SPECviewperf^® 2020 v3.0

The SPECviewperf^® 2020 v3.0 benchmark, released on December 9, 2021, is the worldwide standard for measuring graphics performance based on professional applications. The benchmark measures the 3D graphics performance of systems running under the OpenGL and DirectX application programming interfaces. The benchmark workloads are called viewsets, and represent graphics content and behavior from actual workstation-class applications, without the need to install the applications themselves.

Major updates in the SPECviewperf v3.0 benchmark include:

The solidworks-07 viewset has been updated to use the same viewport rendering modes in both 4K and 2K resolutions. Results are not comparable with SPECviewperf 2020 solidworks-05, solidworks-06 or any previous version.
Viewsets are now individually downloaded and may be independently installed and removed using the new “Manage Viewsets” utility.

SPECviewperf 2020 v3.0 supports all the features previously introduced in the SPECviewperf 2020 v1.0, released in October 2020:

New viewsets created from API traces of the latest versions of 3ds Max, Catia, Maya, and Solidworks applications.
Updated models in the viewsets based on 3ds Max, Catia, Creo, Solidworks, and real-world medical applications.
Support within all viewsets for both 2K and 4K resolution displays.
User interface improvements, including better interrogation and assessment of underlying hardware, clickable thumbnails of screen grabs, and a new results manager.
Support for running the benchmark using command-line options.

Hardware and Operating System Requirements

Microsoft Windows 10 Version 1709 (Fall Creators Update / RS3) or newer
16GB of system RAM or greater
80GB of available disk space
A minimum screen resolution of 1920×1080 for submissions published on the SPEC website
OpenGL 4.5 (for catia-06, creo-03, energy-03, maya-06, medical-03, snx-04, and solidworks-07) and DirectX 12 API support (for 3dsmax-07)
A GPU with 2GB or greater dedicated GPU memory

Workload Details

maya-06

The maya-06 viewset was created from traces of the graphics workload generated by the Maya 2019 application from Autodesk. The viewset includes numerous rendering modes supported by the application, including shaded mode, ambient occlusion, multi-sample antialiasing, and transparency. All tests are rendered using Viewport 2.0.

energy-03

The energy-03 viewset is based on rendering techniques used by the open-source OpendTect seismic visualization application. Similar to medical imaging such as MRI or CT, geophysical surveys generate image slices through the subsurface that are built into a 3D grid. Volume rendering provides a 2D projection of this 3D volumetric grid for further analysis and interpretation. In addition to the volume rendering, the test includes both inline and crossline planes (slices in the X and Y planes). Also, for some subtests, “horizons” are present – these are geological strata boundaries of interest, generated by exploration geophysicists, and are rendered using textured triangle strips. The 3D datasets used in this viewset are real-world seismic datasets found at https://wiki.seg.org/wiki/Open_data". They were translated from their native SEG-Y format and compressed using JPEG-2000. Note: subtests 3 and 6 will have a score of 0.01 on GPUs with less than 3584MB (3.5GB) of framebuffer memory.

catia-06

The catia-06 viewset was created from traces of the graphics workload generated by the CATIA V5 and 3DEXPERIENCE CATIA applications from Dassault Systèmes. Model sizes range from 5.1 to 21 million vertices. The viewset includes several rendering modes supported by the application, including anti-aliasing, shaded, and shaded with edges.

creo-03

The creo-03 viewset was created from traces of the graphics workload generated by the Creo 4 application from PTC. Model sizes range from 20 to 48 million vertices. The viewsets include numerous rendering modes supported by the application. Order-independent transparency is enabled for all models with transparent components.

3dsmax-07

The 3dsmax-07 viewset was created from traces of the graphics workload generated by 3ds Max 2016 using the default Nitrous DX11 driver. The models for this viewset came from the SPECapc for 3ds Max 2015 benchmark and other sources. In order to best approximate real-world use cases, several tests incorporate multiple viewsets on screen, each using a different rendering method. The styles of rendering in the viewset reflect those most commonly used in major markets, including realistic, shaded and wireframe. Some lesser-used but interesting rendering modes such as facets, graphite and clay are also incorporated. The animations in the viewset are a combination of model spin and camera fly-through, depending on the model.

snx-04

The snx-04 viewset was created from traces of the graphics workload generated by the NX 8.0 application from Siemens PLM. Model sizes range from 7.15 to 8.45 million vertices. The viewset includes numerous rendering modes supported by the application, including wireframe, anti-aliasing, shaded, shaded with edges, and studio mode.

solidworks-07

The solidworks-07 viewset was created from traces of Dassault Systèmes’ SolidWorks 2020 application. Models used in the viewset range in size from 2.1 to 21 million vertices. The viewset includes numerous rendering modes supported by the application, including shaded mode, shaded with edges, ambient occlusion, shaders, and environment maps. Note that this benchmark is not representative of Solidworks 2020 performance if less than 4GB of dedicated GPU memory is present, and should not be used to draw conclusions about Solidworks 2020 application performance with less than 4GB of video RAM.

medical-03

The medical-03 viewset demonstrates the performance of several medical visualization volume rendering techniques. The first is "slice rendering", where many 2D slices are projected through the volume and composited on the screen. The second is "raycasting" where rays are projected through the volume accumulating the final pixel color. Two different transfer functions are used: 1D, where the density is used to look up each voxel color, and 2D, where density and gradient magnitude are used to look up each voxel color. A clipping plane is used in several tests. The Tuvok visualization library is used for rendering.

