Commit Graph
639 Commits
Author SHA1 Message Date
Nigel Tao becd1a6b25 Fix a comment typo. 2017-11-08 16:56:22 +11:00
Nigel Tao 1910ca31cf Run the mimic checksum benchmarks for longer. 2017-11-08 12:46:57 +11:00
Nigel Tao 39952faca1 Tweak the copy_from_history32 unroll count.
name                           old speed      new speed      delta

puffs_adler32_10k/clang        2.42GB/s ± 1%  2.43GB/s ± 1%     ~     (p=0.720 n=10+9)
puffs_adler32_100k/clang       2.43GB/s ± 0%  2.42GB/s ± 1%   -0.41%  (p=0.004 n=8+10)
puffs_flate_decode_1k/clang     138MB/s ± 1%   139MB/s ± 1%   +1.20%  (p=0.000 n=10+10)
puffs_flate_decode_10k/clang    189MB/s ± 1%   187MB/s ± 1%   -1.27%  (p=0.000 n=9+9)
puffs_flate_decode_100k/clang   211MB/s ± 1%   210MB/s ± 1%   -0.72%  (p=0.001 n=10+9)
puffs_zlib_decode_10k/clang     175MB/s ± 1%   173MB/s ± 1%   -1.23%  (p=0.000 n=10+10)
puffs_zlib_decode_100k/clang    194MB/s ± 1%   193MB/s ± 0%   -0.50%  (p=0.018 n=10+9)

puffs_adler32_10k/gcc          3.26GB/s ± 0%  3.22GB/s ± 1%   -1.00%  (p=0.000 n=9+10)
puffs_adler32_100k/gcc         3.27GB/s ± 0%  3.23GB/s ± 1%   -1.05%  (p=0.000 n=8+9)
puffs_flate_decode_1k/gcc       139MB/s ± 0%   141MB/s ± 1%   +1.27%  (p=0.000 n=9+10)
puffs_flate_decode_10k/gcc      203MB/s ± 0%   231MB/s ± 0%  +13.87%  (p=0.000 n=10+9)
puffs_flate_decode_100k/gcc     229MB/s ± 0%   258MB/s ± 0%  +12.63%  (p=0.000 n=9+9)
puffs_zlib_decode_10k/gcc       201MB/s ± 0%   215MB/s ± 1%   +6.86%  (p=0.000 n=10+9)
puffs_zlib_decode_100k/gcc      224MB/s ± 0%   239MB/s ± 0%   +6.89%  (p=0.000 n=9+9)
2017-11-08 11:40:09 +11:00
Nigel Tao 7ccb9234a4 Fix hand-written decode_huffman_fast C impl. 2017-11-08 10:12:47 +11:00
Nigel Tao 848d66ffdf Tighten the Huffman n_bits invariant. 2017-11-07 09:30:16 +11:00
Nigel Tao 30ce73ad26 Remove some superfluous braces. 2017-11-06 17:01:34 +11:00
Nigel Tao 0bc6f792fb Remove some suspensions from decode_huffman_fast.
name                           old speed      new speed      delta

puffs_adler32_10k/clang        2.41GB/s ± 1%  2.39GB/s ± 2%  -0.88%  (p=0.022 n=9+10)
puffs_adler32_100k/clang       2.41GB/s ± 1%  2.39GB/s ± 2%    ~     (p=0.095 n=10+9)
puffs_flate_decode_1k/clang     136MB/s ± 2%   134MB/s ± 1%  -0.86%  (p=0.036 n=9+8)
puffs_flate_decode_10k/clang    172MB/s ± 0%   175MB/s ± 0%  +1.96%  (p=0.000 n=8+9)
puffs_flate_decode_100k/clang   206MB/s ± 0%   209MB/s ± 1%  +1.38%  (p=0.000 n=8+9)
puffs_zlib_decode_10k/clang     160MB/s ± 1%   163MB/s ± 2%  +1.73%  (p=0.001 n=9+9)
puffs_zlib_decode_100k/clang    189MB/s ± 1%   188MB/s ± 6%    ~     (p=0.143 n=10+10)

puffs_adler32_10k/gcc          3.27GB/s ± 0%  3.20GB/s ± 2%  -2.03%  (p=0.000 n=8+10)
puffs_adler32_100k/gcc         3.27GB/s ± 0%  3.21GB/s ± 1%  -1.89%  (p=0.000 n=8+10)
puffs_flate_decode_1k/gcc       141MB/s ± 1%   139MB/s ± 1%  -1.66%  (p=0.000 n=9+10)
puffs_flate_decode_10k/gcc      200MB/s ± 0%   209MB/s ± 1%  +4.73%  (p=0.000 n=10+10)
puffs_flate_decode_100k/gcc     242MB/s ± 0%   237MB/s ± 0%  -2.19%  (p=0.000 n=9+10)
puffs_zlib_decode_10k/gcc       188MB/s ± 0%   195MB/s ± 1%  +3.71%  (p=0.000 n=10+10)
puffs_zlib_decode_100k/gcc      225MB/s ± 0%   221MB/s ± 0%  -1.84%  (p=0.000 n=8+9)
2017-11-06 16:59:27 +11:00
Nigel Tao 058938006a Remove some suspensions from decode_huffman_fast.
name                           old speed      new speed      delta

puffs_adler32_10k/clang        2.45GB/s ± 0%  2.41GB/s ± 1%  -1.82%  (p=0.000 n=9+9)
puffs_adler32_100k/clang       2.45GB/s ± 0%  2.41GB/s ± 1%  -1.74%  (p=0.000 n=9+10)
puffs_flate_decode_1k/clang     133MB/s ± 0%   136MB/s ± 2%  +1.93%  (p=0.003 n=9+9)
puffs_flate_decode_10k/clang    181MB/s ± 0%   172MB/s ± 0%  -5.18%  (p=0.000 n=9+8)
puffs_flate_decode_100k/clang   204MB/s ± 0%   206MB/s ± 0%  +0.63%  (p=0.000 n=10+8)
puffs_zlib_decode_10k/clang     168MB/s ± 0%   160MB/s ± 1%  -4.82%  (p=0.000 n=10+9)
puffs_zlib_decode_100k/clang    189MB/s ± 0%   189MB/s ± 1%    ~     (p=0.143 n=10+10)

