More NVIDIA TITAN RTX vs. RTX 2080 Ti Linux

NVIDIA GeForce RTX 2080 Ti versus TITAN RTX Linux benchmarks for a future article on Phoronix by Michael Larabel.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1812283-PTS-MORENVID24
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts

Limit displaying results to tests within:

Desktop Graphics 3 Tests
NVIDIA GPU Compute 2 Tests
OpenCL 2 Tests
OpenGL Demos Test Suite 3 Tests
Steam 16 Tests
Unigine Test Suite 3 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
NVIDIA TITAN RTX
December 27 2018
  6 Hours, 43 Minutes
NVIDIA RTX 2080 Ti
December 27 2018
  6 Hours, 57 Minutes
Invert Hiding All Results Option
  6 Hours, 50 Minutes
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

NVIDIA TITAN RTX

Processor: Intel Core i9-9900K @ 5.00GHz (8 Cores / 16 Threads), Motherboard: ASUS PRIME Z390-A (0602 BIOS), Chipset: Intel Cannon Lake PCH Shared SRAM, Memory: 16384MB, Disk: 2000GB SABRENT + Samsung SSD 970 EVO 250GB, Graphics: NVIDIA TITAN RTX 24GB (1350/7000MHz), Audio: Realtek ALC1220, Monitor: Acer B286HK, Network: Intel Connection

OS: Ubuntu 18.04, Kernel: 4.19.5-041905-generic (x86_64), Desktop: GNOME Shell 3.28.3, Display Server: X Server 1.19.6, Display Driver: NVIDIA 415.23, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 10.0.132, Vulkan: 1.1.84, Compiler: GCC 7.3.0 + LLVM 6.0.0 + CUDA 10.0, File-System: ext4, Screen Resolution: 3840x2160

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: intel_pstate performance
OpenCL Notes: GPU Compute Cores: 4608
Security Notes: __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + SSB disabled via prctl and seccomp

NVIDIA RTX 2080 Ti

Changed Graphics to NVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz).

OpenCL Change: GPU Compute Cores: 4352

More NVIDIA TITAN RTX vs. RTX 2080 Ti LinuxOpenBenchmarking.orgPhoronix Test SuiteIntel Core i9-9900K @ 5.00GHz (8 Cores / 16 Threads)ASUS PRIME Z390-A (0602 BIOS)Intel Cannon Lake PCH Shared SRAM16384MB2000GB SABRENT + Samsung SSD 970 EVO 250GBNVIDIA TITAN RTX 24GB (1350/7000MHz)NVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz)Realtek ALC1220Acer B286HKIntel ConnectionUbuntu 18.044.19.5-041905-generic (x86_64)GNOME Shell 3.28.3X Server 1.19.6NVIDIA 415.234.6.0OpenCL 1.2 CUDA 10.0.1321.1.84GCC 7.3.0 + LLVM 6.0.0 + CUDA 10.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionMore NVIDIA TITAN RTX Vs. RTX 2080 Ti Linux BenchmarksSystem Logs- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v - Scaling Governor: intel_pstate performance- NVIDIA TITAN RTX: GPU Compute Cores: 4608- NVIDIA RTX 2080 Ti: GPU Compute Cores: 4352- __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + SSB disabled via prctl and seccomp

NVIDIA TITAN RTX vs. NVIDIA RTX 2080 Ti ComparisonPhoronix Test SuiteBaseline+5.4%+5.4%+10.8%+10.8%+16.2%+16.2%+21.6%+21.6%5.7%5.2%2.4%Furmark - 3840 x 2160 - Fullscreen21.7%VGG-16, FP1617.9%GiMark - 3840 x 2160 - Fullscreen15.5%AlexNet, FP1613.2%ResNet-50, FP1612.9%Inception v4, FP1612.6%Googlenet, FP1612%Write11.7%TessMark - 3840 x 2160 - Fullscreen11.3%GPU - Luxball HDR10%3840 x 2160 - Very High - SSAA 4x - Geothermal Valley8.3%3840 x 21608%Googlenet, FP327.7%VGG-16, FP327.2%3840 x 2160 - Very High - SSAA 4x - Prophets Tomb7%AlexNet, FP326.8%3840 x 2160 - High - SSAA 4x - Prophets Tomb6.8%3840 x 2160 - High - SSAA 4x - Geothermal Valley6.7%3840 x 2160 - Ultra - Vulkan6.7%Copy6.6%Double Precision6.2%GPU - Hotel6.1%GPU - Microphone6%3840 x 2160 - Fullscreen - OpenGL3840 x 2160 - Fullscreen - High - OpenGL5.5%3840 x 2160 - High - Skaven Battle5.4%3840 x 2160 - Fullscreen - Ultra - OpenGL3840 x 2160 - Fullscreen - Medium - OpenGL5.1%3840 x 2160 - Fullscreen - OpenGL5.1%3840 x 2160 - Ultra5.1%Vulkan - 3840 x 21605%Inception v4, FP325%3840 x 2160 - High - SSAA 4x - S.O.T.M5%ResNet-50, FP324.9%Integer4.9%3840 x 21604.8%3840 x 2160 - High - F.G.B4.8%G.M.B4.6%Single Precision4.6%Pixmark Piano - 3840 x 2160 - Fullscreen4.4%3840 x 2160 - Ultra - F.G.B4.4%3840 x 2160 - Ultra - Vulkan4.4%3840 x 2160 - Fullscreen - Low - OpenGL4.3%D.P.D4.3%Read4.2%3840 x 2160 - Low Quality4.1%S.P.F4.1%3840 x 2160 - Extreme4%I.C.I3.6%3840 x 2160 - GL2 Tunnel Beauty3.6%Pixmark Volplosion - 3840 x 2160 - Fullscreen3.5%Triangle - 3840 x 2160 - Fullscreen3.5%3840 x 2160 - GL2 Hot Tunnel DNA3.3%3840 x 2160 - Ultra3%3840 x 2160 - High - TAA3%3840 x 2160 - Very High - SSAA 4x - S.O.T.M3%3840 x 2160 - Ultra High - TAA2.7%3840 x 2160 - Ultra High Quality2.6%Kernel Latency3840 x 2160 - Ultra - Skaven Battle2.2%3840 x 2160 - Ultra2.1%3840 x 2160 - Ultimate2%GpuTestNVIDIA GPU Cloud TensorFlowGpuTestNVIDIA GPU Cloud TensorFlowNVIDIA GPU Cloud TensorFlowNVIDIA GPU Cloud TensorFlowNVIDIA GPU Cloud TensorFlowcl-memGpuTestLuxMarkRise of the Tomb RaiderCounter-Strike: Global OffensiveNVIDIA GPU Cloud TensorFlowNVIDIA GPU Cloud TensorFlowRise of the Tomb RaiderNVIDIA GPU Cloud TensorFlowRise of the Tomb RaiderRise of the Tomb RaiderSerious Sam 3: BFEcl-memMixbenchLuxMarkLuxMarkUnigine HeavenUnigine SuperpositionTotal War: WARHAMMER IIUnigine SuperpositionUnigine SuperpositionUnigine ValleyA Total War Saga: THRONES OF BRITANNIAThe Talos PrincipleNVIDIA GPU Cloud TensorFlowRise of the Tomb RaiderNVIDIA GPU Cloud TensorFlowMixbenchBatman: Arkham OriginsTotal War: WARHAMMER IIclpeakMixbenchGpuTestTotal War: WARHAMMER IIDawn of War IIIUnigine Superpositionclpeakcl-memDeus Ex: Mankind DividedclpeakA Total War Saga: THRONES OF BRITANNIAclpeakGeeXLabGpuTestGpuTestGeeXLabDiRT RallyF1 2017Rise of the Tomb RaiderF1 2017F1 2018clpeakTotal War: WARHAMMER IITomb RaiderXonoticNVIDIA TITAN RTXNVIDIA RTX 2080 Ti

