AMD Ryzen Threadripper 7980X benchmarks on Ubuntu 24.04 LTS for a future article on Phoronix.
Ubuntu 23.10 Processor: AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (FA Z5 BIOS), Chipset: AMD Device 14a4, Memory: 4 x 32GB DRAM-4800MT/s Micron MTC20F1045S1RC48BA2, Disk: 1000GB CT1000T700SSD5, Graphics: AMD Radeon Pro W7900 45GB (1760/1124MHz), Audio: AMD Device 14cc, Monitor: DELL P2415Q, Network: Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX210/AX211/AX411
OS: Ubuntu 23.10, Kernel: 6.5.0-26-generic (x86_64), Desktop: GNOME Shell 45.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 23.2.1-1ubuntu3.1 (LLVM 15.0.7 DRM 3.54), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105Graphics Notes: BAR1 / Visible vRAM Size: 46064 MB - vBIOS Version: 113-D7070600-101Python Notes: Python 3.11.6Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + 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 / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Ubuntu 24.04 29 March Processor: AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (FA Z5 BIOS), Chipset: AMD Device 14a4, Memory: 4 x 32GB DDR5-4800MT/s Micron MTC20F1045S1RC48BA2Disk: 1000GB CT1000T700SSD5, Graphics: AMD Radeon Pro W7900 45GBAudio: AMD Device 14cc, Monitor: DELL P2415Q, Network: Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6E
OS: Ubuntu 24.04, Kernel: 6.8.0-11-generic (x86_64), Desktop: GNOME Shell 45.3, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.0.3-1ubuntu3 (LLVM 17.0.6 DRM 3.57), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-5jjdWe/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-5jjdWe/gcc-13-13.2.0/debian/tmp-gcn/usr --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=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105Graphics Notes: BAR1 / Visible vRAM Size: 46064 MBPython Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + 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 / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Ubuntu 23.10 vs. 24.04 LTS - System76 Thelio Major Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution Ubuntu 23.10 Ubuntu 24.04 29 March AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads) System76 Thelio Major (FA Z5 BIOS) AMD Device 14a4 4 x 32GB DRAM-4800MT/s Micron MTC20F1045S1RC48BA2 1000GB CT1000T700SSD5 AMD Radeon Pro W7900 45GB (1760/1124MHz) AMD Device 14cc DELL P2415Q Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX210/AX211/AX411 Ubuntu 23.10 6.5.0-26-generic (x86_64) GNOME Shell 45.2 X Server + Wayland 4.6 Mesa 23.2.1-1ubuntu3.1 (LLVM 15.0.7 DRM 3.54) GCC 13.2.0 ext4 1920x1080 4 x 32GB DDR5-4800MT/s Micron MTC20F1045S1RC48BA2 AMD Radeon Pro W7900 45GB Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6E Ubuntu 24.04 6.8.0-11-generic (x86_64) GNOME Shell 45.3 4.6 Mesa 24.0.3-1ubuntu3 (LLVM 17.0.6 DRM 3.57) OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - Ubuntu 23.10: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Ubuntu 24.04 29 March: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-5jjdWe/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-5jjdWe/gcc-13-13.2.0/debian/tmp-gcn/usr --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=auto --with-tune=generic --without-cuda-driver -v Processor Details - Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105 Graphics Details - Ubuntu 23.10: BAR1 / Visible vRAM Size: 46064 MB - vBIOS Version: 113-D7070600-101 - Ubuntu 24.04 29 March: BAR1 / Visible vRAM Size: 46064 MB Python Details - Ubuntu 23.10: Python 3.11.6 - Ubuntu 24.04 29 March: Python 3.12.2 Security Details - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + 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 / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Ubuntu 23.10 vs. Ubuntu 24.04 29 March Comparison Phoronix Test Suite Baseline +3.9% +3.9% +7.8% +7.8% +11.7% +11.7% 11.1% 11% 9.4% 9.4% 9.3% 7.8% 6.4% 6.3% 5.6% 5.4% 4.7% 4.6% 4% 3.9% 2.9% 2.7% 2.4% 2.4% 2.3% 2.1% 5.6% 3.9% 2.1% F.D.R.F.I - CPU 15.5% Read While Writing 13.2% A.G.R.R.0.F.I - CPU Bosphorus 4K Time To Compile 10% Unix Makefiles 9.6% 1920 x 1080 - F.K.V - 4 1920 x 1080 - F.K.O - 4 1920 x 1080 - FurMark Vulkan - 4 F.D.R.F.I - CPU 9.1% Time To Compile 8.6% Rand Read 8.6% Ninja 8.2% Time To Compile 7.8% R.R.W.R Chrysler Neon 1M 7.7% CPU - 256 - ResNet-50 7.3% CPU - 256 - ResNet-152 6.9% 1920 x 1080 - FurMark OpenGL - 4 Preset 13 - Bosphorus 4K Many Spheres - 1920 x 1080 Timed Time - Size 1,000 allmodconfig 5% Update Rand C.P.D.T V.D.F - CPU 4.4% V.D.F - CPU 4.1% A.G.R.R.0.F.I - CPU Wavelet Volume - 1920 x 1080 defconfig 3.3% H.E.R.F.I - CPU 3.1% Lion Overwrite H.E.R.F.I - CPU 2.5% Preset 12 - Bosphorus 4K V.P.M B.S.o.W W.P.D.F - CPU 2.2% Wavelet Contour - 1920 x 1080 R.S.A.F.I - CPU 2% N.S.P.L.F - CPU 2% Many Spheres - 1920 x 1080 Wavelet Volume - 1920 x 1080 Wavelet Contour - 1920 x 1080 OpenVINO RocksDB OpenVINO x265 Timed Mesa Compilation Timed LLVM Compilation FurMark FurMark FurMark OpenVINO Timed Godot Game Engine Compilation RocksDB Timed LLVM Compilation Timed Node.js Compilation RocksDB OpenRadioss PyTorch PyTorch FurMark SVT-AV1 ParaView SQLite Speedtest Timed Linux Kernel Compilation RocksDB OpenRadioss OpenVINO OpenVINO OpenVINO ParaView Timed Linux Kernel Compilation OpenVINO Google Draco RocksDB OpenVINO SVT-AV1 BRL-CAD OpenRadioss OpenVINO ParaView OpenVINO OpenVINO ParaView ParaView ParaView Ubuntu 23.10 Ubuntu 24.04 29 March
Ubuntu 23.10 vs. 24.04 LTS - System76 Thelio Major gravitymark: 1920 x 1080 - Vulkan 3dmark: 1920 x 1080 unigine-super: 1920 x 1080 - Fullscreen - Low - OpenGL unigine-super: 1920 x 1080 - Fullscreen - High - OpenGL unigine-super: 1920 x 1080 - Fullscreen - Medium - OpenGL furmark: 1920 x 1080 - FurMark OpenGL - 4 furmark: 1920 x 1080 - FurMark Vulkan - 4 furmark: 1920 x 1080 - FurMark Knot OpenGL - 4 furmark: 1920 x 1080 - Furmark Knot Vulkan - 4 paraview: Many Spheres - 1920 x 1080 paraview: Many Spheres - 1920 x 1080 paraview: Wavelet Volume - 1920 x 1080 paraview: Wavelet Volume - 1920 x 1080 paraview: Wavelet Contour - 1920 x 1080 paraview: Wavelet Contour - 1920 x 1080 npb: BT.C npb: CG.C npb: EP.D npb: LU.C npb: MG.C npb: SP.C quicksilver: CTS2 quicksilver: CORAL2 P1 quicksilver: CORAL2 P2 namd: ATPase with 327,506 Atoms namd: STMV with 1,066,628 Atoms openradioss: Bumper Beam openradioss: Chrysler Neon 1M openradioss: Cell Phone Drop Test openradioss: Bird Strike on Windshield openradioss: Rubber O-Ring Seal Installation openradioss: INIVOL and Fluid Structure Interaction Drop Container embree: Pathtracer