Convert inline-assembly from Intel to AT&T syntax

Question

The code below multiplies arrays arr1 with arr2 using SSE and puts result to arr3 . Arrays have count elements. arr1 , arr2 and arr3 have type float* . The problem is that the compiler doesn't support Intel syntax. How does this code look like in AT&T syntax?

Compiler is GCC 4.4.7.

__asm__ volatile (
    ".intel_syntax noprefix \n\t"
    "loop:                  \n\t"
    "movups xmm0, [eax+edx] \n\t"
    "movups xmm1, [ebx+edx] \n\t"
    "mulps xmm0, xmm1       \n\t"
    "movups [ecx+edx], xmm0 \n\t"
    "sub edx, 16            \n\t"
    "jnz loop               \n\t"
    :
    : "a"(arr1), "b"(arr2), "c"(arr3), "d"(count)
    : "xmm0", "xmm1"
);

Answer 1

__asm__ volatile (
    "loop:                          \n\t"
    "subq $0x10, %%rdx              \n\t"
    "movups (%%rax,%%rdx), %%xmm0   \n\t"
    "movups (%%rbx,%%rdx), %%xmm1   \n\t"
    "mulps %%xmm1, %%xmm0           \n\t"
    "movups %%xmm0, (%%rcx,%%rdx)   \n\t"
    "jnz loop                       \n\t"
    :
    : "a"(arr1), "b"(arr2), "c"(arr3), "d"(count)
    : "xmm0", "xmm1"
);

arr1 , arr2 and arr3 are 8-byte pointers and count is 8-byte integer, so registers are r_x