Commit Graph
38 Commits
Author SHA1 Message Date
Nigel Tao 744b5fcc31 Add puffs_base__writer1__copy_from_history32__bco. 2017-11-09 14:02:10 +11:00
Nigel Tao 82e5734778 Fix puffs_base__writer1__copy_from_history32. 2017-11-09 13:35:45 +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 eefe590e04 Remove unreachable coroutine suspension code. 2017-11-03 11:57:07 +11:00
Nigel Tao 7f47f19d4a Don't hard-code the printf signature. 2017-11-03 11:14:05 +11:00
Nigel Tao e3822f9951 Re-introduce puffs_base__limit1.
It's not immediately obvious why this data structure performs differently, but
on net, the benchmark numbers seem better. It also won't require any
PUFFS_USE_NO_OP_PERFORMANCE_HACKS or "redundant but mysteriously performant"
use_limit fields.

name                             old speed      new speed      delta

puffs_adler32_10k/clang          2.46GB/s ± 0%  2.43GB/s ± 3%     ~     (p=0.513 n=5+10)
puffs_adler32_100k/clang         2.46GB/s ± 0%  2.44GB/s ± 2%     ~     (p=0.241 n=5+10)
puffs_flate_decode_1k/clang       122MB/s ± 1%   119MB/s ± 2%   -1.86%  (p=0.013 n=5+10)
puffs_flate_decode_10k/clang      147MB/s ± 0%   142MB/s ± 2%   -3.47%  (p=0.001 n=5+10)
puffs_flate_decode_100k/clang     161MB/s ± 0%   161MB/s ± 4%     ~     (p=0.635 n=4+10)
puffs_zlib_decode_10k/clang       139MB/s ± 0%   135MB/s ± 1%   -2.69%  (p=0.001 n=5+10)
puffs_zlib_decode_100k/clang      151MB/s ± 0%   152MB/s ± 3%     ~     (p=1.000 n=5+10)

puffs_adler32_10k/gcc            3.21GB/s ± 1%  3.18GB/s ± 2%     ~     (p=0.310 n=5+10)
puffs_adler32_100k/gcc           3.22GB/s ± 0%  3.19GB/s ± 2%     ~     (p=0.075 n=5+10)
puffs_flate_decode_1k/gcc         121MB/s ± 4%   126MB/s ± 1%   +4.54%  (p=0.002 n=5+8)
puffs_flate_decode_10k/gcc        144MB/s ± 1%   141MB/s ± 1%   -2.52%  (p=0.001 n=5+9)
puffs_flate_decode_100k/gcc       154MB/s ± 1%   158MB/s ± 0%   +2.39%  (p=0.001 n=5+9)
puffs_zlib_decode_10k/gcc         137MB/s ± 2%   135MB/s ± 1%     ~     (p=0.055 n=5+10)
puffs_zlib_decode_100k/gcc        146MB/s ± 2%   150MB/s ± 0%   +2.87%  (p=0.001 n=5+10)

puffs_gif_lzw_decode_20k/clang    132MB/s ± 0%   125MB/s ± 0%   -5.24%  (p=0.001 n=5+10)
puffs_gif_lzw_decode_100k/clang   176MB/s ± 0%   164MB/s ± 0%   -6.82%  (p=0.001 n=5+9)
puffs_gif_decode_1k/clang         363MB/s ± 0%   339MB/s ± 1%   -6.58%  (p=0.002 n=4+10)
puffs_gif_decode_10k/clang        138MB/s ± 0%   133MB/s ± 1%   -3.77%  (p=0.001 n=5+10)
puffs_gif_decode_100k/clang       125MB/s ± 0%   119MB/s ± 0%   -4.79%  (p=0.001 n=5+10)
puffs_gif_decode_1000k/clang      127MB/s ± 0%   121MB/s ± 0%   -5.04%  (p=0.001 n=5+10)

puffs_gif_lzw_decode_20k/gcc      141MB/s ± 0%   140MB/s ± 2%     ~     (p=1.000 n=5+10)
puffs_gif_lzw_decode_100k/gcc     182MB/s ± 0%   180MB/s ± 2%   -1.56%  (p=0.001 n=5+10)
puffs_gif_decode_1k/gcc           363MB/s ± 0%   409MB/s ± 3%  +12.71%  (p=0.001 n=5+10)
puffs_gif_decode_10k/gcc          127MB/s ± 0%   161MB/s ± 3%  +26.15%  (p=0.001 n=5+10)
puffs_gif_decode_100k/gcc         112MB/s ± 0%   136MB/s ± 2%  +21.95%  (p=0.001 n=5+10)
puffs_gif_decode_1000k/gcc        114MB/s ± 0%   140MB/s ± 2%  +22.78%  (p=0.001 n=5+10)
2017-11-03 10:09:57 +11:00
Nigel Tao e5db8233fc Re-introduce writer1.use_limit.
Nobody uses it yet, as we only decode and not encode, but it's there for
symmetry.

