https://gcc.gnu.org/bugzilla/show_bug.cgi?id=102117
--- Comment #1 from Jens Seifert <jens.seifert at de dot ibm.com> ---
Sorry small bug in optimal sequence.
__int128 imul128_opt(long long a, long long b)
{
unsigned __int128 x = (unsigned __int128)(unsigned long long)a;
unsigned __int128 y = (unsigned __int128)(unsigned long long)b;
unsigned long long t1 = (a >> 63) & b;
unsigned long long t2 = (b >> 63) & a;
unsigned __int128 u128 = x * y;
unsigned long long hi = (u128 >> 64) - (t1 + t2);
unsigned long long lo = (unsigned long long)u128;
unsigned __int128 res = hi;
res <<= 64;
res |= lo;
return (__int128)res;
}
_Z11imul128_optxx:
.LFB1:
.cfi_startproc
ldgr %f2,%r12
.cfi_register 12, 17
ldgr %f0,%r13
.cfi_register 13, 16
lgr %r13,%r3
mlgr %r12,%r4
srag %r1,%r3,63
ngr %r1,%r4
srag %r4,%r4,63
ngr %r4,%r3
agr %r4,%r1
sgrk %r4,%r12,%r4
stg %r13,8(%r2)
lgdr %r12,%f2
.cfi_restore 12
lgdr %r13,%f0
.cfi_restore 13
stg %r4,0(%r2)
br %r14
.cfi_endproc
