Reuse PrgFixedKeyAes128 keys within IDPF calls

[divergentdave]

Stacked on top of #523.

This adds a new path to construct PrgFixedKeyAes128, reusing cSHAKE128 computations across many PRG instances. The IDPF generate and evaluate functions are then modified to use this new API, and pass the fixed key around instead of the binder. This leads to some tremendous speedups, as we are now fully exploiting the lower cost of PrgFixedKeyAes128.

idpf_codec
  Instructions:               33008 (No change)
  L1 Accesses:                45548 (-0.002195%)
  L2 Accesses:                   23 (-8.000000%)
  RAM Accesses:                 170 (+1.796407%)
  Estimated Cycles:           51613 (+0.182457%)

idpf_poplar_gen_8
  Instructions:              100885 (-85.44957%)
  L1 Accesses:               139920 (-85.30501%)
  L2 Accesses:                  107 (+2.884615%)
  RAM Accesses:                 316 (+6.397306%)
  Estimated Cycles:          151515 (-84.26760%)

idpf_poplar_gen_128
  Instructions:              663491 (-93.82247%)
  L1 Accesses:               950878 (-93.56055%)
  L2 Accesses:                  143 (+2.877698%)
  RAM Accesses:                 496 (+3.983229%)
  Estimated Cycles:          968953 (-93.44586%)

idpf_poplar_gen_2048
  Instructions:             9663954 (-94.36478%)
  L1 Accesses:             13924014 (-94.09481%)
  L2 Accesses:                 1309 (+0.153022%)
  RAM Accesses:                3147 (+0.607417%)
  Estimated Cycles:        14040704 (-94.04825%)

idpf_poplar_eval_8
  Instructions:               88080 (-75.83692%)
  L1 Accesses:               121133 (-75.77088%)
  L2 Accesses:                  113 (+2.727273%)
  RAM Accesses:                 365 (+4.285714%)
  Estimated Cycles:          134473 (-73.77406%)

idpf_poplar_eval_128
  Instructions:              466403 (-91.49974%)
  L1 Accesses:               661920 (-91.22421%)
  L2 Accesses:                  144 (-1.369863%)
  RAM Accesses:                 537 (+2.873563%)
  Estimated Cycles:          681435 (-90.98818%)

idpf_poplar_eval_2048
  Instructions:             7016253 (-92.02173%)
  L1 Accesses:              9931939 (-91.78106%)
  L2 Accesses:                 2079 (+0.096293%)
  RAM Accesses:                3233 (+0.466128%)
  Estimated Cycles:        10055489 (-91.68728%)

poplar1_shard/16        time:   [28.741 µs 28.851 µs 28.966 µs]
                        thrpt:  [67.429 KiB/s 67.696 KiB/s 67.957 KiB/s]
                 change:
                        time:   [-74.244% -73.824% -73.438%] (p = 0.00 < 0.05)
                        thrpt:  [+276.48% +282.04% +288.26%]
                        Performance has improved.
Found 4 outliers among 100 measurements (4.00%)
  2 (2.00%) high mild
  2 (2.00%) high severe
poplar1_shard/128       time:   [94.024 µs 96.512 µs 99.528 µs]
                        thrpt:  [156.99 KiB/s 161.90 KiB/s 166.18 KiB/s]
                 change:
                        time:   [-87.356% -87.101% -86.806%] (p = 0.00 < 0.05)
                        thrpt:  [+657.95% +675.27% +690.89%]
                        Performance has improved.
Found 7 outliers among 100 measurements (7.00%)
  4 (4.00%) high mild
  3 (3.00%) high severe
poplar1_shard/256       time:   [160.11 µs 162.82 µs 165.95 µs]
                        thrpt:  [188.31 KiB/s 191.93 KiB/s 195.18 KiB/s]
                 change:
                        time:   [-88.695% -88.579% -88.455%] (p = 0.00 < 0.05)
                        thrpt:  [+766.18% +775.58% +784.59%]
                        Performance has improved.
Found 10 outliers among 100 measurements (10.00%)
  4 (4.00%) high mild
  6 (6.00%) high severe

