main: pushl %ebp xorl %eax, %eax movl %esp, %ebp subl $8, %esp andl $-16, %esp movaps inp_sse1, %xmm2 movaps inp_sse2, %xmm0 movaps %xmm2, a mulps %xmm0, %xmm2 movaps %xmm0, b movaps %xmm2, c movaps %xmm2, out_sse movl %ebp, %esp popl %ebp ret C code a = _mm_load_ps(inp_sse1); b = _mm_load_ps(inp_sse2); c = _mm_mul_ps(a, b); _mm_store_ps(out_sse, c);