puffs_adler32_10k/gcc          3.26GB/s ± 0%  3.27GB/s ± 0%  +0.12%  (p=0.000 n=10+8)
puffs_adler32_100k/gcc         3.27GB/s ± 0%  3.27GB/s ± 0%  +0.18%  (p=0.000 n=10+8)
puffs_flate_decode_1k/gcc       130MB/s ± 0%   141MB/s ± 1%  +8.71%  (p=0.000 n=10+9)
puffs_flate_decode_10k/gcc      203MB/s ± 0%   200MB/s ± 0%  -1.72%  (p=0.000 n=9+10)
puffs_flate_decode_100k/gcc     241MB/s ± 0%   242MB/s ± 0%  +0.54%  (p=0.000 n=8+9)
puffs_zlib_decode_10k/gcc       188MB/s ± 0%   188MB/s ± 0%  +0.26%  (p=0.000 n=9+10)
puffs_zlib_decode_100k/gcc      223MB/s ± 0%   225MB/s ± 0%  +0.93%  (p=0.000 n=9+8)
2017-11-06 15:25:19 +11:00
Nigel Tao ccdd74a17f Remove some suspensions from decode_huffman_fast.
name                           old speed      new speed      delta

puffs_adler32_10k/clang        2.45GB/s ± 0%  2.45GB/s ± 0%   -0.08%  (p=0.006 n=10+9)
puffs_adler32_100k/clang       2.46GB/s ± 0%  2.45GB/s ± 0%   -0.12%  (p=0.000 n=10+9)
puffs_flate_decode_1k/clang     137MB/s ± 0%   133MB/s ± 0%   -2.71%  (p=0.000 n=9+9)
puffs_flate_decode_10k/clang    177MB/s ± 0%   181MB/s ± 0%   +2.22%  (p=0.000 n=10+9)
puffs_flate_decode_100k/clang   198MB/s ± 0%   204MB/s ± 0%   +3.04%  (p=0.000 n=10+10)
puffs_zlib_decode_10k/clang     163MB/s ± 0%   168MB/s ± 0%   +3.23%  (p=0.000 n=9+10)
puffs_zlib_decode_100k/clang    182MB/s ± 0%   189MB/s ± 0%   +3.56%  (p=0.000 n=9+10)

puffs_adler32_10k/gcc          3.26GB/s ± 0%  3.26GB/s ± 0%     ~     (p=0.280 n=10+10)
puffs_adler32_100k/gcc         3.27GB/s ± 0%  3.27GB/s ± 0%     ~     (p=0.075 n=10+10)
puffs_flate_decode_1k/gcc       111MB/s ± 1%   130MB/s ± 0%  +17.19%  (p=0.000 n=10+10)
puffs_flate_decode_10k/gcc      142MB/s ± 0%   203MB/s ± 0%  +43.11%  (p=0.000 n=10+9)
puffs_flate_decode_100k/gcc     153MB/s ± 0%   241MB/s ± 0%  +57.62%  (p=0.000 n=9+8)
puffs_zlib_decode_10k/gcc       142MB/s ± 0%   188MB/s ± 0%  +32.47%  (p=0.000 n=9+9)
puffs_zlib_decode_100k/gcc      149MB/s ± 0%   223MB/s ± 0%  +50.03%  (p=0.000 n=8+9)
2017-11-06 14:03:11 +11:00
Nigel Tao bf50d268ae Remove some suspensions from decode_huffman_fast.
name                           old speed      new speed      delta

puffs_adler32_10k/clang        2.40GB/s ± 3%  2.45GB/s ± 0%   +2.21%  (p=0.000 n=10+10)
puffs_adler32_100k/clang       2.41GB/s ± 1%  2.46GB/s ± 0%   +2.05%  (p=0.000 n=9+10)
puffs_flate_decode_1k/clang     127MB/s ± 1%   137MB/s ± 0%   +7.94%  (p=0.000 n=9+9)
puffs_flate_decode_10k/clang    177MB/s ± 1%   177MB/s ± 0%     ~     (p=0.234 n=9+10)
puffs_flate_decode_100k/clang   205MB/s ± 1%   198MB/s ± 0%   -3.06%  (p=0.000 n=9+10)
puffs_zlib_decode_10k/clang     165MB/s ± 1%   163MB/s ± 0%   -1.12%  (p=0.000 n=9+9)
puffs_zlib_decode_100k/clang    189MB/s ± 0%   182MB/s ± 0%   -3.42%  (p=0.000 n=9+9)

puffs_adler32_10k/gcc          3.26GB/s ± 0%  3.26GB/s ± 0%     ~     (p=0.065 n=9+10)
puffs_adler32_100k/gcc         3.27GB/s ± 0%  3.27GB/s ± 0%     ~     (p=0.173 n=8+10)
puffs_flate_decode_1k/gcc       111MB/s ± 0%   111MB/s ± 1%     ~     (p=0.971 n=10+10)
puffs_flate_decode_10k/gcc      149MB/s ± 0%   142MB/s ± 0%   -4.67%  (p=0.000 n=9+10)
puffs_flate_decode_100k/gcc     160MB/s ± 0%   153MB/s ± 0%   -4.46%  (p=0.000 n=9+9)
puffs_zlib_decode_10k/gcc       128MB/s ± 0%   142MB/s ± 0%  +11.21%  (p=0.000 n=9+9)
puffs_zlib_decode_100k/gcc      137MB/s ± 0%   149MB/s ± 0%   +8.47%  (p=0.000 n=8+8)
2017-11-06 08:31:03 +11:00
Nigel Tao 5520340d7c Remove some suspensions from decode_huffman_fast.
name                           old speed      new speed      delta

