我试着写与至强融核平台KNC一些指令内联汇编代码,使用k1om-mpss-linux-gcc
编译器。我想在我的代码中使用一个掩码寄存器来向量化我的计算。这是我的代码:无效“汇编”:嵌套的汇编
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/time.h>
#include <assert.h>
#include <stdint.h>
void* aligned_malloc(size_t size, size_t alignment) {
uintptr_t r = (uintptr_t)malloc(size + --alignment + sizeof(uintptr_t));
uintptr_t t = r + sizeof(uintptr_t);
uintptr_t o =(t + alignment) & ~(uintptr_t)alignment;
if (!r) return NULL;
((uintptr_t*)o)[-1] = r;
return (void*)o;
}
int main(int argc, char* argv[])
{
const int vectorSize = 16;
int * n_arr = (int *) aligned_malloc(16 * sizeof(int),64);
int * lenS_arr = (int *) aligned_malloc(16 * sizeof(int),64);
int * tt_i = (int *) aligned_malloc(16 * sizeof(int),64);
int * tt = (int *) aligned_malloc(16 * sizeof(int),64);
int n = 5;
int lenS = 16;
int i;
for(i=0; i< 16; i++){
tt_i[i] = 1;
n_arr[i] = n;
lenS_arr[i] = lenS;
}
__asm__("vmovdqa32 %1,%%zmm0\n\t"
"vmovdqa32 %2,%%zmm1\n\t"
"vmovdqa32 %3,%%zmm2\n\t"
"vpaddd %%zmm0,%%zmm1,%%zmm0\n\t"
"vpcmpgtd %%zmm0,%%zmm2,%%k1\n\t"
"vpsubd %%zmm2,%%zmm0,%%zmm0 {{%%k1}}\n\t"
"vmovdqa32 %%zmm1,%0;"
: "=m" (tt[0]) : "m" (tt_i[0]), "m" (n_arr[0]), "m" (lenS_arr[0]));
for (i=0; i <16 ; i++)
{
printf("tt_i[%d] = %d --- tt[%d] = %d\n",i, tt_i[i], i, tt[i]);
}
return 0;
}
当我编译代码,我得到这个错误:
error: invalid 'asm': nested assembly dialect alternatives
这是关系到这条流水线:
"vpsubd %%zmm2,%%zmm0,%%zmm0 {{%%k1}}\n\t"
有关此错误的任何想法?
不要忘记申报%zmm0,1,和2重挫。和%k1我猜。 –