Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics.

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

Project Site

blender.org

Source Repository

git.blender.org

Test Created

11 July 2016

Last Updated

22 November 2024

Test Maintainer

Michael Larabel

Test Type

System

Average Install Time

23 Seconds

Average Run Time

6 Minutes, 58 Seconds

Accolades

300k+ Downloads + 5k+ Public Benchmark Results

Supported Platforms

Supported Architectures

x86_64

[CLOSE]

* 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 20 December 2024.

Revision History

pts/blender-4.3.0 [View Source] Fri, 22 Nov 2024 11:19:42 GMT
Update against Blender 4.3 upstream.

pts/blender-4.2.0 [View Source] Tue, 16 Jul 2024 12:51:09 GMT
Update against Blender 4.2 LTS release.

pts/blender-4.1.0 [View Source] Tue, 26 Mar 2024 13:26:07 GMT
Update against Blender 4.1 upstream, add Junkshop scene too.

pts/blender-4.0.0 [View Source] Tue, 14 Nov 2023 08:55:43 GMT
Update against Blender 4.0 upstream.

pts/blender-3.6.0 [View Source] Tue, 27 Jun 2023 11:54:02 GMT
Update against Blender 3.6 upstream.

pts/blender-3.5.0 [View Source] Wed, 29 Mar 2023 11:57:14 GMT
Update against Blender 3.5 upstream.

pts/blender-3.4.0 [View Source] Wed, 07 Dec 2022 18:54:02 GMT
Update against Blender 3.4 upstream.

pts/blender-3.3.1 [View Source] Fri, 09 Sep 2022 17:57:49 GMT
Update SHA256 / MD5 for Blender 3.3 Linux as upstream appears to have respun that build. Fixes: https://github.com/phoronix-test-suite/phoronix-test-suite/issues/671

pts/blender-3.3.0 [View Source] Wed, 07 Sep 2022 07:44:20 GMT
Update against Blender 3.3 upstream, add Intel oneAPI back-end option.

pts/blender-3.2.0 [View Source] Wed, 08 Jun 2022 15:25:18 GMT
Update against Blender 3.2 upstram, expose Radeon HIP option, switch to using --cycles-device option in recent versions for setting device acceleration.

pts/blender-3.0.0 [View Source] Fri, 03 Dec 2021 15:08:32 GMT
Update against Blender 3.0 upstream release.

pts/blender-1.9.1 [View Source] Thu, 04 Nov 2021 14:22:17 GMT
Update download links for Barbershop blend files, old mirror broke.

pts/blender-1.9.0 [View Source] Thu, 25 Feb 2021 15:02:18 GMT
Update against Blender 2.92 upstream.

pts/blender-1.8.0 [View Source] Mon, 31 Aug 2020 17:54:31 GMT
Update against upstream Blender 2.90.

pts/blender-1.7.1 [View Source] Sun, 17 May 2020 15:33:56 GMT
Add macOS support, add more download mirrors.

pts/blender-1.7.0 [View Source] Fri, 14 Feb 2020 15:07:03 GMT
Update against Blender 2.82 upstream.

pts/blender-1.6.0 [View Source] Thu, 21 Nov 2019 20:28:12 GMT
Update against Blender 2.81.

pts/blender-1.5.1 [View Source] Sun, 29 Sep 2019 11:55:34 GMT
Fix for Blender 2.80 Python API preferences handling for GPU selection.

pts/blender-1.5.0 [View Source] Mon, 12 Aug 2019 10:39:52 GMT
Update against Blender 2.80 upstream.

pts/blender-1.4.1 [View Source] Thu, 01 Mar 2018 09:47:17 GMT
Square away the Windows support.

pts/blender-1.4.0 [View Source] Thu, 01 Mar 2018 07:43:14 GMT
Update against Blender 2.79a, plumb in initial Windows support.

pts/blender-1.3.2 [View Source] Sun, 26 Nov 2017 16:05:28 GMT
Fix GPU download link

pts/blender-1.3.1 [View Source] Sat, 25 Nov 2017 09:34:23 GMT
Add new Barbershop scene.

pts/blender-1.3.0 [View Source] Sat, 16 Sep 2017 11:15:52 GMT
Update against Blender 2.79 upstream

pts/blender-1.2.0 [View Source] Tue, 18 Apr 2017 18:35:10 GMT
Update to upstream 2.78c

pts/blender-1.1.1 [View Source] Thu, 05 Jan 2017 10:44:56 GMT
Add explicit CPU-only / NONE acceleration option

pts/blender-1.1.0 [View Source] Wed, 02 Nov 2016 16:02:29 GMT
Update against upstream Blender 2.78a

pts/blender-1.0.0 [View Source] Mon, 11 Jul 2016 09:09:41 GMT
Initial commit

Suites Using This Test

Multi-Core

OpenCL

Common Workstation Benchmarks

CPU Massive

Creator Workloads

Server CPU Tests

Renderers

NVIDIA GPU Compute

Game Development

Performance Metrics

Analyze Test Configuration:

Blender 4.0

Blend File: Classroom - Compute: NVIDIA CUDA

OpenBenchmarking.org metrics for this test profile configuration based on 71 public results since 14 November 2023 with the latest data as of 5 March 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)

NVIDIA GeForce RTX 4090

96th

NVIDIA GeForce RTX 4080

85th

Mid-Tier

75th

> 17

AMD Radeon RX 7900 XTX

74th

AMD Radeon RX 7900 XT

67th

NVIDIA GeForce RTX 3080

58th

AMD Radeon RX 6800 XT

51st

Median

50th

XFX AMD Radeon RX 7700 XT

46th

AMD Radeon RX 6800

41st

NVIDIA RTX A4000

26th

Low-Tier

25th

> 40

Gigabyte NVIDIA GeForce GTX 1660 Ti

17th

88 ^{+/- 2}

Gigabyte NVIDIA GeForce GTX 1060

6th

145

Detailed Performance Overview

Based on OpenBenchmarking.org data, the selected test / test configuration (Blender 4.0 - Blend File: Classroom - Compute: NVIDIA CUDA) 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.

