The Application Performance Characterization Project Committee Rules
Version 3.3
Last Updated: 09/09/2020
- Overview
- General
Philosophy
- All rules
declared in "The
Graphics and Workstation Performance Group (SPEC/GWPG): Rules For Project Groups document (known
hereafter as the GWPG Project Groups Ruleset) apply, unless specifically
overruled by a rule in this document.
- Rules declared in this document shall apply in addition to the rules
declared in the GWPG Project Groups Ruleset.
- General
Philosophy
- The Application Performance Characterization Project of SPEC/GWPG
(henceforth abbreviated as SPECapc) believes the user community will
benefit from an objective series of tests that are application-based,
which can serve as a common reference and be considered as part of an
evaluation process.
- The SPECapc seeks to develop benchmarks for generating accurate
application-level graphics performance measures in an open, accessible
and well-publicized manner.
- The SPECapc wishes to contribute to the coherence of the field of
application performance measurement and evaluation so that vendors will
be better able to present well-defined performance measures and customers
will be better able to compare and evaluate vendors' products and environments.
- The SPECapc will provide formal beta benchmarks to members and final
benchmark releases to the public in a timely fashion.
- Hardware and software used to run the SPECapc benchmarks must provide
a suitable environment for running typical workloads for the applications
for which benchmarks are provided.
- SPECapc reserves the right to adapt its benchmarks as it deems necessary
to preserve its goal of fair and useful benchmarking (e.g. remove benchmark,
modify benchmark code or data, etc). If a change is made to the suite,
SPECapc will notify the appropriate parties (i.e. SPECapc members and users
of the benchmark) and SPECapc will re-designate the benchmark by changing
its name and/or version. In the case that a benchmark is removed in whole
or in part, SPECapc reserves the right to republish in summary form "adapted"
results for previously published systems, converted to the new metric. In
the case of other changes, such a republication may necessitate re-testing
and may require support from the original test sponsor.
- Overview
of Optimizations
- SPECapc is aware of the importance of optimizations in producing the best
system performance. SPECapc is also aware that it is sometimes hard to draw an
exact line between legitimate optimizations that happen to benefit SPECapc
benchmarks and optimizations that specifically target SPECapc benchmarks.
However, with the list below, SPECapc wants to increase awareness of implementers
and end-users to issues of unwanted benchmark-specific optimizations that would
be incompatible with SPECapc's goal of fair benchmarking.
- To ensure that results are relevant to end-users, SPECapc expects that the
hardware and software implementations used for running SPECapc benchmarks adhere
to a set of general rules for optimizations.�
- General
Rules for Optimization
- Optimizations must generate correct images for the application under
test, for both the benchmark case and similar cases. Correct images are
those deemed by the SPECapc committee to be sufficiently adherent to the
respective graphics API specification for the targeted application.
- Optimizations must not have an adverse effect on system stability.
A published SPEC APC result carries an implicit claim that the performance
methods employed are more than just "prototype" or "experimental"
or "research" methods. It is a claim that there is a certain
level of maturity and general applicability in its methods.
- Optimizations must improve performance for a class of workloads where
the class of workloads must be larger than a single SPECapc benchmark or
SPECapc benchmark suite.
- No pre-computed (e.g. driver-cached) images, geometric data, or state
may be substituted within an SPECapc benchmark in order to detect the
benchmark (e.g. pattern matching of command stream or recognition of
benchmark's name).�
- Optimizations must be generally available and supported by the
providing vendor.
- In the case where it appears that the guidelines in this document have
not been followed, SPECapc members will follow the SPEC Violations
Determination, Penalties and Remedies Document guidelines to
bring resolution to the matter.
- Benchmarks
- Benchmark
Definition
- Benchmark
components are defined as
- Specific version of the application
- Application models and/or scenes
- Benchmark scripts and framework
- Launch GUI and associated benchmark definition files
- Benchmark run rules
- Benchmark Acceptance
- New or modified benchmark components require a 2/3-majority
vote of the SPECapc electorate to be accepted for publication.
- Selection of the specific version of the application used for
a benchmark (datecode, service pack, etc) is chosen by majority vote.
- A minimum 3-week review period is required for new or significantly
modified benchmark components.
- At the end of the review period a vote will be called to approve
the proposed changes.
- An amendment to a benchmark component during the review period must
be unanimously accepted. If not, the review period shall be restarted.
- Benchmark
Code Versioning
- SPECapc benchmarks use the following version coding: M.m.p (e.g.
SPECapcSM�for Creo 3.0 v1.0.1) M is the
major release number, m is the minor release number and p is the
patch level.
- The major release number is only incremented when large
amounts of code are changed and the scripting language is
dramatically changed as a result — backward compatibility
is highly unlikely when moving scripts or data sets between
major releases (e.g. running v2 scripts on a v3 executable
would almost certainly fail).
- The minor release number is incremented if some small
set of code is replaced or removed - but the standard,
unchanged scripts and data sets, as a whole, must run on
the new version (but perhaps with different performance).
- Patch releases can contain additions of new properties and
additions of new attributes or functionality. These are
typically used for bug fixes, small enhancements and so forth.
- Benchmark Release
- When there is a new major release of a benchmark, submissions using the
previous release will be accepted for at least one submission cycle.
- When a superseded benchmark is retired, the associated run rules and
results will be archived along with the benchmark information page.
- Benchmark Run Rules
- General
Benchmark Run Rules
- The system under test must correctly perform all of the operations
being requested by the application by the benchmark.
- No changes to any files associated with the benchmark are permitted.
- The entire display must be available for use by the application and benchmark.
- 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.
- The display resolution must be at least 1920 pixels by 1080 pixels.
- Screen resolution must be large enough to run the individual tests
at their requested window size, with no reduction or clipping of the test window.
- Windows created by the benchmark must not be obscured by anything other
than other elements created by the benchmark.
- Screen DPI scaling must be set to 100% on Microsoft Windows, and no UI
or other window elements, including the task bar, may occlude the viewport
rendering context
- It is not permissible to override the intended behavior of the application
through any means including, but not limited to, registry settings or environment
variables.
- No interaction is allowed with the system under test during 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.
- Results submitted must be obtained using the scripts, models, and application
revisions which are specified for that submission cycle by the SPECapc.
- Tests may be run with or without a desktop/window manager if the application
allows this, but must be run on some native windowing system.
- Virtualized configurations, defined as any operating system configuration
running on a Hyper Visor 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 Hyper Visor 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
- These rules are specific to SPECapc and shall apply in addition to the
Submission Content Rules in the GWPG Project Group Rules.
- The submission upload is defined in the benchmark-specific section for
each specific SPECapc benchmark.
- Submission Process Rules
- These rules are specific to SPECapc and shall apply in addition to the Submission
Process Rules in the GWPG Project Groups Ruleset.
- The submission zip file name must contain apc_<application benchmark name>,
contain all lower-case letters and not contain "." except prior to the zip
file extension. The initial file version is v0. Resubmitted files must increment the
version number. Example <company>_apc_solidworks2017_v0.zip
- Review Period Rules
- These rules are specific to SPECgpc and shall apply in addition to the Submission
Process Rules in the GWPG Project Groups Ruleset.
- Reviewers
will decide if the image quality and results of the submission are sufficiently
correct with respect to the intent of the application provider to satisfy the
intended application use.
- SPECapc Benchmark Specific Rules and
Procedures
- Autodesk
3ds max 2015
- The
benchmark must be run using Autodesk 3ds Max 2015 with Service Pack 1
(SP1) applied. Do not install the 3ds Max Subscription Advantage Pack,
as it will interfere with the operation and results of the benchmark.
- The
default 3ds Max 2015 application settings must be used.
- The
benchmark may only be run using Nitrous DX11 display driver.
- The
display resolution must be at least 1920 pixels by 1080 pixels. If the
system has an integrated display which cannot achieve 1920x1080
resolution, e.g., a notebook, the system�s maximum possible resolution
must be used.
- Submissions
can optionally be made at 4k resolutions.
- Submissions
can optionally be made with AA modes greater than the default 0.
- This
benchmark is only supported on systems running Microsoft Windows 7 and Windows 10
64-bit operating system.
- The
3dsmax 2015 benchmark should be run with at least 16GB of system memory
installed.
- The
application window must be fully visible and not be occluded by any
other windows. Task-bar auto-hide must be enabled. Any windows on top of
the application rendering window may interfere with the performance. The
benchmark status window is an exception to this rule as it should not
intersect the graphics rendering window.
- The
results.txt file must be generated by the GwpgSystemInfo.exe found in the ./submissions directory.
- After
completion of the benchmark the submitter should create a populated
specAPC2015.xlsm and results.txt files by following these steps:
- Copy <3dsmax 2015
install directory>/maxtest/submissions/GwpgSystemInfo.exe
to the newly created TestResults folder.
- Copy <3dsmax 2015
install directory>/maxtest/submissions/specAPC2015.xlsm
to the newly created TestResults folder.
- Open specAPC2015.xlsm
with Office Excel 2007 or greater. In the spreadsheet; press
Enable Content and Select Test Results Folder buttons.
- Create a results.txt by
running GwpgSystemInfo.exe
- Verify all prepopulated
values in results.txt.
- Copy the scores from
specAPC2015.xlsm Overview sheet into the results.txt file.
- Add appropriate values
to the Submitter fields.
- The
directory structure of the submission must be as follows:
.../company-name/system_1/3dsmax2015/result.txt
.../company-name/system_1/3dsmax2015/results1.xml
.../company-name/system_1/3dsmax2015/results2.xml
.../company-name/system_1/3dsmax2015/results3.xml
.../company-name/system_1/3dsmax2015/testrenders/*.jpeg
.../company-name/system_1/3dsmax2015/specAPC2015.xlsm
.../company-name/system_1/3dsmax2015/result.txt
.../company-name/system_2/3dsmax2015/results1.xml
.../company-name/system_2/3dsmax2015/results2.xml
.../company-name/system_2/3dsmax2015/results3.xml
.../company-name/system_2/3dsmax2015/testrenders/*.jpeg
.../company-name/system_2/3dsmax2015/specAPC2015.xlsm
etc....
- The
submission file must be named company_apc_3dsmax2015_vN.zip
where company is the member company or organization name in lower case and vN is the file version (e.g.
dell_apc_3dsmax2015_v0.zip.) The initial submission is v0. Resubmitted
files must have the version number incremented.
- Autodesk
Maya 2017
- The benchmark must be run using Autodesk Maya 2017 with Update 4 applied.
- The default Maya 2017 application settings must be used.
- The benchmark may only be run using the default display driver.
- The display resolution must be at least 1920 pixels by 1080 pixels. If the system has an integrated display which cannot achieve 1920x1080 resolution, e.g., a notebook, the system’s maximum possible resolution must be used.
- Submissions can optionally be made at 4k resolutions.
- Windows Display scaling in Windows 10 and DPI scaling in Windows 7 must be set to 100%.
- This benchmark is only supported on systems running Microsoft Windows 7 and Windows 10 64-bit operating system.
- The Maya 2017 benchmark should be run with at least 16GB of system memory installed.
- It is recommended that the system be rebooted before running the benchmark, and the application window must be fully visible and not be occluded by any other windows. Task-bar auto-hide must be enabled. Any windows on top of the application rendering window may interfere with the performance. The benchmark status window is an exception to this rule as it should not intersect the graphics rendering window.
- The submission must contain the entire results folder generated from running the benchmark. The results folder will be named results_[MSAA|noMSAA]_timestamp after a successful run of the benchmark. All fields in the "Submission Info" panel must be filled out prior to running the benchmark.
- The directory structure of the submission must be as follows:
.../company-name/system_1/maya2017/results_[MSAA|noMSAA]_timestamp/
.../company-name/system_2/maya2017/results_[MSAA|noMSAA]_timestamp/
etc...
- The submission file must be named company_apc_maya2017_vN.zip where company is the member company or organization name in lower case and vN is the file version (e.g. dell_apc_maya2017_v0.zip.) The initial submission is v0. Resubmitted files must have the version number incremented
- PTC Creo 3.0
- The
benchmark must be run using Creo 3.0 build
M010.
- The Creo 3.0 benchmark is only supported on systems
running Microsoft Windows 7 and Windows 10 64-bit operating system.
- Only
submissions run on Microsoft Windows 7 and Windows 10 64-bit operating system and with
graphics cards supporting a minimum of 8X MSAA and Order Independent
Transparency will be accepted for review.
- The
display resolution must be at least 1920 pixels by 1080 pixels. If the
system has an integrated display which cannot achieve 1920x1080
resolution, e.g., a notebook, the system's maximum possible resolution
must be used.
- It
is recommended that the Creo 3.0 benchmark be
run with at least 8GB of RAM installed.
- The All_V25.txt, config.pro and apc.dat files must be used as-is and may
not be modified or overridden.
- The
benchmark may not use any other config.pro, config.sup, config.win, menu_def.pro,
or protk.dat files. These files must be removed from the
application install location and user folder before running the
benchmark.
- The
graphics card used must support a minimum of 8X MSAA and Order
Independent Transparency for comparable results.
- The
script file utilities\runbench.bat may be modified to accommodate
an alternate install location for Creo 3.0. If
modified, the modified version of runbench.bat must be included
in the benchmark submission.
- The utilities\config.txt file must be edited to reflect the system configuration before running
the benchmark.
- The
submission must contain the result.txt, trail.txt, score-steps.txt, score.csv, apc.dat and *.tif files. These files may be found in the results directory after a
successful run of the benchmark.
- There
must be no license-related warnings in the trail.txt file.
- The
directory structure of the submission must be as follows:
.../company-name/system_1/creo3/result.txt
.../company-name/system_1/creo3/trail.txt
�/company-name/system_1/creo3/score-steps.txt
�/company-name/system_1/creo3/score.csv
.../company-name/system_1/creo3/apc.dat
�/company-name/system_1/creo3/*.tif
.../company-name/system_1/creo3/runbench.bat (if modified, as
required by rule i above)
�/company-name/system_2/creo3/result.txt
.../company-name/system_2/creo3/trail.txt
�/company-name/system_2/creo3/score-steps.txt
�/company-name/system_2/creo3/score.csv
.../company-name/system_2/creo3/apc.dat
�/company-name/system_2/creo3/*.tif
.../company-name/system_2/creo3/runbench.bat (if modified, as
required by rule i above)
etc...
- The
submission file must be named company-name_apc_creo2_vN.zip where
company-name is the member company or organization name in lower case
and vN is the file version (e.g.
dell_apc_creo2_v0.zip.) The initial submission is v0. Resubmitted files
must have the version number incremented.
- Dassault Systemes Solidworks 2020
- Siemens
PLM NX 9.0 and 10.0
- The
benchmark must be run using Siemens
PLM NX 9.0.3.4 (MaintPack5) and/or NX 10.0.2.6 (MaintPack1).
- The
NX 9 and 10 license must include the NX Shape Studio or equivalent
bundle for Advanced Studio rendering and be properly enabled by
disabling all checkboxes except Disable Dynamic Update Shadows and
Disable Dynamic Soft Shadows in the Studio Views section of the
Visualization Performance Preferences General Graphics tab.
- The
benchmark is only supported on systems running Microsoft Windows 7 and Windows 10
64-bit operating system.
- The
display resolution must be at least 1920 pixels by 1080 pixels. If the
system has an integrated display which cannot achieve 1920x1080
resolution, e.g., a notebook, the system�s maximum possible resolution
must be used.
- All
application settings must be the default settings outside of those
documented in rule f and g and the benchmark setup guide. See the document,
SPECapc_NX9-10_BenchmarkSetup, included with the benchmark, for the full
details of the benchmark setup.
- The
"Fixed Frame Rate" setting must be globally disabled.
- The
"Fit View to Stage" setting must be unchecked in the Advanced
Studio Scene Editor Stage tab.
- Any
application setting that is not the default or specified value must be
documented in the Comments field of the "apcNxResults.html"
file.
- Submissions
run on Microsoft Windows 7 and Windows 10 64-bit will be accepted for review. A
submission must include a run with FSAA enabled and may optionally
include a run with FSAA disabled.
- The
submission must contain the entire results folder generated from running
the benchmark. The results folder will be named results_sanx_nx[9|10]_[noaa|fsaa]_timestamp after a successful run of the
benchmark. All fields in the "Submission Info" panel must be
filled out prior to running the benchmark.
- The
directory structure of the submission must be as follows:
.../company-name/system_1/nx[9|10]/results_sanx_nx[9|10]_[noaa|fsaa]_timestamp/
.../company-name/system_2/nx[9|10]/results_sanx_nx[9|10]_[noaa|fsaa]_timestamp/
etc...
- The submission
file must be named company-name_apc_nx[9|10]_vN.zip where
company-name is the member company or organization name in lower case
and vN is the file version (e.g.
hp_apc_nx9_v0.zip.) The initial submission is v0. Resubmitted files must
have the version number incremented.
Adoption
V3.2: Adopted 3 December 2019 (add addition of Windows 10 submissions)
V3.1: Adopted 23 October 2019 (adds Solidworks 2019 benchmark)
V3.0: Adopted 13 July 2018 (update rules to current GWPG practices and add Solidworks 2017 benchmark)
v2.23: Adopted 27 September (adds Maya 2017 and deletes retired Maya 2012)
v2.22: Adopted 21 June 2016 (adds NX 9.0-10.0 and deletes retired NX 8.5)
v2.21: Adopted 30 June 2015 (adds SolidWorks 2015 and deletes retired SolidWorks
2013)
v2.20: Adopted 11 Dec 2014 (adds Creo 3.0 and deletes
retired Creo 2.0 and Lightwave 9.6 benchmark)
v2.19: Adopted 28 July 2014 (adds 3ds Max 2015 and deletes retired 3ds Max 2011
benchmark)
v2.17: Adopted 20 February 2013 (adds SolidWorks 2013 and deletes retired
SolidWorks 2007 benchmark)
v2.16: Adopted 6 August 2012 (PTC Creo 2 rule a.
change, adds Maya 2012 and deletes retired Maya 2009 benchmark)
v2.15: Adopted 22 May 2012 (adds PTC Creo 2 and
deletes retired WF2 benchmark)
v2.14: Adopted 30 March 2012 (adds Siemens NX 6 and deletes retired benchmark)
v2.13: Adopted 30 June 2011 (adds Autodesk 3ds max 2011 rules and deletes
retired benchmarks)
v2.12: Adopted 24 June 2009 (adds Autodesk Maya 2009 rules)
v2.11: Adopted 12 March 2009 (adds Lightwave 9.6
rules, updates NX4 rules, adds non-interaction rule)
v2.10: Adopted 13 September 2007 (reflects GPC-to-GWPG transition, and adds NX4
rules)
v2.06: Adopted 13 July 2007
v2.05: Adopted 18 April 2007
v2.04: Adopted 06 February 2007
v2.03: Adopted 20 July 2006
v2.02: Adopted 27 April 2006 for 01 May 2006 publication
v2.01: Adopted 26 January 2006
v2.00: Adopted 26 January 2006