More NVIDIA TITAN RTX vs. RTX 2080 Ti Linuxss3bfe: 3840 x 2160 - Ultra - Vulkanunigine-heaven: 3840 x 2160 - Fullscreen - OpenGLdirt-rally: 3840 x 2160 - Ultradeus-exmd: 3840 x 2160 - Low Qualitytalos-principle: Vulkan - 3840 x 2160batman-origins: 3840 x 2160unigine-valley: 3840 x 2160 - Fullscreen - OpenGLunigine-super: 3840 x 2160 - Fullscreen - Ultra - OpenGLunigine-super: 3840 x 2160 - Fullscreen - High - OpenGLunigine-super: 3840 x 2160 - Fullscreen - Medium - OpenGLunigine-super: 3840 x 2160 - Fullscreen - Low - OpenGLcsgo: 3840 x 2160f12018: 3840 x 2160 - High Qualityf12017: 3840 x 2160 - High - TAAf12018: 3840 x 2160 - Ultra High Qualitytww2: 3840 x 2160 - High - Skaven Battlef12017: 3840 x 2160 - Ultra High - TAAthronesofbritannia: 3840 x 2160 - Ultraluxmark: GPU - Microphoneluxmark: GPU - Hotelluxmark: GPU - Luxball HDRdeus-exmd: 2560 x 1440 - High Qualitydow3: 3840 x 2160 - Ultra - Vulkanmadmax: 3840 x 2160 - High - OpenGL - Landmovermadmax: 3840 x 2160 - High - OpenGL - Hope, Glory, and Dog is Deadmadmax: 3840 x 2160 - High - OpenGL - Strongholdmadmax: 3840 x 2160 - High - OpenGL - Camp Hollow Pointglmark2: 3840 x 2160riseofthetombraider: 3840 x 2160 - High - SSAA 4x - Geothermal Valleyriseofthetombraider: 3840 x 2160 - High - SSAA 4x - Prophets Tombriseofthetombraider: 3840 x 2160 - High - SSAA 4x - Spine Of The Mountainthronesofbritannia: 3840 x 2160 - Extremetww2: 3840 x 2160 - Ultra - Skaven Battletww2: 3840 x 2160 - High - Fallen Gates Battletww2: 3840 x 2160 - Ultra - Fallen Gates Battlegputest: Pixmark Piano - 3840 x 2160 - Fullscreenngc-tensorflow: Inception v4, FP32tomb-raider: 3840 x 2160 - Ultrametro2033-redux: ngc-tensorflow: Inception v4, FP16riseofthetombraider: 3840 x 2160 - Very High - SSAA 4x - Geothermal Valleyriseofthetombraider: 3840 x 2160 - Very High - SSAA 4x - Prophets Tombriseofthetombraider: 3840 x 2160 - Very High - SSAA 4x - Spine Of The Mountaingputest: GiMark - 3840 x 2160 - Fullscreengputest: Pixmark Volplosion - 3840 x 2160 - Fullscreengputest: TessMark - 3840 x 2160 - Fullscreengputest: Furmark - 3840 x 2160 - Fullscreengputest: Triangle - 3840 x 2160 - Fullscreenngc-tensorflow: Googlenet, FP32xplane11: Very High GPU - 3840 x 2160ngc-tensorflow: Googlenet, FP16ngc-tensorflow: VGG-16, FP32dota2: 3840 x 2160 - Vulkanngc-tensorflow: ResNet-50, FP32clpeak: Double-Precision Doublexonotic: 3840 x 2160 - Ultimatengc-tensorflow: ResNet-50, FP16ngc-tensorflow: VGG-16, FP16ngc-tensorflow: AlexNet, FP32ngc-tensorflow: AlexNet, FP16geexlab: 3840 x 2160 - GL2 Hot Tunnel DNAgeexlab: 3840 x 2160 - GL2 Tunnel Beautyclpeak: Transfer Bandwidth enqueueReadBufferclpeak: Integer Compute INTclpeak: Single-Precision Floatcl-mem: Writecl-mem: Readcl-mem: Copymixbench: Integerclpeak: Global Memory Bandwidthmixbench: Single Precisionmixbench: Double Precisionclpeak: Kernel LatencyNVIDIA TITAN RTXNVIDIA RTX 2080 Ti78.1970.5613671.6714617381.9811.5042.9361.9014628416513911985.1311658.803057497444656083.8380.5142.4436.4641.1339.59239038.8036.1051.7031.6365.9067.0754.20195594.1791.8314715234.5534.5548.6515499414630125708916007382333.7311321631462985383025092443571500728026111.40155151683949556748317326528172904663.8873.2774.5813268.8313916578.0212.1040.7058.9014026316213511680.8011355.972885591824234682.5377.1442.4436.4641.1339.59235636.3533.8049.2530.4064.5064.0051.93187289.7089.9014813531.9032.3047.2513421400527077582715467576433.8010111521442845162964512073343442527125211.36149791617444354445316524505165374393.79OpenBenchmarking.org