ISPC - Crown embree: Pathtracer ISPC - Asian Dragon kvazaar: Bosphorus 4K - Very Fast kvazaar: Bosphorus 4K - Super Fast kvazaar: Bosphorus 4K - Ultra Fast svt-av1: Preset 8 - Bosphorus 4K svt-av1: Preset 12 - Bosphorus 4K svt-av1: Preset 13 - Bosphorus 4K uvg266: Bosphorus 4K - Very Fast uvg266: Bosphorus 4K - Super Fast uvg266: Bosphorus 4K - Ultra Fast vvenc: Bosphorus 4K - Fast vvenc: Bosphorus 4K - Faster x265: Bosphorus 4K ospray: particle_volume/ao/real_time ospray: particle_volume/scivis/real_time ospray: particle_volume/pathtracer/real_time ospray: gravity_spheres_volume/dim_512/ao/real_time ospray: gravity_spheres_volume/dim_512/scivis/real_time ospray: gravity_spheres_volume/dim_512/pathtracer/real_time compress-7zip: Compression Rating compress-7zip: Decompression Rating build-godot: Time To Compile build-linux-kernel: defconfig build-linux-kernel: allmodconfig build-llvm: Ninja build-llvm: Unix Makefiles build-mesa: Time To Compile build-nodejs: Time To Compile ospray-studio: 1 - 4K - 1 - Path Tracer - CPU ospray-studio: 3 - 4K - 1 - Path Tracer - CPU ospray-studio: 1 - 4K - 16 - Path Tracer - CPU ospray-studio: 1 - 4K - 32 - Path Tracer - CPU ospray-studio: 3 - 4K - 16 - Path Tracer - CPU ospray-studio: 3 - 4K - 32 - Path Tracer - CPU gromacs: MPI CPU - water_GMX50_bare pytorch: CPU - 256 - ResNet-50 pytorch: CPU - 256 - ResNet-152 tensorflow: CPU - 256 - AlexNet tensorflow: CPU - 256 - GoogLeNet tensorflow: CPU - 256 - ResNet-50 sqlite-speedtest: Timed Time - Size 1,000 darktable: Boat - CPU-only darktable: Masskrug - CPU-only darktable: Server Rack - CPU-only darktable: Server Room - CPU-only gimp: resize gimp: rotate gimp: auto-levels gimp: unsharp-mask rawtherapee: Total Benchmark Time draco: Lion draco: Church Facade openvino: Vehicle Detection FP16 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Face Detection Retail FP16-INT8 - CPU openvino: Face Detection Retail FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Noise Suppression Poconet-Like FP16 - CPU openvino: Noise Suppression Poconet-Like FP16 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU rocksdb: Overwrite rocksdb: Rand Read rocksdb: Update Rand rocksdb: Read While Writing rocksdb: Read Rand Write Rand llamafile: llava-v1.5-7b-q4 - CPU llamafile: mistral-7b-instruct-v0.2.Q8_0 - CPU llamafile: wizardcoder-python-34b-v1.0.Q6_K - CPU brl-cad: VGR Performance Metric darktable: Boat - CPU-only darktable: Masskrug - CPU-only darktable: Server Rack - CPU-only darktable: Server Room - CPU-only gimp: resize gimp: rotate gimp: auto-levels gimp: unsharp-mask Ubuntu 23.10 Ubuntu 24.04 29 March 326.8 595.89 237.3 202.0 215.4 216.466848 140.048681 104.474096 87.501902 167.07 16749.527 748.31 11972.880 816.49 8508.829 115266.12 24627.86 9708.11 141501.22 47183.70 40335.38 20873333 27780000 20806667 6.45088 1.61432 72.85 385.71 22.73 108.35 51.35 118.72 93.1179 102.7775 77.20 94.01 96.41 94.844 193.035 187.722 71.81 73.18 74.45 8.979 18.763 35.62 27.5284 27.6169 246.261 23.9426 23.4879 28.3727 359462 562659 88.735 28.744 274.810 128.939 182.944 11.639 115.851 1292 1529 20762 45373 24522 53006 7.585 47.84 18.93 1136.55 306.93 88.90 53.617 1.779 1.247 0.087 1.514 16.825 11.925 14.835 18.975 42.421 4190 5377 1693.54 18.85 85.24 374.33 4379.19 