FREE

For everyone except sellers of computers and related products

$2,500.00

For sellers of computers and related products

Would you like to receive news, reviews, and updates on graphics and workstation benchmarking via e-mail? There will be no spam, marketing offers, or selling of this mailing list to 3rd parties. Signing up for the mailing list is not required for benchmark downloads.

Yes No

Email Address:

License Agreement:

Read the terms and conditions of this Agreement carefully before downloading or opening the package containing the SPEC product or any accompanying documentation (collectively, "the Materials").  Except where explicitly superseded by wording in the attached product license, this Agreement represents the entire Agreement between you and SPEC concerning the Materials and supersedes any prior proposal, representation or understanding between the parties.

Use and re-export of SPEC's software is subject to the United States Export Control Administration regulations. The software may not be used by unlicensed person or entities and may not be re-exported to another country. See Export Assurance (Clause 12) of this license.

The restrictions and limitations of this Agreement do not apply to those items contained in the Materials that have been modified under, or used under, licenses that require free redistribution. SPEC has collected copies or links to copies of all such items underneath the directory redistributable_sources, along with the licenses applicable to each item in that directory.

By downloading the Materials or opening the package containing the Materials, you are accepting and agreeing to the terms of this Agreement. If you are not willing to be bound by these terms, you should promptly cease downloading the Materials and remove the Materials from your system. Or, if you received the Materials via physical media, you should return the media and the Materials to SPEC. You may receive a refund for purchased products.

1. Grant. SPEC agrees to grant and USER agrees to accept a nontransferable and nonexclusive license to use and modify the Materials, subject to the restrictions and conditions set forth below and in any accompanying product specific license.

2. Copies and Location. USER may make only exact and complete copies of the original of the Materials. The original and copies thereof may be used only:

By the user, if purchased by a non-corporate entity. This user must also abide by the Export Assurance (Clause 12) of this license.
By anyone within the same corporate structure, if purchased by a corporation. Note that a "corporate user" must be identified and all technical support and contact with SPEC must be handled through that contact. This user and corporation must also abide by the Export Assurance (Clause 12) of this license.
USER will not permit any third party to use or copy the original or any copy thereof. In the event of unauthorized transfer or copying, USER will pay SPEC a penalty in the amount of one additional fee for each such transfer or copy.

3. Scope of Use. The Materials may be used only for the generation of data regarding measurement and analysis of computer system (hardware and software) performance and/or power usage on those Materials. Modification or merger with other software is allowed only as specified in the Run and Reporting Rules for the given SPEC benchmark or tool product. USER may not distribute the Materials or any modification to the Materials with the following exceptions:

USER may distribute those items specifically included in the directory of redistributable sources according to the terms of their open source licenses.
USER may share only with other SPEC licensees of this product modifications created by USER for purposes of performance and/or power usage analysis. Such modifications shall be limited to 1) modifying the code to instrument the product; or 2) modifying the workload to enable further analysis on systems under the USER's control or 3) a combination of 1) and 2).
For performance or power measurement results obtained from such modified product, USER may not 1) represent the results as being compliant results of the product or 2) use official SPEC metric name(s) to identify the results.

The Materials may include executable code for the SPEC PTDaemon tool. The SPEC PTDaemon tool is licensed for use only with the Materials or modifications of the Materials as described herein. It is NOT licensed for use as a standalone tool or for integration into a tool that is unrelated to the Materials.

4. Fee. The fee paid by the USER to SPEC for the Materials is in consideration of SPEC's cost in connection with the production and distribution of the Materials and is not a royalty.

5. Reports. In order to preserve the integrity of SPEC's performance standards, USER agrees to run the Materials in accordance with the benchmark product rules published by SPEC for the Materials. If the USER chooses to publicly report measured results, the reporting must be strictly in accordance with the SPEC product rules, including the SPEC Fair Use Rule.

The SPEC Fair Use Rules are posted at www.spec.org. SPEC product rules are posted at www.spec.org in the documentation pages for each SPEC product. Both the SPEC Fair Use rules and the SPEC product rules may be updated from time to time. USERS are required to comply with the latest versions of the rules, including all updates, as posted on the SPEC website.

SPEC practices associated with perceived violations of Fair Use or other license terms can be found at: http://www.spec.org/spec/docs/penaltiesremedies.pdf.

6. Term. This Agreement is effective upon USER opening the package containing the Materials or upon downloading the Materials from an electronic distribution source and shall continue until terminated. USER may terminate the Agreement at any time by providing written notification to SPEC that all copies have been destroyed, but the provisions of Sections 5, 7, 8 and 10 shall survive any termination.

The license granted as to the current release of the Materials shall terminate when SPEC issues and makes available to the USER a subsequent release of such materials.

In the event of a breach by the USER of any provision hereof, SPEC may terminate this Agreement, and the license granted hereunder, in whole or as to any portion of the Materials upon 30 days written notice unless the default is cured within such 30-day period. Upon termination of the license, USER shall immediately destroy all copies of the Materials and shall provide written notification to SPEC that all copies have been destroyed.

7. Use of Name. It is acknowledged that all trademark and trade name rights in the names are owned exclusively by SPEC and such ownership shall be acknowledged in any use of the name by the USER (i.e. - noting that these are "trademarks of the Standard Performance Evaluation Corporation").

8. Ownership of Material: This Agreement does not constitute a sale of the Materials but is only a license to use in accordance with the terms of this Agreement. USER acknowledges that title, ownership and all intellectual property rights in and to the Materials and any copies are owned by and remain with SPEC.

9. Indemnity. USER agrees to indemnify and hold SPEC harmless from any claims, expenses, or liabilities caused by USER's use of the Materials or by USER's publication or use of data arising from its use of the Materials.

DISCLAIMER OF WARRANTIES

SPEC MAKES NO WARRANTIES WHATSOEVER, EXPRESS OR IMPLIED, RELATING TO THE SALE, USE OR PERFORMANCE OF THE MATERIALS, INCLUDING WITHOUT LIMITATION, ANY WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR USE OR PURPOSE, AND ALL SUCH WARRANTIES ARE HEREBY DISCLAIMED AND EXCLUDED BY SPEC.

USER RECOGNIZES THAT THE PRODUCTS ARE THE RESULT OF A COOPERATIVE, NON-PROFIT EFFORT AND THAT SPEC DOES NOT CONDUCT A TYPICAL BUSINESS. USER ACCEPTS THE MATERIALS "AS IS" AND WITHOUT ANY WARRANTY, EXPRESS OR IMPLIED.

10. Limitation of Liability. SPEC assumes no liability with respect to the Materials, including liability for infringement of intellectual property rights, negligence, or any other liability.

SPEC is not aware of any infringement of copyright or patent that may result from its transfer to USER of the Materials. If USER receives any notice of infringement, such notice shall be immediately communicated to SPEC who will take immediate action to evaluate the claim and, if practicable, modify the Materials as necessary to avoid infringement. USER waives any claim against SPEC in the event of such infringement.

SPEC's total liability for any reason shall not exceed the amount of the fee paid to SPEC. In no event will SPEC be liable for any indirect, special, incidental or consequential damages arising out of or in connection with this Agreement, including the sale, use or performance of the Materials, even if SPEC shall have knowledge of the possibility of such damages.

11. Maintenance and Support. SPEC has no obligation to provide support, maintenance, updates, modifications or new releases of the Materials to USER under this Agreement.

12. Export Assurance. Use and re-export of SPEC's software and related technical information is subject to the Export Administration Regulations (EAR) of the United States Department of Commerce. USER hereby agrees that USER (a) assumes responsibility for compliance with the EAR in its use of the software and technical information, and (b) will not export, re-export, or otherwise disclose directly or indirectly, the software, technical data, or any direct product of the software or technical data in violation of the EAR.

13. Governing Law. This Agreement shall be construed and governed in accordance with the laws of the State of California. If any term of this Agreement is declared void or not enforceable by any competent court of jurisdiction, all other terms shall remain in effect.

14. No Waiver. The failure of either party to enforce any term herein or to take action in the event of any violation of these terms shall not be deemed a waiver by that party as to the subsequent enforcement of any rights.

I have read, understand, and agree to abide by the terms of the SPEC General License Agreement.

Am I required to purchase a benchmark license?

A paid license is required for any for-profit entity that sells computers or computer related products in the commercial marketplace, with the exception of SPEC/GWPG member companies (AMD, Dell, Fujitsu, HP Inc, Intel, Lenovo, Nvidia, VeriSilicon) that receive benchmark licenses as a membership benefit. Examples of those requiring a paid license include:

Computer hardware and software vendors
Computer component manufacturers (hard drives, memory, device vendors)
Computer-related service providers (for-profit resellers, distributors, consultants)
Computer operating system companies

License holders are eligible for a free upgrade to a newly released benchmark of the same application or suite that is released within 6 months of the license purchase. Please contact us to take advantage of this offer.

