -fsplit-ivs-in-unroller               [启用]
  -fsplit-wide-types                    [启用]
  -fssa-backprop                        [启用]
  -fssa-phiopt                          [启用]
  -fstdarg-opt                          [启用]
  -fstore-merging                       [启用]
  -fstrict-aliasing                     [启用]
  -fstrict-volatile-bitfields           [启用]
  -fthread-jumps                        [启用]
  -fno-threadsafe-statics               [启用]
  -ftrapping-math                       [启用]
  -ftree-bit-ccp                        [启用]
  -ftree-builtin-call-dce               [启用]
  -ftree-ccp                            [启用]
  -ftree-ch                             [启用]
  -ftree-coalesce-vars                  [启用]
  -ftree-copy-prop                      [启用]
  -ftree-cselim                         [启用]
  -ftree-dce                            [启用]
  -ftree-dominator-opts                 [启用]
  -ftree-dse                            [启用]
  -ftree-forwprop                       [启用]
  -ftree-fre                            [启用]
  -ftree-loop-if-convert                [启用]
  -ftree-loop-im                        [启用]
  -ftree-loop-ivcanon                   [启用]
  -ftree-loop-optimize                  [启用]
  -ftree-phiprop                        [启用]
  -ftree-pre                            [启用]
  -ftree-pta                            [启用]
  -ftree-reassoc                        [启用]
  -ftree-scev-cprop                     [启用]
  -ftree-sink                           [启用]
  -ftree-slsr                           [启用]
  -ftree-sra                            [启用]
  -ftree-switch-conversion              [启用]
  -ftree-tail-merge                     [启用]
  -ftree-ter                            [启用]
  -ftree-vrp                            [启用]
  -funwind-tables                       [启用]
  -fvar-tracking                        [启用]
  -fvar-tracking-assignments            [启用]
  -fweb                                 [启用]

上述命令也可以查看-O3、-O1开启的编译选项，默认-O == -O1。 如：

gcc -Q -O1 --help=optimizers | grep "启用"
gcc -Q -O3 --help=optimizers | grep "启用"

关于具体每个编译选项的解释，牵扯到太多的背景知识。可以通过man文档查找说明。也可以查阅GNU在线文档：Option Summary (Using the GNU Compiler Collection (GCC))

 

如何禁用某个函数的编译优化？

有通过在函数体中添加空的汇编指令的方法(不推荐)：

void func()
{
	// ...
	asm volatile("");
	// ...
}

还有通过添加预处理指令的方式：

#pragma GCC optimize ("O0")
void func()
{
	// ...
}

但我还是更倾向在函数声明时就表示不使用编译优化：

void func() __attribute__((optimize("O0")));

void func()
{
	// ...
}