Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings.

To run this test with the Phoronix Test Suite, the basic command is: phoronix-test-suite benchmark compress-zstd.

Project Site

facebook.github.io

Source Repository

github.com

Test Created

24 May 2018

Last Updated

10 February 2023

Test Maintainer

Michael Larabel 

Test Type

Processor

Average Install Time

1 Minute, 47 Seconds

Average Run Time

15 Minutes, 11 Seconds

Test Dependencies

C/C++ Compiler Toolchain

Accolades

100k+ Downloads + 5k+ Public Benchmark Results

Supported Platforms


Reported Installs **Public Result Uploads *Reported Test Completions **Test Profile Page Views ***OpenBenchmarking.orgEventsZstd Compression Popularity Statisticspts/compress-zstd2018.042018.062018.082018.102018.122019.022019.042019.062019.082019.102019.122020.022020.042020.062020.082020.102020.122021.022021.042021.062021.082021.102021.122022.022022.042022.062022.082022.102022.122023.022023.042023.062023.082023.102023.122024.0220K40K60K80K100K
* Uploading of benchmark result data to OpenBenchmarking.org is always optional (opt-in) via the Phoronix Test Suite for users wishing to share their results publicly.
** Data based on those opting to upload their test results to OpenBenchmarking.org and users enabling the opt-in anonymous statistics reporting while running benchmarks from an Internet-connected platform.
*** Test profile page view reporting began March 2021.
Data updated weekly as of 25 March 2024.
1214.9%19, Long Mode16.9%1917.6%8, Long Mode13.4%813.3%312.6%3, Long Mode11.4%Compression Level Option PopularityOpenBenchmarking.org

Revision History

pts/compress-zstd-1.6.0   [View Source]   Fri, 10 Feb 2023 07:59:36 GMT
Update against Zstandard 1.5.4 upstream.

pts/compress-zstd-1.5.0   [View Source]   Fri, 14 May 2021 13:28:48 GMT
Update against upstream Zstd 1.5.

pts/compress-zstd-1.3.0   [View Source]   Wed, 03 Mar 2021 16:48:52 GMT
Update against upstream Zstd 1.4.9, expose decompression speed, switch to FreeBSD img as input test, also add long mode options.

pts/compress-zstd-1.2.1   [View Source]   Fri, 04 Sep 2020 18:26:12 GMT
Zstd output parser fix per https://github.com/phoronix-test-suite/phoronix-test-suite/pull/467

pts/compress-zstd-1.2.0   [View Source]   Fri, 22 May 2020 07:18:54 GMT
Update against Zstd 1.4.5, transition to MB/s reporting with -b interface.

pts/compress-zstd-1.1.3   [View Source]   Fri, 03 Apr 2020 16:24:17 GMT
Update patch per https://github.com/phoronix-test-suite/test-profiles/issues/132

pts/compress-zstd-1.1.2   [View Source]   Mon, 02 Mar 2020 07:34:12 GMT
Build fix for some platforms via https://github.com/phoronix-test-suite/test-profiles/pull/128

pts/compress-zstd-1.1.1   [View Source]   Thu, 17 Jan 2019 10:59:33 GMT
Add Windows support.

pts/compress-zstd-1.1.0   [View Source]   Thu, 08 Nov 2018 20:33:01 GMT
Enforce threading for Zstd

pts/compress-zstd-1.0.0   [View Source]   Thu, 24 May 2018 10:22:41 GMT
Initial commit of a basic Zstandard compression benchmark.

Suites Using This Test

Compression Tests

C/C++ Compiler Tests

Multi-Core

CPU Massive

Server CPU Tests

Programmer / Developer System Benchmarks


Performance Metrics

Analyze Test Configuration:

Zstd Compression 1.4.5

Compression Level: 3

OpenBenchmarking.org metrics for this test profile configuration based on 1,239 public results since 22 May 2020 with the latest data as of 11 March 2023.

Below is an overview of the generalized performance for components where there is sufficient statistically significant data based upon user-uploaded results. It is important to keep in mind particularly in the Linux/open-source space there can be vastly different OS configurations, with this overview intended to offer just general guidance as to the performance expectations.

