simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others.

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

Project Site

simdjson.org

Test Created

13 December 2020

Last Updated

14 December 2020

Test Maintainer

Michael Larabel

Test Type

Processor

Average Install Time

1 Minute, 40 Seconds

Average Run Time

3 Minutes, 29 Seconds

Test Dependencies

C/C++ Compiler Toolchain + CMake

Supported Platforms


Public Result UploadsReported Installs*Test Completions*OpenBenchmarking.orgEventssimdjson Popularity Statisticspts/simdjson2020.122021.012021.025001000150020002500
* 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.
Data current as of Thu, 25 Feb 2021 07:21:27 GMT.
DistinctUserID24.6%PartialTweets25.3%Kostya25.2%LargeRandom24.9%Throughput Test Option PopularityOpenBenchmarking.org

Revision History

pts/simdjson-1.1.1   [View Source]   Mon, 14 Dec 2020 13:25:30 GMT
Don't bother with the documents/s report for now.

pts/simdjson-1.1.0   [View Source]   Mon, 14 Dec 2020 11:39:20 GMT
Update against simdjson 0.7.1 that was just released with POWER/ARM fixes. Also report documents/s as well.

pts/simdjson-1.0.0   [View Source]   Sun, 13 Dec 2020 16:06:04 GMT
Initial commit of simdjson benchmark.

Suites Using This Test

Server

Programmer / Developer System Benchmarks


Performance Metrics

Analyze Test Configuration:

simdjson 0.7.1

Throughput Test: PartialTweets

OpenBenchmarking.org metrics for this test profile configuration based on 485 public results since 14 December 2020 with the latest data as of 21 February 2021.

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
# Matching Public Results
GB/s (Average)
99th
11
1.19
99th
4
1.19
93rd
12
0.91 +/- 0.01
91st
22
0.90 +/- 0.04
91st
7
0.90 +/- 0.01
88th
3
0.89 +/- 0.04
86th
6
0.87 +/- 0.01
86th
4
0.87 +/- 0.02
84th
4
0.86 +/- 0.01
80th
3
0.76 +/- 0.01
Mid-Tier
75th
< 0.73
74th
3
0.72 +/- 0.01
73rd
3
0.71 +/- 0.01
73rd
5
0.71 +/- 0.01
72nd
5
0.70 +/- 0.03
68th
4
0.68 +/- 0.01
68th
3
0.68 +/- 0.01
64th
7
0.66 +/- 0.02
61st
5
0.64 +/- 0.01
58th
3
0.63 +/- 0.01
Median
50th
0.62
49th
5
0.61 +/- 0.01
44th
3
0.60 +/- 0.01
44th
4
0.60 +/- 0.01
40th
8
0.59 +/- 0.04
35th
4
0.57 +/- 0.01
35th
8
0.57 +/- 0.02
35th
3
0.57 +/- 0.01
32nd
3
0.56 +/- 0.01
31st
3
0.55 +/- 0.01
31st
4
0.55 +/- 0.03
27th
3
0.52 +/- 0.01
Low-Tier
25th
< 0.52
20th
6
0.48 +/- 0.01
11th
4
0.44 +/- 0.01
7th
4
0.39 +/- 0.01
4th
7
0.35 +/- 0.01
2nd
3
0.25 +/- 0.01
OpenBenchmarking.orgDistribution Of Public Results - Throughput Test: PartialTweets485 Results Range From 0 To 6 GB/s00.511.522.533.544.555.5680160240320400

Based on OpenBenchmarking.org data, the selected test / test configuration (simdjson 0.7.1 - Throughput Test: PartialTweets) 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 BenchmarkThroughput Test: PartialTweetsRun-Time3691215Min: 1 / Avg: 2.96 / Max: 10

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 0.3%.

OpenBenchmarking.orgPercent, Fewer Is BetterAverage Deviation Between RunsThroughput Test: PartialTweetsDeviation246810Min: 0 / Avg: 0.33 / Max: 3

Does It Scale Well With Increasing Cores?

No, based on the automated analysis of the collected public benchmark data, this test / test settings does not 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.

AMDIntelOpenBenchmarking.orgRelative Core Scaling To Basesimdjson CPU Core ScalingThroughput Test: PartialTweets468162432640.68131.36262.04392.72523.4065

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 MOVDQU MOVDQA SHUFPD CVTSI2SD ADDSD MULSD DIVSD SUBSD CVTTSD2SI MOVAPD PADDQ UCOMISD XORPD PUNPCKLQDQ MOVD MAXSD ANDPD PSHUFD PSUBQ MOVUPD MOVHPD SQRTSD UNPCKLPD SUBPD MULPD UNPCKHPD DIVPD CMPNLTSD ANDNPD ORPD
SSSE3 (SSSE3)
Used by default on supported hardware.
 
PSHUFB PALIGNR PMADDUBSW
SSE 4.2 (SSE4_2)
Used by default on supported hardware.
Found on Intel processors since at least 2010.
Found on AMD processors since Bulldozer (2011).

 
POPCNT
Used by default on supported hardware.
Found on Intel processors since Sandy Bridge (2011).
Found on AMD processors since Bulldozer (2011).

 
VZEROUPPER VEXTRACTF128 VINSERTF128 VPERMILPD VBROADCASTSD
Used by default on supported hardware.
Found on Intel processors since Haswell (2013).
Found on AMD processors since Excavator (2016).