poplar1_prepare_init/16 time:   [236.69 µs 237.80 µs 239.18 µs]
                        change: [-69.108% -68.929% -68.739%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 5 outliers among 100 measurements (5.00%)
  5 (5.00%) high mild
poplar1_prepare_init/128
                        time:   [705.96 µs 716.79 µs 728.91 µs]
                        change: [-88.244% -88.084% -87.895%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 12 outliers among 100 measurements (12.00%)
  8 (8.00%) high mild
  4 (4.00%) high severe
poplar1_prepare_init/256
                        time:   [1.3446 ms 1.3638 ms 1.3872 ms]
                        change: [-89.411% -89.244% -89.040%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 5 outliers among 100 measurements (5.00%)
  4 (4.00%) high mild
  1 (1.00%) high severe

idpf_gen/8              time:   [7.8101 µs 7.8455 µs 7.8820 µs]
                        thrpt:  [123.90 KiB/s 124.47 KiB/s 125.04 KiB/s]
                 change:
                        time:   [-82.168% -82.062% -81.952%] (p = 0.00 < 0.05)
                        thrpt:  [+454.07% +457.47% +460.78%]
                        Performance has improved.
Found 25 outliers among 100 measurements (25.00%)
  9 (9.00%) low mild
  10 (10.00%) high mild
  6 (6.00%) high severe
idpf_gen/128            time:   [50.419 µs 50.953 µs 51.624 µs]
                        thrpt:  [302.67 KiB/s 306.65 KiB/s 309.90 KiB/s]
                 change:
                        time:   [-93.491% -93.272% -93.055%] (p = 0.00 < 0.05)
                        thrpt:  [+1339.9% +1386.4% +1436.2%]
                        Performance has improved.
Found 3 outliers among 100 measurements (3.00%)
  2 (2.00%) high mild
  1 (1.00%) high severe
idpf_gen/2048           time:   [705.23 µs 707.03 µs 708.81 µs]
                        thrpt:  [352.70 KiB/s 353.59 KiB/s 354.49 KiB/s]
                 change:
                        time:   [-95.008% -94.863% -94.715%] (p = 0.00 < 0.05)
                        thrpt:  [+1792.3% +1846.5% +1903.3%]
                        Performance has improved.
Found 25 outliers among 100 measurements (25.00%)
  13 (13.00%) low severe
  1 (1.00%) low mild
  7 (7.00%) high mild
  4 (4.00%) high severe

idpf_eval/8             time:   [22.643 µs 22.733 µs 22.830 µs]
                        thrpt:  [42.776 KiB/s 42.958 KiB/s 43.128 KiB/s]
                 change:
                        time:   [-26.404% -24.697% -23.026%] (p = 0.00 < 0.05)
                        thrpt:  [+29.914% +32.797% +35.877%]
                        Performance has improved.
Found 5 outliers among 100 measurements (5.00%)
  4 (4.00%) high mild
  1 (1.00%) high severe
idpf_eval/128           time:   [373.28 µs 381.41 µs 390.49 µs]
                        thrpt:  [40.014 KiB/s 40.966 KiB/s 41.858 KiB/s]
                 change:
                        time:   [-10.725% -7.3672% -4.0925%] (p = 0.00 < 0.05)
                        thrpt:  [+4.2672% +7.9531% +12.014%]
                        Performance has improved.
Found 16 outliers among 100 measurements (16.00%)
  6 (6.00%) high mild
  10 (10.00%) high severe
idpf_eval/2048          time:   [6.4637 ms 6.5128 ms 6.5627 ms]
                        thrpt:  [38.094 KiB/s 38.386 KiB/s 38.678 KiB/s]
                 change:
                        time:   [-17.307% -14.515% -11.670%] (p = 0.00 < 0.05)
                        thrpt:  [+13.212% +16.979% +20.930%]
                        Performance has improved.
Found 1 outliers among 100 measurements (1.00%)
  1 (1.00%) high mild

Closes #511.