No benchmark changes, as nobody uses it yet.
2017-11-02 16:46:03 +11:00
Nigel Tao 7d8085f891 Re-introduce reader1.use_limit.
The std/flate benchmarks get better. The std/gif benchmarks get worse,
but that's possibly because the PUFFS_USE_NO_OP_PERFORMANCE_HACKS hacks
are fragile.

name                             old speed      new speed      delta

puffs_adler32_10k/clang          2.45GB/s ± 0%  2.45GB/s ± 0%     ~     (p=0.310 n=5+5)
puffs_adler32_100k/clang         2.46GB/s ± 0%  2.46GB/s ± 0%     ~     (p=0.690 n=5+5)
puffs_flate_decode_1k/clang       113MB/s ± 0%   113MB/s ± 0%     ~     (p=0.690 n=5+5)
puffs_flate_decode_10k/clang      140MB/s ± 0%   140MB/s ± 0%     ~     (p=0.222 n=5+5)
puffs_flate_decode_100k/clang     151MB/s ± 0%   151MB/s ± 0%     ~     (p=0.095 n=5+5)
puffs_zlib_decode_10k/clang       132MB/s ± 1%   132MB/s ± 0%     ~     (p=0.548 n=5+5)
puffs_zlib_decode_100k/clang      143MB/s ± 0%   143MB/s ± 0%     ~     (p=0.730 n=5+4)

puffs_adler32_10k/gcc            3.26GB/s ± 0%  3.26GB/s ± 0%     ~     (p=0.548 n=5+5)
puffs_adler32_100k/gcc           3.27GB/s ± 0%  3.27GB/s ± 0%     ~     (p=0.841 n=5+5)
puffs_flate_decode_1k/gcc         108MB/s ± 0%   125MB/s ± 0%  +14.97%  (p=0.008 n=5+5)
puffs_flate_decode_10k/gcc        128MB/s ± 0%   148MB/s ± 0%  +15.48%  (p=0.016 n=4+5)
puffs_flate_decode_100k/gcc       136MB/s ± 0%   158MB/s ± 0%  +16.40%  (p=0.008 n=5+5)
puffs_zlib_decode_10k/gcc         123MB/s ± 0%   141MB/s ± 0%  +14.70%  (p=0.016 n=4+5)
puffs_zlib_decode_100k/gcc        131MB/s ± 0%   151MB/s ± 0%  +15.60%  (p=0.016 n=5+4)

puffs_gif_lzw_decode_20k/clang    131MB/s ± 1%   128MB/s ± 3%   -2.04%  (p=0.032 n=5+5)
puffs_gif_lzw_decode_100k/clang   172MB/s ± 1%   173MB/s ± 1%     ~     (p=0.151 n=5+5)
puffs_gif_decode_1k/clang         351MB/s ± 3%   341MB/s ± 5%     ~     (p=0.310 n=5+5)
puffs_gif_decode_10k/clang        138MB/s ± 1%   134MB/s ± 3%   -3.34%  (p=0.008 n=5+5)
puffs_gif_decode_100k/clang       122MB/s ± 2%   122MB/s ± 2%     ~     (p=1.000 n=5+5)
puffs_gif_decode_1000k/clang      126MB/s ± 1%   122MB/s ± 4%   -3.07%  (p=0.016 n=5+5)

puffs_gif_lzw_decode_20k/gcc      140MB/s ± 3%   140MB/s ± 3%     ~     (p=0.421 n=5+5)
puffs_gif_lzw_decode_100k/gcc     187MB/s ± 2%   184MB/s ± 1%     ~     (p=0.056 n=5+5)
puffs_gif_decode_1k/gcc           401MB/s ± 1%   357MB/s ± 1%  -10.88%  (p=0.008 n=5+5)
puffs_gif_decode_10k/gcc          154MB/s ± 1%   126MB/s ± 1%  -18.42%  (p=0.008 n=5+5)
puffs_gif_decode_100k/gcc         131MB/s ± 2%   109MB/s ± 0%  -17.37%  (p=0.008 n=5+5)
puffs_gif_decode_1000k/gcc        135MB/s ± 1%   111MB/s ± 1%  -17.65%  (p=0.008 n=5+5)
2017-11-02 16:35:15 +11:00
Nigel Tao aa396e7992 Change cgen's limit from a count to a pointer. 2017-10-27 10:28:35 +11:00
Nigel Tao 8ff453c752 Re-do how limits work. 2017-10-26 16:59:03 +11:00
Nigel Tao a9ba7e85ac Add reader1.limitt and writer1.limitt methods.
The "limitt" typo will be renamed to "limit" once we remove the keyword
named "limit".
2017-10-26 15:06:59 +11:00
Nigel Tao 9550f37359 Remove codegen referencing b_wstart_dst. 2017-10-26 12:54:15 +11:00
Nigel Tao 474a0d2ed7 Make mark a method, not a keyword. 2017-10-26 12:31:27 +11:00
Nigel Tao f29c4e278f Follow the pkg__type__method convention for base. 2017-10-21 15:59:08 +11:00
Nigel Tao 709d34f8e2 Move some #define's into base-impl.h. 2017-10-21 15:16:55 +11:00
Nigel Tao c99fdaf63d Actually copy from the flate decoder's history. 2017-10-13 14:50:34 +11:00
Nigel Tao a33f744da5 Drop the "?" from "writer1.copy_from_slice?". 2017-10-13 11:44:53 +11:00
Nigel Tao 587be36759 Re-order cgen/base-impl.h methods for consistency. 2017-10-13 11:06:14 +11:00
Nigel Tao 2335024d43 Rename cgen/base-impl.h methods for consistency. 2017-10-13 11:04:36 +11:00
Nigel Tao d4372cb5b8 Change license to Apache 2.
Also remove explicit PATENTS file. The new LICENSE file already
discusses patents.