Component
Percentile Rank
# Compatible Public Results
MB/s (Average)
100th
8
8621 +/- 873
99th
7
8489 +/- 7
97th
13
8413 +/- 56
94th
32
8248 +/- 164
93rd
7
8200 +/- 19
93rd
7
8192 +/- 194
92nd
11
8075 +/- 198
91st
11
8011 +/- 87
91st
9
8001 +/- 146
91st
9
7940 +/- 160
89th
6
7841 +/- 56
89th
5
7791 +/- 52
88th
11
7747 +/- 951
84th
7
6652 +/- 37
83rd
11
6430 +/- 163
83rd
5
6360 +/- 126
81st
11
6102 +/- 461
79th
37
5836 +/- 503
77th
6
5181 +/- 42
Mid-Tier
75th
< 5088
75th
9
5036 +/- 70
73rd
5
4950 +/- 32
72nd
46
4910 +/- 408
71st
20
4822 +/- 94
71st
12
4818 +/- 578
70th
6
4797 +/- 37
66th
4
4528 +/- 38
63rd
20
4453 +/- 166
63rd
4
4402 +/- 120
62nd
6
4357 +/- 12
61st
9
4234 +/- 257
61st
3
4230 +/- 426
60th
12
4121 +/- 601
60th
13
4101 +/- 147
57th
10
3919 +/- 495
56th
28
3861 +/- 360
56th
10
3845 +/- 285
56th
6
3786 +/- 80
54th
13
3691 +/- 42
54th
7
3665 +/- 28
52nd
5
3577 +/- 36
52nd
4
3557 +/- 52
Median
50th
3489
50th
4
3383 +/- 8
49th
4
3333 +/- 20
49th
4
3300 +/- 5
47th
3
3121 +/- 167
46th
6
3058 +/- 422
45th
9
2995 +/- 41
45th
5
2970 +/- 20
43rd
4
2898 +/- 55
41st
6
2869 +/- 164
41st
6
2857 +/- 37
39th
41
2775 +/- 165
38th
4
2763 +/- 10
38th
3
2755 +/- 5
38th
3
2709 +/- 2
36th
4
2642 +/- 7
33rd
16
2540 +/- 77
33rd
4
2536 +/- 15
33rd
4
2502 +/- 7
32nd
27
2428 +/- 105
30th
6
2386 +/- 5
29th
10
2361 +/- 96
29th
6
2360 +/- 164
28th
4
2292 +/- 9
27th
3
2271 +/- 1
26th
6
2247 +/- 10
26th
3
2240 +/- 12
26th
3
2230 +/- 2
Low-Tier
25th
< 2161
25th
3
2146 +/- 13
25th
6
2096 +/- 142
23rd
7
1916 +/- 23
23rd
4
1902 +/- 90
22nd
3
1889 +/- 24
21st
4
1805 +/- 20
19th
3
1742 +/- 2
19th
11
1739 +/- 48
19th
5
1717 +/- 143
19th
8
1694 +/- 26
18th
3
1680 +/- 14
17th
6
1609 +/- 2
15th
5
1436 +/- 8
14th
9
1305 +/- 11
13th
4
1254 +/- 19
11th
3
674 +/- 8
7th
19
101 +/- 9
OpenBenchmarking.orgDistribution Of Public Results - Compression Level: 31239 Results Range From 2 To 10805 MB/s22194366538701087130415211738195521722389260628233040325734743691390841254342455947764993521054275644586160786295651267296946716373807597781480318248846586828899911693339550976799841020110418106351085220406080100

Based on OpenBenchmarking.org data, the selected test / test configuration (Zstd Compression 1.4.5 - Compression Level: 3) has an average run-time of 3 minutes. By default this test profile is set to run at least 3 times but may increase if the standard deviation exceeds pre-defined defaults or other calculations deem additional runs necessary for greater statistical accuracy of the result.

OpenBenchmarking.orgMinutesTime Required To Complete BenchmarkCompression Level: 3Run-Time612182430Min: 1 / Avg: 2.6 / Max: 26

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 0.7%.