Serious Sam 3: BFE

This is a benchmark of Serious Sam 3: BFE with the Fusion 2017 update. The test profile assumes you have a Steam account, have Steam installed for the system, and that you own the game. This automates the process of executing the game and using a standardized test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSerious Sam 3: BFEResolution: 3840 x 2160 - Quality: Ultra - Renderer: VulkanNVIDIA TITAN RTXNVIDIA RTX 2080 Ti20406080100SE +/- 1.95, N = 12SE +/- 1.73, N = 1278.1973.27

Unigine Heaven

This test calculates the average frame-rate within the Heaven demo for the Unigine engine. This engine is extremely demanding on the system's graphics card. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Heaven 4.0Resolution: 3840 x 2160 - Mode: Fullscreen - Renderer: OpenGLNVIDIA RTX 2080 TiNVIDIA TITAN RTX20406080100SE +/- 0.04, N = 3SE +/- 0.15, N = 374.5870.56

DiRT Rally

This is a benchmark of DiRT Rally on Steam. The test profile assumes you have a Steam account, have Steam installed for the system, and that you own a copy of this game. This automates the process of executing the game and using its built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterDiRT RallyResolution: 3840 x 2160 - Graphics Preset: UltraNVIDIA TITAN RTXNVIDIA RTX 2080 Ti306090120150SE +/- 0.19, N = 3SE +/- 0.14, N = 3136132

Deus Ex: Mankind Divided

This is a benchmark of Deus Ex: Mankind Divided on Steam. The test profile assumes you have a Steam account, have Steam installed for the system, and that you own a copy of this game. This automates the process of executing the game and using its built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterDeus Ex: Mankind DividedPreset: 3840 x 2160 - Low QualityNVIDIA TITAN RTXNVIDIA RTX 2080 Ti1632486480SE +/- 0.37, N = 3SE +/- 0.44, N = 371.6768.83MIN: 56.1 / MAX: 91.8MIN: 54.1 / MAX: 88.7

The Talos Principle

This is a benchmark of The Talos Principle. The test profile assumes you have a Steam account, have Steam installed for the system, and that The Talos Principle can be installed. This automates the process of executing the game and using a standardized time demo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterThe Talos PrincipleRenderer: Vulkan - Resolution: 3840 x 2160NVIDIA TITAN RTXNVIDIA RTX 2080 Ti306090120150SE +/- 1.61, N = 11SE +/- 2.00, N = 11146139

Batman: Arkham Origins

This is a benchmark of >Batman: Arkham Origins running under Steam Play (Proton) on Linux. The test profile assumes you have a Steam account, have Steam installed for the system, and that Batman: Arkham Origins is already purchased/installed. This automates the process of executing the game and using a standardized time demo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterBatman: Arkham OriginsResolution: 3840 x 2160NVIDIA TITAN RTXNVIDIA RTX 2080 Ti4080120160200SE +/- 1.45, N = 3SE +/- 1.46, N = 3173165MIN: 5.99 / MAX: 272.52MIN: 61 / MAX: 210.24

Unigine Valley

This test calculates the average frame-rate within the Valley demo for the Unigine engine, released in February 2013. This engine is extremely demanding on the system's graphics card. Unigine Valley relies upon an OpenGL 3 core profile context. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Valley 1.0Resolution: 3840 x 2160 - Mode: Fullscreen - Renderer: OpenGLNVIDIA TITAN RTXNVIDIA RTX 2080 Ti20406080100SE +/- 0.02, N = 3SE +/- 0.02, N = 381.9878.02

Unigine Superposition

This test calculates the average frame-rate within the Superposition demo for the Unigine engine, released in 2017. This engine is extremely demanding on the system's graphics card. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Superposition 1.0Resolution: 3840 x 2160 - Mode: Fullscreen - Quality: Ultra - Renderer: OpenGLNVIDIA RTX 2080 TiNVIDIA TITAN RTX3691215SE +/- 0.00, N = 3SE +/- 0.00, N = 312.1011.50MAX: 14.3MAX: 13.2

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Superposition 1.0Resolution: 3840 x 2160 - Mode: Fullscreen - Quality: High - Renderer: OpenGLNVIDIA TITAN RTXNVIDIA RTX 2080 Ti1020304050SE +/- 0.03, N = 3SE +/- 0.06, N = 342.9340.70MAX: 48.6MAX: 46.1

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Superposition 1.0Resolution: 3840 x 2160 - Mode: Fullscreen - Quality: Medium - Renderer: OpenGLNVIDIA TITAN RTXNVIDIA RTX 2080 Ti1428425670SE +/- 0.06, N = 3SE +/- 0.00, N = 361.9058.90MAX: 72.8MAX: 68.8

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Superposition 1.0Resolution: 3840 x 2160 - Mode: Fullscreen - Quality: Low - Renderer: OpenGLNVIDIA TITAN RTXNVIDIA RTX 2080 Ti306090120150SE +/- 0.32, N = 3SE +/- 0.07, N = 3146140MAX: 185.9MAX: 180.3

Counter-Strike: Global Offensive

OpenBenchmarking.orgMilliseconds, Fewer Is BetterCounter-Strike: Global OffensiveResolution: 3840 x 2160 - Total Frame TimeNVIDIA TITAN RTXNVIDIA RTX 2080 Ti7001400210028003500Min: 1.93 / Avg: 4.53 / Max: 3842.37Min: 1.85 / Avg: 4.58 / Max: 3831.8

OpenBenchmarking.orgFrames Per Second, More Is BetterCounter-Strike: Global OffensiveResolution: 3840 x 2160NVIDIA TITAN RTXNVIDIA RTX 2080 Ti60120180240300SE +/- 1.55, N = 3SE +/- 30.54, N = 9284263

F1 2018

OpenBenchmarking.orgMilliseconds, Fewer Is BetterF1 2018Configuration: 3840 x 2160 - High Quality - Total Frame TimeNVIDIA TITAN RTXNVIDIA RTX 2080 Ti1632486480Min: 3.7 / Avg: 6.03 / Max: 83.3Min: 3.77 / Avg: 6.17 / Max: 83.3

