CacheBench

This is a performance test of CacheBench, which is part of LLCbench. CacheBench is designed to test the memory and cache bandwidth performance

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

Project Site

icl.cs.utk.edu

Test Created

6 December 2010

Last Updated

7 April 2018

Test Maintainer

Michael Larabel 

Test Type

Processor

Average Install Time

1 Second

Average Run Time

7 Minutes, 29 Seconds

Test Dependencies

C/C++ Compiler Toolchain

Accolades

300k+ Downloads + 10k+ Public Benchmark Results

Supported Platforms


Public Result UploadsTest Completions*Reported Installs*OpenBenchmarking.orgEventsCacheBench Popularity Statisticspts/cachebench2011.022011.062011.102012.022012.062012.102013.022013.062013.102014.022014.062014.102015.022015.062015.102016.022016.062016.102017.022017.062017.102018.022018.062018.102019.022019.062019.102020.022020.062020.102021.02140K280K420K560K700K
* 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 Fri, 26 Feb 2021 12:50:50 GMT.
Read / Modify / Write43.1%Write26.4%Read30.5%Test Option PopularityOpenBenchmarking.org

Revision History

pts/cachebench-1.1.2   [View Source]   Sat, 07 Apr 2018 17:38:36 GMT
Fix for FreeBSD

pts/cachebench-1.1.1   [View Source]   Sun, 04 Mar 2018 10:07:15 GMT
Windows support.

pts/cachebench-1.1.0   [View Source]   Wed, 04 Jan 2017 20:24:47 GMT
Change download link to a static one.

pts/cachebench-1.0.0   [View Source]   Mon, 06 Dec 2010 14:34:54 GMT
Initial import into OpenBenchmarking.org

Suites Using This Test

Memory Test Suite

CPU Massive

Single-Threaded


Performance Metrics

Analyze Test Configuration:

CacheBench

Test: Read / Modify / Write

OpenBenchmarking.org metrics for this test profile configuration based on 2,939 public results since 4 January 2017 with the latest data as of 19 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
MB/s (Average)
100th
5
68957 +/- 385
97th
6
55866 +/- 82
96th
6
53029 +/- 950
88th
16
44997 +/- 1691
87th
24
44480 +/- 382
85th
3
43333 +/- 3514
85th
7
42620 +/- 6349
83rd
15
42307 +/- 183
83rd
3
42134 +/- 963
82nd
32
41999 +/- 614
82nd
6
41942 +/- 1543
82nd
3
41839 +/- 62
82nd
3
41682 +/- 1482
79th
4
39772 +/- 3060
78th
3
39761 +/- 119
78th
3
39468 +/- 118
78th
6
39262 +/- 206
77th
4
38880 +/- 461
77th
4
38548 +/- 4672
76th
3
38168 +/- 42
76th
4
37786 +/- 911
76th
23
37762 +/- 229
76th
4
37732 +/- 5005
Mid-Tier
75th
< 37542
73rd
6
35342 +/- 179
71st
38
34461 +/- 214
70th
24
34281 +/- 224
70th
3
34188 +/- 565
70th
19
34181 +/- 1095
68th
5
33903 +/- 5
66th
4
33051 +/- 4413
66th
4
32974 +/- 206
65th
5
32931 +/- 87
64th
3
32368 +/- 1051
61st
4
31594 +/- 2912
61st
7
31560 +/- 3706
61st
5
31552 +/- 2608
59th
3
30802 +/- 1547
58th
7
30383 +/- 4370
57th
3
30072 +/- 1820
57th
4
29829 +/- 1807
54th
6
28747 +/- 733
54th
3
28479 +/- 1182
53rd
13
28426 +/- 570
53rd
6
28242 +/- 60
Median
50th
27359
50th
4
27358 +/- 62
45th
3
25405 +/- 47
44th
12
25213 +/- 1862
40th
5
23877 +/- 1265
39th
3
23607 +/- 13
39th
3
23600 +/- 13
39th
4
23537 +/- 370
38th
10
23210 +/- 461
38th
6
22994 +/- 518
36th
5
22125 +/- 1170
34th
4
21612 +/- 168
34th
3
21294 +/- 119
33rd
3
20968 +/- 1631
30th
3
19195 +/- 76
29th
16
18898 +/- 2
28th
14
18893 +/- 10
28th
21
18884 +/- 17
Low-Tier
25th
< 17991
24th
22
17055 +/- 1825
22nd
4
15999 +/- 41
22nd
3
15968 +/- 1
22nd
5
15967 +/- 1
20th
24
15477 +/- 139
20th
3
15427 +/- 16
19th
18
15287 +/- 107
17th
5
14222 +/- 558
16th
3
13317 +/- 410
14th
18
12142 +/- 133
13th
11
11789 +/- 1599
13th
3
11095 +/- 20
13th
6
11057 +/- 10
12th
17
10969 +/- 1
11th
5
10604 +/- 425
10th
18
9666 +/- 2
9th
6
9647 +/- 1324
9th
3
8612 +/- 3
7th
3
6690 +/- 844
5th
5
2539 +/- 265
4th
5
2303 +/- 204
4th
25
2181 +/- 295
3rd
3
2073 +/- 85
2nd
4
1840 +/- 198
OpenBenchmarking.orgDistribution Of Public Results - Test: Read / Modify / Write2939 Results Range From 25 To 17912463584660 MB/s25358249271718716498543411107474781510414329970867971791246358490214949563018325077449018762865994173569322424344526235824927169553940741988648429899126034146572405320345015489803727537373907542057319883471136090237618806644848689049968067361621927164985433885752323470557878814839772718239733248964859798252065789562317923509314481064043967273033573610030979607429103892288791221074747815081511105727422508114639766942011182222596589412180475237587125387245092801289697378097313255223052666136134723243591397172159605214329970867745146882201394381504646941113115404718682824157629679545171612121722621016479466497903168377157695961719596504128917554214312982179124635846756001200180024003000

Based on OpenBenchmarking.org data, the selected test / test configuration (CacheBench - Test: Read / Modify / Write) 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 BenchmarkTest: Read / Modify / WriteRun-Time612182430Min: 1 / Avg: 3.4 / Max: 25

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 0.5%.