puffs_adler32_10k/clang        2.45GB/s ± 2%  2.40GB/s ± 3%   -1.87%  (p=0.001 n=9+10)
puffs_adler32_100k/clang       2.46GB/s ± 0%  2.41GB/s ± 1%   -2.08%  (p=0.000 n=8+9)
puffs_flate_decode_1k/clang     125MB/s ± 0%   127MB/s ± 1%   +1.53%  (p=0.000 n=9+9)
puffs_flate_decode_10k/clang    168MB/s ± 0%   177MB/s ± 1%   +5.59%  (p=0.000 n=10+9)
puffs_flate_decode_100k/clang   193MB/s ± 0%   205MB/s ± 1%   +6.20%  (p=0.000 n=9+9)
puffs_zlib_decode_10k/clang     157MB/s ± 0%   165MB/s ± 1%   +5.00%  (p=0.000 n=9+9)
puffs_zlib_decode_100k/clang    179MB/s ± 0%   189MB/s ± 0%   +5.69%  (p=0.000 n=8+9)

puffs_adler32_10k/gcc          3.26GB/s ± 0%  3.26GB/s ± 0%   -0.14%  (p=0.000 n=10+9)
puffs_adler32_100k/gcc         3.27GB/s ± 0%  3.27GB/s ± 0%   -0.09%  (p=0.000 n=9+8)
puffs_flate_decode_1k/gcc       122MB/s ± 0%   111MB/s ± 0%   -9.40%  (p=0.000 n=10+10)
puffs_flate_decode_10k/gcc      176MB/s ± 0%   149MB/s ± 0%  -15.45%  (p=0.000 n=10+9)
puffs_flate_decode_100k/gcc     199MB/s ± 0%   160MB/s ± 0%  -19.51%  (p=0.000 n=10+9)
puffs_zlib_decode_10k/gcc       168MB/s ± 0%   128MB/s ± 0%  -24.01%  (p=0.000 n=10+9)
puffs_zlib_decode_100k/gcc      187MB/s ± 0%   137MB/s ± 0%  -26.84%  (p=0.000 n=9+8)
2017-11-05 23:02:19 +11:00
Nigel Tao e7c14dfe63 Remove some suspensions from decode_huffman_fast.
name                           old speed      new speed      delta

puffs_adler32_10k/clang        2.46GB/s ± 0%  2.45GB/s ± 2%     ~     (p=0.352 n=9+9)
puffs_adler32_100k/clang       2.46GB/s ± 0%  2.46GB/s ± 0%     ~     (p=0.673 n=9+8)
puffs_flate_decode_1k/clang     124MB/s ± 0%   125MB/s ± 0%   +0.39%  (p=0.000 n=8+9)
puffs_flate_decode_10k/clang    165MB/s ± 0%   168MB/s ± 0%   +1.81%  (p=0.000 n=8+10)
puffs_flate_decode_100k/clang   195MB/s ± 0%   193MB/s ± 0%   -1.30%  (p=0.000 n=9+9)
puffs_zlib_decode_10k/clang     154MB/s ± 1%   157MB/s ± 0%   +1.96%  (p=0.000 n=9+9)
puffs_zlib_decode_100k/clang    181MB/s ± 0%   179MB/s ± 0%   -1.19%  (p=0.000 n=10+8)

puffs_adler32_10k/gcc          3.26GB/s ± 0%  3.26GB/s ± 0%     ~     (p=0.549 n=9+10)
puffs_adler32_100k/gcc         3.27GB/s ± 0%  3.27GB/s ± 0%     ~     (p=0.450 n=9+9)
puffs_flate_decode_1k/gcc       112MB/s ± 0%   122MB/s ± 0%   +9.10%  (p=0.000 n=10+10)
puffs_flate_decode_10k/gcc      155MB/s ± 0%   176MB/s ± 0%  +13.63%  (p=0.000 n=10+10)
puffs_flate_decode_100k/gcc     176MB/s ± 0%   199MB/s ± 0%  +12.74%  (p=0.000 n=9+10)
puffs_zlib_decode_10k/gcc       137MB/s ± 0%   168MB/s ± 0%  +22.54%  (p=0.000 n=9+10)
puffs_zlib_decode_100k/gcc      158MB/s ± 0%   187MB/s ± 0%  +18.87%  (p=0.000 n=9+9)
2017-11-05 22:40:18 +11:00
Nigel Tao 934705a6e1 Remove some suspensions from decode_huffman_fast.
name                           old speed      new speed      delta

puffs_adler32_10k/clang        2.46GB/s ± 0%  2.46GB/s ± 0%     ~     (p=0.243 n=10+9)
puffs_adler32_100k/clang       2.46GB/s ± 0%  2.46GB/s ± 0%   +0.07%  (p=0.002 n=10+9)
puffs_flate_decode_1k/clang     125MB/s ± 0%   124MB/s ± 0%   -0.58%  (p=0.000 n=10+8)
puffs_flate_decode_10k/clang    168MB/s ± 0%   165MB/s ± 0%   -2.07%  (p=0.000 n=9+8)
puffs_flate_decode_100k/clang   203MB/s ± 0%   195MB/s ± 0%   -3.85%  (p=0.000 n=9+9)
puffs_zlib_decode_10k/clang     157MB/s ± 0%   154MB/s ± 1%   -2.07%  (p=0.000 n=9+9)
puffs_zlib_decode_100k/clang    187MB/s ± 0%   181MB/s ± 0%   -3.50%  (p=0.000 n=10+10)

