Primesieve

Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve primarily benchmarks the CPU's L1/L2 cache performance.

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

Project Site

primesieve.org

Source Repository

github.com

Test Created

23 October 2012

Last Updated

22 November 2024

Test Maintainer

Kim Walisch

Test Type

Processor

Average Install Time

21 Seconds

Average Run Time

8 Minutes, 23 Seconds

Test Dependencies

C/C++ Compiler Toolchain + CMake

Accolades

250k+ Downloads + 5k+ Public Benchmark Results

Supported Platforms

* 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 28 January 2025.

Revision History

pts/primesieve-1.12.0 [View Source] Fri, 22 Nov 2024 09:47:25 GMT
Update against Primesieve 12.6 Closes: https://github.com/phoronix-test-suite/phoronix-test-suite/pull/822

pts/primesieve-1.11.0 [View Source] Fri, 25 Oct 2024 12:53:19 GMT
Update against Primesieve 12.5 upstream.

pts/primesieve-1.10.0 [View Source] Fri, 15 Mar 2024 19:16:10 GMT
Update against Primesieve 12.1 upstream. Closes: https://github.com/phoronix-test-suite/phoronix-test-suite/pull/776

pts/primesieve-1.9.0 [View Source] Wed, 20 Jul 2022 09:19:25 GMT
Update against Primesieve 8.0 upstream.

pts/primesieve-1.8.0 [View Source] Sat, 04 Dec 2021 05:39:18 GMT
Update against Primesieve 7.7 upstream.

pts/primesieve-1.7.0 [View Source] Mon, 18 Feb 2019 12:11:15 GMT
Update against Primesieve 7.4 upstream, https://github.com/phoronix-test-suite/test-profiles/pull/61

pts/primesieve-1.6.0 [View Source] Fri, 07 Dec 2018 15:57:57 GMT
Update against upstream Primesieve, https://github.com/phoronix-test-suite/test-profiles/pull/43

pts/primesieve-1.5.0 [View Source] Wed, 22 Aug 2018 15:51:39 GMT
Updated against Primesieve 7.1 from upstream, posted via GitHub tracker.

pts/primesieve-1.4.1 [View Source] Tue, 27 Feb 2018 15:13:46 GMT
Update download links.

pts/primesieve-1.4.0 [View Source] Mon, 16 Oct 2017 13:25:19 GMT
Upstream updates, switch from using OpenMP to C++11 threads.

pts/primesieve-1.3.1 [View Source] Mon, 20 Apr 2015 11:52:52 GMT
Update against new Primesieve.

pts/primesieve-1.3.0 [View Source] Sun, 05 Oct 2014 08:16:32 GMT
Updated test profile for new upstream Primesieve 5.4 by Kim Walisch.

pts/primesieve-1.2.0 [View Source] Mon, 24 Feb 2014 17:46:52 GMT
Update Primesieve test profile against upstream v5.0 by Kim Walisch. Also add in SHA256 file sums and test against PTS5 Git.

pts/primesieve-1.1.1 [View Source] Thu, 14 Mar 2013 09:59:40 GMT
Update download links file correctly.

pts/primesieve-1.1.0 [View Source] Thu, 14 Mar 2013 09:56:17 GMT
Update against upstream Primesieve 4.2.

pts/primesieve-1.0.2 [View Source] Tue, 23 Oct 2012 15:11:38 GMT
Improve some text string formatting.

pts/primesieve-1.0.1 [View Source] Tue, 23 Oct 2012 14:58:14 GMT
Add SMP internal tag since Primesieve can use OpenMP.

pts/primesieve-1.0.0 [View Source] Tue, 23 Oct 2012 14:55:00 GMT
Initial commit of the Primesieve test profile submitted by Kim Walisch.

Suites Using This Test

Multi-Core

CPU Massive

Performance Metrics

Analyze Test Configuration:

Primesieve 12.6

Length: 1e12

OpenBenchmarking.org metrics for this test profile configuration based on 149 public results since 22 November 2024 with the latest data as of 24 January 2025.

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)

2 x AMD EPYC 9654 96-Core

96th

2 x AMD EPYC 9684X 96-Core

90th

2 x AMD EPYC 9535 64-Core

88th

AMD EPYC 9655P 96-Core

83rd

AMD EPYC 9575F 64-Core

80th

AMD Ryzen Threadripper 7980X 64-Cores

76th

Mid-Tier

75th

> 2

ARMv8 Neoverse-N1 128-Core

71st

ARMv8 Neoverse-V2 72-Core

70th

2 x AMD EPYC 9124 16-Core

66th

AMD Ryzen 9 9950X 16-Core

64th

AMD EPYC 4564P 16-Core

58th

Intel Core Ultra 9 285K

52nd

Median

50th

AMD EPYC 4584PX 16-Core

47th

AMD EPYC 4484PX 12-Core

40th

AMD EPYC 4464P 12-Core

37th

AMD Ryzen 7 9800X3D 8-Core

32nd

AMD EPYC 4364P 8-Core

29th

AMD Ryzen 7 7840HS

26th

Low-Tier

25th

> 15

AMD Ryzen AI 9 365

21st

Intel Core Ultra 7 256V

15th

AMD EPYC 4124P 4-Core

12th

Intel Core Ultra 7 155H

10th

28 ^{+/- 1}

ARMv8 Cortex-A76 4-Core

5th

113 ^{+/- 11}

ARMv8 Cortex-A72 4-Core

3rd

839 ^{+/- 20}

Detailed Performance Overview

Based on OpenBenchmarking.org data, the selected test / test configuration (Primesieve 12.6 - Length: 1e12) has an average run-time of 2 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.

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.

PUNPCKLQDQ MOVDQA MOVDQU MOVD CVTSI2SD MULSD ADDSD MOVAPD CVTTSD2SI DIVSD COMISD UCOMISD SQRTSD SUBSD MAXSD PADDQ MINSD SHUFPD

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

Advanced Vector Extensions (AVX)

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

VZEROUPPER VINSERTF128 VEXTRACTF128

Advanced Vector Extensions 2 (AVX2)

Used by default on supported hardware.
Found on Intel processors since Haswell (2013).
Found on AMD processors since Excavator (2016).

VPBROADCASTQ VINSERTI128 VEXTRACTI128

Advanced Vector Extensions 512 (AVX512)

Used by default on supported hardware.

(ZMM REGISTER USE)

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

The test / benchmark does honor compiler flag changes.

Last automated analysis: 16 March 2024

This test profile binary relies on the shared libraries libm.so.6, 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)

ARMv8 64-bit

arm64

Apple M4, Apple M4 Pro