Retired benchmarks are not available for licensed purchase or download.

Still not certain, contact us.

Benchmark Run Rules

The system under test must perform all of the respective graphics API’s functionality and other work requested by the benchmark.
The systems under test must be OpenGL Conformant for the pixel format or visual used by the benchmark.
Settings for environment variables, registry variables and hints must not disable compliant behavior.
No interaction is allowed with the system under test during the benchmark, unless required by the benchmark.
The system under test cannot skip frames during the benchmark run.
It is not permissible to change the system configuration during the running of a given benchmark. For example, one cannot power off the system, make some changes, then power back on and run the rest of the benchmark.
Screen grabs for SPECviewperf will be full window size.
The color depth used must be at least 24 bits (true color), with at least 8 bits of red, 8 bits of green and 8 bits of blue.
If a depth buffer is requested, it must have at least 24 bits of resolution.
The display raster resolution must be at least as high as that selected in the “Resolution” dropdown of the SPECviewperf benchmark user interface and must fully display all of the benchmark tests being submitted. Higher desktop resolutions may be used, and while the operating system may create the appearance of a higher raster resolution, the actual raster resolution corresponds to that selected and will be noted in the results file and log files. An optional feature to adjust the raster resolution to the native resolution of the display (less a ten-pixel border) may be selected, but not all viewsets will support this method of scaling. Therefore, native resolution runs are not considered official and results are unacceptable for publication.
The screen resolution must be large enough to run the individual tests at their requested window size, with no reduction or clipping of test window contents.
Results to be made public must be generated by the official benchmark which may not be changed, except to correct errors in reporting by the benchmark, and these changes shall be disclosed voluntarily upon submission.
Screen DPI scaling must be set to 100%, and no UI or other window elements (including but not limited to task bars, tool bars, menu bars, and title bars) may occlude the viewport rendering context. Such elements must be configured to auto-hide or to be sized to allow all test window contents to be visible on-screen without being clipped or obscured. Results which show viewport warnings in viewset log files are unacceptable for publication.
Tests may be run with or without a desktop/window manager, but must be run on some native windowing system.
Virtualized configurations, defined as any operating system configuration running on a hypervisor or virtualization layer of any kind, must include the word “virtualized” in the comment field of the config.txt file. This information must be populated before the execution of the benchmark to ensure the results reflect this attribute.
Virtualized configurations as defined above must also include a declaration of the transport layer name and version used by the virtualization software in parenthesis after the graphics accelerator listed in the Graphics Accelerator field of the Graphics Hardware Configuration section of the result file.
Virtualized configurations as defined above must also include a declaration of the hypervisor name and version used by the virtualization software in parenthesis after the model listed in the Model field of the System Hardware Configuration section of the result file.
All configurations shall include a link (URL) to a publicly-accessible device driver package used to generate the submission.

Submission and Review Rules

Submission Content Rules
1. These rules are specific to SPECgpc and shall apply in addition to the Submission Content Rules in the GWPG Project Groups Ruleset.
2. A SPECviewperf submission can be for one or more viewsets per configuration.
3. A SPECviewperf submission must be run on a 64-bit operating system.
4. The Specviewperf submission must include all directory and files located in the results folder. The results folder is created by the benchmark with the following naming convention: “results_”YYYYMMDD”T”HHMM”_t1”
Submission Process Rules
1. These rules are specific to SPECgpc and shall apply in addition to the Submission Process Rules in the GWPG Project Groups Ruleset.
2. The submission file names must contain gpc_v for SPECviewperf, contain all lower case letters and not contain ‘.’ except prior to the zip or tar file extension (e.g. intel_gpc_v_jun10_v0.zip). The file version is denoted prior to the file extension. The initial file version is v0. Resubmitted files must increment the version number.
Review Period Rules
1. These rules are specific to SPECgpc and shall apply in addition to the Review Period Rules in the GWPG Project Groups Ruleset.
2. Reviewers will decide if the image quality of the submission is sufficiently adherent to the respective graphics API’s specification to satisfy the intended end user’s expectations. If a reviewer rejects the quality of an image for a stated reason, the submitter can ask for a vote of the full SPECgpc electorate. In case of a tie the submission is rejected.
3. System configurations submitted for the SPECgpc benchmark suite must be able to run the corresponding SPECapc application benchmarks if applicable. If this criterion is not met the submission will be rejected.

Have a question regarding a SPEC GWPG benchmark? We are here to help! We can provide technical assistance with benchmark related issues. We are unable to assist with hardware installation issues, hardware problems, non-SPEC software installation issues, non-SPEC software problems, hardware or software specific tuning.

For benchmark specific questions, please include benchmark name, benchmark version, and full system configuration details.