puffs_adler32_10k/gcc          3.20GB/s ± 1%  3.26GB/s ± 0%   +2.07%  (p=0.000 n=10+9)
puffs_adler32_100k/gcc         3.21GB/s ± 1%  3.27GB/s ± 0%   +1.71%  (p=0.000 n=9+9)
puffs_flate_decode_1k/gcc       128MB/s ± 2%   112MB/s ± 0%  -12.35%  (p=0.000 n=10+10)
puffs_flate_decode_10k/gcc      181MB/s ± 1%   155MB/s ± 0%  -14.07%  (p=0.000 n=10+10)
puffs_flate_decode_100k/gcc     208MB/s ± 0%   176MB/s ± 0%  -15.23%  (p=0.000 n=9+9)
puffs_zlib_decode_10k/gcc       172MB/s ± 1%   137MB/s ± 0%  -20.14%  (p=0.000 n=10+9)
puffs_zlib_decode_100k/gcc      195MB/s ± 1%   158MB/s ± 0%  -18.97%  (p=0.000 n=10+9)
2017-11-05 21:59:59 +11:00
Nigel Tao 44323f95ad Remove some suspensions from decode_huffman_fast.
name                           old speed      new speed      delta

puffs_adler32_10k/clang        2.46GB/s ± 0%  2.46GB/s ± 0%    ~     (p=0.968 n=9+10)
puffs_adler32_100k/clang       2.46GB/s ± 0%  2.46GB/s ± 0%    ~     (p=0.579 n=10+10)
puffs_flate_decode_1k/clang     132MB/s ± 0%   125MB/s ± 0%  -5.22%  (p=0.000 n=10+10)
puffs_flate_decode_10k/clang    167MB/s ± 0%   168MB/s ± 0%  +0.80%  (p=0.000 n=8+9)
puffs_flate_decode_100k/clang   205MB/s ± 0%   203MB/s ± 0%  -0.91%  (p=0.000 n=9+9)
puffs_zlib_decode_10k/clang     156MB/s ± 0%   157MB/s ± 0%  +0.91%  (p=0.000 n=9+9)
puffs_zlib_decode_100k/clang    189MB/s ± 0%   187MB/s ± 0%  -0.92%  (p=0.000 n=8+10)

puffs_adler32_10k/gcc          3.18GB/s ± 3%  3.20GB/s ± 1%    ~     (p=0.796 n=10+10)
puffs_adler32_100k/gcc         3.22GB/s ± 1%  3.21GB/s ± 1%    ~     (p=0.730 n=9+9)
puffs_flate_decode_1k/gcc       125MB/s ± 1%   128MB/s ± 2%  +2.20%  (p=0.000 n=9+10)
puffs_flate_decode_10k/gcc      177MB/s ± 1%   181MB/s ± 1%  +1.82%  (p=0.000 n=9+10)
puffs_flate_decode_100k/gcc     203MB/s ± 1%   208MB/s ± 0%  +2.67%  (p=0.000 n=10+9)
puffs_zlib_decode_10k/gcc       168MB/s ± 0%   172MB/s ± 1%  +2.11%  (p=0.000 n=10+10)
puffs_zlib_decode_100k/gcc      190MB/s ± 1%   195MB/s ± 1%  +2.36%  (p=0.000 n=9+10)
2017-11-05 21:33:44 +11:00
Nigel Tao 7e33a2cc14 Remove some suspensions from decode_huffman_fast.
name                           old speed      new speed      delta

puffs_adler32_10k/clang        2.39GB/s ± 1%  2.46GB/s ± 0%  +2.88%  (p=0.000 n=8+9)
puffs_adler32_100k/clang       2.40GB/s ± 1%  2.46GB/s ± 0%  +2.18%  (p=0.000 n=9+10)
puffs_flate_decode_1k/clang     129MB/s ± 4%   132MB/s ± 0%  +2.31%  (p=0.000 n=10+10)
puffs_flate_decode_10k/clang    164MB/s ± 1%   167MB/s ± 0%  +1.89%  (p=0.000 n=10+8)
puffs_flate_decode_100k/clang   194MB/s ± 1%   205MB/s ± 0%  +5.49%  (p=0.000 n=9+9)
puffs_zlib_decode_10k/clang     153MB/s ± 1%   156MB/s ± 0%  +1.73%  (p=0.000 n=9+9)
puffs_zlib_decode_100k/clang    180MB/s ± 1%   189MB/s ± 0%  +5.09%  (p=0.000 n=8+8)

puffs_adler32_10k/gcc          3.21GB/s ± 1%  3.18GB/s ± 3%    ~     (p=0.203 n=8+10)
puffs_adler32_100k/gcc         3.22GB/s ± 0%  3.22GB/s ± 1%    ~     (p=0.931 n=9+9)
puffs_flate_decode_1k/gcc       124MB/s ± 1%   125MB/s ± 1%  +1.41%  (p=0.001 n=9+9)
puffs_flate_decode_10k/gcc      179MB/s ± 1%   177MB/s ± 1%  -0.77%  (p=0.006 n=10+9)
puffs_flate_decode_100k/gcc     192MB/s ± 0%   203MB/s ± 1%  +5.57%  (p=0.000 n=10+10)
puffs_zlib_decode_10k/gcc       169MB/s ± 1%   168MB/s ± 0%  -0.45%  (p=0.011 n=10+10)
puffs_zlib_decode_100k/gcc      180MB/s ± 1%   190MB/s ± 1%  +5.37%  (p=0.000 n=10+9)
2017-11-05 21:11:24 +11:00
Nigel Tao 465b4e1815 Remove some suspensions from decode_huffman_fast.
name                           old speed      new speed      delta

