Summary of the multiple file compression benchmark tests


File type : Multiple file types (46 in total)
# of files to compress in this test : 510
Total File Size (bytes) : 316.355.757
Average File Size (bytes) : 620,305
Largest File (bytes) : 18,403,071
Smallest File (bytes) : 3,554

This test is designed to model 'real-world' performance of lossless data compressors. The test set contains a mix of different file types which are chosen with 'What do people use archivers for the most' in mind. The testset should contain data, weighted (in both type and proportion of files in the set) by how often these files are used for compression by normal users using compression software. So for example there will be more txt files then .ocx files in the set (yes, this is arbitrary). The set contains 100's of files and has a total size of over 300 Mb. The idea of a large collection is filtering out the 'noise'. A compressor might perform bad on 1 or 2 filetypes, but on a very large collection it will not hurt as much.

Some programs like CCM and BZIP2 can only compress one file at a time. For these programs a single TAR-file is created containing all files. The files in this TAR-file are ordered alphabetically on suffix, then name. Results of these compressors are marked with an 'Y' in the tarred column.

The testset consists of the following file types :

Filetype(s) Description % of total # of files
TOC, MBXEudora mailboxes12.31 16
EXE, DLL, OCX, DRVExecutables10.99 35
TXT, RTF, DIC, LNGText files in several languages10.21 41
BMP, TIFFBitmaps/TIF images7.88 15
LOGLog files6.34 6
HTM, PHPHTML files6.13 19
DOCMS Word files6.08 30
C, CPP, PAS, DCUSource Code6.00 235
MDB, CSVDatabases4.26 7
HLPWindows Help files4.23 7
CBF, CBGPrecompressed chess-databases3.55 2
WAVWave soundfiles3.45 9
XLSXLS Spreadsheets2.41 16
PDFAdobe Acrobat document1.59 6
TTFTrue Type Fonts1.15 15
DEFVirus definition files1.10 3
JPG, GIFImage files0.53 9
CHMPrecompressed help files0.49 2
INI, INFINI files0.42 10
OthersDAT,JAR,M3D,SYS,PPT,MAP,WP,RLL,RIB..10.88 27

Considering the fact it's supposed to be a 'real-world' test I will not look at the best possible (command-line or gui) switch combination to use for optimal compression, but only test a limited set as 'normal users' would do. For 7-zip this means for example I will use the GUI and select the Ultra compression method (which can be easily beaten with some good command line switches), WinRar will be tested with max dictionary size and solid archiving etc. Programs are allowed to use a maximum of 800 Mb memory and must finish the compression stage within 12h. Compressed size must be 50% or less compared to the original size to be listed on MFC.

For my single file tests I got lots of requests to add the compression time to the tables. I did not do this for the reasons stated in the single file summary file, but I'm planning to measure compression times for this multiple file test!. I also decided to make this testset 'non public', so it's harder for developers to tune their program towards this specific test. I think this is the most fair way to get 'real life' performance tests.

Scoring system: The program yielding the lowest compressed size is considered the best program. The most efficient (read:use full) program is calculated by multiplying the compression + decompression time (in seconds) it took to produce the archive with the power of the archive size divided by the lowest measured archive size. The lower score the better. The basic idea is a compressor X has the same efficiency as compressor Y if X can compress twice as fast as Y and resulting archive size of X is 10% larger than size of Y. (Special thanks to Uwe Herklotz to get this formula right)


score_X = POWER(2; ((size_X / size_TOP) - 1) / 0,1) * time_X

with  score_X     efficiency score for a certain compressor X
      time_X      time elapsed by compressor X (comp + decomp time)
      size_X      archive size achieved with compressor X
      size_TOP    archive size by top archiver (smallest benchmark result)
Formula to calculate compressor efficiency based on compressed size and compression time
"0,1" represents 10% and power of 2 ensures that for each 10% worse results (compared
with top) the time is doubled, so any archiver (except top compressor) will get a
penalty on time. The score of top compressor is always equal to its time value.


