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)
This commit is contained in:
Nigel Tao committed 2017-11-05 15:59:02 +11:00
1 parent 6621526a2c
commit 13731f989f
7 files changed
+38 -16

No files matched your search

+9 -11
View File
@@ -877,18 +877,17 @@ proc tests[] = {
test_puffs_flate_decode_flate_backref_crosses_blocks, //
test_puffs_flate_decode_midsummer, //
test_puffs_flate_decode_pi, //
// TODO: uncomment.
//test_puffs_flate_decode_pi_many_big_reads, //
//test_puffs_flate_decode_pi_many_medium_reads, //
//test_puffs_flate_decode_pi_many_small_writes_reads, //
//test_puffs_flate_decode_romeo, //
//test_puffs_flate_decode_romeo_fixed, //
test_puffs_flate_decode_pi_many_big_reads, //
test_puffs_flate_decode_pi_many_medium_reads, //
test_puffs_flate_decode_pi_many_small_writes_reads, //
test_puffs_flate_decode_romeo, //
test_puffs_flate_decode_romeo_fixed, //
test_puffs_flate_decode_split_src, //
test_puffs_flate_history_full, //
test_puffs_flate_history_partial, //
test_puffs_flate_table_redirect, //
//test_puffs_zlib_checksum_mismatch, //
//test_puffs_zlib_decode_midsummer, //
test_puffs_zlib_checksum_mismatch, //
test_puffs_zlib_decode_midsummer, //
test_puffs_zlib_decode_pi, //
#ifdef PUFFS_MIMIC
@@ -915,11 +914,10 @@ proc benches[] = {
// Flate Benches
bench_puffs_adler32_10k, //
bench_puffs_adler32_100k, //
// TODO: uncomment.
//bench_puffs_flate_decode_1k, //
bench_puffs_flate_decode_1k, //
bench_puffs_flate_decode_10k, //
bench_puffs_flate_decode_100k, //
//bench_puffs_zlib_decode_10k, //
bench_puffs_zlib_decode_10k, //
bench_puffs_zlib_decode_100k, //
#ifdef PUFFS_MIMIC