puffs_adler32_10k/clang        2.45GB/s ± 0%  2.39GB/s ± 1%   -2.74%  (p=0.000 n=10+8)
puffs_adler32_100k/clang       2.46GB/s ± 0%  2.40GB/s ± 1%   -2.13%  (p=0.000 n=10+9)
puffs_flate_decode_1k/clang     132MB/s ± 0%   129MB/s ± 4%   -2.25%  (p=0.000 n=10+10)
puffs_flate_decode_10k/clang    174MB/s ± 0%   164MB/s ± 1%   -5.78%  (p=0.000 n=10+10)
puffs_flate_decode_100k/clang   208MB/s ± 0%   194MB/s ± 1%   -6.45%  (p=0.000 n=10+9)
puffs_zlib_decode_10k/clang     162MB/s ± 0%   153MB/s ± 1%   -5.46%  (p=0.000 n=9+9)
puffs_zlib_decode_100k/clang    192MB/s ± 0%   180MB/s ± 1%   -6.02%  (p=0.000 n=9+8)

puffs_adler32_10k/gcc          3.26GB/s ± 0%  3.21GB/s ± 1%   -1.58%  (p=0.000 n=10+8)
puffs_adler32_100k/gcc         3.27GB/s ± 0%  3.22GB/s ± 0%   -1.42%  (p=0.000 n=8+9)
puffs_flate_decode_1k/gcc       106MB/s ± 0%   124MB/s ± 1%  +17.14%  (p=0.000 n=10+9)
puffs_flate_decode_10k/gcc      140MB/s ± 0%   179MB/s ± 1%  +27.45%  (p=0.000 n=9+10)
puffs_flate_decode_100k/gcc     150MB/s ± 0%   192MB/s ± 0%  +27.77%  (p=0.000 n=10+10)
puffs_zlib_decode_10k/gcc       120MB/s ± 0%   169MB/s ± 1%  +40.32%  (p=0.000 n=9+10)
puffs_zlib_decode_100k/gcc      134MB/s ± 0%   180MB/s ± 1%  +34.56%  (p=0.000 n=8+10)
2017-11-05 20:50:58 +11:00
Nigel Tao 73778b0767 Re-pack token keys' numeric values. 2017-11-05 20:07:30 +11:00
Nigel Tao 13731f989f Add a reader1.unread_u8 method.
Also re-enable a number of std/flate tests and benchmarks.

It's not an optimization per se, but as a data point, here are some
benchmark numbers between 36a93fa and this commit. 36a93fa is "36a93fa
Add a TODO about impure functions", which is one commit before "f968950
Read bits up front in decode_huffman_fast", and f968950 was the commit
that made decode_huffman_fast read more than one byte at a time.

name                             old speed      new speed       delta

puffs_adler32_10k/clang          2.45GB/s ± 0%   2.45GB/s ± 0%     ~     (p=0.684 n=10+10)
puffs_adler32_100k/clang         2.45GB/s ± 0%   2.46GB/s ± 0%   +0.07%  (p=0.019 n=10+10)
puffs_flate_decode_1k/clang       124MB/s ± 0%    132MB/s ± 0%   +6.06%  (p=0.000 n=10+10)
puffs_flate_decode_10k/clang      145MB/s ± 0%    174MB/s ± 0%  +20.19%  (p=0.000 n=9+10)
puffs_flate_decode_100k/clang     168MB/s ± 0%    208MB/s ± 0%  +23.31%  (p=0.000 n=10+10)
puffs_zlib_decode_10k/clang       136MB/s ± 0%    162MB/s ± 0%  +18.94%  (p=0.000 n=10+9)
puffs_zlib_decode_100k/clang      158MB/s ± 0%    192MB/s ± 0%  +21.58%  (p=0.000 n=10+9)

puffs_adler32_10k/gcc            3.26GB/s ± 0%   3.26GB/s ± 0%     ~     (p=0.631 n=10+10)
puffs_adler32_100k/gcc           3.27GB/s ± 0%   3.27GB/s ± 0%     ~     (p=0.237 n=10+8)
puffs_flate_decode_1k/gcc        95.3MB/s ± 0%  105.5MB/s ± 0%  +10.67%  (p=0.000 n=10+10)
puffs_flate_decode_10k/gcc        110MB/s ± 0%    140MB/s ± 0%  +27.32%  (p=0.000 n=9+9)
puffs_flate_decode_100k/gcc       121MB/s ± 0%    150MB/s ± 0%  +24.02%  (p=0.000 n=8+10)
puffs_zlib_decode_10k/gcc         112MB/s ± 0%    120MB/s ± 0%   +6.96%  (p=0.000 n=10+9)
puffs_zlib_decode_100k/gcc        123MB/s ± 0%    134MB/s ± 0%   +8.93%  (p=0.000 n=9+8)
2017-11-05 15:59:02 +11:00
Nigel Tao 6621526a2c Re-introduce codegen for b_wstart_dst. 2017-11-05 14:24:33 +11:00
Nigel Tao 586413dbd3 Run "go generate".
I previously forgot to do this after a trivial edit to the cgen package.
2017-11-05 14:21:02 +11:00
Nigel Tao 325c36314a Prepare decode_huffman_fast to rewind in.src. 2017-11-05 14:13:27 +11:00
Nigel Tao 3099991d7f Add an "invalid I/O operation" error code. 2017-11-05 13:53:35 +11:00
Nigel Tao b6a079fd3e Tweak the decode_huffman_fast loop condition more. 2017-11-05 13:47:28 +11:00
Nigel Tao f6e072fe77 Add some more "inconsistent n_bits" checks.
This uncovered a bug in the decode_huffman_fast function. A follow up commit
will actually fix the bug.

For what it's worth, some benchmark numbers are below, but they're
possibly bogus, as we might be decoding incorrect (and truncated) output
for some inputs. Everything since "f968950 Read bits up front in
decode_huffman_fast" landed possibly has bogus numbers too.

name                           old speed     new speed     delta
puffs_flate_decode_100k/clang  194MB/s ± 0%  204MB/s ± 1%   +5.02%  (p=0.008 n=5+5)
puffs_flate_decode_100k/gcc    180MB/s ± 3%  202MB/s ± 1%  +12.09%  (p=0.008 n=5+5)
2017-11-05 09:23:49 +11:00
Nigel Tao db57d8b707 Bump decode_huffman_fast's src available hurdle.
We will need this later, to prove that the other read_u8 calls in
decode_huffman_fast will not suspend.

