mattsu2020:base32_performance_check - Branch - uutils/coreutils

base(nc|32|64): Optimize performances reduction memset

#9632Merged

Comparing

mattsu2020:base32_performance_check

(

27b72b4

) with

main

(

2000af8

)

+3%

Improvements: 2

Untouched: 125

Skipped: 6

Benchmarks

Skipped (6)

Improved

b64_decode_synthetic

src/uu/base64/benches/base64_bench.rs

+3%

169.8 µs164.6 µs

b64_decode_ignore_garbage_synthetic

src/uu/base64/benches/base64_bench.rs

+3%

169.7 µs164.6 µs

Passed

sort_ascii_only[500000]

src/uu/sort/benches/sort_bench.rs

+1%

356.8 ms354.3 ms

cksum_crc32b

src/uu/cksum/benches/cksum_bench.rs

+1%

13.8 ms13.8 ms

cksum_multiple_files

src/uu/cksum/benches/cksum_bench.rs

26.2 ms26.1 ms

cksum_default

src/uu/cksum/benches/cksum_bench.rs

17.5 ms17.4 ms

cksum_crc

src/uu/cksum/benches/cksum_bench.rs

17.5 ms17.4 ms

cksum_raw_output

src/uu/cksum/benches/cksum_bench.rs

17.5 ms17.5 ms

cp_large_file[16]

src/uu/cp/benches/cp_bench.rs

357.9 µs356.8 µs

du_wide_tree[(5000, 500)]

src/uu/du/benches/du_bench.rs

11.3 ms11.3 ms

cp_preserve_metadata[(5, 4, 10)]

src/uu/cp/benches/cp_bench.rs

75.1 ms74.9 ms

b64_encode_synthetic

src/uu/base64/benches/base64_bench.rs

162.4 µs162.1 µs

sort_numeric[500000]

src/uu/sort/benches/sort_bench.rs

1.2 s1.2 s

tsort_input_parsing_heavy[5000]

src/uu/tsort/benches/tsort_bench.rs

84 ms83.9 ms

mv_multiple_to_dir

src/uu/mv/benches/mv_bench.rs

12.9 ms12.9 ms

du_all_wide_tree[(5000, 500)]

src/uu/du/benches/du_bench.rs

18.2 ms18.2 ms

sort_mixed_data[500000]

src/uu/sort/benches/sort_bench.rs

327.9 ms327.7 ms

sort_long_line[160000]

src/uu/sort/benches/sort_bench.rs

1.7 ms1.7 ms

split_bytes

src/uu/split/benches/split_bench.rs

508.9 µs508.6 µs

du_max_depth_balanced_tree[(6, 4, 10)]

src/uu/du/benches/du_bench.rs

33.1 ms33 ms

shuf_lines[100000]

src/uu/shuf/benches/shuf_bench.rs

26.9 ms26.9 ms

mv_force_overwrite

src/uu/mv/benches/mv_bench.rs

137.9 ms137.9 ms

cksum_blake2b

src/uu/cksum/benches/cksum_bench.rs

192.7 ms192.7 ms

cksum_md5

src/uu/cksum/benches/cksum_bench.rs

317.9 ms317.9 ms

factor_multiple_u64s[2]

src/uu/factor/benches/factor_bench.rs

213 ms213 ms

seq_large_integers

src/uu/seq/benches/seq_bench.rs

2.2 ms2.2 ms

ls_recursive_deep_tree[(200, 2)]

src/uu/ls/benches/ls_bench.rs

2.2 ms2.2 ms

sort_mixed_utf8_locale

src/uu/sort/benches/sort_locale_bench.rs

38.9 ms38.9 ms

rm_single_file

src/uu/rm/benches/rm_bench.rs

119.3 ms119.3 ms

cp_recursive_balanced_tree[(5, 4, 10)]

src/uu/cp/benches/cp_bench.rs

72.4 ms72.4 ms

sort_unique_locale[500000]

src/uu/sort/benches/sort_bench.rs

494.5 ms494.4 ms

mv_single_file

src/uu/mv/benches/mv_bench.rs

135.5 ms135.5 ms

ls_recursive_long_all_deep_tree[(100, 4)]

