Timed LLVM Compilation

This test times how long it takes to compile/build the LLVM compiler stack.

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

Project Site

llvm.org

Source Repository

github.com

Test Created

27 August 2017

Last Updated

22 March 2023

Test Maintainer

Michael Larabel 

Test Type

Processor

Average Install Time

2 Seconds

Average Run Time

54 Minutes, 13 Seconds

Test Dependencies

C/C++ Compiler Toolchain + CMake + Python

Accolades

150k+ Downloads

Supported Platforms


Public Result Uploads *Reported Installs **Reported Test Completions **Test Profile Page Views ***OpenBenchmarking.orgEventsTimed LLVM Compilation Popularity Statisticspts/build-llvm2017.082017.112018.022018.052018.082018.112019.022019.052019.082019.112020.022020.052020.082020.112021.022021.052021.082021.112022.022022.052022.082022.112023.022023.052023.082023.112024.022024.052024.0811K22K33K44K55K
* 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 4 October 2024.
Ninja64.0%Unix Makefiles36.0%Build System Option PopularityOpenBenchmarking.org

Revision History

pts/build-llvm-1.5.0   [View Source]   Wed, 22 Mar 2023 11:12:53 GMT
Update against LLVM 16.0 to fix GCC 13 build issues.

pts/build-llvm-1.4.0   [View Source]   Fri, 01 Oct 2021 14:29:57 GMT
Update against LLVM 13.0 upstream. Also fix: https://github.com/phoronix-test-suite/openbenchmarking/issues/15

pts/build-llvm-1.3.1   [View Source]   Fri, 16 Apr 2021 08:04:57 GMT
Fix possible shell script issue based on the interpreter.

pts/build-llvm-1.3.0   [View Source]   Fri, 16 Apr 2021 05:40:02 GMT
Update against LLVM 12.0 upstream, also add build system option for those wanting Ninja builds.

pts/build-llvm-1.2.1   [View Source]   Sat, 12 Sep 2020 16:11:15 GMT
Drop Windows support as it seems to have problems running now.

pts/build-llvm-1.2.0   [View Source]   Tue, 24 Mar 2020 14:28:14 GMT
Update against LLVM 10.0.

pts/build-llvm-1.1.0   [View Source]   Wed, 15 Aug 2018 08:56:02 GMT
Update against LLVM 6.0.1 upstream as LLVM 4.0 these days seems to be having build problems under newer compilers.

pts/build-llvm-1.0.1   [View Source]   Thu, 08 Mar 2018 19:17:13 GMT
Windows support.

pts/build-llvm-1.0.0   [View Source]   Sun, 27 Aug 2017 20:32:05 GMT
Initial commit of a timed LLVM compilation test profile.

Suites Using This Test

Timed Code Compilation

C/C++ Compiler Tests

Multi-Core

CPU Massive

Server CPU Tests

Programmer / Developer System Benchmarks


Performance Metrics

Analyze Test Configuration:

Timed LLVM Compilation 16.0

Build System: Ninja

OpenBenchmarking.org metrics for this test profile configuration based on 1,862 public results since 22 March 2023 with the latest data as of 4 October 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
Seconds (Average)
99th
20
79 +/- 5
93rd
8
104 +/- 1
86th
17
127 +/- 7
85th
9
133 +/- 5
82nd
17
142 +/- 10
76th
25
176 +/- 16
Mid-Tier
75th
> 177
74th
15
181 +/- 9
72nd
4
186 +/- 12
71st
15
189 +/- 16
71st
12
190 +/- 8
67th
7
210 +/- 6
61st
5
263 +/- 11
61st
20
264 +/- 2
55th
3
296 +/- 18
Median
50th
313
50th
27
316 +/- 17
47th
17
334 +/- 20
45th
5
349 +/- 17
43rd
3
366 +/- 12
39th
23
413 +/- 24
38th
8
436 +/- 1
36th
13
461 +/- 26
35th
3
473 +/- 1
35th
5
486 +/- 44
35th
5
489 +/- 36
35th
3
494 +/- 7
31st
20
562 +/- 29
31st
16
573 +/- 36
28th
4
638 +/- 3
28th
8
665 +/- 36
27th
7
673 +/- 11
27th
4
682 +/- 27
Low-Tier
25th
> 697
25th
17
715 +/- 35
25th
6
719 +/- 15
25th
7
723 +/- 44
24th
5
751 +/- 60
23rd
13
780 +/- 82
23rd
14
794 +/- 24
21st
9
827 +/- 26
20th
7
861 +/- 29
19th
4
888 +/- 8
18th
3
918 +/- 84
17th
9
962 +/- 117
17th
4
964 +/- 1
17th
10
981 +/- 1
16th
9
1032 +/- 109
15th
7
1098 +/- 56
15th
6
1105 +/- 99
14th
5
1155 +/- 5
13th
6
1177 +/- 165
13th
5
1186 +/- 52
12th
4
1241 +/- 1
12th
8
1255 +/- 100
12th
10
1274 +/- 137
12th
6
1280 +/- 87
10th
5
1342 +/- 1
10th
9
1348 +/- 128
10th
15
1371 +/- 187
9th
3
1474 +/- 11
9th
3
1517 +/- 7
8th
3
1620 +/- 6
7th
18
1711 +/- 32
7th
5
1754 +/- 157
6th
3
1903 +/- 1
6th
3
1989 +/- 13
5th
10
2087 +/- 99
5th
3
2113 +/- 11
5th
8
2139 +/- 196
4th
3
2870 +/- 7
4th
5
2966 +/- 147
3rd
4
3077 +/- 132
2nd
4
5340 +/- 5
OpenBenchmarking.orgDistribution Of Public Results - Build System: Ninja1833 Results Range From 62 To 50842 Seconds62107820943110412651426158717481909206102221123812254132701428615302163181733418350193662038221398224142343024446254622647827494285102952630542315583257433590346063562236638376543867039686407024171842734437504476645782467984781448830498465086230060090012001500

Based on OpenBenchmarking.org data, the selected test / test configuration (Timed LLVM Compilation 16.0 - Build System: Ninja) has an average run-time of 31 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 BenchmarkBuild System: NinjaRun-Time60120180240300Min: 3 / Avg: 30.41 / Max: 318

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 RunsBuild System: NinjaDeviation3691215Min: 0 / Avg: 0.3 / Max: 9

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 BaseTimed LLVM Compilation CPU Core ScalingBuild System: Ninja4681012141624324856643691215

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)
ARMv8 64-bit
arm64
Apple M1, Apple M2 Pro, Apple M3 Max
ARMv8 64-bit
aarch64
ARMv8, ARMv8 Cortex-A72 4-Core, ARMv8 Cortex-A76 4-Core, ARMv8 Neoverse-N1, ARMv8 Neoverse-N1 128-Core, ARMv8 Neoverse-N1 160-Core, ARMv8 Neoverse-V1, ARMv8 Neoverse-V2, ARMv8 Neoverse-V2 72-Core, ARMv8 Neoverse-V2 96-Core, AmpereOne 128-Core, AmpereOne 160-Core, AmpereOne 192-Core, AmpereOne 32-Core, AmpereOne 64-Core, AmpereOne 72-Core, AmpereOne 96-Core, Apple M1 Pro, Rockchip ARMv8 Cortex-A76 4-Core, rk1-mainline-emmc, rk1-mainline-nvme, rk1-rok-emmc, rk1-rok-emmc6