It's not obvious why the clang benchmarks don't change but the gcc ones
(including the adler numbers, which are superficially unrelated) look
worse. If the change from 6 to 12 bytes is a genuine performance
regression, then a future commit can tighten the bound back to 6,
although it would probably make the decode_huffman_fast assertions and
proof requirements considerably more complicated.

name                           old speed      new speed      delta

puffs_adler32_10k/clang        2.40GB/s ± 1%  2.41GB/s ± 0%    ~     (p=0.690 n=5+5)
puffs_adler32_100k/clang       2.39GB/s ± 2%  2.40GB/s ± 1%    ~     (p=1.000 n=5+5)
puffs_flate_decode_1k/clang     128MB/s ± 0%   128MB/s ± 0%    ~     (p=1.000 n=5+5)
puffs_flate_decode_10k/clang    167MB/s ± 2%   168MB/s ± 0%    ~     (p=0.548 n=5+5)
puffs_flate_decode_100k/clang   193MB/s ± 2%   194MB/s ± 0%    ~     (p=0.310 n=5+5)
puffs_zlib_decode_10k/clang     157MB/s ± 0%   155MB/s ± 4%    ~     (p=0.421 n=5+5)
puffs_zlib_decode_100k/clang    180MB/s ± 1%   177MB/s ± 3%    ~     (p=0.222 n=5+5)

puffs_adler32_10k/gcc          3.26GB/s ± 0%  3.20GB/s ± 1%  -1.81%  (p=0.008 n=5+5)
puffs_adler32_100k/gcc         3.26GB/s ± 0%  3.21GB/s ± 0%  -1.63%  (p=0.008 n=5+5)
puffs_flate_decode_1k/gcc       129MB/s ± 0%   126MB/s ± 1%  -2.30%  (p=0.008 n=5+5)
puffs_flate_decode_10k/gcc      164MB/s ± 0%   161MB/s ± 0%  -1.86%  (p=0.008 n=5+5)
puffs_flate_decode_100k/gcc     185MB/s ± 0%   180MB/s ± 3%  -2.81%  (p=0.016 n=4+5)
puffs_zlib_decode_10k/gcc       157MB/s ± 0%   151MB/s ± 2%  -3.49%  (p=0.008 n=5+5)
puffs_zlib_decode_100k/gcc      175MB/s ± 0%   170MB/s ± 2%  -2.97%  (p=0.016 n=4+5)
2017-11-05 08:56:55 +11:00
Nigel Tao 55e0bc513b Don't suspend for read_u8 if data is available.
It's not obvious why the benchmarks get worse when the code looks
better, but the long term goal is for all of decode_huffman_fast to not
suspend, and this is one step along that path.

name                           old speed      new speed      delta

puffs_adler32_10k/clang        2.40GB/s ± 1%  2.40GB/s ± 1%     ~     (p=0.841 n=5+5)
puffs_adler32_100k/clang       2.40GB/s ± 1%  2.39GB/s ± 2%     ~     (p=0.421 n=5+5)
puffs_flate_decode_1k/clang     131MB/s ± 1%   128MB/s ± 0%   -2.51%  (p=0.008 n=5+5)
puffs_flate_decode_10k/clang    171MB/s ± 1%   167MB/s ± 2%   -2.86%  (p=0.008 n=5+5)
puffs_flate_decode_100k/clang   202MB/s ± 0%   193MB/s ± 2%   -4.64%  (p=0.016 n=4+5)
puffs_zlib_decode_10k/clang     159MB/s ± 1%   157MB/s ± 0%   -1.65%  (p=0.008 n=5+5)
puffs_zlib_decode_100k/clang    185MB/s ± 1%   180MB/s ± 1%   -3.11%  (p=0.008 n=5+5)

puffs_adler32_10k/gcc          3.26GB/s ± 0%  3.26GB/s ± 0%     ~     (p=0.421 n=5+5)
puffs_adler32_100k/gcc         3.27GB/s ± 0%  3.26GB/s ± 0%     ~     (p=0.151 n=5+5)
puffs_flate_decode_1k/gcc       132MB/s ± 0%   129MB/s ± 0%   -2.29%  (p=0.008 n=5+5)
puffs_flate_decode_10k/gcc      170MB/s ± 0%   164MB/s ± 0%   -3.13%  (p=0.008 n=5+5)
puffs_flate_decode_100k/gcc     207MB/s ± 0%   185MB/s ± 0%  -10.45%  (p=0.016 n=5+4)
puffs_zlib_decode_10k/gcc       162MB/s ± 0%   157MB/s ± 0%   -2.95%  (p=0.008 n=5+5)
puffs_zlib_decode_100k/gcc      194MB/s ± 0%   175MB/s ± 0%   -9.78%  (p=0.016 n=5+4)
2017-11-05 08:03:21 +11:00
Nigel Tao cf61ca11c3 Run the adler benchmarks for longer.
A future commit could set each benchmark's iteration count (call it N)
dynamically, but for now, the iteration counts are hard-coded. The rough
guiding principle is those N iterations should take more or less one
second, on my modern desktop CPU.

Prior to this commit, the adler benchmarks ran for the same N as the
zlib benchmarks. Each zlib decode involves exactly one adler checksum
computation, so both having the same N makes it very easy to calculate a
rough estimate of what fraction of zlib decoding is spent in adler code.
But in having the same N, the adler benchmarks run for a tiny fraction
of a second (and would run for an even tinier fraction if we further
optimize the adler code, e.g. with SIMD).

This commit raises that N for the adler benchmarks (but not for the zlib
benchmarks), which should hopefully make the adler numbers a little more
reliable. It will make that very easy calculation slightly less easy,
but it'd still be trivial.