OpenBenchmarking.orgFrames Per Second, More Is BetterF1 2018Configuration: 3840 x 2160 - High QualityNVIDIA TITAN RTXNVIDIA RTX 2080 Ti4080120160200SE +/- 0.33, N = 3SE +/- 0.33, N = 3165162MIN: 17 / MAX: 207MIN: 34 / MAX: 204

F1 2017

F1 2017 on Steam. The test profile assumes you have a Steam account, have Steam installed for the system, and that you own a copy of this game. This automates the process of executing the game and using its built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterF1 2017Resolution: 3840 x 2160 - Graphics Preset: High - Anti Aliasing: TAANVIDIA TITAN RTXNVIDIA RTX 2080 Ti306090120150SE +/- 0.58, N = 3139135MIN: 120 / MAX: 160MIN: 118 / MAX: 155

F1 2018

OpenBenchmarking.orgMilliseconds, Fewer Is BetterF1 2018Configuration: 3840 x 2160 - Ultra High Quality - Total Frame TimeNVIDIA TITAN RTXNVIDIA RTX 2080 Ti1632486480Min: 4.76 / Avg: 8.35 / Max: 83.3Min: 4.55 / Avg: 8.61 / Max: 83.3

OpenBenchmarking.orgFrames Per Second, More Is BetterF1 2018Configuration: 3840 x 2160 - Ultra High QualityNVIDIA TITAN RTXNVIDIA RTX 2080 Ti306090120150SE +/- 0.33, N = 3119116MIN: 41 / MAX: 158MIN: 34 / MAX: 153

Total War: WARHAMMER II

OpenBenchmarking.orgMilliseconds, Fewer Is BetterTotal War: WARHAMMER II 1.0Resolution: 3840 x 2160 - Graphics Preset: High - Scenario: Skaven Battle - Total Frame TimeNVIDIA TITAN RTXNVIDIA RTX 2080 Ti1326395265Min: 5.3 / Avg: 11.69 / Max: 66.6Min: 4.9 / Avg: 12.58 / Max: 67.7

OpenBenchmarking.orgFrames Per Second, More Is BetterTotal War: WARHAMMER II 1.0Resolution: 3840 x 2160 - Graphics Preset: High - Scenario: Skaven BattleNVIDIA TITAN RTXNVIDIA RTX 2080 Ti20406080100SE +/- 1.01, N = 3SE +/- 0.89, N = 385.1380.80MIN: 14.6 / MAX: 223.9MIN: 12.9 / MAX: 202.5

F1 2017

F1 2017 on Steam. The test profile assumes you have a Steam account, have Steam installed for the system, and that you own a copy of this game. This automates the process of executing the game and using its built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterF1 2017Resolution: 3840 x 2160 - Graphics Preset: Ultra High - Anti Aliasing: TAANVIDIA TITAN RTXNVIDIA RTX 2080 Ti306090120150SE +/- 0.58, N = 3116113MIN: 93 / MAX: 140MIN: 93 / MAX: 137

A Total War Saga: THRONES OF BRITANNIA

OpenBenchmarking.orgMilliseconds, Fewer Is BetterA Total War Saga: THRONES OF BRITANNIAResolution: 3840 x 2160 - Graphics Preset: Ultra - Total Frame TimeNVIDIA TITAN RTXNVIDIA RTX 2080 Ti50100150200250Min: 7.2 / Avg: 17.06 / Max: 253.9Min: 8.9 / Avg: 17.86 / Max: 267

OpenBenchmarking.orgFrames Per Second, More Is BetterA Total War Saga: THRONES OF BRITANNIAResolution: 3840 x 2160 - Graphics Preset: UltraNVIDIA TITAN RTXNVIDIA RTX 2080 Ti1326395265SE +/- 0.20, N = 3SE +/- 0.03, N = 358.8055.97MIN: 3.7 / MAX: 139.6MIN: 3.6 / MAX: 118.5

LuxMark

LuxMark is a multi-platform OpenGL benchmark using LuxRender. LuxMark supports targeting different OpenCL devices and has multiple scenes available for rendering. LuxMark is a fully open-source OpenCL program with real-world rendering examples. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.1OpenCL Device: GPU - Scene: MicrophoneNVIDIA TITAN RTXNVIDIA RTX 2080 Ti7K14K21K28K35KSE +/- 5.81, N = 3SE +/- 10.17, N = 33057428855

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.1OpenCL Device: GPU - Scene: HotelNVIDIA TITAN RTXNVIDIA RTX 2080 Ti2K4K6K8K10KSE +/- 8.69, N = 3SE +/- 3.06, N = 397449182

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.1OpenCL Device: GPU - Scene: Luxball HDRNVIDIA TITAN RTXNVIDIA RTX 2080 Ti10K20K30K40K50KSE +/- 27.87, N = 3SE +/- 20.74, N = 34656042346

Deus Ex: Mankind Divided

This is a benchmark of Deus Ex: Mankind Divided on Steam. The test profile assumes you have a Steam account, have Steam installed for the system, and that you own a copy of this game. This automates the process of executing the game and using its built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterDeus Ex: Mankind DividedPreset: 2560 x 1440 - High QualityNVIDIA TITAN RTXNVIDIA RTX 2080 Ti20406080100SE +/- 0.44, N = 3SE +/- 0.13, N = 383.8382.53MIN: 60.5 / MAX: 115.9MIN: 60.2 / MAX: 112.2

Dawn of War III

Dawn of War III Mad Max on Steam. The test profile assumes you have a Steam account, have Steam installed for the system, and that you own a copy of this game. This automates the process of executing the game and using its built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterDawn of War IIIResolution: 3840 x 2160 - Graphics Preset: Ultra - Renderer: VulkanNVIDIA TITAN RTXNVIDIA RTX 2080 Ti20406080100SE +/- 0.67, N = 3SE +/- 0.51, N = 380.5177.14MIN: 70.23 / MAX: 116.88MIN: 66.67 / MAX: 111.89

Mad Max

This is a benchmark of Mad Max on Steam. The test profile assumes you have a Steam account, have Steam installed for the system, and that you own a copy of this game. This automates the process of executing the game and using its built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterMad MaxResolution: 3840 x 2160 - Graphics Preset: High - Renderer: OpenGL - Scene: LandmoverNVIDIA RTX 2080 TiNVIDIA TITAN RTX102030405042.4442.44MIN: 18.36 / MAX: 2564.1MIN: 18.36 / MAX: 2564.1

