improved shifting by 48-63 in llshr

[ZERICO2005]

The compiler often emits __llshru(63) to get the signbit of (u)int64_t, which takes around ~1550F clock cycles instead of 2F bit 7, b. This contributes to the very slow performance of long double operations which often need to shift by 52 or 63 bits. Similarly, __llshrs(63) also appears when doing a "branchless" long long llabs(long long).

I have added an optimized path for __llshr(u/s) that handles shift amounts of 48-63, taking no more than 100F to complete. The new worst case is shifting by 47 (1165F + 110R + 108W + 141)