我正在尝试在内mpz_t联 X86 程序集中实现 GMP 对象的多精度乘法。根据我对输出变量的约束选择，我要么得到分段错误，要么输出变量中的值以不一致的方式损坏（即不同的代码运行导致值以不同的方式损坏）。
这段代码所做的是采用两个 GMPmpz_t对象，ain并且bin，每个对象都保证大小为 13（即_mp_size设置为 13，对象由 13、64 位数字定义），然后生成mpz_t大小为 26 的对象 res，即是相乘ain和bin相加的结果。我不使用的原因mpz_mul是因为此方法通常会导致此特定设置的性能提高。
请注意res->_mp_d, ain->_mp_d并bin->_mp_d参考定义各个mpz_t对象的“肢体”数组，其中最(obj->_mp_d)[0]不重要(obj->_mp_d)[obj->_mp_size-1]的肢体是最重要的肢体。
如果有人可以帮助解释我在这里做错了什么，我将不胜感激！下面是一段代码。我已经排除了大部分程序集，因为它是重复的，但我认为我给出了足够的信息来很好地说明正在发生的事情：
void mpz_mul_x86_1(mpz_t res, mpz_t ain, mpz_t bin){
if( res->_mp_alloc<26) //the next few lines makes sure res is large enough
_mpz_realloc(res,26); //the result of the multiplication
res->_mp_size = 26;
asm volatile (
"movq 0(%1), %%rax;"
"mulq 0(%2);"
"movq %%rax, 0(%0);"
"movq %%rdx, %%r8;" //A0*B0
//0
"xorq %%r10, %%r10;"
"movq 8(%1), %%rax;"
"mulq 0(%2);"
"addq %%rax, %%r8;"
"movq %%rdx, %%r9;"
"adcq $0, %%r9;" //A1*B0
"movq 0(%1), %%rax;"
"mulq 8(%2);"
"addq %%rax, %%r8;"
"movq %%r8, 8(%0);"
"adcq %%rdx,%%r9;"
"adcq $0, %%r10;" //A0*B1
//1
"xorq %%r8, %%r8;"
"movq 0(%1), %%rax;"
"mulq 16(%2);"
"addq %%rax, %%r9;"
"adcq %%rdx, %%r10;"
"adcq $0, %%r8;" //A0*B2
"movq 8(%1), %%rax;"
"mulq 8(%2);"
"addq %%rax, %%r9;"
"adcq %%rdx, %%r10;"
"adcq $0, %%r8;" //A1*B1
"movq 16(%1), %%rax;"
"mulq 0(%2);"
"addq %%rax, %%r9;"
"movq %%r9, 16(%0);"
"adcq %%rdx, %%r10;"
"adcq $0, %%r8;" //A2*B0
//2
"xorq %%r9, %%r9;"
"movq 24(%1), %%rax;"
"mulq 0(%2);"
"addq %%rax, %%r10;"
"adcq %%rdx, %%r8;"
"adcq $0, %%r9;" //A3*B0
"movq 0(%1), %%rax;"
"mulq 24(%2);"
"addq %%rax, %%r10;"
"adcq %%rdx, %%r8;"
"adcq $0, %%r9;" //A0*B3
"movq 16(%1), %%rax;"
"mulq 8(%2);"
"addq %%rax, %%r10;"
"adcq %%rdx, %%r8;"
"adcq $0, %%r9;" //A2*B1
"movq 8(%1), %%rax;"
"mulq 16(%2);"
"addq %%rax, %%r10;"
"movq %%r10, 24(%0);"
"adcq %%rdx, %%r8;"
"adcq $0, %%r9;" //A1*B2
//3
/*About 1000 lines of omitted Assembly code is from here*/
"xor %%r8, %%r8;"
"movq 96(%1), %%rax;"
"mulq 88(%2);"
"addq %%rax, %%r9;"
"adcq %%rdx, %%r10;"
"adcq $0, %%r8;" //A12*B11
"movq 88(%1), %%rax;"
"mulq 96(%2);"
"addq %%rax, %%r9;"
"movq %%r9, 184(%0);"
"adcq %%rdx, %%r10;"
"adcq $0, %%r8;" //A11*B12
//23
"xor %%r9, %%r9;"
"movq 96(%1), %%rax;"
"mulq 96(%2);"
"addq %%rax, %%r10;"
"movq %%r10, 192(%0);"
"adcq %%rdx, %%r8;"
"adcq $0, %%r8;" //A12*B12
//24
"movq %%r8, 200(%0);" //25
: "=&r" (res->_mp_d)
: "r" ((ain->_mp_d)), "r" ((bin->_mp_d))
: "%rax", "%rdx", "%r8", "%r9", "%r10", "memory", "cc"
);
}