Results sorted on Compression ratio.

Pos Program Switches used TAR Q6600 Compressed Compression Comp time Decomp time Efficiency
  Size (bytes) Ratio (%) (sec) (sec) lower is better
001PAQ8px-7NY6244373880.26
23427
2201945446
002PAQ8P-7NY6268317280.19
17976
1665335562
003WinRK 3.1.2MaximumNY6429424379.68
14265
1398534692
004PAQ8JC-6 (dir /oen)NN6619113979.08
18908
1621253237
005PAQAR 4.5-7e (dir /oen/b)NN6843571578.37
21322
2141083103
006WinRK 3.1.2HighNY6900345878.19
1311
9804745
007PAsQDa 4.4-7eNN6910918778.15
21101
2117388594
008NanoZip 0.06a-cc -m800mNY7007465377.85
438
4081974
009UDA 0.301(none)YY7147876777.41
3369
341218487
010DURILCA 0.5-m800 -t1NY7217557877.19
738
6574109
011Slim 0.23d-m800 -o64NY7366468376.71
1574
152910783
012WinUDA 0.291mode-3NY7373557476.69
3663
369125756
013Slim 0.23d(none)NY7378197276.68
1555
148610706
014KGB 1.1 (PAQ6)(very good)NY7534137576.18
7830
788965796
015NanoZip 0.06a-cONY7597190275.99
264
571441
016ZPAQ 1.00max.cfgNY7629285875.88
2578
257723981
017CCMx 1.30c6YY7707994975.64
130
1261300
018DURILCA 0.5(none)NY7760445375.47
947
95110213
019PPMonstr J-m800 -o32NY7769968675.44
587
5936417
020CCM 1.30c6YY7792692275.37
107
1031171
021UHARC 0.6b-mx -md32768 -mm+NY7834487675.24
278
2342991
022PPMonstr J(none)NY7844386275.20
568
5736739
023FreeARC 0.51-mxNY7850397575.18
92.9
38.7783
024CCM 1.30c(none)YY7859898075.15
102
981202
025NanoZip 0.06a(none)NY7867513475.13
113
35.2898
026LPAQ88YN7870418675.12
508
5116195
027WinRK 3.1.2NormalNY7888289075.07
157
33.51181
028FreeARC 0.51(none)NY7935336074.92
65.4
33.8648
029PIMPLE2(none)YN7962815774.83
2195
220729654
030WinUDA 0.291mode-0NY7971066974.80
1178
118016031
031COMPRESSIA 1.0bmax sol dict 15 MbNN8069834074.49
803
99999764699
032DURILCA light 0.5-m800 -t1NY8166647474.19
155
761951
033EPM r9-m800YN8193490974.10
963
97016822
034CMM4 0.2b26YN8243545873.94
250
2564655
035EPM r9(none)YN8272785273.85
898
90717153
036Ocamyd 1.66 test1-m8 -s0YN8288038573.80
4666
466490177
037BIT 0.7(none)YY8332188873.66
305
2986121
038SQUEEZ 5.61Ultra 32Mb M E SolidNY8356300273.59
181
30.22202
039Quark 0.95r-l7 -d25YN8367356773.55
2095
3822513
040FreeARC 0.51-m3NY8369625273.54
33.8
19.2561
041RZM 0.07h(none)YN8403037473.44
230
192734
042SBC 0.970 rev3-m3 -b62NY8473617673.21
102
401686
043Quark 0.95r(none)YN8474131473.21
702
378782
044Ultra7z Opt 0.05(none)NY8493233573.15
406
40.25416
045UHARC 0.6b(none)NY8495450673.15
209
332945
046SBC 0.970 rev3-b9NY8574026572.90
60
331235
047StuffIt 12.0Method=2 L3 E25 bm=onNN8589206272.85
