Precalculate Non-zero divisors for lak

[mcroomp]

Simplify division step in Lak calculations so that we don't need to check for divide by zero.

[Melirius]

It is OK, do you want to change division later to division-by-multiplication here?

[mcroomp]

Not sure the division-by-multiply will fly because of the i16 cast to determine the sign. It messes up a bunch of potential optimizations.

[Melirius]

Unfortunately it is slower than current main:

main 82d6547

2024-11-15T21:03:34.699Z INFO  [lepton_jpeg::structs::lepton_file_writer] compressing to Lepton format
2024-11-15T21:03:35.173Z INFO  [lepton_jpeg::structs::lepton_file_writer] Number of threads: 8
2024-11-15T21:03:36.610Z INFO  [lepton_jpeg::structs::lepton_file_writer] worker threads 9632ms of CPU time in 1436ms of wall time
2024-11-15T21:03:36.610Z INFO  [lepton_jpeg::structs::lepton_file_writer] decompressing to verify contents
2024-11-15T21:03:38.216Z INFO  [lepton_jpeg_util] compressed input 22171278, output 17324076 bytes (compression = 28.0%)
2024-11-15T21:03:38.216Z INFO  [lepton_jpeg_util] Main thread CPU: 3517ms, Worker thread CPU: 20710 ms, walltime: 3517 ms

 Performance counter stats for 'taskset -c 10 nice -n -20 target/release/lepton_jpeg_util images/img_52MP_7k.jpg images/img_52MP_7k2.lep':

       871 003 064      cache-references                                                        (41,51%)
        86 439 870      cache-misses                     #    9,92% of all cache refs           (41,52%)
    15 795 148 123      cycles                                                                  (41,72%)
       834 608 725      ic_fetch_stall.ic_stall_back_pressure                                        (41,87%)
     1 014 898 692      stalled-cycles-frontend          #    6,43% frontend cycles idle        (42,14%)
    39 107 914 014      instructions                     #    2,48  insn per cycle            
                                                  #    0,03  stalled cycles per insn     (42,43%)
     4 396 207 542      branch-instructions                                                     (42,50%)
       162 547 993      branch-misses                    #    3,70% of all branches             (42,32%)
     5 434 637 214      ic_fetch_stall.ic_stall_any                                             (42,14%)
        45 374 631      ic_fetch_stall.ic_stall_dq_empty                                        (41,99%)
        72 770 962      l2_cache_misses_from_ic_miss                                            (41,75%)
     2 149 017 778      l2_latency.l2_cycles_waiting_on_fills                                        (41,47%)
           184 005      faults                                                                
                 1      migrations                                                            

       3,551824055 seconds time elapsed

       3,224073000 seconds user
       0,324906000 seconds sys

this PR rebased on main:

2024-11-15T21:02:37.776Z INFO  [lepton_jpeg::structs::lepton_file_writer] compressing to Lepton format
2024-11-15T21:02:38.258Z INFO  [lepton_jpeg::structs::lepton_file_writer] Number of threads: 8
2024-11-15T21:02:39.715Z INFO  [lepton_jpeg::structs::lepton_file_writer] worker threads 9853ms of CPU time in 1456ms of wall time
2024-11-15T21:02:39.715Z INFO  [lepton_jpeg::structs::lepton_file_writer] decompressing to verify contents
2024-11-15T21:02:41.327Z INFO  [lepton_jpeg_util] compressed input 22171278, output 17324076 bytes (compression = 28.0%)
2024-11-15T21:02:41.327Z INFO  [lepton_jpeg_util] Main thread CPU: 3550ms, Worker thread CPU: 20941 ms, walltime: 3550 ms

 Performance counter stats for 'taskset -c 10 nice -n -20 target/release/lepton_jpeg_util images/img_52MP_7k.jpg images/img_52MP_7k2.lep':

       871 415 376      cache-references                                                        (41,78%)
        81 979 646      cache-misses                     #    9,41% of all cache refs           (41,60%)
    15 921 809 354      cycles                                                                  (41,64%)
       927 421 935      ic_fetch_stall.ic_stall_back_pressure                                        (41,85%)
     1 064 411 574      stalled-cycles-frontend          #    6,69% frontend cycles idle        (42,04%)
    38 932 713 731      instructions                     #    2,45  insn per cycle            
                                                  #    0,03  stalled cycles per insn     (42,18%)
     4 399 352 404      branch-instructions                                                     (42,15%)
       163 853 521      branch-misses                    #    3,72% of all branches             (42,07%)
     5 490 454 599      ic_fetch_stall.ic_stall_any                                             (42,14%)
        40 739 513      ic_fetch_stall.ic_stall_dq_empty                                        (42,01%)
        67 832 885      l2_cache_misses_from_ic_miss                                            (41,87%)
     2 175 383 646      l2_latency.l2_cycles_waiting_on_fills                                        (41,81%)
           184 003      faults                                                                
                 1      migrations                                                            

       3,585066645 seconds time elapsed

       3,248145000 seconds user
       0,333706000 seconds sys