Need faster emulation for pdep instruction

[newhoggy]

benchmarking pdep-single/pdep64
time                 4.374 ns   (4.260 ns .. 4.519 ns)
                     0.996 R²   (0.993 R² .. 1.000 R²)
mean                 4.262 ns   (4.231 ns .. 4.346 ns)
std dev              151.2 ps   (71.89 ps .. 310.0 ps)
variance introduced by outliers: 60% (severely inflated)

benchmarking pdep-single/pdep32
time                 4.926 ns   (4.819 ns .. 5.062 ns)
                     0.995 R²   (0.989 R² .. 0.999 R²)
mean                 4.828 ns   (4.755 ns .. 4.961 ns)
std dev              332.1 ps   (172.7 ps .. 519.3 ps)
variance introduced by outliers: 85% (severely inflated)

benchmarking pdep-slow/slowPdep64  8-bits
time                 11.95 ns   (11.73 ns .. 12.16 ns)
                     0.998 R²   (0.997 R² .. 0.999 R²)
mean                 11.89 ns   (11.78 ns .. 12.02 ns)
std dev              420.3 ps   (326.6 ps .. 541.9 ps)
variance introduced by outliers: 58% (severely inflated)

benchmarking pdep-slow/slowPdep64 16-bits
time                 23.33 ns   (22.32 ns .. 24.38 ns)
                     0.989 R²   (0.985 R² .. 0.994 R²)
mean                 23.87 ns   (23.23 ns .. 24.52 ns)
std dev              2.222 ns   (1.847 ns .. 2.962 ns)
variance introduced by outliers: 90% (severely inflated)

benchmarking pdep-slow/slowPdep64 32-bits
time                 53.33 ns   (53.08 ns .. 53.60 ns)
                     1.000 R²   (1.000 R² .. 1.000 R²)
mean                 53.29 ns   (53.14 ns .. 53.46 ns)
std dev              551.8 ps   (440.2 ps .. 692.7 ps)

benchmarking pdep-slow/slowPdep64 48-bits
time                 61.08 ns   (60.85 ns .. 61.42 ns)
                     1.000 R²   (0.999 R² .. 1.000 R²)
mean                 61.67 ns   (61.34 ns .. 62.65 ns)
std dev              1.683 ns   (629.2 ps .. 3.275 ns)
variance introduced by outliers: 42% (moderately inflated)

benchmarking pdep-slow/slowPdep64 64-bits
time                 95.69 ns   (95.02 ns .. 96.77 ns)
                     0.999 R²   (0.998 R² .. 1.000 R²)
mean                 97.08 ns   (96.01 ns .. 99.17 ns)
std dev              5.032 ns   (3.156 ns .. 7.456 ns)
variance introduced by outliers: 72% (severely inflated)