% ./par2 +RTS -s               
1422546
  42,417,819,472 bytes allocated in the heap
      43,692,272 bytes copied during GC
         858,768 bytes maximum residency (8 sample(s))
          72,880 bytes maximum slop
               6 MB total memory in use (1 MB lost due to fragmentation)

                                    Tot time (elapsed)  Avg pause  Max pause
  Gen  0     69761 colls,     0 par    0.29s    0.28s     0.0000s    0.0010s
  Gen  1         8 colls,     0 par    0.00s    0.00s     0.0001s    0.0002s

  TASKS: 4 (1 bound, 3 peak workers (3 total), using -N1)

  SPARKS: 1 (0 converted, 0 overflowed, 0 dud, 1 GC'd, 0 fizzled)

  INIT    time    0.00s  (  0.00s elapsed)
  MUT     time    5.28s  (  5.29s elapsed)
  GC      time    0.29s  (  0.28s elapsed)
  EXIT    time    0.00s  (  0.00s elapsed)
  Total   time    5.57s  (  5.57s elapsed)

  Alloc rate    8,030,303,884 bytes per MUT second

  Productivity  94.8% of total user, 94.9% of total elapsed

gc_alloc_block_sync: 0
whitehole_spin: 0
gen[0].sync: 0
gen[1].sync: 0


% ./par2 +RTS -s -N2
1422546
  42,417,832,488 bytes allocated in the heap
      80,082,040 bytes copied during GC
         868,792 bytes maximum residency (8 sample(s))
          88,168 bytes maximum slop
               7 MB total memory in use (1 MB lost due to fragmentation)

                                    Tot time (elapsed)  Avg pause  Max pause
  Gen  0     69761 colls, 69761 par    0.79s    0.38s     0.0000s    0.0008s
  Gen  1         8 colls,     7 par    0.00s    0.00s     0.0001s    0.0001s

  Parallel GC work balance: 2.30% (serial 0%, perfect 100%)

  TASKS: 6 (1 bound, 5 peak workers (5 total), using -N2)

  SPARKS: 1 (0 converted, 0 overflowed, 0 dud, 1 GC'd, 0 fizzled)

  INIT    time    0.00s  (  0.00s elapsed)
  MUT     time    6.24s  (  5.95s elapsed)
  GC      time    0.79s  (  0.38s elapsed)
  EXIT    time    0.00s  (  0.00s elapsed)
  Total   time    7.04s  (  6.33s elapsed)

  Alloc rate    6,797,502,905 bytes per MUT second

  Productivity  88.7% of total user, 98.5% of total elapsed

gc_alloc_block_sync: 412
whitehole_spin: 0
gen[0].sync: 0
gen[1].sync: 0


% ./par2 +RTS -s -N3
1422546
  42,417,848,664 bytes allocated in the heap
      79,581,592 bytes copied during GC
         882,336 bytes maximum residency (8 sample(s))
          92,400 bytes maximum slop
               7 MB total memory in use (1 MB lost due to fragmentation)

                                    Tot time (elapsed)  Avg pause  Max pause
  Gen  0     69761 colls, 69761 par    1.52s    0.51s     0.0000s    0.0040s
  Gen  1         8 colls,     7 par    0.00s    0.00s     0.0001s    0.0001s

  Parallel GC work balance: 2.14% (serial 0%, perfect 100%)

  TASKS: 8 (1 bound, 7 peak workers (7 total), using -N3)

  SPARKS: 1 (0 converted, 0 overflowed, 0 dud, 1 GC'd, 0 fizzled)

  INIT    time    0.00s  (  0.00s elapsed)
  MUT     time    7.04s  (  6.20s elapsed)
  GC      time    1.52s  (  0.51s elapsed)
  EXIT    time    0.00s  (  0.00s elapsed)
  Total   time    8.57s  (  6.71s elapsed)

  Alloc rate    6,022,011,173 bytes per MUT second

  Productivity  82.2% of total user, 104.9% of total elapsed

gc_alloc_block_sync: 4716
whitehole_spin: 0
gen[0].sync: 2
gen[1].sync: 0


% ./par2 +RTS -s -N4
1422546
  42,417,862,824 bytes allocated in the heap
     130,243,048 bytes copied during GC
       1,646,496 bytes maximum residency (17 sample(s))
         103,656 bytes maximum slop
              57 MB total memory in use (48 MB lost due to fragmentation)

                                    Tot time (elapsed)  Avg pause  Max pause
  Gen  0     67070 colls, 67070 par    3.10s    0.82s     0.0000s    0.0083s
  Gen  1        17 colls,    16 par    0.03s    0.01s     0.0005s    0.0037s

  Parallel GC work balance: 12.64% (serial 0%, perfect 100%)

  TASKS: 10 (1 bound, 9 peak workers (9 total), using -N4)

  SPARKS: 1 (1 converted, 0 overflowed, 0 dud, 0 GC'd, 0 fizzled)

  INIT    time    0.00s  (  0.00s elapsed)
  MUT     time   11.13s  (  4.19s elapsed)
  GC      time    3.13s  (  0.82s elapsed)
  EXIT    time    0.00s  (  0.00s elapsed)
  Total   time   14.26s  (  5.02s elapsed)

  Alloc rate    3,811,418,874 bytes per MUT second

  Productivity  78.0% of total user, 221.9% of total elapsed

gc_alloc_block_sync: 96708
whitehole_spin: 0
gen[0].sync: 54147
gen[1].sync: 34