The benchmark numbers do change. I'm not entirely sure why, but keep in
mind that this commit only changes the benchmark harness code, not the
actual std/flate code running in that harness.

name                           old speed      new speed      delta

puffs_adler32_10k/clang        2.45GB/s ± 0%  2.40GB/s ± 1%  -2.00%  (p=0.008 n=5+5)
puffs_adler32_100k/clang       2.44GB/s ± 0%  2.40GB/s ± 1%  -1.67%  (p=0.008 n=5+5)
puffs_flate_decode_1k/clang     133MB/s ± 0%   131MB/s ± 1%  -1.37%  (p=0.008 n=5+5)
puffs_flate_decode_10k/clang    174MB/s ± 0%   171MB/s ± 1%  -1.66%  (p=0.008 n=5+5)
puffs_flate_decode_100k/clang   205MB/s ± 0%   202MB/s ± 0%  -1.28%  (p=0.016 n=5+4)
puffs_zlib_decode_10k/clang     162MB/s ± 0%   159MB/s ± 1%  -1.94%  (p=0.008 n=5+5)
puffs_zlib_decode_100k/clang    188MB/s ± 0%   185MB/s ± 1%  -1.60%  (p=0.008 n=5+5)

puffs_adler32_10k/gcc          3.25GB/s ± 0%  3.26GB/s ± 0%  +0.25%  (p=0.016 n=4+5)
puffs_adler32_100k/gcc         3.25GB/s ± 0%  3.27GB/s ± 0%  +0.39%  (p=0.008 n=5+5)
puffs_flate_decode_1k/gcc       132MB/s ± 0%   132MB/s ± 0%    ~     (p=0.151 n=5+5)
puffs_flate_decode_10k/gcc      170MB/s ± 0%   170MB/s ± 0%    ~     (p=0.738 n=5+5)
puffs_flate_decode_100k/gcc     207MB/s ± 0%   207MB/s ± 0%    ~     (p=0.841 n=5+5)
puffs_zlib_decode_10k/gcc       161MB/s ± 1%   162MB/s ± 0%    ~     (p=0.841 n=5+5)
puffs_zlib_decode_100k/gcc      194MB/s ± 0%   194MB/s ± 0%    ~     (p=0.841 n=5+5)
2017-11-05 07:16:04 +11:00
Nigel Tao fe5e9c68b3 Remove a superfluous while loop.
It's not obvious why the adler benchmark numbers also change (for the
better), but it seems superficially repeatable for fresh before/after
measurements. I'll take it for now, but perhaps the adler benchmarks
need to run for longer.

name                           old speed      new speed      delta

puffs_adler32_10k/clang        2.38GB/s ± 2%  2.45GB/s ± 0%  +2.87%  (p=0.008 n=5+5)
puffs_adler32_100k/clang       2.39GB/s ± 1%  2.44GB/s ± 0%  +2.42%  (p=0.008 n=5+5)
puffs_flate_decode_1k/clang     129MB/s ± 2%   133MB/s ± 0%  +3.41%  (p=0.008 n=5+5)
puffs_flate_decode_10k/clang    161MB/s ± 1%   174MB/s ± 0%  +8.46%  (p=0.008 n=5+5)
puffs_flate_decode_100k/clang   187MB/s ± 3%   205MB/s ± 0%  +9.51%  (p=0.008 n=5+5)
puffs_zlib_decode_10k/clang     150MB/s ± 1%   162MB/s ± 0%  +8.09%  (p=0.008 n=5+5)
puffs_zlib_decode_100k/clang    174MB/s ± 1%   188MB/s ± 0%  +8.13%  (p=0.008 n=5+5)

puffs_adler32_10k/gcc          3.12GB/s ± 3%  3.25GB/s ± 0%  +4.30%  (p=0.016 n=5+4)
puffs_adler32_100k/gcc         3.12GB/s ± 3%  3.25GB/s ± 0%  +4.15%  (p=0.008 n=5+5)
puffs_flate_decode_1k/gcc       128MB/s ± 3%   132MB/s ± 0%  +3.11%  (p=0.008 n=5+5)
puffs_flate_decode_10k/gcc      172MB/s ± 4%   170MB/s ± 0%    ~     (p=0.151 n=5+5)
puffs_flate_decode_100k/gcc     196MB/s ± 2%   207MB/s ± 0%  +5.46%  (p=0.008 n=5+5)
puffs_zlib_decode_10k/gcc       164MB/s ± 1%   161MB/s ± 1%  -1.34%  (p=0.008 n=5+5)
puffs_zlib_decode_100k/gcc      186MB/s ± 0%   194MB/s ± 0%  +4.12%  (p=0.016 n=4+5)
2017-11-05 06:57:10 +11:00
Nigel Tao f968950345 Read bits up front in decode_huffman_fast.
name                           old speed      new speed       delta

puffs_adler32_10k/clang        2.36GB/s ± 4%   2.38GB/s ± 2%     ~     (p=1.000 n=5+5)
puffs_adler32_100k/clang       2.39GB/s ± 4%   2.39GB/s ± 1%     ~     (p=0.841 n=5+5)
puffs_flate_decode_1k/clang     121MB/s ± 1%    129MB/s ± 2%   +5.95%  (p=0.008 n=5+5)
puffs_flate_decode_10k/clang    138MB/s ± 3%    161MB/s ± 1%  +16.52%  (p=0.008 n=5+5)
puffs_flate_decode_100k/clang   163MB/s ± 4%    187MB/s ± 3%  +14.50%  (p=0.008 n=5+5)
puffs_zlib_decode_10k/clang     132MB/s ± 2%    150MB/s ± 1%  +13.92%  (p=0.008 n=5+5)
puffs_zlib_decode_100k/clang    152MB/s ± 6%    174MB/s ± 1%  +14.60%  (p=0.008 n=5+5)