Note that the Puffs project has not yet been publicly released.
2017-10-12 11:17:41 +11:00
Nigel Tao a12292d094 Have "return ok" set coro_susp_point = 0. 2017-10-07 14:43:25 +11:00
Nigel Tao 585ea2024d Drop the "?" from "copy_from32?".
Also add a PUFFS_COROUTINE_SUSPENSION_POINT_MAYBE_SUSPEND macro.

Also add a loop to decoder.decode, as the code generator was previously
(incorrectly) not generating a coro_susp_point at the end of the
function.
2017-10-07 14:34:31 +11:00
Nigel Tao 2e883fcc23 Drop the "?" from "copy_history32?".
This makes the caller, not the implementation, responsible for detecting
short reads and writes. This (the lack of "?") is consistent with the
slice.copy_from method.

name                           old speed     new speed     delta
puffs_flate_decode_1k/clang    117MB/s ± 6%  120MB/s ± 0%   +2.31%  (p=0.016 n=5+5)
puffs_flate_decode_10k/clang   153MB/s ± 1%  155MB/s ± 0%   +1.16%  (p=0.008 n=5+5)
puffs_flate_decode_100k/clang  168MB/s ± 1%  177MB/s ± 0%   +5.41%  (p=0.008 n=5+5)
puffs_flate_decode_1k/gcc      127MB/s ± 1%  143MB/s ± 0%  +12.15%  (p=0.008 n=5+5)
puffs_flate_decode_10k/gcc     145MB/s ± 0%  180MB/s ± 1%  +24.00%  (p=0.008 n=5+5)
puffs_flate_decode_100k/gcc    163MB/s ± 0%  212MB/s ± 1%  +29.90%  (p=0.008 n=5+5)
2017-10-06 17:02:09 +11:00
Nigel Tao 9b6a1760cd Rename puffs_base_make_slice_u8_subslice_ij. 2017-10-02 14:33:45 +11:00
Nigel Tao 6c53fde1da Remove unused puffs_base_make_slice_u8_from_ints. 2017-10-02 14:31:32 +11:00
Nigel Tao 6f132a74e2 Remove the 'mark' concept, no longer necessary. 2017-10-02 14:02:13 +11:00
Nigel Tao 3b57548b0d Generate C code for a non-trivial slice-of-slice. 2017-09-29 17:07:41 +10:00
Nigel Tao f1643be221 Have copy_from return the number of bytes copied. 2017-09-28 17:27:34 +10:00
Nigel Tao a9bdeee7c1 Generate C code for a[i:j] with explicit i or j. 2017-09-28 15:57:25 +10:00
Nigel Tao d5c8e20268 Have writer1.slice take mark arguments. 2017-09-23 13:57:48 +10:00
Nigel Tao 7aaa6f6222 Remove obsolete optimization TODO.
Modern compilers already optimize functions like puffs_base_load_u32le:
https://godbolt.org/g/uZ9xNa (clang)
https://godbolt.org/g/q5amWw (gcc)
2017-09-23 11:03:51 +10:00
Nigel Tao 1a28112ebd In copy_from, don't call memmove with NULLs. 2017-09-23 11:00:23 +10:00
Nigel Tao f107ec155d Rename puffs_u16be to puffs_base_load_u16be. 2017-09-23 09:29:45 +10:00
Nigel Tao ed8a91ef51 Add an array.copy_from method. 2017-09-22 16:32:11 +10:00
Nigel Tao b14bafa717 Make puffs_u16be etc functions, not macros. 2017-09-22 14:41:08 +10:00
Nigel Tao 2fb9972bb9 Add a slice.suffix method. 2017-09-22 14:12:54 +10:00
Nigel Tao fda696bf95 Add PUFFS_IGNORE_POTENTIALLY_UNUSED_VARIABLE. 2017-09-22 12:00:14 +10:00
Nigel Tao fdddcc8e1d Merge multiple puffs-xxx-c binaries into one. 2017-08-24 09:43:57 +10:00