OpenBenchmarking.orgFrames Per Second, More Is BetterMad MaxResolution: 3840 x 2160 - Graphics Preset: High - Renderer: OpenGL - Scene: Hope, Glory, and Dog is DeadNVIDIA RTX 2080 TiNVIDIA TITAN RTX81624324036.4636.46MIN: 17.73 / MAX: 51.64MIN: 17.73 / MAX: 51.64

OpenBenchmarking.orgFrames Per Second, More Is BetterMad MaxResolution: 3840 x 2160 - Graphics Preset: High - Renderer: OpenGL - Scene: StrongholdNVIDIA RTX 2080 TiNVIDIA TITAN RTX91827364541.1341.13MIN: 39.37 / MAX: 42.57MIN: 39.37 / MAX: 42.57

OpenBenchmarking.orgFrames Per Second, More Is BetterMad MaxResolution: 3840 x 2160 - Graphics Preset: High - Renderer: OpenGL - Scene: Camp Hollow PointNVIDIA RTX 2080 TiNVIDIA TITAN RTX91827364539.5939.59MIN: 38 / MAX: 40.78MIN: 38 / MAX: 40.78

GLmark2

This is a test of any system-installed GLMark2 OpenGL benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterGLmark2Resolution: 3840 x 2160NVIDIA TITAN RTXNVIDIA RTX 2080 Ti500100015002000250023902356

Rise of the Tomb Raider

Rise of the Tomb Raider on Steam. The test profile assumes you have a Steam account, have Steam installed for the system, and that you own a copy of this game. This automates the process of executing the game and using its built-in benchmark mode. Backs up old preferences (in ~/.local/share/feral-interactive/) for the run. NOTES for cross-platform comparisons: Due to the extreme demands of "Very High" 4K Texture Detail on all platforms, which can need ~6GB+ of VRAM, the "Very High" graphics preset on Linux only sets Texture Detail to "High". Nvidia ambient occlusion modes are not featured on the Linux version (HBAO+ and VXAO). See notes in install.sh for a few small tweaks including disabling the CPU governor check when testing for it's effects Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterRise of the Tomb RaiderResolution: 3840 x 2160 - Graphics Preset: High - Anti Aliasing: SSAA 4x - Scene: Geothermal ValleyNVIDIA TITAN RTXNVIDIA RTX 2080 Ti918273645SE +/- 0.80, N = 2SE +/- 0.55, N = 238.8036.35MIN: 25 / MAX: 47.6MIN: 28.3 / MAX: 46.8

OpenBenchmarking.orgFrames Per Second, More Is BetterRise of the Tomb RaiderResolution: 3840 x 2160 - Graphics Preset: High - Anti Aliasing: SSAA 4x - Scene: Prophets TombNVIDIA TITAN RTXNVIDIA RTX 2080 Ti816243240SE +/- 0.10, N = 2SE +/- 0.10, N = 236.1033.80MIN: 27.6 / MAX: 39.7MIN: 27.5 / MAX: 36.8

OpenBenchmarking.orgFrames Per Second, More Is BetterRise of the Tomb RaiderResolution: 3840 x 2160 - Graphics Preset: High - Anti Aliasing: SSAA 4x - Scene: Spine Of The MountainNVIDIA TITAN RTXNVIDIA RTX 2080 Ti1224364860SE +/- 0.70, N = 2SE +/- 0.15, N = 251.7049.25MIN: 26.9 / MAX: 113.7MIN: 25.7 / MAX: 89.4

A Total War Saga: THRONES OF BRITANNIA

OpenBenchmarking.orgMilliseconds, Fewer Is BetterA Total War Saga: THRONES OF BRITANNIAResolution: 3840 x 2160 - Graphics Preset: Extreme - Total Frame TimeNVIDIA TITAN RTXNVIDIA RTX 2080 Ti50100150200250Min: 10.1 / Avg: 31.63 / Max: 247Min: 9.9 / Avg: 32.78 / Max: 275.5

OpenBenchmarking.orgFrames Per Second, More Is BetterA Total War Saga: THRONES OF BRITANNIAResolution: 3840 x 2160 - Graphics Preset: ExtremeNVIDIA TITAN RTXNVIDIA RTX 2080 Ti714212835SE +/- 0.03, N = 3SE +/- 0.10, N = 331.6330.40MIN: 3.9 / MAX: 98.7MIN: 3.6 / MAX: 100.6

Total War: WARHAMMER II

OpenBenchmarking.orgMilliseconds, Fewer Is BetterTotal War: WARHAMMER II 1.0Resolution: 3840 x 2160 - Graphics Preset: Ultra - Scenario: Skaven Battle - Total Frame TimeNVIDIA TITAN RTXNVIDIA RTX 2080 Ti160320480640800Min: 6.7 / Avg: 15.3 / Max: 896.7Min: 8 / Avg: 15.58 / Max: 67.3

OpenBenchmarking.orgFrames Per Second, More Is BetterTotal War: WARHAMMER II 1.0Resolution: 3840 x 2160 - Graphics Preset: Ultra - Scenario: Skaven BattleNVIDIA TITAN RTXNVIDIA RTX 2080 Ti1530456075SE +/- 0.29, N = 3SE +/- 0.15, N = 365.9064.50MIN: 1.1 / MAX: 167.4MIN: 14.8 / MAX: 170.1

OpenBenchmarking.orgMilliseconds, Fewer Is BetterTotal War: WARHAMMER II 1.0Resolution: 3840 x 2160 - Graphics Preset: High - Scenario: Fallen Gates Battle - Total Frame TimeNVIDIA TITAN RTXNVIDIA RTX 2080 Ti1122334455Min: 5.3 / Avg: 14.88 / Max: 54.1Min: 5.3 / Avg: 15.65 / Max: 57.8

OpenBenchmarking.orgFrames Per Second, More Is BetterTotal War: WARHAMMER II 1.0Resolution: 3840 x 2160 - Graphics Preset: High - Scenario: Fallen Gates BattleNVIDIA TITAN RTXNVIDIA RTX 2080 Ti1530456075SE +/- 0.09, N = 3SE +/- 0.06, N = 367.0764.00MIN: 17.7 / MAX: 204MIN: 17.3 / MAX: 200.8

OpenBenchmarking.orgMilliseconds, Fewer Is BetterTotal War: WARHAMMER II 1.0Resolution: 3840 x 2160 - Graphics Preset: Ultra - Scenario: Fallen Gates Battle - Total Frame TimeNVIDIA TITAN RTXNVIDIA RTX 2080 Ti1224364860Min: 7.3 / Avg: 18.45 / Max: 59.5Min: 4.6 / Avg: 19.28 / Max: 61.6

