本文展示如何把c语言源码编译成llvm ir。
编写代码 multiply.c
int mult() {
int a = 5;
int b = 3;
int c = a * b;
return c;
}
执行命令：
clang -emit-llvm -S multiply.c -o multiply.ll
输出 multiply.ll
; ModuleID = 'multiply.c'
source_filename = "multiply.c"
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.14.0"
; Function Attrs: noinline nounwind optnone ssp uwtable
define i32 @mult() #0 {
entry:
%a = alloca i32, align 4
%b = alloca i32, align 4
%c = alloca i32, align 4
store i32 5, i32* %a, align 4
store i32 3, i32* %b, align 4
%0 = load i32, i32* %a, align 4
%1 = load i32, i32* %b, align 4
%mul = mul nsw i32 %0, %1
store i32 %mul, i32* %c, align 4
%2 = load i32, i32* %c, align 4
ret i32 %2
}
attributes #0 = { noinline nounwind optnone ssp uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="penryn" "target-features"="+cx16,+fxsr,+mmx,+sse,+sse2,+sse3,+sse4.1,+ssse3,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" }
!llvm.module.flags = !{!0, !1}
!llvm.ident = !{!2}
!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{i32 7, !"PIC Level", i32 2}
!2 = !{!"clang version 7.0.0 (trunk 324834)"}
这里提到还可以用 ccl 工具，没试。
从源码到ir：
- 词法分析，源码分割成token流；
- 语法分析，借助上下文无关文法生成抽象语法树
- 语义分析，检查是否有语义错误
- 生成ir