src/uu/ls/benches/ls_bench.rs

3.3 ms3.3 ms

cksum_sha1

src/uu/cksum/benches/cksum_bench.rs

723.1 ms723 ms

rm_force_files

src/uu/rm/benches/rm_bench.rs

2 ms2 ms

split_numeric_suffix

src/uu/split/benches/split_bench.rs

5.9 ms5.9 ms

tsort_complex_dag[50000]

src/uu/tsort/benches/tsort_bench.rs

84.1 ms84.1 ms

rm_multiple_files

src/uu/rm/benches/rm_bench.rs

2.2 ms2.2 ms

sort_dictionary_order[500000]

src/uu/sort/benches/sort_bench.rs

1.1 s1.1 s

sort_german_locale

src/uu/sort/benches/sort_locale_bench.rs

39.1 ms39.1 ms

cksum_sm3

src/uu/cksum/benches/cksum_bench.rs

1.6 s1.6 s

sort_ascii_c_locale

src/uu/sort/benches/sort_locale_bench.rs

22.6 ms22.6 ms

sort_mixed_c_locale

src/uu/sort/benches/sort_locale_bench.rs

38.3 ms38.3 ms

uniq_case_insensitive[10000]

src/uu/uniq/benches/uniq_bench.rs

1.8 ms1.8 ms

seq_with_step

src/uu/seq/benches/seq_bench.rs

13.3 ms13.3 ms

wc_bytes_synthetic[500]

src/uu/wc/benches/wc_bench.rs

180 µs180 µs

cut_bytes

src/uu/cut/benches/cut_bench.rs

8.4 ms8.4 ms

tsort_wide_dag[100000]

src/uu/tsort/benches/tsort_bench.rs

133.5 ms133.5 ms

seq_integers

src/uu/seq/benches/seq_bench.rs

26.1 ms26.1 ms

mv_directory

src/uu/mv/benches/mv_bench.rs

3.5 ms3.5 ms

rm_recursive_tree

src/uu/rm/benches/rm_bench.rs

13.5 ms13.5 ms

seq_custom_separator

src/uu/seq/benches/seq_bench.rs

28.7 ms28.7 ms

numfmt_to_iec[10000]

src/uu/numfmt/benches/numfmt_bench.rs

33.8 ms33.8 ms

numfmt_to_si_precision[10000]

src/uu/numfmt/benches/numfmt_bench.rs

35.3 ms35.3 ms

numfmt_to_si[10000]

src/uu/numfmt/benches/numfmt_bench.rs

33.8 ms33.8 ms

hashsum_sha512

src/uu/hashsum/benches/hashsum_bench.rs

110.8 ms110.8 ms

sort_ascii_utf8_locale

src/uu/sort/benches/sort_locale_bench.rs

43.3 ms43.3 ms

numfmt_round_modes[("towards-zero", 10000)]

src/uu/numfmt/benches/numfmt_bench.rs

34.3 ms34.3 ms

cut_fields_tab

src/uu/cut/benches/cut_bench.rs

34.1 ms34.1 ms

seq_formatted

src/uu/seq/benches/seq_bench.rs

96.1 ms96.1 ms

numfmt_round_modes[("up", 10000)]

src/uu/numfmt/benches/numfmt_bench.rs

34.3 ms34.3 ms

sort_key_field[500000]

src/uu/sort/benches/sort_bench.rs

704.4 ms704.3 ms

numfmt_round_modes[("down", 10000)]

src/uu/numfmt/benches/numfmt_bench.rs

34.3 ms34.3 ms

fold_custom_width[50000]

src/uu/fold/benches/fold_bench.rs

33 ms33 ms

uniq_with_count[10000]

src/uu/uniq/benches/uniq_bench.rs

1.9 ms1.9 ms

sort_accented_data[500000]

src/uu/sort/benches/sort_bench.rs

363.1 ms363.1 ms

cut_fields_custom_delim

src/uu/cut/benches/cut_bench.rs

40.8 ms40.8 ms

nl_many_lines[100000]

src/uu/nl/benches/nl_bench.rs

44.9 ms44.9 ms

fold_many_lines[100000]

