小编Ale*_*Xie的帖子

我正在尝试优化以下代码complex.cpp:

typedef struct {
    float re;
    float im;
} dcmplx;

dcmplx ComplexConv(int len, dcmplx *hat, dcmplx *buf)
{
    int    i;
    dcmplx    z, xout;

    xout.re = xout.im = 0.0;
    asm volatile (
    "movs r3, #0\n\t"
    ".loop:\n\t"
    "vldr s11, [%[hat], #4]\n\t"
    "vldr s13, [%[hat]]\n\t"
    "vneg.f32 s11, s11\n\t"
    "vldr s15, [%[buf], #4]\n\t"
    "vldr s12, [%[buf]]\n\t"
    "vmul.f32 s14, s15, s13\n\t"
    "vmul.f32 s15, s11, s15\n\t"
    "adds %[hat], #8\n\t"
    "vmla.f32 s14, s11, s12\n\t"
    "vnmls.f32 s15, s12, s13\n\t"
    "adds %[buf], #8\n\t"
    "vadd.f32 s1, s1, s14\n\t"
    "vadd.f32 s0, …