1. OC源文件

// Command Line Tool

#include <stdio.h>
#define AGE 30
int main(int argc, const char * argv[]) {
    int a = 10;
    int b = 20;
    int c = a + b + AGE;
    
    return 0;
}

2. 编译过程

命令行查看编译过程： clang -ccc-print-phases main.m

0: input, "main.m", objective-c //找到原代码main.m
1: preprocessor, {0}, objective-c-cpp-output //预处理器导入include import 及换掉宏定义
2: compiler, {1}, ir //编译器中间代码生成ir
3: backend, {2}, assembler// 后端，{2}，汇编程序
4: assembler, {3}, object// 汇编程序生成目标代码
5: linker, {4}, image// 链接器 --- 动态库、静态库
6: bind-arch, "x86_64", {5}, image //生成适合某个架构的代码

查看preprocessor（预处理）的结果： clang -E main.m

...
...
...
extern int __vsnprintf_chk (char * restrict, size_t, int, size_t,
const char * restrict, va_list);
412 "/usr/include/stdio.h" 2 3 4
10 "main.m" 2
上面的一大段为：导入include <stdio.h>里的内容
int main(int argc, const char * argv[]) {
int a = 10;
int b = 20;
int c = a + b + 30; //这里宏定义的AGE已经被替换掉了
return 0;
}

词法分析，生成Token： clang -fmodules -E -Xclang -dump-tokens main.m

annot_module_include '#include <stdio.h>
.#define AGE 30
int main(int argc, const char * argv[]) {
int a = 10;
int b = 20;
int c = a + b + A' Loc=<main.m:9:1>
int 'int' [StartOfLine] Loc=<main.m:11:1>//m:11:14 第11行第14个字符
identifier 'main' [LeadingSpace] Loc=<main.m:11:5>
l_paren'(' Loc=<main.m:11:9>
int 'int' Loc=<main.m:11:10>
identifier 'argc' [LeadingSpace] Loc=<main.m:11:14>
comma',' Loc=<main.m:11:18>
const'const' [LeadingSpace] Loc=<main.m:11:20>
char'char' [LeadingSpace] Loc=<main.m:11:26>
star'*' [LeadingSpace] Loc=<main.m:11:31>
identifier'argv' [LeadingSpace] Loc=<main.m:11:33>
l_square '[' Loc=<main.m:11:37>
r_square ']' Loc=<main.m:11:38>
r_paren ')' Loc=<main.m:11:39>
l_brace '{' [LeadingSpace] Loc=<main.m:11:41>
int 'int' [StartOfLine] [LeadingSpace] Loc=<main.m:12:5>
identifier 'a' [LeadingSpace] Loc=<main.m:12:9>
equal '=' [LeadingSpace] Loc=<main.m:12:11>
numeric_constant '10' [LeadingSpace] Loc=<main.m:12:13>
semi';' Loc=<main.m:12:15>
int'int' [StartOfLine] [LeadingSpace] Loc=<main.m:13:5>
identifier 'b' [LeadingSpace] Loc=<main.m:13:9>
equal'=' [LeadingSpace] Loc=<main.m:13:11>
numeric_constant '20' [LeadingSpace] Loc=<main.m:13:13>
semi ';' Loc=<main.m:13:15>
int 'int' [StartOfLine] [LeadingSpace] Loc=<main.m:14:5>
identifier 'c' [LeadingSpace] Loc=<main.m:14:9>
equal '=' [LeadingSpace] Loc=<main.m:14:11>
identifier 'a' [LeadingSpace] Loc=<main.m:14:13>
plus '+' [LeadingSpace] Loc=<main.m:14:15>
identifier'b' [LeadingSpace] Loc=<main.m:14:17>
plus '+' [LeadingSpace] Loc=<main.m:14:19>
numeric_constant'30' [LeadingSpace] Loc=<main.m:14:21 <Spelling=main.m:10:13>>
semi';' Loc=<main.m:14:24>
return 'return' [StartOfLine] [LeadingSpace] Loc=<main.m:16:5>
numeric_constant'0' [LeadingSpace] Loc=<main.m:16:12>
semi';' Loc=<main.m:16:13>
r_brace'}' [StartOfLine] Loc=<main.m:17:1>
eof '' Loc=<main.m:17:2>

词法分析，生成语法树（AST，Abstract Syntax Tree）：

- 主要看FunctionDecl之后。main函数语法树

image.png

单词解释😃.png

3. LLVM IR（中间代码）

LLVM IR 有三种表现形式（但本质是等价的，就好比水有气态、液态、固态三种形式）

text：便于阅读的文本格式，类似于汇编语言，拓展名 .ll ,$clang -S -emit-llvm main.m
memory：内存格式
bitcode：二进制格式，拓展名 .bc , $clang -c -emit-llvm main.m

//$clang -S -emit-llvm main.m
; Function Attrs: noinline nounwind optnone ssp uwtable
define i32 @main(i32, i8**) #0 {
  %3 = alloca i32, align 4
  %4 = alloca i32, align 4
  %5 = alloca i8**, align 8
  %6 = alloca i32, align 4
  %7 = alloca i32, align 4
  %8 = alloca i32, align 4
  store i32 0, i32* %3, align 4
  store i32 %0, i32* %4, align 4
  store i8** %1, i8*** %5, align 8
  store i32 10, i32* %6, align 4
  store i32 20, i32* %7, align 4
  %9 = load i32, i32* %6, align 4
  %10 = load i32, i32* %7, align 4
  %11 = add nsw i32 %9, %10
  %12 = add nsw i32 %11, 30
  store i32 %12, i32* %8, align 4
  ret i32 0
}