[Bug target/93449] PPC: Missing conversion builtin from vector to _Decimal128 and vice versa

[jens.seifert at de dot ibm.com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=93449

--- Comment #2 from Jens Seifert <jens.seifert at de dot ibm.com> ---
#include <memory.h>

typedef float _Decimal128 __attribute__((mode(TD)));

_Decimal128 bcdtodpd(vector double v)
{
   _Decimal128 res;
   memcpy(&res, &v, sizeof(res));
   res = __builtin_denbcdq(0, res);
   return res;
}

_Decimal128 bcdtodpd_opt(vector double bcd)
{
   _Decimal128 res;
   __asm__ volatile("xxlor 4,%x1,%x1;\n"
       "xxpermdi 5,%x1,%x1,3;\n"
       "denbcdq 0,%0,4":"=d"(res):"v"(bcd):"vs36","vs37");
   return res;
}

vector double dpdtobcd(_Decimal128 dpd)
{
   _Decimal128 bcd = __builtin_ddedpdq(0, dpd);
   vector double res;
   memcpy(&res, &bcd, sizeof(res));
   return res;
}

vector double dpdtobcd_opt(_Decimal128 dpd)
{
   vector double res;
   __asm__ volatile("ddedpdq 0,4,%1;\n"
                    "xxpermdi %x0,4,5,0":"=v"(res):"d"(dpd):"vs36","vs37");
   return res;
}

The non-inline assembly show store/load (very slow).
The assembly version does the conversion from vector to _Decimal128 with
optimal sequence for Power7 and above.