puffs_adler32_10k/gcc          3.25GB/s ± 0%   3.12GB/s ± 3%   -4.06%  (p=0.008 n=5+5)
puffs_adler32_100k/gcc         3.25GB/s ± 0%   3.12GB/s ± 3%   -3.99%  (p=0.008 n=5+5)
puffs_flate_decode_1k/gcc      95.1MB/s ± 0%  127.7MB/s ± 3%  +34.25%  (p=0.008 n=5+5)
puffs_flate_decode_10k/gcc      110MB/s ± 0%    172MB/s ± 4%  +55.66%  (p=0.008 n=5+5)
puffs_flate_decode_100k/gcc     121MB/s ± 0%    196MB/s ± 2%  +61.45%  (p=0.008 n=5+5)
puffs_zlib_decode_10k/gcc       112MB/s ± 0%    164MB/s ± 1%  +46.14%  (p=0.008 n=5+5)
puffs_zlib_decode_100k/gcc      123MB/s ± 0%    186MB/s ± 0%  +51.22%  (p=0.016 n=5+4)
2017-11-04 17:37:54 +11:00
Nigel Tao 36a93fa6b7 Add a TODO about impure functions. 2017-11-04 16:04:28 +11:00
Nigel Tao 1c7a6792de Tweak the decode_huffman_fast loop condition. 2017-11-04 15:19:40 +11:00
Nigel Tao 8fafcbcb31 Tweak the flate end_of_block check. 2017-11-04 14:54:56 +11:00
Nigel Tao aa1f0078db Add decode_huffman_fast.
It's not fast yet, and the immediate impact is indeed a significant
performance loss, but follow-up commits should make it faster.

name                           old speed      new speed      delta

puffs_adler32_10k/clang        2.41GB/s ± 0%  2.40GB/s ± 1%     ~     (p=0.222 n=5+5)
puffs_adler32_100k/clang       2.41GB/s ± 1%  2.39GB/s ± 1%   -0.97%  (p=0.016 n=5+5)
puffs_flate_decode_1k/clang     116MB/s ± 5%   115MB/s ± 0%     ~     (p=0.310 n=5+5)
puffs_flate_decode_10k/clang    145MB/s ± 0%   139MB/s ± 0%   -4.18%  (p=0.016 n=4+5)
puffs_flate_decode_100k/clang   164MB/s ± 5%   158MB/s ± 1%     ~     (p=0.151 n=5+5)
puffs_zlib_decode_10k/clang     135MB/s ± 2%   131MB/s ± 0%   -2.84%  (p=0.008 n=5+5)
puffs_zlib_decode_100k/clang    154MB/s ± 1%   148MB/s ± 2%   -4.09%  (p=0.016 n=4+5)

puffs_adler32_10k/gcc          3.13GB/s ± 4%  3.19GB/s ± 0%   +1.94%  (p=0.032 n=5+5)
puffs_adler32_100k/gcc         3.14GB/s ± 3%  3.20GB/s ± 3%     ~     (p=0.056 n=5+5)
puffs_flate_decode_1k/gcc       122MB/s ± 1%    94MB/s ± 1%  -22.84%  (p=0.008 n=5+5)
puffs_flate_decode_10k/gcc      143MB/s ± 0%   110MB/s ± 0%  -23.24%  (p=0.008 n=5+5)
puffs_flate_decode_100k/gcc     158MB/s ± 0%   118MB/s ± 0%  -24.98%  (p=0.008 n=5+5)
puffs_zlib_decode_10k/gcc       136MB/s ± 0%   119MB/s ± 1%  -12.63%  (p=0.008 n=5+5)
puffs_zlib_decode_100k/gcc      150MB/s ± 1%   124MB/s ± 2%  -17.17%  (p=0.008 n=5+5)
2017-11-04 14:45:11 +11:00
Nigel Tao c550ad9bda Add redundant but clearer continue/break labels. 2017-11-04 14:14:07 +11:00
Nigel Tao ded044da41 Add a flate end_of_block field. 2017-11-04 14:12:38 +11:00
Nigel Tao 4810db3994 Rename decode_huffman to decode_huffman_slow. 2017-11-04 13:38:24 +11:00
Nigel Tao c3420dd138 Refactor std/flate/*.puffs code. 2017-11-04 13:31:39 +11:00
Nigel Tao a36535ec6d Generate "static" for private functions. 2017-11-04 11:43:48 +11:00
Nigel Tao 9ebcd54d43 Discuss "puffs bench" in doc/benchmarks.md. 2017-11-04 11:33:49 +11:00
Nigel Tao a0fd42f6d4 Add a puffs/cmd/commonflags package. 2017-11-04 11:09:14 +11:00
Nigel Tao 66047db6d8 Be more paranoid about calling strncmp. 2017-11-04 10:49:23 +11:00
Nigel Tao 6602dea7be Make focus's "/gcc" suffix optional. 2017-11-04 10:40:43 +11:00
Nigel Tao 4729170678 Make focus's "Benchmark" prefix optional. 2017-11-04 10:25:24 +11:00
Nigel Tao 0230a65c7b Let focus have a trailing comma. 2017-11-04 10:21:32 +11:00
Nigel Tao c62aa518a5 Make focus's "test_" or "bench_" prefix optional. 2017-11-04 10:05:37 +11:00
Nigel Tao 7e654ba652 Note that -focus specifies a prefix. 2017-11-04 09:55:42 +11:00
Nigel Tao 1487da7af8 Add a -focus flag. 2017-11-03 17:54:29 +11:00
Nigel Tao e3643574d7 Fix script/inline-c-relative-includes.go. 2017-11-03 15:33:23 +11:00
Nigel Tao aec5715f12 Declare proc_filename exactly once. 2017-11-03 15:09:22 +11:00
Nigel Tao e57c8d77db Add script/inline-c-relative-includes.go. 2017-11-03 15:05:19 +11:00