OpenBenchmarking.orgFrames Per Second, More Is BetterTotal War: WARHAMMER II 1.0Resolution: 3840 x 2160 - Graphics Preset: Ultra - Scenario: Fallen Gates BattleNVIDIA TITAN RTXNVIDIA RTX 2080 Ti1224364860SE +/- 0.00, N = 3SE +/- 0.03, N = 354.2051.93MIN: 16.5 / MAX: 202.1MIN: 16.2 / MAX: 219.2

GpuTest

GpuTest is a cross-platform OpenGL benchmark developed at Geeks3D.com that offers tech demos such as FurMark, TessMark, and other workloads to stress various areas of GPUs and drivers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Pixmark Piano - Resolution: 3840 x 2160 - Mode: FullscreenNVIDIA TITAN RTXNVIDIA RTX 2080 Ti400800120016002000SE +/- 27.16, N = 5SE +/- 33.41, N = 319551872

NVIDIA GPU Cloud TensorFlow

This test profile uses the NVIDIA GPU Cloud (NGC/nvcr.io) for running the TensorFlow image inside Docker for benchmarking. You must have already signed into NGC for this test profile to work. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: Inception v4, FP32NVIDIA TITAN RTXNVIDIA RTX 2080 Ti20406080100SE +/- 0.03, N = 3SE +/- 0.06, N = 394.1789.70

Tomb Raider

This is a benchmark of the Tomb Raider (2013) game. The test profile assumes you have a Steam account, have Steam installed for the system, and that you own Tomb Raider. This automates the process of executing the game and using the built-in benchmark functionality. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterTomb RaiderResolution: 3840 x 2160 - Quality: UltraNVIDIA TITAN RTXNVIDIA RTX 2080 Ti20406080100SE +/- 0.07, N = 3SE +/- 0.15, N = 391.8389.90MIN: 73.6 / MAX: 105.6MIN: 71.7 / MAX: 102.8

Metro 2033 Redux

A Steam-based test of the Metro 2033 Redux game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterMetro 2033 ReduxNVIDIA RTX 2080 TiNVIDIA TITAN RTX306090120150SE +/- 0.99, N = 3SE +/- 0.23, N = 3148147

NVIDIA GPU Cloud TensorFlow

This test profile uses the NVIDIA GPU Cloud (NGC/nvcr.io) for running the TensorFlow image inside Docker for benchmarking. You must have already signed into NGC for this test profile to work. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: Inception v4, FP16NVIDIA TITAN RTXNVIDIA RTX 2080 Ti306090120150SE +/- 0.09, N = 3SE +/- 0.09, N = 3152135

Rise of the Tomb Raider

Rise of the Tomb Raider on Steam. The test profile assumes you have a Steam account, have Steam installed for the system, and that you own a copy of this game. This automates the process of executing the game and using its built-in benchmark mode. Backs up old preferences (in ~/.local/share/feral-interactive/) for the run. NOTES for cross-platform comparisons: Due to the extreme demands of "Very High" 4K Texture Detail on all platforms, which can need ~6GB+ of VRAM, the "Very High" graphics preset on Linux only sets Texture Detail to "High". Nvidia ambient occlusion modes are not featured on the Linux version (HBAO+ and VXAO). See notes in install.sh for a few small tweaks including disabling the CPU governor check when testing for it's effects Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterRise of the Tomb RaiderResolution: 3840 x 2160 - Graphics Preset: Very High - Anti Aliasing: SSAA 4x - Scene: Geothermal ValleyNVIDIA TITAN RTXNVIDIA RTX 2080 Ti816243240SE +/- 0.05, N = 2SE +/- 0.00, N = 234.5531.90MIN: 26.5 / MAX: 44.1MIN: 26.2 / MAX: 41.9

OpenBenchmarking.orgFrames Per Second, More Is BetterRise of the Tomb RaiderResolution: 3840 x 2160 - Graphics Preset: Very High - Anti Aliasing: SSAA 4x - Scene: Prophets TombNVIDIA TITAN RTXNVIDIA RTX 2080 Ti816243240SE +/- 0.05, N = 2SE +/- 0.00, N = 234.5532.30MIN: 15.9 / MAX: 78.1MIN: 14.9 / MAX: 65

OpenBenchmarking.orgFrames Per Second, More Is BetterRise of the Tomb RaiderResolution: 3840 x 2160 - Graphics Preset: Very High - Anti Aliasing: SSAA 4x - Scene: Spine Of The MountainNVIDIA TITAN RTXNVIDIA RTX 2080 Ti1122334455SE +/- 0.25, N = 2SE +/- 0.25, N = 248.6547.25MIN: 25.1 / MAX: 71.1MIN: 23.7 / MAX: 70.7

GpuTest

GpuTest is a cross-platform OpenGL benchmark developed at Geeks3D.com that offers tech demos such as FurMark, TessMark, and other workloads to stress various areas of GPUs and drivers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: GiMark - Resolution: 3840 x 2160 - Mode: FullscreenNVIDIA TITAN RTXNVIDIA RTX 2080 Ti3K6K9K12K15KSE +/- 29.87, N = 3SE +/- 70.06, N = 31549913421

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Pixmark Volplosion - Resolution: 3840 x 2160 - Mode: FullscreenNVIDIA TITAN RTXNVIDIA RTX 2080 Ti9001800270036004500SE +/- 6.89, N = 3SE +/- 5.13, N = 341464005

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: TessMark - Resolution: 3840 x 2160 - Mode: FullscreenNVIDIA TITAN RTXNVIDIA RTX 2080 Ti6K12K18K24K30KSE +/- 43.11, N = 3SE +/- 11.15, N = 33012527077

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Furmark - Resolution: 3840 x 2160 - Mode: FullscreenNVIDIA TITAN RTXNVIDIA RTX 2080 Ti15003000450060007500SE +/- 66.42, N = 3SE +/- 1.15, N = 370895827

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Triangle - Resolution: 3840 x 2160 - Mode: FullscreenNVIDIA TITAN RTXNVIDIA RTX 2080 Ti30K60K90K120K150KSE +/- 784.94, N = 3SE +/- 345.22, N = 3160073154675

NVIDIA GPU Cloud TensorFlow

This test profile uses the NVIDIA GPU Cloud (NGC/nvcr.io) for running the TensorFlow image inside Docker for benchmarking. You must have already signed into NGC for this test profile to work. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: Googlenet, FP32NVIDIA TITAN RTXNVIDIA RTX 2080 Ti2004006008001000SE +/- 0.66, N = 3SE +/- 0.18, N = 3823764

X-Plane

This is a test of X-Plane, a realistic multi-platform flight simulator designed for personal computers. This is commercial closed-source software and relies upon the Steam version. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterX-Plane 11Quality: Very High GPU - Resolution: 3840 x 2160NVIDIA RTX 2080 TiNVIDIA TITAN RTX81624324033.8033.73

NVIDIA GPU Cloud TensorFlow

This test profile uses the NVIDIA GPU Cloud (NGC/nvcr.io) for running the TensorFlow image inside Docker for benchmarking. You must have already signed into NGC for this test profile to work. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: Googlenet, FP16NVIDIA TITAN RTXNVIDIA RTX 2080 Ti2004006008001000SE +/- 1.75, N = 3SE +/- 0.81, N = 311321011

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: VGG-16, FP32NVIDIA TITAN RTXNVIDIA RTX 2080 Ti4080120160200SE +/- 0.15, N = 3SE +/- 0.07, N = 3163152

Dota 2

This is a benchmark of Valve's Dota 2 game. The test profile assumes you have a Steam account, have Steam installed for the system, and that you have rights to Dota 2. This automates the process of executing the game and using a standardized time demo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterDota 2Resolution: 3840 x 2160 - Renderer: VulkanNVIDIA TITAN RTXNVIDIA RTX 2080 Ti306090120150SE +/- 1.35, N = 3SE +/- 1.42, N = 12146144MIN: 143.9 / MAX: 148.4MIN: 129 / MAX: 148

NVIDIA GPU Cloud TensorFlow

This test profile uses the NVIDIA GPU Cloud (NGC/nvcr.io) for running the TensorFlow image inside Docker for benchmarking. You must have already signed into NGC for this test profile to work. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: ResNet-50, FP32NVIDIA TITAN RTXNVIDIA RTX 2080 Ti60120180240300SE +/- 0.33, N = 3SE +/- 0.15, N = 3298284

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision DoubleNVIDIA TITAN RTXNVIDIA RTX 2080 Ti120240360480600SE +/- 0.01, N = 3SE +/- 0.39, N = 3538516

Xonotic

This is a benchmark of Xonotic, which is a fork of the DarkPlaces-based Nexuiz game. Development began in March of 2010 on the Xonotic game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: UltimateNVIDIA TITAN RTXNVIDIA RTX 2080 Ti70140210280350SE +/- 0.61, N = 3SE +/- 0.95, N = 3302296MIN: 58 / MAX: 564MIN: 57 / MAX: 534

NVIDIA GPU Cloud TensorFlow

This test profile uses the NVIDIA GPU Cloud (NGC/nvcr.io) for running the TensorFlow image inside Docker for benchmarking. You must have already signed into NGC for this test profile to work. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: ResNet-50, FP16NVIDIA TITAN RTXNVIDIA RTX 2080 Ti110220330440550SE +/- 4.92, N = 3SE +/- 4.34, N = 3509451

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: VGG-16, FP16NVIDIA TITAN RTXNVIDIA RTX 2080 Ti50100150200250SE +/- 0.19, N = 3SE +/- 0.12, N = 3244207

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: AlexNet, FP32NVIDIA TITAN RTXNVIDIA RTX 2080 Ti8001600240032004000SE +/- 2.31, N = 3SE +/- 3.38, N = 335713343

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: AlexNet, FP16NVIDIA TITAN RTXNVIDIA RTX 2080 Ti11002200330044005500SE +/- 4.94, N = 3SE +/- 2.32, N = 350074425

GeeXLab

GeeXLab is a cross-platform tool for 3D programming and demo creation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterGeeXLab 0.25.3.0Resolution: 3840 x 2160 - Test: GL2 Hot Tunnel DNANVIDIA TITAN RTXNVIDIA RTX 2080 Ti60120180240300SE +/- 1.05, N = 3SE +/- 0.58, N = 3280271

OpenBenchmarking.orgFPS, More Is BetterGeeXLab 0.25.3.0Resolution: 3840 x 2160 - Test: GL2 Tunnel BeautyNVIDIA TITAN RTXNVIDIA RTX 2080 Ti60120180240300SE +/- 0.63, N = 3SE +/- 0.40, N = 3261252

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Transfer Bandwidth enqueueReadBufferNVIDIA TITAN RTXNVIDIA RTX 2080 Ti3691215SE +/- 0.01, N = 3SE +/- 0.00, N = 311.4011.36

OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INTNVIDIA TITAN RTXNVIDIA RTX 2080 Ti3K6K9K12K15KSE +/- 248.70, N = 11SE +/- 183.60, N = 121551514979

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision FloatNVIDIA TITAN RTXNVIDIA RTX 2080 Ti4K8K12K16K20KSE +/- 270.99, N = 12SE +/- 245.91, N = 121683916174

cl-mem

A basic OpenCL memory benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteNVIDIA TITAN RTXNVIDIA RTX 2080 Ti110220330440550SE +/- 3.64, N = 3SE +/- 1.47, N = 34954431. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadNVIDIA TITAN RTXNVIDIA RTX 2080 Ti120240360480600SE +/- 0.27, N = 3SE +/- 0.20, N = 35675441. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyNVIDIA TITAN RTXNVIDIA RTX 2080 Ti100200300400500SE +/- 0.03, N = 3SE +/- 0.43, N = 34834531. (CC) gcc options: -O2 -flto -lOpenCL

Mixbench

A benchmark suite for GPUs on mixed operational intensity kernels. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGIOPS, More Is BetterMixbench 2016-06-06Benchmark: IntegerNVIDIA TITAN RTXNVIDIA RTX 2080 Ti4K8K12K16K20KSE +/- 17.31, N = 3SE +/- 46.18, N = 317326165241. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory BandwidthNVIDIA TITAN RTXNVIDIA RTX 2080 Ti110220330440550SE +/- 0.99, N = 3SE +/- 0.70, N = 3528505