144
322376
048ASH 07-m800 -o60YY8622563272.74
3641
3639102003
049SBC 0.970 rev3(none)NY8624528872.74
57
331264
050WINZIP 12Optimize for best comp.NY8627792072.73
95
31.71786
051WinRAR 3.80Best solid 4096KbNY8666954172.60
58
28.11267
052KGB 1.1 (PAQ6)(normal)NY8687845872.54
1133
115734498
0537-Zip 4.65Ultra LZMA 64MbNY8722410872.43
92
14.61669
054SQUEEZ 5.61Max 8Mb M E SolidNY8769330272.28
155
20.12888
055ENC 0.15abies -d256NN8795559072.20
3498
999991757147
056COMPRESSIA 1.0bsol dict 15 MbNN8815278472.13
86
622568
057CTXf 0.75-meNN8835799272.07
83
642610
0587-Zip 4.65Norm LZMA 16Mb ws=32NY8847047772.03
74
13.41571
059WinACE 2.69Max 4096Kb solid ace20NY8848521572.03
108
12.32166
060ACE 2.6-m5 -d4096NY8848603172.03
109
12.92195
061TC 5.2 dev2(none)YN8946477871.72
429
43117264
062PIM 2.90Best + filtersNY8963993971.66
299
907962
063WinACE 2.69Norm solid ace20NY8974271571.63
74
12.31787
064ENC 0.15-d256NN8975052871.63
1440
999992101919
065DGCA 1.10(none)NN8983430471.60
83
342447
066CTXf 0.75(none)NN9003888471.54
66
482439
067777 0.04b1-mg -mu32NN9022947771.48
1067
59136231
068WinRAR 3.80Normal solid 4096KbNY9040331571.42
46.2
9.61243
069777 0.04b1(none)NN9054438271.38
1215
63341820
070WinRK 3.1.2FastestNY9082141171.29
30.9
23.71274
071LZPX(J) 1.2h-8YN9145135971.09
119
1185931
072NanoZip 0.06a-cDNY9192475970.94
24.4
10.7926
073WinRAR 3.80NormalNY9199533170.92
39.4
9.81308
074Bee 0.7.9 bld 0316-m3 -d8 -sNN9200398070.92
654
65834912
075LZPX(J) 1.2h(none)YN9207518370.90
110
1115927
076LZTurbo 0.94-59YY9309774470.57
210
10.96637
077Bee 0.7.9 bld 0316-m2 -d8NN9310349170.57
362
36821947
078FreeARC 0.51-m2NY9319405670.54
12.7
11.9747
079UFA 0.04b1-mg -mx -mu32NN9342829270.47
521
13820540
080DST 0.91b-meYN9356834770.42
243
18313486
081SQUEEZ 5.61Norm 4Mb M E SolidNY9408262270.26
54.1
19.82477
082UFA 0.04b1(none)NN9417563870.23
350
4213275
083ACB 2.00cuNN9505528969.95
1056
110780761
084BOA 0.58b-m15 -sNN9508046869.95
773
78658372
085BMA 1.35b-m16m -ax -mxNN9528441869.88
101
616204
086PPMN 1.00b1 km-O9 -M:50 -DAYN9551381769.81
263
26420704
087LZPM 0.16(none)YY9552505169.80
448
20.818441
088BSSC 0.95a(none)YN9581121869.71
52
253127
089StuffIt 12.0Method=5 E26 bm=onNN9606913969.63
55
614847
090PPMVC 1.2-o16 -m256NN9652507169.49
128
14712087
091PPMd var J rev.1-m256 -o16NY9673751569.42
73
806885
092DURILCA light 0.5(none)NY9682356569.39
71
806861
093BOA 0.58b(none)NN9685751569.38
596
62055457
094BIX 1.00 b7-mdG -sNY9707914169.31
152
11.57642
