CCS 的优化:
三、16 位变为 32 位操作,使用 intrinsic 函数,用 const 等。
1、源代码:
Word32 L_mpy_ll(Word32 L_var1, Word32 L_var2)
{
double aReg;
Word32 lvar;
/* (unsigned)low1 * (unsigned)low1 */
aReg = (double)(0xffff & L_var1) * (double)(0xffff & L_var2) * 2.0;
/* >> 16 */
aReg = (aReg / 65536);
aReg = floor(aReg);
/* (unsigned)low1 * (signed)high2 */
aReg += (double)(0xffff & L_var1) * ((double)L_shr(L_var2,16)) * 2.0;
/* (unsigned)low2 * (signed)high1 */
aReg += (double)(0xffff & L_var2) * ((double)L_shr(L_var1,16)) * 2.0;
/* >> 16 */
aReg = (aReg / 65536);
aReg = floor(aReg);
/* (signed)high1 * (signed)high2 */
aReg += (double)(L_shr(L_var1,16)) * (double)(L_shr(L_var2,16)) * 2.0;
/* saturate result.. */
lvar = L_saturate(aReg);
return(lvar);
}
2、改编后的代码:
static inline Word32 L_mpy_ll(Word32 L_var1, Word32 L_var2)
{
Word32 aReg_hh;
Word40 aReg,aReg_ll,aReg_lh,aReg_hl;
aReg_ll = (Word40)_mpyu(L_var1, L_var2)>>16;
aReg_lh = (Word40)_mpyluhs(L_var1, L_var2);
aReg_hl = (Word40)_mpyhslu(L_var1, L_var2);
aReg_hh = _smpyh(L_var1, L_var2);
aReg = _lsadd(aReg_ll, _lsadd(aReg_lh, aReg_hl));
aReg = _lsadd(aReg>>15, aReg_hh);
return(_sat(aReg));
}
3、优化方法说明: