NVIDIA Windows vs. Linux GPU Compute

Benchmarks by Michael Larabel for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2301024-NE-NVCOMPUTE35&sor.

ProcessorMotherboardMemoryDiskGraphicsAudioMonitorNetworkChipsetOSKernelDisplay DriverCompilerFile-SystemScreen ResolutionDesktopDisplay ServerOpenGLOpenCLVulkanRTX 3080RTX 3090RTX 3080RTX 3090 Windows 11 Windows 11 Ubuntu 22.10 Ubuntu 22.10Intel Core i9-13900K (24 Cores / 32 Threads)ASUS PRIME Z790-P WIFI (0602 BIOS)2 x 16384 MB 6000MHz Corsair CMK32GX5M2B6000C361908GB SOLIDIGM SSDPFKKW020X7NVIDIA GeForce RTX 3080 10GBHD Audio Device + NVIDIA HD AudioASUS V8UBluetooth Device (Personal Area )Microsoft Windows 11 Pro Build 2262110.0.22621.963 (x86_64)527.56 (31.0.15.2756)GCC 8.3.0NTFS3840x2160NVIDIA GeForce RTX 3090 24GBIntel Device 7a2732GB2048GB SOLIDIGM SSDPFKKW020X7 + 2000GBNVIDIA GeForce RTX 3080 10GBRealtek ALC897ASUS VP28UIntel Device 7a70Ubuntu 22.105.19.0-26-generic (x86_64)GNOME Shell 43.1X Server 1.21.1.4NVIDIA 525.60.114.6.0OpenCL 3.0 CUDA 12.0.891.3.224GCC 12.2.0ext4NVIDIA GeForce RTX 3090 24GBOpenBenchmarking.orgProcessor Details- RTX 3080: Windows 11: CPU Microcode: 000000000E010000- RTX 3090: Windows 11: CPU Microcode: 000000000E010000- RTX 3080: Ubuntu 22.10: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x10e - Thermald 2.5.1- RTX 3090: Ubuntu 22.10: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x10e - Thermald 2.5.1Security Details- RTX 3080: Windows 11: VBS: Enabled and running + HVCI: Running + MBEC: Available- RTX 3090: Windows 11: VBS: Enabled and running + HVCI: Running + MBEC: Available- RTX 3080: Ubuntu 22.10: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected - RTX 3090: Ubuntu 22.10: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected Kernel Details- RTX 3080: Ubuntu 22.10, RTX 3090: Ubuntu 22.10: Transparent Huge Pages: madviseGraphics Details- RTX 3080: Ubuntu 22.10: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 94.02.20.00.07- RTX 3090: Ubuntu 22.10: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 94.02.27.00.02OpenCL Details- RTX 3080: Ubuntu 22.10: GPU Compute Cores: 8704- RTX 3090: Ubuntu 22.10: GPU Compute Cores: 10496

hashcat: MD5hashcat: SHA1hashcat: 7-Ziphashcat: SHA-512hashcat: TrueCrypt RIPEMD160 + XTSoctanebench: Total Scorefahbench: blender: BMW27 - NVIDIA CUDAblender: BMW27 - NVIDIA OptiXblender: Classroom - NVIDIA CUDAblender: Fishy Cat - NVIDIA CUDAblender: Barbershop - NVIDIA CUDAblender: Classroom - NVIDIA OptiXblender: Fishy Cat - NVIDIA OptiXblender: Barbershop - NVIDIA OptiXblender: Pabellon Barcelona - NVIDIA CUDAblender: Pabellon Barcelona - NVIDIA OptiXv-ray: NVIDIA RTX GPUv-ray: NVIDIA CUDA GPURTX 3080RTX 3090RTX 3080RTX 3090 Windows 11 Windows 11 Ubuntu 22.10 Ubuntu 22.1060704666667191820000009766332409200000716100553.473864241.926712.357.0524.5926.27104.4416.9512.0861.4560.7319.3623421783718370333332279260000011348002862100000839100663.425984242.634710.486.1220.5222.1388.2214.5710.4452.2649.6616.1828252091608938000001927473333310182002427200000718333572.856139314.125911.816.6123.9924.76100.2016.3111.7759.3659.2718.2524091779716071333332269033333311731002844866667837167689.77824333.758010.035.7020.0320.9683.8213.939.9550.4248.6215.2629602116OpenBenchmarking.org

Hashcat

Benchmark: MD5

RTX 3090RTX 3080OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: MD5Windows 11Ubuntu 22.1015000M30000M45000M60000M75000MSE +/- 128630508.74, N = 3SE +/- 87864238.71, N = 3SE +/- 143096785.43, N = 3SE +/- 60645151.86, N = 371837033333716071333336089380000060704666667

Hashcat

Benchmark: SHA1

RTX 3090RTX 3080OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: SHA1Windows 11Ubuntu 22.105000M10000M15000M20000M25000MSE +/- 9242474.42, N = 3SE +/- 16442255.86, N = 3SE +/- 24230307.01, N = 3SE +/- 25474758.75, N = 322792600000226903333331927473333319182000000

Hashcat

Benchmark: 7-Zip

RTX 3090RTX 3080OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: 7-ZipUbuntu 22.10Windows 11300K600K900K1200K1500KSE +/- 1415.39, N = 3SE +/- 3946.31, N = 3SE +/- 3955.17, N = 3SE +/- 5976.71, N = 3117310011348001018200976633