095PPMVC 1.2(none)NN9715252069.29
82
1018624
096WINIMP 1.211 BEST MM 16Mb B=1020KbNY9723772769.26
72.3
14.14110
097GRZipII 0.2.4-b8m -aYN9748413669.19
48
434449
0987-Zip 4.65Max PPMD 64Mb ws=16NY9757374469.16
89
1049530
099CABARC 1.00.0106-m LZX:21NY9769144469.12
187
13.410026
100StuffIt 12.0Method=3 E25 bm=onNN9801753869.02
93
507418
101Blizzard 0.24b(none)YN9829628268.93
60
525992
102MNZIP(none)YN9848804568.87
111
287597
103QC 0.050-8YN9851093368.86
720
22551780
104BMA 1.35b(none)NN9872890068.79
54
405277
105WinHKI 1.74HKI2 maxNN9877107568.78
123
12614043
106EPC 1.0-m256 -o18YN9879715968.77
150
999995664733
107QC 0.050(none)YN9905504468.69
259
9920838
108BALZ 1.15exYY9912375368.67
108
21.37584
109UHARC 0.6b-mz -md32768 -mm+NY9925115768.63
28.6
363843
110FlashZIP 0.94-m2 -s7YY9941430168.58
257
14.916470
111DC 0.99.307b-b4096NY9954659068.53
107
999996153492
112WINIMP 1.211 Normal MM 4Mb B=600KbNY9963886268.50
34.2
14.13000
113BIX 1.00 b7(none)NY9969443268.49
101
11.77042
114BioArc 1.9UltraNN9969905868.49
66
768878
115BA 1.01(none)YN9987309868.43
59
406310
116M03(none)YN9993465168.41
1356
221101205
117Tornado 0.4a-11YY9995983868.40
87
8.16120
118BioArc 1.9NormalNN10001277768.39
64
748933
119WinHKI 1.74HKI2 normNN10020800668.32
91
9412238
120UHBC 1.0-b4m -m3YN10062322068.19
180
15623276
121DARK 0.51-b128mNN10078545068.14
61
397053
122DARK 0.51(none)NN10087706268.11
60
386983
123BruteCM 0.1d(none)YN10090260068.10
107
16019078
124UHBC 1.0(none)YN10099006268.08
143
11718760
125JAR 1.02(none)NN10116907168.02
37
93386
126PPMN 1.00b1 km(none)YN10118137068.02
196
19929112
127QLFC 6.6wBS=8388608NN10121754468.01
693
3353722
128EPC 1.0(none)YN10125866667.99
83
9112934
129DC 0.99.307b(none)NY10131422467.97
101
999997487039
130PPMX 0.05(none)YY10139764367.95
191
20029517
131GRZipII 0.2.4(none)YN10168637067.86
48
457249
132M99 2.2.1-m 512mYN10174666267.84
86
7912948
133ZZIP 0.36c-mx -a -6mNN10239264367.63
1598
41138179
134BCM 0.07(none)YY10241645467.63
103
8515892
135PPMd var J rev.1(none)NY10274352567.52
49
569204
136FlashZIP 0.94-m1 -s1YY10293732367.46
16.8
15.42884
137QLFC 6.6w(none)NN10293827667.46
343
3033410
138BWMonstr 0.01(none)YY10307340767.42
6010
3372853058
139WinTurtle 1.60SolidNN10312967267.40
31
335856
140CABARC 1.00.0106-m LZX:17NY10314825667.39
89
13.29370
141DACT 0.8.41-b1000000YN10317608867.39
283
1727590
142DACT 0.8.41(none)YN10337871867.32
286
1928688
143DST 0.91b(none)YN10338637667.32
113
4815156
144WinTurtle 1.60(none)NN10356765867.26
28
305571
145ABC 2.4(none)YN10366974467.23