 
VINSERTI128 VEXTRACTI128 VPERM2I128 VPBROADCASTD VPERMD VPERMQ VPBROADCASTB VPBROADCASTQ
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 VFMADD231SD VFNMADD213SD VFMSUB132SD
The test / benchmark does honor compiler flag changes.
Last automated analysis: 31 January 2021

This test profile binary relies on the shared libraries libsimdjson.so.5, librt.so.1, libm.so.6, libpthread.so.0, libc.so.6.

Recent Test Results

OpenBenchmarking.org Results Compare

4 Systems - 4 Benchmark Results

AMD Ryzen 7 5800X 8-Core - ASRock X570 Pro4 - AMD Starship

Ubuntu 20.10 - 5.10.0-051000rc7daily20201213-generic - GNOME Shell 3.38.1

1 System - 53 Benchmark Results

AMD Ryzen 5 3600 6-Core - ASUS PRIME X470-PRO - AMD Starship

Arch rolling - 5.10.16-zen1-1-zen - X Server 1.20.10

1 System - 358 Benchmark Results

Ampere Altra ARMv8 Neoverse-N1 - WIWYNN Mt.Jade - Ampere Computing LLC Device e100

Ubuntu 20.04 - 5.11.0-051100-generic-64k - GNOME Shell 3.36.4

1 System - 37 Benchmark Results

12 x AMD EPYC-Rome - QEMU Standard PC - Intel 82G33

Ubuntu 20.04 - 5.8.0-43-generic - GNOME Shell 3.36.4

5 Systems - 42 Benchmark Results

Ampere eMAG ARMv8 - AmpereComputing OSPREY - Applied Micro Circuits X-Gene

Ubuntu 20.04 - 5.7.0-050700-generic - GNOME Shell 3.36.3

1 System - 33 Benchmark Results

Intel Xeon Platinum 8275CL - Amazon EC2 c5.2xlarge - Intel 440FX 82441FX PMC

Ubuntu 18.04 - 5.4.0-1037-aws - GCC 7.5.0

1 System - 34 Benchmark Results

Intel Xeon Platinum 8275CL - Amazon EC2 c5.2xlarge - Intel 440FX 82441FX PMC

Ubuntu 20.04 - 5.4.0-1037-aws - GCC 9.3.0

1 System - 20 Benchmark Results

Intel Xeon Platinum 8275CL - Amazon EC2 c5.2xlarge - Intel 440FX 82441FX PMC

Ubuntu 20.04 - 5.4.0-1037-aws - GCC 9.3.0

1 System - 19 Benchmark Results

Intel Xeon Platinum 8275CL - Amazon EC2 c5.2xlarge - Intel 440FX 82441FX PMC

Ubuntu 18.04 - 5.4.0-1037-aws - GCC 7.5.0

2 Systems - 151 Benchmark Results

Intel Xeon E-2278GEL - Logic Supply RXM-181 - Intel Cannon Lake PCH

Ubuntu 20.10 - 5.8.0-41-generic - GNOME Shell 3.38.2

Most Popular Test Results

OpenBenchmarking.org Results Compare

2 Systems - 151 Benchmark Results

Intel Core i7-10700T - Logic Supply RXM-181 - Intel Comet Lake PCH

Ubuntu 20.10 - 5.8.0-41-generic - GNOME Shell 3.38.2

4 Systems - 5 Benchmark Results

AMD Ryzen Threadripper 3990X 64-Core - System76 Thelio Major - AMD Starship

Pop 20.10 - 5.8.0-7625-generic - GNOME Shell 3.38.1

5 Systems - 42 Benchmark Results

Ampere eMAG ARMv8 - AmpereComputing OSPREY - Applied Micro Circuits X-Gene

Ubuntu 20.04 - 5.7.0-050700-generic - GNOME Shell 3.36.3

3 Systems - 191 Benchmark Results

AMD Ryzen 3 2200G - ASUS PRIME B350M-E - AMD Raven

Ubuntu 20.10 - 5.8.0-38-generic - GNOME Shell 3.38.1

5 Systems - 118 Benchmark Results

AMD Ryzen 9 5900X 12-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship

Clear Linux OS 34220 - 5.10.10-1017.native - GNOME Shell 3.38.3

4 Systems - 131 Benchmark Results

Intel Core i7-10700T - Insyde CometLake TBD by OEM - Intel

FreeBSD - 13.0-BETA1 - Clang 11.0.1

3 Systems - 28 Benchmark Results

Intel Xeon Silver 4216 - TYAN S7100AG2NR - Intel Sky Lake-E DMI3 Registers

Debian 10 - 4.19.0-9-amd64 - GNOME Shell 3.30.2

3 Systems - 376 Benchmark Results

2 x AMD EPYC 7F72 24-Core - Supermicro H11DSi-NT v2.00 - AMD Starship

Ubuntu 20.10 - 5.11.0-051100rc4daily20210122-generic - GNOME Shell 3.38.1

4 Systems - 14 Benchmark Results

Intel Core i7-4870HQ - Apple MacBook Pro - Apple SSD

macOS 10.15.7 - 19.6.0 - X Server 1.18.4

4 Systems - 104 Benchmark Results

AMD Ryzen 5 2400G - MSI B350M GAMING PRO - AMD Raven

Ubuntu 19.10 - 5.3.0-64-generic - GNOME Shell 3.34.1

3 Systems - 24 Benchmark Results

AMD Ryzen 9 5950X 16-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship

Ubuntu 20.10 - 5.11.0-051100rc2daily20210108-generic - GNOME Shell 3.38.1

Find More Test Results

OpenBenchmarking.org Community User Comments

Post A Comment