Hashcat

Benchmark: SHA-512

RTX 3090RTX 3080OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: SHA-512Windows 11Ubuntu 22.10600M1200M1800M2400M3000MSE +/- 907377.17, N = 3SE +/- 1836966.10, N = 3SE +/- 850490.05, N = 3SE +/- 1115048.58, N = 32862100000284486666724272000002409200000

Hashcat

Benchmark: TrueCrypt RIPEMD160 + XTS

RTX 3090RTX 3080OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: TrueCrypt RIPEMD160 + XTSWindows 11Ubuntu 22.10200K400K600K800K1000KSE +/- 1305.12, N = 3SE +/- 5217.07, N = 3SE +/- 1267.98, N = 3SE +/- 2891.94, N = 3839100837167718333716100

OctaneBench

Total Score

RTX 3090RTX 3080OpenBenchmarking.orgScore, More Is BetterOctaneBench 2020.1Total ScoreUbuntu 22.10Windows 11150300450600750689.78663.43572.86553.47

FAHBench

RTX 3090RTX 3080OpenBenchmarking.orgNs Per Day, More Is BetterFAHBench 2.3.2Ubuntu 22.10Windows 1170140210280350SE +/- 0.38, N = 3SE +/- 2.35, N = 15SE +/- 0.25, N = 3SE +/- 1.08, N = 3333.76242.63314.13241.93

Blender

Blend File: BMW27 - Compute: NVIDIA CUDA

RTX 3090RTX 3080OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: BMW27 - Compute: NVIDIA CUDAUbuntu 22.10Windows 113691215SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 310.0310.4811.8112.35

Blender

Blend File: BMW27 - Compute: NVIDIA OptiX

RTX 3090RTX 3080OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: BMW27 - Compute: NVIDIA OptiXUbuntu 22.10Windows 11246810SE +/- 0.00, N = 3SE +/- 0.06, N = 15SE +/- 0.05, N = 14SE +/- 0.04, N = 35.706.126.617.05

Blender

Blend File: Classroom - Compute: NVIDIA CUDA

RTX 3090RTX 3080OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Classroom - Compute: NVIDIA CUDAUbuntu 22.10Windows 11612182430SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 320.0320.5223.9924.59

Blender

Blend File: Fishy Cat - Compute: NVIDIA CUDA

RTX 3090RTX 3080OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Fishy Cat - Compute: NVIDIA CUDAUbuntu 22.10Windows 11612182430SE +/- 0.00, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.24, N = 320.9622.1324.7626.27

Blender

Blend File: Barbershop - Compute: NVIDIA CUDA

RTX 3090RTX 3080OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Barbershop - Compute: NVIDIA CUDAUbuntu 22.10Windows 1120406080100SE +/- 0.10, N = 3SE +/- 0.17, N = 3SE +/- 0.08, N = 3SE +/- 0.19, N = 383.8288.22100.20104.44

Blender

Blend File: Classroom - Compute: NVIDIA OptiX

RTX 3090RTX 3080OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Classroom - Compute: NVIDIA OptiXUbuntu 22.10Windows 1148121620SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 313.9314.5716.3116.95

Blender

Blend File: Fishy Cat - Compute: NVIDIA OptiX

RTX 3090RTX 3080OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Fishy Cat - Compute: NVIDIA OptiXUbuntu 22.10Windows 113691215SE +/- 0.01, N = 3SE +/- 0.08, N = 9SE +/- 0.12, N = 6SE +/- 0.01, N = 39.9510.4411.7712.08

Blender

Blend File: Barbershop - Compute: NVIDIA OptiX

RTX 3090RTX 3080OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Barbershop - Compute: NVIDIA OptiXUbuntu 22.10Windows 111428425670SE +/- 0.02, N = 3SE +/- 0.10, N = 3SE +/- 0.10, N = 3SE +/- 0.09, N = 350.4252.2659.3661.45

Blender

Blend File: Pabellon Barcelona - Compute: NVIDIA CUDA

RTX 3090RTX 3080OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Pabellon Barcelona - Compute: NVIDIA CUDAUbuntu 22.10Windows 111428425670SE +/- 0.00, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 348.6249.6659.2760.73

Blender

Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX

RTX 3090RTX 3080OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXUbuntu 22.10Windows 11510152025SE +/- 0.00, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 315.2616.1818.2519.36

Chaos Group V-RAY

Mode: NVIDIA RTX GPU

RTX 3090RTX 3080OpenBenchmarking.orgvrays, More Is BetterChaos Group V-RAY 5.02Mode: NVIDIA RTX GPUUbuntu 22.10Windows 116001200180024003000SE +/- 2.08, N = 3SE +/- 1.53, N = 3SE +/- 5.46, N = 3SE +/- 7.86, N = 32960282524092342

Chaos Group V-RAY

Mode: NVIDIA CUDA GPU

RTX 3090RTX 3080OpenBenchmarking.orgvpaths, More Is BetterChaos Group V-RAY 5.02Mode: NVIDIA CUDA GPUUbuntu 22.10Windows 115001000150020002500SE +/- 1.15, N = 3SE +/- 0.00, N = 3SE +/- 0.88, N = 3SE +/- 5.03, N = 32116209117831779

Phoronix Test Suite v10.8.4