465
7852751
146ZZIP 0.36c(none)NN10384540467.17
706
4173998
147Bicom 1.01(none)YN10394051367.14
826
838166586
148M1 0.3b-1text2.txtYY10437767667.01
75
7916184
149PACKET 0.90b-m4 -s9YN10452402466.96
302
1133432
150QazaR 0.0 pre5-d9 -l7YN10486710566.85
358
10251040
151YBS 0.03f(none)YN10507408366.79
57
309878
152ASD 0.2.0-m5 -mdgNN10510974066.77
2425
163294995
153RZIP 2.1-9YN10530541866.71
65
2610600
154RZIP 2.1(none)YN10541772366.68
56
259554
155UC II 3.05(max compress)NY10562549666.61
157
10.520218
156Tornado 0.4a(none)YY10574292266.57
13.9
8.12690
157SZIP 1.12-b41 -o40YN10579318366.56
373
7755336
158RINGS 1.5c5YN10580070366.56
31
317630
159CHILE 0.3d(none)YN10607254266.47
345
6351752
160CHILE 0.3d-b=2048YN10616556466.44
423
6562542
161BBB ver1m512YN10636476166.38
12294
5111677772
162UC II 3.05-TTNY10637088066.38
73
11.111027
163WinHKI 1.74HKI1 maxNN10639121866.37
64
1810776
164SZIP 1.12(none)YN10656717966.31
55
3011390
165ShipInBottle 1.0 b17alg:ppm :mem:128NN10674242266.26
1620
1635444745
166QUAD 1.12xYN10696829166.19
71
2413310
167AI 1.1-mtNN10736515166.06
27097
377369492408
168YBS 0.03f-m16mYN10746234666.03
73
3716280
169HA 0.999ba21NN10763741465.98
373
14177566
170BZIP2 1.0.5(none)YN10772092365.95
56
1610966
171HOOK 1.4800YY10778894265.93
128
12438673
172QazaR 0.0 pre5(none)YN10816597965.81
63
4517283
173QUAD 1.12(none)YN10821543465.79
44
2410942
174M99 2.2.1(none)YN10829487665.77
53
3113636
175ASD 0.2.0(none)NN10910136065.51
158
5637992
176KZIP 14-APR-2007(none)NY11069493265.01
1778
11.3379128
177TarsaLZP 21Aug2007(none)YN11099461464.91
39
4718839
178SEMONE 0.6 b2(none)YN11144268664.77
81
1421871
179BZP 0.3(none)NN11148580264.76
16
177634
180WINZIP 12Enhanced DeflateNY11150329064.75
48.4
9.713466
181LHARK 0.4d-tobNY11187091564.64
59
11.116924
182THOR 0.96e5YY11227511264.51
12.6
6.24747
183SLUG X(none)YY11228638364.51
4.4
6.92857
184MAR-gNN11255478664.42
100
727871
185TURTLE 0.07(none)YN11264674964.39
37
3518947
186LHARK 0.4d(none)NY11343906364.14
26.5
10.110517
187LZ2A-Cb12 -Szd26YN11358889764.09
138
1945869
188LZTurbo 0.94-43YY11390755763.99
5.9
9.34601
189PKZIP 2.50-exxNY11402234763.96
19.8
12.49871
190ShipInBottle 1.0 b17alg:lzNN11405109163.95
481
22154691
191LZXQ 0.4normalYN11449298763.81
71
10857817
192PKZIP 2.50(none)NY11450126363.81
16
11.78955
193AMG 2.2(Max Compression)NN11466275863.76
97
9999932945907
194VuZip 1.8MaxNN11467960863.75
37
714509
195DZip 2.90-9NY11468849063.75
44.5
11.718551
196EAZEL 1.0(best)NN11472837063.73
41
