C 如何避免多次取消引用同一个变量？

Question

我有一个结构数组，我有一些函数将使用这些结构的多个成员。我想避免在每一行中取消引用。我认为会有一些方法可以在某个内存位置声明一个变量......像这样:

someStruct &myStruct = arrayOfStructs[i];
myStruct.x = foo+bar*myStruct.y*myStruct.w;
//Instead of myStruct->x = foo+bar*myStruct->y*myStruct->w;
//It would/should even be possible to access the members in a similar way:
int &x = &myStruct.x;
x = x+4*y+2*z;
//This should avoid overhead of dereferencing the pointer, and offsetting to the member
//by just accessing that particular address of memory as though it was where the variable
//had always been.

这段示例代码可能有助于解释:

#define NUM_BIGSTRUCTS 10000

typedef struct {
  int a,b,c;
  float d,e,f;
} bigStruct;

bigStruct* arrayOfStructs;

void foo() {
  for(int i=0; i<NUM_BIGSTRUCTS; i++) {
    bigStruct* temp = arrayOfStructs[i];
    temp->f = (temp->d+temp->e)*((float)temp->a+temp->e);
    //more similar, with conditionals, etc...
    //actually I've got nested loops, and a very very large array
    //so any gains per inner loop would decrease my number of instructions exponentially

    //So, if I could declare a bigStruct and set its address to the location of a bigStruct in the array
    //then I could avoid a dereference every time I access a member of that bigStruct
    //Leaving just the member access overhead... which could be handled in a similar manner
    //if possible, and when appropriate
  }
}

int main(int argx, char** argv) {
  arrayOfStructs = g_new0(bigStruct,NUM_BIGSTRUCTS); //Allocate and 0 memory for simplicity

  foo();

  return 0;
}

我从来没有在 SO 上取得过巨大的成功，所以希望我解释了我想做的事情。顺便说一句，我正在使用 C99，而且考虑到 c 的低级性质，我相信这是可能的。

[编辑]看起来我正在寻找来自 C++ 的“引用”，但对于 C。即便如此，它们只允许赋值一次(初始化)，这在我的示例中不起作用。我决定依靠编译器来优化对同一内存部分的多次访问。

谢谢，詹姆斯· Newman

Answer 1

您正在尝试编译器优化比手动优化做得更好的事情。此外，C99 没有您尝试在示例中定义它们的方式(特别是 C++ 取消引用声明)的这些引用构造，如果您也变得非常庞大和深入，我建议您重新考虑您的算法。如果你试图引入一些临时变量和更多的内存来做引用，你会让你的生活更加艰难。

例如，如果您查看:

struct some_struct {
        int a;
        struct {
                float f;
                double d;
        } s;
};

struct some_struct array[10000];

int process1(struct some_struct *r) {
#define R (*r)
        R.a+= 1;
        R.s.f = R.s.f/2;
        R.s.d = ( R.s.d + R.s.f ) * 2;
}

int process2(struct some_struct *r) {
        r->a+= 1;
        r->s.f = r->s.f/2;
        r->s.d = ( r->s.d + r->s.f ) * 2;
}

int doit() {
        int i;
        for (i = 0; i < sizeof(array)/sizeof(struct some_struct); i++ ) {
                struct some_struct *r = &array[i]; /* via reference */
                process1(r);
                process2(r);
        }
}

process1 和 process2 在 x86_64 平台上使用 gcc -O2 生成相同的汇编输出:

        .file   "foo.c"
        .text
        .p2align 4,,15
        .globl  process1
        .type   process1, @function
process1:
.LFB11:
        .cfi_startproc
        movss   .LC0(%rip), %xmm0
        addl    $1, (%rdi)
        mulss   8(%rdi), %xmm0
        movss   %xmm0, 8(%rdi)
        unpcklps        %xmm0, %xmm0
        cvtps2pd        %xmm0, %xmm0
        addsd   16(%rdi), %xmm0
        addsd   %xmm0, %xmm0
        movsd   %xmm0, 16(%rdi)
        ret
        .cfi_endproc
.LFE11:
        .size   process1, .-process1
        .p2align 4,,15
        .globl  process2
        .type   process2, @function
process2:
.LFB12:
        .cfi_startproc
        movss   .LC0(%rip), %xmm0
        addl    $1, (%rdi)
        mulss   8(%rdi), %xmm0
        movss   %xmm0, 8(%rdi)
        unpcklps        %xmm0, %xmm0
        cvtps2pd        %xmm0, %xmm0
        addsd   16(%rdi), %xmm0
        addsd   %xmm0, %xmm0
        movsd   %xmm0, 16(%rdi)
        ret
        .cfi_endproc
.LFE12:
        .size   process2, .-process2
        .p2align 4,,15
        .globl  doit
        .type   doit, @function
doit:
.LFB13:
        .cfi_startproc
        xorl    %edx, %edx

        movss   .LC0(%rip), %xmm2
        .p2align 4,,10
        .p2align 3
.L4:
        leaq    (%rdx,%rdx,2), %rax
        addq    $1, %rdx
        leaq    array(,%rax,8), %rax
        movss   8(%rax), %xmm1
        addl    $2, (%rax)
        mulss   %xmm2, %xmm1
        cmpq    $10000, %rdx
        unpcklps        %xmm1, %xmm1
        cvtps2pd        %xmm1, %xmm0
        mulss   %xmm2, %xmm1
        addsd   16(%rax), %xmm0
        movss   %xmm1, 8(%rax)
        unpcklps        %xmm1, %xmm1
        cvtps2pd        %xmm1, %xmm1
        addsd   %xmm0, %xmm0
        addsd   %xmm1, %xmm0
        addsd   %xmm0, %xmm0
        movsd   %xmm0, 16(%rax)
        jne     .L4
        rep
        ret
        .cfi_endproc
.LFE13:
        .size   doit, .-doit
        .comm   array,240000,32
        .section        .rodata.cst4,"aM",@progbits,4
        .align 4
.LC0:
        .long   1056964608
        .ident  "GCC: (GNU) 4.6.1"
        .section        .note.GNU-stack,"",@progbits