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, 58 Seconds

Average Run Time

5 Minutes, 49 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-zstd2018.042018.072018.102019.012019.042019.072019.102020.012020.042020.072020.102021.012021.042021.072021.102022.012022.042022.072022.102023.012023.042023.072023.102024.012024.042024.072024.1020K40K60K80K100K
* 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 3 November 2024.
1214.7%19, Long Mode17.7%1919.6%8, Long Mode12.2%813.1%312.3%3, Long Mode10.3%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 1.5.0

Compression Level: 19 - Compression Speed

OpenBenchmarking.org metrics for this test profile configuration based on 2,042 public results since 14 May 2021 with the latest data as of 5 November 2024.

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
4
109 +/- 2
100th
8
107 +/- 1
99th
8
103 +/- 1
85th
23
79 +/- 6
77th
10
60 +/- 1
Mid-Tier
75th
< 57
74th
13
55 +/- 1
73rd
17
53 +/- 2
53rd
32
37 +/- 3
Median
50th
35
50th
12
35 +/- 1
49th
11
35 +/- 2
49th
30
35 +/- 1
43rd
18
31 +/- 1
42nd
11
31 +/- 2
40th
9
30 +/- 1
37th
16
27 +/- 1
36th
13
27 +/- 2
36th
13
27 +/- 1
35th
4
26 +/- 1
34th
6
26 +/- 2
34th
22
26 +/- 2
33rd
27
25 +/- 1
30th
19
23 +/- 1
29th
5
23 +/- 2
27th
4
21 +/- 1
Low-Tier
25th
< 20
25th
14
19 +/- 1
23rd
28
18 +/- 1
23rd
10
18 +/- 1
20th
19
18 +/- 1
20th
3
17 +/- 1
19th
7
17 +/- 1
18th
11
17 +/- 1
15th
6
15 +/- 1
15th
6
15 +/- 1
14th
7
14 +/- 1
13th
7
13 +/- 2
8th
4
9 +/- 1
OpenBenchmarking.orgDistribution Of Public Results - Compression Level: 19 - Compression Speed2042 Results Range From 0 To 115 MB/s10203040506070809010011012080160240320400

Based on OpenBenchmarking.org data, the selected test / test configuration (Zstd Compression 1.5.0 - Compression Level: 19 - Compression Speed) has an average run-time of 5 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: 19 - Compression SpeedRun-Time816243240Min: 1 / Avg: 4.45 / Max: 37

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 0.6%.

OpenBenchmarking.orgPercent, Fewer Is BetterAverage Deviation Between RunsCompression Level: 19 - Compression SpeedDeviation246810Min: 0 / Avg: 0.59 / Max: 5

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: 19 - Compression Speed24681012162432641282.474.947.419.8812.35

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)
RISC-V 64-bit
riscv64
SiFive RISC-V, rv64imafdc, rv64imafdcsu
IBM POWER (PowerPC) 64-bit
ppc64le
POWER8E
Loongson LoongArch 64-bit
loongarch64
Loongson-3C5000L
ARMv7 32-bit
armv7l
ARMv7 Cortex-A72 4-Core
ARMv8 64-bit
arm64
Apple M1, Apple M1 Max, Apple M1 Pro, Apple M2
ARMv8 64-bit
aarch64
ARMv8 Cortex-A53 4-Core, ARMv8 Cortex-A55 4-Core, ARMv8 Cortex-A55 6-Core, ARMv8 Cortex-A72, ARMv8 Cortex-A72 16-Core, ARMv8 Cortex-A72 4-Core, ARMv8 Cortex-X1C 8-Core, ARMv8 Neoverse-N1, ARMv8 Neoverse-N1 4-Core, ARMv8 Neoverse-N1 80-Core, ARMv8 Neoverse-V1, ARMv8 Neoverse-V1 4-Core, ARMv8 rev 0 8-Core, Ampere ARMv8 Neoverse-N1 160-Core, Ampere Altra ARMv8 Neoverse-N1 160-Core, Ampere eMAG ARMv8 32-Core, Apple M1, Apple M2, Phytium D2000, Phytium FT-2000, Rockchip ARMv8 Cortex-A76 8-Core