src/uu/fold/benches/fold_bench.rs

80.4 ms80.4 ms

sort_reverse_locale[500000]

src/uu/sort/benches/sort_bench.rs

362.1 ms362.1 ms

nl_large_file[10]

src/uu/nl/benches/nl_bench.rs

57.1 ms57.1 ms

wc_bytes_lines_synthetic[2000]

src/uu/wc/benches/wc_bench.rs

120.2 ms120.2 ms

wc_default_large_line_count[100000]

src/uu/wc/benches/wc_bench.rs

50.4 ms50.4 ms

expand_many_lines[100000]

src/uu/expand/benches/expand_bench.rs

148.6 ms148.6 ms

wc_words_large_line_count[100000]

src/uu/wc/benches/wc_bench.rs

48 ms48 ms

cksum_shake256

src/uu/cksum/benches/cksum_bench.rs

1.9 s1.9 s

cksum_shake128

src/uu/cksum/benches/cksum_bench.rs

1.5 s1.5 s

wc_words_synthetic[2000]

src/uu/wc/benches/wc_bench.rs

11.4 s11.4 s

cksum_sha256

src/uu/cksum/benches/cksum_bench.rs

1.7 s1.7 s

cksum_sha384

src/uu/cksum/benches/cksum_bench.rs

1.1 s1.1 s

cksum_sha2

src/uu/cksum/benches/cksum_bench.rs

1.7 s1.7 s

unexpand_large_file[10]

src/uu/unexpand/benches/unexpand_bench.rs

562.8 ms562.8 ms

cksum_sha224

src/uu/cksum/benches/cksum_bench.rs

1.7 s1.7 s

cksum_sha512

src/uu/cksum/benches/cksum_bench.rs

1.1 s1.1 s

unexpand_many_lines[100000]

src/uu/unexpand/benches/unexpand_bench.rs

268.4 ms268.4 ms

numfmt_large_numbers_si[10000]

src/uu/numfmt/benches/numfmt_bench.rs

32.5 ms32.5 ms

hashsum_sha1

src/uu/hashsum/benches/hashsum_bench.rs

72.5 ms72.5 ms

wc_lines_large_line_count[500000]

src/uu/wc/benches/wc_bench.rs

2.9 ms2.9 ms

numfmt_from_si[10000]

src/uu/numfmt/benches/numfmt_bench.rs

32.7 ms32.7 ms

hashsum_md5_check

src/uu/hashsum/benches/hashsum_bench.rs

32 ms32 ms

hashsum_sha256_check

src/uu/hashsum/benches/hashsum_bench.rs

173 ms173 ms

cksum_bsd

src/uu/cksum/benches/cksum_bench.rs

128.4 ms128.4 ms

expand_custom_tabstops[50000]

src/uu/expand/benches/expand_bench.rs

36.8 ms36.8 ms

cksum_sysv

src/uu/cksum/benches/cksum_bench.rs

48.3 ms48.3 ms

numfmt_padding[(10000, 50)]

src/uu/numfmt/benches/numfmt_bench.rs

48 ms48 ms

split_lines

src/uu/split/benches/split_bench.rs

5.7 ms5.7 ms

ls_recursive_mixed_tree

src/uu/ls/benches/ls_bench.rs

1.5 ms1.5 ms

ls_recursive_wide_tree[(10000, 1000)]

src/uu/ls/benches/ls_bench.rs

52.9 ms52.9 ms

cut_characters

src/uu/cut/benches/cut_bench.rs

7.4 ms7.4 ms

uniq_heavy_duplicates[10000]

src/uu/uniq/benches/uniq_bench.rs

2 ms2 ms

wc_lines_variable_length[(50, 500)]

src/uu/wc/benches/wc_bench.rs

3.4 ms3.4 ms

cksum_sha3

src/uu/cksum/benches/cksum_bench.rs

1.8 s1.8 s

ls_recursive_long_all_balanced_tree[(6, 4, 15)]

src/uu/ls/benches/ls_bench.rs

134.5 ms134.5 ms

ls_recursive_long_all_wide_tree[(15000, 1500)]