816246
197CODEC 3.21(none)NN11476727563.72
27
2015650
198GZIP 1.2.4-9YY11485797763.69
35.1
9.915136
199ESP 1.92(none)NY11516457763.60
22.3
11.111623
200AIN 2.32-m1NY11517808263.59
22.6
13.212477
201VuZip 1.8DefaultNN11526112963.57
19
79145
202DZip 2.90(none)NY11526988263.56
18.4
10.610211
203LZ2A(none)YN11529898363.55
120
2049452
204File2Pack 2.0(none)NY11530590163.55
16.3
10.29368
205EAZEL 1.0(normal)NN11530976263.55
20
79549
206GZIP 1.2.4(none)YY11544296463.51
15.5
10.29224
207AIN 2.32(none)NY11558711563.46
17.7
10.510285
208 BCArchive 1.08.7(none)NN11582112463.39
19
1412352
209ARJ32 3.15(none)NY11610726563.30
25.8
10.614064
210ARJ 2.85(none)NY11610961263.30
35
10.217469
211WinXP (Built-in Zip)(none)NY11632401163.23
15.1
18.613338
212aPLib 0.43(none)NN11759676262.83
253
7118523
213SR3a(none)YN11818319962.64
23
2623839
214ALZip 7.0b1(normal)NN11849287762.54
17
812588
215HPACK 0.79a(none)NN12070201461.85
377
31262535
216SAR 1.0(none)NN12206742361.41
94
1178621
217SYMBRA 0.2-m5YN12212055861.40
1110
6701340701
218AR 1.0(none)YN12214734261.39
96
1180833
219DeepFreezer 1.06(none)NN12335035161.01
20
925038
220Chaos Comp 3.0(none)NN12368156060.90
31
834932
221Ocamyd 1.66 test1(none)YN12426269060.72
203
202386932
222THOR 0.96e3YY12458865660.62
3.8
6.310005
223WINZIP 12SuperFastNY12527905760.40
9.6
8.118930
224LCSSR 0.2-l9 -b6YN12637878760.05
2918
27856891230
225HYPER 2.5(none)NN12843987059.40
24
1559241
226LZOP 1.02rc1-9YY12960173359.03
64
6120966
227LZTurbo 0.94-22YY13277338158.03
3.6
6.524819
228ARX 1.0(none)NN13346419957.81
35
11122047
229QuickLZ 1.40b9mode3NY13397390957.65
10.1
13.666541
230CTW 0.1(none)YN13468738057.43
2661
285116751159
231Secura Archiver 1.7(none)NN13987634855.79
131
6740640
232CA-ZIP 3.4(none)YY14024776255.67
32.4
7.5224784
233AI 1.1(none)NN14025973555.66
3523
584652852078
234QPress 0.35b-L3YY14119460755.37
4.3
8.881980
235QPress 0.35b-L2YY14807067253.19
3.6
8.2158417
236LZC 0.082YN14965190952.70
16
8384025
237BriefLZ 1.04(none)NY15161187652.08
5.2
7.9260559
238THOR 0.96e1YY15193695451.97
3.1
6.3193836
239LZW 0.2(none)YN15328952051.55
251
96229951
240LZOP 1.02rc1-1YY15499381451.01
6
5.8341629
241LZOP 1.02rc1(none)YY15538908950.88
5.7
6.5369052
242QuickLZ 1.40b9mode1NY15684000650.42
2.7
15.9660978
243BigCrunch 0.4a1(none)NN15750260050.21
546
147677338794
244CODER 1.1-ew 4194304NN15878862149.81
330
10819323559
245SRANK 1.0(none)YY16411092948.12
7.3
7.81202732
246WinXP (NTFS)(none)NY19082252939.68
5.4
7.419775154
247TESTSETNY3163557570.00
0
00