OpenBenchmarking.orgPercent, Fewer Is BetterAverage Deviation Between RunsTest: Read / Modify / WriteDeviation48121620Min: 0 / Avg: 0.52 / Max: 14

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.

IntelAMDOpenBenchmarking.orgRelative Core Scaling To BaseCacheBench CPU Core ScalingTest: Read / Modify / Write2481216200.77771.55542.33313.11083.8885

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 MULSD SUBSD DIVSD ADDSD CVTSI2SD MOVAPD
Last automated analysis: 30 January 2021

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

Recent Test Results

OpenBenchmarking.org Results Compare

1 System - 22 Benchmark Results

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

Ubuntu 16.04 - 4.4.0-1121-aws - 1.0.61

13 Systems - 26 Benchmark Results

Intel Celeron J3455 - Compulab fitlet2 v1.1 - Intel Celeron N3350

Ubuntu 18.04 - 4.15.0-10-generic - GNOME Shell 3.27.91

1 System - 22 Benchmark Results

AMD Ryzen 9 3950X 16-Core - Gigabyte X570 AORUS MASTER - AMD Starship

Fedora 33 - 5.10.15-200.fc33.x86_64 - GNOME Shell 3.38.3

1 System - 3 Benchmark Results

2 x Intel Xeon Gold 5218 - Dell 0WXD1Y - Intel Sky Lake-E DMI3 Registers

HyperServer v1.0.1-Release - 5.10.0 - xfs

1 System - 3 Benchmark Results

2 x Intel Xeon (Cascadelake) - QEMU Standard PC - Intel 440FX- 82441FX PMC

CentOS Linux 7 - 3.10.0-1127.el7.x86_64 - GCC 4.8.5 20150623

1 System - 120 Benchmark Results

2 x AMD EPYC 7V12 64-Core - Microsoft Virtual Machine - 434GB

Ubuntu 20.04 - 5.4.0-1039-azure - GNOME Shell 3.36.4

3 Systems - 22 Benchmark Results

AMD Eng Sample ZS1711E3VIVG5_24/17_N - Supermicro H11SSL-i v2.00 - AMD Starship

Debian GNU - 5.4.73-1-pve - nouveau

1 System - 22 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 - 22 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 - 22 Benchmark Results

AMD Eng Sample ZS1711E3VIVG5_24/17_N - Supermicro H11SSL-i v2.00 - AMD Starship

Debian GNU - 5.4.73-1-pve - nouveau

1 System - 74 Benchmark Results

2 x AMD EPYC 7V12 64-Core - Microsoft Virtual Machine - 434GB

Ubuntu 20.04 - 5.4.0-1039-azure - GNOME Shell 3.36.4

1 System - 22 Benchmark Results

AMD Ryzen 9 5900X 12-Core - ASRock X570 Taichi - AMD Starship

Arch Linux - 5.10.8-arch1-1 - GCC 10.2.0

Most Popular Test Results

OpenBenchmarking.org Results Compare

2 Systems - 927 Benchmark Results

Intel Celeron N3160 - SECO UDOO x86 - Intel Atom

Debian 9.0 - 4.9.0-3-amd64 - LXDE 0.9.3

2 Systems - 178 Benchmark Results

AMD Ryzen Threadripper 1950X 16-Core - Gigabyte X399 AORUS Gaming 7 - AMD Family 17h

Ubuntu 18.04 - 4.15.2-041502-generic - GNOME Shell 3.26.2

5 Systems - 87 Benchmark Results

ARMv7 rev 1 - Rockchip - 2048MB

Ubuntu 16.04 - 4.4.66-rockchip - Xfce 4.12

1 System - 88 Benchmark Results

AArch64 rev 3 - HiKey Development Board - 2048MB

Debian 8.7 - 3.18.0-linaro-hikey - X Server 1.16.4

2 Systems - 6 Benchmark Results

Unknown - NationalChip gx6605s - 57MB

Buildroot 2018.02-git - 4.9.56 - GNOME Shell

1 System - 1004 Benchmark Results

SiFive RISC-V - FriendlyElec NanoPC-T4 - Rockchip RK3399

Ubuntu 18.04 - 4.4.138 - LXDE 0.9.3

1 System - 248 Benchmark Results

AMD Ryzen 9 3900X 12-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Device 1480

Ubuntu 18.04 - 5.2.0-999-generic - GNOME Shell 3.28.3

2 Systems - 9 Benchmark Results

Intel Xeon E5620 - 10240MB - 40GB

Debian unstable - 4.14.0-3-amd64 - GCC 7.2.0

3 Systems - 9 Benchmark Results

Intel Xeon E5620 - 10240MB - 40GB

Debian unstable - 4.14.0-3-amd64 - GCC 7.2.0

6 Systems - 1421 Benchmark Results

Unknown - Marvell Armada 3720 Board - 2048MB

Ubuntu 16.04 - 4.4.52-armada-17.06.2-g12feccb - GCC 5.4.0 20160609

Find More Test Results

OpenBenchmarking.org Community User Comments

Post A Comment