src/uu/ls/benches/ls_bench.rs

143.3 ms143.3 ms

sort_case_insensitive[500000]

src/uu/sort/benches/sort_bench.rs

277.1 ms277.1 ms

wc_lines_extreme_line_lengths[(100000, 200)]

src/uu/wc/benches/wc_bench.rs

1.6 ms1.6 ms

sort_case_sensitive[500000]

src/uu/sort/benches/sort_bench.rs

174.4 ms174.4 ms

tsort_linear_chain[1000000]

src/uu/tsort/benches/tsort_bench.rs

1.5 s1.5 s

sort_unique_mixed

src/uu/sort/benches/sort_locale_bench.rs

39.2 ms39.2 ms

wc_chars_large_line_count[100000]

src/uu/wc/benches/wc_bench.rs

1 ms1 ms

sort_numeric

src/uu/sort/benches/sort_locale_bench.rs

23.5 ms23.5 ms

ls_recursive_balanced_tree[(6, 4, 15)]

src/uu/ls/benches/ls_bench.rs

56 ms56 ms

hashsum_sha256

src/uu/hashsum/benches/hashsum_bench.rs

172.9 ms173 ms

shuf_repeat_sampling[50000]

src/uu/shuf/benches/shuf_bench.rs

4.6 ms4.6 ms

ls_recursive_long_all_mixed_tree

src/uu/ls/benches/ls_bench.rs

2.9 ms2.9 ms

sort_reverse_mixed

src/uu/sort/benches/sort_locale_bench.rs

38.9 ms38.9 ms

du_summarize_balanced_tree[(5, 4, 10)]

src/uu/du/benches/du_bench.rs

8.5 ms8.5 ms

shuf_input_range[1000000]

src/uu/shuf/benches/shuf_bench.rs

229.1 ms229.1 ms

cksum_blake3

src/uu/cksum/benches/cksum_bench.rs

206.3 µs206.3 µs

hashsum_md5

src/uu/hashsum/benches/hashsum_bench.rs

32 ms32 ms

split_number_chunks

src/uu/split/benches/split_bench.rs

286 µs286.1 µs

tsort_tree_dag[(10, 3)]

src/uu/tsort/benches/tsort_bench.rs

34.1 ms34.1 ms

cp_recursive_deep_tree[(120, 4)]

src/uu/cp/benches/cp_bench.rs

13.6 ms13.7 ms

cp_archive_balanced_tree[(5, 4, 10)]

src/uu/cp/benches/cp_bench.rs

77.8 ms77.9 ms

sort_german_c_locale

src/uu/sort/benches/sort_locale_bench.rs

38.5 ms38.5 ms

du_deep_tree[(100, 3)]

src/uu/du/benches/du_bench.rs

1.2 ms1.2 ms

cp_recursive_wide_tree[(6000, 800)]

src/uu/cp/benches/cp_bench.rs

189.6 ms189.8 ms

Commits

Click on a commit to change the comparison range

Base

main

2000af8

-2.31%

refactor(base32): reorder std imports in base_common.rs for consistency Moved the `slice` import from after `collections::VecDeque` to after `num::NonZeroUsize` to better align with the module's import grouping style.

5db1fe0

17 days ago

by mattsu2020

+5.16%

Merge branch 'main' into base32_performance_check

21d325e

16 days ago

by mattsu2020

-2.86%

refactor(base32): remove unsafe buffer handling in encode/decode Replace unsafe spare_capacity_mut and from_raw_parts_mut usage with safe Vec initialization and direct read calls in fast_encode and fast_decode. This eliminates potential safety risks while preserving buffer functionality.

dbeacf7

15 days ago

by mattsu2020

+3.15%

perf(base32): optimize input handling by switching to BufRead for efficient buffering Switch from unbuffered Read to BufRead in get_input, handle_input, and fast_encode_stream functions. This reduces syscalls by leveraging buffered reads, improving performance for base32 encoding/decoding operations. Refactor fast_encode_stream to use fill_buf() and manage leftover buffers more efficiently.

27b72b4

11 days ago

by mattsu2020

Home Terms Privacy Docs