Green Compression Ratio (larger bar is better)   Red Compression Time (shorter bar is better)   Blue Efficiency Ratio (larger bar is better)

Remarks:
Ten programs so far crashed during compressing:
- Emilcont 0.3a
- RKC 1.02
- PPMZ2 0.81
- HIPP 0.5819
- OrangeArchiver 1.05
- PPMT 1.0
- HIP beta1
- LZ 1.0
- HuffComp 1.3
- Chile 0.5

- Some programs fail to correctly decompressing the archive created. Those programs are marked with a red penalty time of 99999 seconds. Do *not* use these programs to backup your data!.

- (De)compression time of ACB 2.00c is an approximation as ACB only runs under Win98 (which is installed on the 1800+ machine only). Measured time on the 1800+ is devided by the approximate ratio of compression speed on both machines.

- The command-line version of Squeez 5 seems to get different compression then the GUI version. The switch combination '-m5 -MD32768 -uxx9 -ME -MM -s' gets it down to 83.384.794 bytes...

- Stuffit 12.0 contains recompression techniques for several file types like JPG, GIF, BMP and PDF. For the MFC test I disabled PDF recompression as it appears to be "pixel perfect" rather then "bit-perfect" for most PDF files. This hurts compression a bit, but prevents the decompressed file to be slightly different than the original. This would be fine for normal users, but this is a lossless compression test. It would be unfair towards the lossless "bit perfect" compressors to include these result.

Conclusions and observations:
- Top performers (based on compression) in this test are PAQ8 and WinRK (PWCM). They are able to compress the 300+ Mb testset to under 62 Mb (80% reduction in size) but take a minimum of 8,5 hour to complete the test. The number one program (PAQ8P) takes almost 12 hours and number four (PAQAR) even 17 hours to complete the test. WinRK, the program with the 2nd best compression (79.7%) takes about 8,5 hours. Not surprisingly all mentioned programs make use of a PAQ(-like) engine for compression. If you have files with embedded images (e.g. Word DOC files) use PAQ8, it will recognize them and separately compress them, boosting compression significantly. All mentioned programs (except the current number 2, WinRK) are free of charge.

- WinRAR but especially NanoZip, FreeARC, SBC 0.970 and CCM score very well on efficiency, they have good compression and are reasonably fast. FreeARC and NanoZIP are capable of compressing the testset down to 79 Mb in under 3 minutes. CCM takes just under 5 minutes. SBC compresses to about 85 MB but only needs 2 minutes for that. People looking for good (but not ultimate) and fast compression should have a look at those programs. Of the mentioned programs NanoZIP and CCM have the best compression, SBC and FReeARC are the fastest (FreeARC being both faster and the better compressor). Best 'super' compressor with a not to dramatic compression time is NanoZip, compressing then MFC testset to under 69 MB in 18 minutes using CM-mode.

- The speed-kings in this test are THOR, QuickLZ, SLUG and LZOP, the first two compress the total testset of 300+ MB in under 3.4 seconds (which generates a total data stream of 300 MB input + 150 MB output / 3.5 sec = 128 MB/s). At this speed IO/harddisk performance has a large impact on the compression speed, when compression from-to memory probably even higher compression speeds are possible. As a consequence of this speed compression ratio is not very high (barely 50%). Other fast compressors, with a bit better compression, are the oldies Pkzip, Arj and Gzip. If you are looking for a fast compressor with still good compression, consider UHARC 0.6b using LZP-mode (-mz) or FreeARC in m1 or m2 mode.

- Decompression speeds are usually a lot faster then compression speeds except for the compressors using a PPM or PAQ-engine. Decompression times of 5-7 seconds seem to be the systems (IO/hardisk) limit; compressing to ramdisk (or /dev/null) should probably be even faster...

- Normally I would expect 7-Zip to outperform WinRAR, but in this case I suspect WinRAR beats 7-Zip because there are (embedded) multimedia files (wav,bmp etc) which can be handled by WinRAR's multimedia filter. 7-Zip still lacks such a filter. I included multimedia files because many games are distributed in compressed form (games typically have lots of bmp and wav-like files).

- The higher the fraction of pre-compressed files the smaller the difference between the top and the other compressors. Because the testset contains files like chm,gif,jpeg the difference between the compressors looks rather small. I will probably make a 2nd testset with easy to compress non-multimedia data later on. Home

©2003-2009 MaximumCompression (lossless data compression software benchmarks)
email