Mixbench

A benchmark suite for GPUs on mixed operational intensity kernels. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2016-06-06Benchmark: Single PrecisionNVIDIA TITAN RTXNVIDIA RTX 2080 Ti4K8K12K16K20KSE +/- 51.05, N = 3SE +/- 7.39, N = 317290165371. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2016-06-06Benchmark: Double PrecisionNVIDIA TITAN RTXNVIDIA RTX 2080 Ti100200300400500SE +/- 1.75, N = 3SE +/- 5.61, N = 34664391. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus, Fewer Is BetterclpeakOpenCL Test: Kernel LatencyNVIDIA RTX 2080 TiNVIDIA TITAN RTX0.8731.7462.6193.4924.365SE +/- 0.07, N = 4SE +/- 0.03, N = 33.793.88

82 Results Shown

Serious Sam 3: BFE
Unigine Heaven
DiRT Rally
Deus Ex: Mankind Divided
The Talos Principle
Batman: Arkham Origins
Unigine Valley
Unigine Superposition:
  3840 x 2160 - Fullscreen - Ultra - OpenGL
  3840 x 2160 - Fullscreen - High - OpenGL
  3840 x 2160 - Fullscreen - Medium - OpenGL
  3840 x 2160 - Fullscreen - Low - OpenGL
Counter-Strike: Global Offensive
Counter-Strike: Global Offensive
F1 2018
F1 2018
F1 2017
F1 2018
F1 2018
Total War: WARHAMMER II
Total War: WARHAMMER II
F1 2017
A Total War Saga: THRONES OF BRITANNIA
A Total War Saga: THRONES OF BRITANNIA
LuxMark:
  GPU - Microphone
  GPU - Hotel
  GPU - Luxball HDR
Deus Ex: Mankind Divided
Dawn of War III
Mad Max:
  3840 x 2160 - High - OpenGL - Landmover
  3840 x 2160 - High - OpenGL - Hope, Glory, and Dog is Dead
  3840 x 2160 - High - OpenGL - Stronghold
  3840 x 2160 - High - OpenGL - Camp Hollow Point
GLmark2
Rise of the Tomb Raider:
  3840 x 2160 - High - SSAA 4x - Geothermal Valley
  3840 x 2160 - High - SSAA 4x - Prophets Tomb
  3840 x 2160 - High - SSAA 4x - Spine Of The Mountain
A Total War Saga: THRONES OF BRITANNIA
A Total War Saga: THRONES OF BRITANNIA
Total War: WARHAMMER II
Total War: WARHAMMER II
Total War: WARHAMMER II
Total War: WARHAMMER II
Total War: WARHAMMER II
Total War: WARHAMMER II
GpuTest
NVIDIA GPU Cloud TensorFlow
Tomb Raider
Metro 2033 Redux
NVIDIA GPU Cloud TensorFlow
Rise of the Tomb Raider:
  3840 x 2160 - Very High - SSAA 4x - Geothermal Valley
  3840 x 2160 - Very High - SSAA 4x - Prophets Tomb
  3840 x 2160 - Very High - SSAA 4x - Spine Of The Mountain
GpuTest:
  GiMark - 3840 x 2160 - Fullscreen
  Pixmark Volplosion - 3840 x 2160 - Fullscreen
  TessMark - 3840 x 2160 - Fullscreen
  Furmark - 3840 x 2160 - Fullscreen
  Triangle - 3840 x 2160 - Fullscreen
NVIDIA GPU Cloud TensorFlow
X-Plane
NVIDIA GPU Cloud TensorFlow:
  Googlenet, FP16
  VGG-16, FP32
Dota 2
NVIDIA GPU Cloud TensorFlow
clpeak
Xonotic
NVIDIA GPU Cloud TensorFlow:
  ResNet-50, FP16
  VGG-16, FP16
  AlexNet, FP32
  AlexNet, FP16
GeeXLab:
  3840 x 2160 - GL2 Hot Tunnel DNA
  3840 x 2160 - GL2 Tunnel Beauty
clpeak:
  Transfer Bandwidth enqueueReadBuffer
  Integer Compute INT
  Single-Precision Float
cl-mem:
  Write
  Read
  Copy
Mixbench
clpeak
Mixbench:
  Single Precision
  Double Precision
clpeak

NVIDIA TITAN RTX

Processor: Intel Core i9-9900K @ 5.00GHz (8 Cores / 16 Threads), Motherboard: ASUS PRIME Z390-A (0602 BIOS), Chipset: Intel Cannon Lake PCH Shared SRAM, Memory: 16384MB, Disk: 2000GB SABRENT + Samsung SSD 970 EVO 250GB, Graphics: NVIDIA TITAN RTX 24GB (1350/7000MHz), Audio: Realtek ALC1220, Monitor: Acer B286HK, Network: Intel Connection

OS: Ubuntu 18.04, Kernel: 4.19.5-041905-generic (x86_64), Desktop: GNOME Shell 3.28.3, Display Server: X Server 1.19.6, Display Driver: NVIDIA 415.23, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 10.0.132, Vulkan: 1.1.84, Compiler: GCC 7.3.0 + LLVM 6.0.0 + CUDA 10.0, File-System: ext4, Screen Resolution: 3840x2160

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: intel_pstate performance
OpenCL Notes: GPU Compute Cores: 4608
Security Notes: __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + SSB disabled via prctl and seccomp

Testing initiated at 27 December 2018 09:16 by user pts.

NVIDIA RTX 2080 Ti

Processor: Intel Core i9-9900K @ 5.00GHz (8 Cores / 16 Threads), Motherboard: ASUS PRIME Z390-A (0602 BIOS), Chipset: Intel Cannon Lake PCH Shared SRAM, Memory: 16384MB, Disk: 2000GB SABRENT + Samsung SSD 970 EVO 250GB, Graphics: NVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz), Audio: Realtek ALC1220, Monitor: Acer B286HK, Network: Intel Connection

OS: Ubuntu 18.04, Kernel: 4.19.5-041905-generic (x86_64), Desktop: GNOME Shell 3.28.3, Display Server: X Server 1.19.6, Display Driver: NVIDIA 415.23, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 10.0.132, Vulkan: 1.1.84, Compiler: GCC 7.3.0 + LLVM 6.0.0 + CUDA 10.0, File-System: ext4, Screen Resolution: 3840x2160

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: intel_pstate performance
OpenCL Notes: GPU Compute Cores: 4352
Security Notes: __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + SSB disabled via prctl and seccomp

Testing initiated at 27 December 2018 15:34 by user pts.