用 clang 编译成 IR 汇编 和 目标机器汇编语言文件

$ clang -emit-llvm -c sum.c -o sum.bc
$ clang -emit-llvm  -S -c sum.c -o sum.ll
$ clang  -S  sum.c -o sum.asm

一，C源文件

sum.c

int sum(int x, int y){
        return x+y;
}

二，clang 14.0.3 生成的 LLVM IR 和 asm程序

1. clang 14.0.3 编译出来的 LLVM IR结果

cat  sum.ll

; ModuleID = 'sumPara.c'
source_filename = "sumPara.c"
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

; Function Attrs: noinline nounwind optnone uwtable
define dso_local i32 @sum(i32 noundef %a, i32 noundef %b) #0 {
entry:
  %a.addr = alloca i32, align 4
  %b.addr = alloca i32, align 4
  store i32 %a, i32* %a.addr, align 4
  store i32 %b, i32* %b.addr, align 4
  %0 = load i32, i32* %a.addr, align 4
  %1 = load i32, i32* %b.addr, align 4
  %add = add nsw i32 %0, %1
  ret i32 %add
}

attributes #0 = { noinline nounwind optnone uwtable "frame-pointer"="all" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "tune-cpu"="generic" }

!llvm.module.flags = !{!0, !1, !2}
!llvm.ident = !{!3}

!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{i32 7, !"uwtable", i32 1}
!2 = !{i32 7, !"frame-pointer", i32 2}
!3 = !{!"clang version 14.0.3"}

加注释：

// 以;开始的行，是注释行，直到行尾;
// 以@开头的标识符，是全局标识符; 可能是函数，也可能是全局变量;
// 以%开头的标识符，是局部标识符; 即局部变量的名称，也就是寄存器变量或C语言中的内存变量，其前边是类型;
// 函数的函数体在IR中，是基本块; 基本块以entry:开始, 以ret i32 %add 结束, 表示返回一个int32的局部变量add的值;
// i32 表示整型，即 c语言的int型; i是int，32是32bit;
// align 4 表示 4 字节对齐;
// alloca 是分配堆栈内存的指令，生命周期结束时会自动释放;
// store 是将数据写入局部变量、寄存器变量或叫做内存变量; 
// load 是加载数据;


; ModuleID = 'sumPara.c'        //注释行
source_filename = "sumPara.c"
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
 
; Function Attrs: noinline nounwind optnone uwtable             //注释行
define dso_local i32 @sum(i32 noundef %a, i32 noundef %b) #0 {  //@sum 是全局函数;  %a是一个局部变量，即寄存器，类型是 i32，int32;
entry:
  %a.addr = alloca i32, align 4
  %b.addr = alloca i32, align 4
  store i32 %a, i32* %a.addr, align 4
  store i32 %b, i32* %b.addr, align 4
  %0 = load i32, i32* %a.addr, align 4
  %1 = load i32, i32* %b.addr, align 4
  %add = add nsw i32 %0, %1
  ret i32 %add
}
 
attributes #0 = { noinline nounwind optnone uwtable "frame-pointer"="all" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "tune-cpu"="generic" }
 
!llvm.module.flags = !{!0, !1, !2}
!llvm.ident = !{!3}
 
!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{i32 7, !"uwtable", i32 1}
!2 = !{i32 7, !"frame-pointer", i32 2}
!3 = !{!"clang version 14.0.3"}

2. clang 14.0.3 编译出来的 asm

        .text
        .file   "sumPara.c"
        .globl  sum                             # -- Begin function sum
        .p2align        4, 0x90
        .type   sum,@function
sum:                                    # @sum
        .cfi_startproc
# %bb.0:                                # %entry
        pushq   %rbp
        .cfi_def_cfa_offset 16
        .cfi_offset %rbp, -16
        movq    %rsp, %rbp
        .cfi_def_cfa_register %rbp
        movl    %edi, -4(%rbp)
        movl    %esi, -8(%rbp)
        movl    -4(%rbp), %eax
        addl    -8(%rbp), %eax
        popq    %rbp
        .cfi_def_cfa %rsp, 8
        retq
.Lfunc_end0:
        .size   sum, .Lfunc_end0-sum
        .cfi_endproc
                                        # -- End function
        .ident  "clang version 14.0.3"
        .section        ".note.GNU-stack","",@progbits
        .addrsig

三，clang 7.0.0 生成的 LLVM IR 和 asm程序

这个第三部分整体可以忽略，只为增加历史感。 

1. clang 7.0.0 编译出来的 LLVM IR结果

cat sum.ll

//$ cat sum.ll
; ModuleID = 'sum.c'
source_filename = "sum.c"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

; Function Attrs: noinline nounwind optnone uwtable
define dso_local i32 @sum(i32, i32) #0 {
  %3 = alloca i32, align 4
  %4 = alloca i32, align 4
  store i32 %0, i32* %3, align 4
  store i32 %1, i32* %4, align 4
  %5 = load i32, i32* %3, align 4
  %6 = load i32, i32* %4, align 4
  %7 = add nsw i32 %5, %6
  ret i32 %7
}

attributes #0 = { noinline nounwind optnone 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"="x86-64" "target-features"="+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" }

!llvm.module.flags = !{!0}
!llvm.ident = !{!1}

!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{!"clang version 7.0.0 (tags/RELEASE_700/final)"}

2. clang 7.0.0 编译出来的 asm

//$ cat sum.asm
        .text
        .file   "sum.c"
        .globl  sum                     # -- Begin function sum
        .p2align        4, 0x90
        .type   sum,@function
sum:                                    # @sum
        .cfi_startproc
# %bb.0:
        pushq   %rbp
        .cfi_def_cfa_offset 16
        .cfi_offset %rbp, -16
        movq    %rsp, %rbp
        .cfi_def_cfa_register %rbp
        movl    %edi, -4(%rbp)
        movl    %esi, -8(%rbp)
        movl    -4(%rbp), %esi
        addl    -8(%rbp), %esi
        movl    %esi, %eax
        popq    %rbp
        .cfi_def_cfa %rsp, 8
        retq
.Lfunc_end0:
        .size   sum, .Lfunc_end0-sum
        .cfi_endproc
                                        # -- End function

        .ident  "clang version 7.0.0 (tags/RELEASE_700/final)"
        .section        ".note.GNU-stack","",@progbits
        .addrsig
        .addrsig_sym sum

四，参考资料

1，阅读 LLVM IR的文档

先入个门，再详读官方文档

        简单了解LLVM IR基本语法_七妹要奈斯的博客-CSDN博客_llvm nswhttps://blog.csdn.net/qq_42570601/article/details/107157224

LLVM Language Reference Manual — LLVM 15.0.0git documentationhttps://llvm.org/docs/LangRef.html

https://llvm.liuxfe.comhttps://llvm.liuxfe.com/

2，阅读LLVM编译出来的 x86 汇编语言辅助文档

其中目标机器的汇编语言格式，是llvm特定的规范组织而成的文件。这样可以由llvm中的工具llvm-mc 来处理机器汇编语言文件，翻译成 机器语言的目标文件。

规范说明文档：

LLVM Extensions — LLVM 15.0.0git documentationhttps://llvm.org/docs/Extensions.html