OpenBenchmarking.orgPercent, Fewer Is BetterAverage Deviation Between RunsCompression Level: 3Deviation3691215Min: 0 / Avg: 0.7 / Max: 11

Does It Scale Well With Increasing Cores?

Yes, based on the automated analysis of the collected public benchmark data, this test / test settings does generally scale well with increasing CPU core counts. Data based on publicly available results for this test / test settings, separated by vendor, result divided by the reference CPU clock speed, grouped by matching physical CPU core count, and normalized against the smallest core count tested from each vendor for each CPU having a sufficient number of test samples and statistically significant data.

IntelAMDOpenBenchmarking.orgRelative Core Scaling To BaseZstd Compression CPU Core ScalingCompression Level: 324681216243248641.833.665.497.329.15

Notable Instruction Set Usage

Notable instruction set extensions supported by this test, based on an automatic analysis by the Phoronix Test Suite / OpenBenchmarking.org analytics engine.

Instruction Set
Support
Instructions Detected
SSE2 (SSE2)
Used by default on supported hardware.
 
COMISD MOVAPD MULSD DIVSD SUBSD CVTTSD2SI CVTSI2SD ADDSD MOVDQA MOVD PUNPCKLQDQ MOVDQU PSHUFD PMULUDQ PSRLDQ PADDQ SHUFPD PSUBQ PUNPCKHQDQ MINSD UCOMISD
Requires passing a supported compiler/build flag (verified with targets: sandybridge, skylake, tigerlake, cascadelake, sapphirerapids, alderlake, znver2, znver3).
Found on Intel processors since Sandy Bridge (2011).
Found on AMD processors since Bulldozer (2011).

 
VBROADCASTSD VEXTRACTF128 VZEROUPPER VINSERTF128 VBROADCASTSS
Requires passing a supported compiler/build flag (verified with targets: skylake, tigerlake, cascadelake, sapphirerapids, alderlake, znver2, znver3).
Found on Intel processors since Haswell (2013).
Found on AMD processors since Excavator (2016).

 
VPBROADCASTQ VPBROADCASTD VPSLLVD VEXTRACTI128 VPBROADCASTB VPERM2I128 VPERMD VINSERTI128 VPERMQ VPBROADCASTW VPBLENDD
FMA (FMA)
Requires passing a supported compiler/build flag (verified with targets: skylake, tigerlake, cascadelake, sapphirerapids, alderlake, znver2, znver3).
Found on Intel processors since Haswell (2013).
Found on AMD processors since Bulldozer (2011).

 
VFMADD132SD
Advanced Vector Extensions 512 (AVX512)
Requires passing a supported compiler/build flag (verified with targets: cascadelake, sapphirerapids).
 
(ZMM REGISTER USE)
The test / benchmark does honor compiler flag changes.
Last automated analysis: 18 March 2023

This test profile binary relies on the shared libraries libz.so.1, liblzma.so.5, liblz4.so.1, libc.so.6.

Tested CPU Architectures

This benchmark has been successfully tested on the below mentioned architectures. The CPU architectures listed is where successful OpenBenchmarking.org result uploads occurred, namely for helping to determine if a given test is compatible with various alternative CPU architectures.

CPU Architecture
Kernel Identifier
Verified On
Intel / AMD x86 64-bit
x86_64
(Many Processors)
SPARC64
sparc64
(Many Processors)
RISC-V 64-bit
riscv64
SiFive RISC-V
IBM POWER (PowerPC) 64-bit
ppc64le
POWER9 4-Core, POWER9 44-Core
ARMv7 32-bit
armv7l
ARMv7 Cortex-A53 4-Core, ARMv7 Cortex-A72 4-Core, ARMv7 rev 3 4-Core, ARMv7 rev 4 4-Core
ARMv8 64-bit
aarch64
ARMv8, ARMv8 Cortex-A53 4-Core, ARMv8 Cortex-A72 4-Core, ARMv8 Neoverse-N1 64-Core, ARMv8 rev 0 6-Core, Ampere Altra ARMv8 Neoverse-N1 160-Core, Ampere eMAG ARMv8 32-Core