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.

MOVDQA PUNPCKLQDQ PADDQ PSUBQ SHUFPD MOVD MOVDQU SUBSD MULSD COMISD CVTTSD2SI MAXSD MINSD DIVSD UCOMISD CVTSS2SD CVTSI2SD ADDSD CVTSD2SS SQRTSD MOVAPD CVTSD2SI ADDPD UNPCKHPD UNPCKLPD MULPD SUBPD XORPD ANDPD ORPD PSHUFD PUNPCKHQDQ ANDNPD CMPNLESD CMPLTSD DIVPD PSHUFLW PSRLDQ CVTTPS2DQ CVTDQ2PS CMPNLTSD CVTPS2DQ MOVUPD CMPEQPD MAXPD MOVHPD MOVLPD PMULUDQ CVTPS2PD CVTPD2PS CMPLESD SQRTPD MOVMSKPD CVTDQ2PD PSLLDQ PSHUFHW MOVNTDQ MOVDQ2Q MOVQ2DQ CMPLTPD CVTTPD2DQ CMPLEPD CMPNLEPD CMPNLTPD

SSE3 (SSE3)

Used by default on supported hardware.

MOVDDUP MOVSHDUP MOVSLDUP HADDPS LDDQU ADDSUBPS

SSSE3 (SSSE3)

Used by default on supported hardware.

PSHUFB PABSD PALIGNR PHADDD PABSW PSIGNW PMULHRSW PMADDUBSW PSIGND PABSB PHADDW PHADDSW

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 VPERMILPS VBROADCASTSS VINSERTF128 VEXTRACTF128 VBROADCASTF128 VPERM2F128 VBROADCASTSD VPERMILPD VMASKMOVPS

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).

VPBROADCASTD VPERM2I128 VINSERTI128 VPERMQ VEXTRACTI128 VPBLENDD VPERMD VPBROADCASTB VPBROADCASTW VPERMPD VPERMPS VGATHERDPD VGATHERDPS VPBROADCASTQ VPGATHERDD VPSRAVD VPSLLVD VPGATHERQQ VPMASKMOVD

AVX Vector Neural Network Instructions (AVX-VNNI)

Used by default on supported hardware.

VPDPBUSD

FMA (FMA)

Used by default on supported hardware.
Found on Intel processors since Haswell (2013).
Found on AMD processors since Bulldozer (2011).

VFMADD231SS VFMADD213SS VFNMADD213SS VFMADD132PS VFMADD132SS VFMADD231PS VFNMADD132SS VFNMADD231SS VFNMADD132PS VFMSUB132PS VFMSUB231PS VFNMADD231PS VFMADD213PS VFMSUB132SS VFMSUB231SS VFNMADD213PS VFNMSUB132SS VFMSUB213PS VFNMSUB231SS VFMSUB213SS VFNMADD231PD VFMADD231PD VFMADD213PD VFMADDSUB213PS VFMSUBADD213PS VFMADDSUB231PS VFMADD213SD VFMADD132PD VFMADD231SD VFMADD132SD VFNMSUB231PS VFNMSUB213SS

Advanced Vector Extensions 512 (AVX512)

Used by default on supported hardware.

(ZMM REGISTER USE)

Last automated analysis: 23 August 2024

This test profile binary relies on the shared libraries libtbb.so.2, libutil.so.1, libpthread.so.0, libdl.so.2, libm.so.6, libosdGPU.so.3.6.0, libosdCPU.so.3.6.0, libX11.so.6, libXrender.so.1, libXxf86vm.so.1, libXfixes.so.3, libXi.so.6, libxkbcommon.so.0, libembree4.so.4, libsycl.so.7, libOpenImageIO.so.2.5, liboslcomp.so.1.13, liboslexec.so.1.13, liboslquery.so.1.13, liboslnoise.so.1.13, libOpenColorIO.so.2.3, libOpenImageDenoise.so.2, libMaterialXFormat.so.1, libMaterialXCore.so.1, libopenvdb.so.11.0, libIex.so.31, libOpenEXR.so.31, libOpenEXRCore.so.31, libIlmThread.so.31, libImath.so.30, librt.so.1, libc.so.6, libxcb.so.1, libXext.so.6, libSM.so.6, libICE.so.6, libGL.so.1, libMaterialXRender.so.1, libMaterialXGenGlsl.so.1, libMaterialXGenMsl.so.1, libMaterialXGenShader.so.1, libz.so.1, libXau.so.6, libXdmcp.so.6, libuuid.so.1, libbsd.so.0, libGLdispatch.so.0, libGLX.so.0, libmd.so.0.

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)