perf: extend_fallback optimization - #567

bench_extend            time:   [34.645 ns 34.823 ns 34.999 ns]
                        change: [−74.574% −74.269% −74.003%] (p = 0.00 < 0.05)
                        Performance has improved.

bench_extend_small      time:   [20.678 ns 20.851 ns 21.036 ns]
                        change: [−44.092% −42.884% −41.620%] (p = 0.00 < 0.05)
                        Performance has improved.

bench_extend_filtered   time:   [117.77 ns 118.27 ns 118.79 ns]
                        change: [−32.519% −32.049% −31.581%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 4 outliers among 100 measurements (4.00%)
  2 (2.00%) low mild
  2 (2.00%) high mild

bench_extend_filtered_small
                        time:   [22.823 ns 23.030 ns 23.247 ns]
                        change: [−35.161% −33.879% −32.470%] (p = 0.00 < 0.05)
                        Performance has improved.

bench_extend_from_slice time:   [36.363 ns 36.499 ns 36.644 ns]
                        change: [−74.015% −73.725% −73.444%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 2 outliers among 100 measurements (2.00%)
  2 (2.00%) high severe

bench_extend_from_slice_small
                        time:   [20.650 ns 20.784 ns 20.940 ns]
                        change: [−43.591% −42.283% −40.916%] (p = 0.00 < 0.05)
                        Performance has improved.

bench_extend_vec        time:   [60.429 ns 60.616 ns 60.839 ns]
                        change: [−10.449% −9.9262% −9.3862%] (p = 0.00 < 0.05)
                        Performance has improved.

bench_extend_vec_small  time:   [18.259 ns 18.324 ns 18.391 ns]
                        change: [+0.2642% +0.9616% +1.6561%] (p = 0.01 < 0.05)
                        Change within noise threshold.
Found 3 outliers among 100 measurements (3.00%)
  3 (3.00%) high severe

bench_extend_vec_filtered
                        time:   [150.21 ns 150.63 ns 151.08 ns]
                        change: [+5.9960% +6.5508% +7.0910%] (p = 0.00 < 0.05)
                        Performance has regressed.

bench_extend_vec_filtered_small
                        time:   [18.556 ns 18.663 ns 18.779 ns]
                        change: [−3.2075% −2.4870% −1.8235%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 100 measurements (1.00%)
  1 (1.00%) high mild

bench_extend_from_slice_vec
                        time:   [62.906 ns 63.110 ns 63.350 ns]
                        change: [−1.0367% −0.5490% −0.0662%] (p = 0.03 < 0.05)
                        Change within noise threshold.
Found 1 outliers among 100 measurements (1.00%)
  1 (1.00%) high mild

bench_extend_from_slice_vec_small
                        time:   [18.380 ns 18.463 ns 18.569 ns]
                        change: [+3.8765% +6.5163% +9.4532%] (p = 0.00 < 0.05)
                        Performance has regressed.