14.60 15789.16 4.05 1336.25 23.91 360.38 88.72 3479.92 17.83 2361.96 27.08 123608.15 0.4 637472 459425256 595447 13548278 5201523 21.64 13.36 4.52 1244893 325.5 593.56 236.4 202.5 212.0 230.415095 153.027969 114.294378 95.730868 176.49 17694.181 777.63 12442.092 833.45 8685.587 114935.25 24466.02 9723.94 142451.17 47534.30 40169.63 20853333 27710000 20710000 6.42930 1.60893 73.36 415.38 21.74 105.96 51.06 118.97 92.8933 102.2510 77.30 93.71 97.79 93.791 197.678 199.523 71.84 73.17 74.64 9.003 19.059 39.55 27.5631 27.5407 245.776 23.7729 23.2497 28.2652 365164 560711 96.380 29.704 288.610 139.480 200.520 12.799 124.938 1298 1538 20867 45722 24676 53377 7.534 44.59 17.70 1115.86 304.67 88.12 50.848 41.756 4072 5286 1622.44 19.62 84.75 376.51 4285.02 14.76 13670.94 4.42 1309.45 24.31 359.33 88.78 3411.04 18.07 2290.49 27.77 128490.72 0.36 654919 423040119 623281 11968393 5609140 21.69 13.37 4.53 1274397 1.900 1.369 0.125 1.610 15.957 11.894 14.652 19.004 OpenBenchmarking.org
GravityMark GravityMark is a cross-API, cross-platform GPU accelerated benchmark developed by Tellusim. GravityMark aims to exploit the performance of modern GPUs and render hundreds of thousands of objects in real-time all using GPU acceleration. GravityMark supports a variety of graphics rendering APIs and optionally supports accelerated ray-tracing. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.82 Resolution: 1920 x 1080 - Renderer: Vulkan Ubuntu 23.10 Ubuntu 24.04 29 March 70 140 210 280 350 SE +/- 2.03, N = 3 SE +/- 2.05, N = 3 326.8 325.5
3DMark Wild Life Extreme This test profile only automates the vendor build of 3DMark with its command-line / JSON support. If you do not have a licensed copy of the necessary 3DMark binaries in your Phoronix Test Suite download cache on your system, this test profile will not do anything and simply fail. You must have already obtained the proper licensed binaries from UL for this test profile to work -- this test profile simply automates the firing of the 3DMark benchmark at your desired resolution and capturing the results within the Phoronix Test Suite while you must already have the necessary 3DMark files on your system. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better 3DMark Wild Life Extreme 1.1.2.1 Resolution: 1920 x 1080 Ubuntu 23.10 Ubuntu 24.04 29 March 130 260 390 520 650 SE +/- 1.44, N = 3 SE +/- 1.19, N = 3 595.89 593.56
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.org Frames Per Second, More Is Better Unigine Superposition 1.0 Resolution: 1920 x 1080 - Mode: Fullscreen - Quality: Low - Renderer: OpenGL Ubuntu 23.10 Ubuntu 24.04 29 March 50 100 150 200 250 SE +/- 1.40, N = 3 SE +/- 1.16, N = 3 237.3 236.4 MAX: 343.8 MAX: 348.2
OpenBenchmarking.org Frames Per Second, More Is Better Unigine Superposition 1.0 Resolution: 1920 x 1080 - Mode: Fullscreen - Quality: High - Renderer: OpenGL Ubuntu 23.10 Ubuntu 24.04 29 March 40 80 120 160 200 SE +/- 0.92, N = 3 SE +/- 1.06, N = 3 202.0 202.5 MAX: 268.6 MAX: 270.7
OpenBenchmarking.org Frames Per Second, More Is Better Unigine Superposition 1.0 Resolution: 1920 x 1080 - Mode: Fullscreen - Quality: Medium - Renderer: OpenGL Ubuntu 23.10 Ubuntu 24.04 29 March 50 100 150 200 250 SE +/- 1.14, N = 3 SE +/- 0.97, N = 3 215.4 212.0 MAX: 288.1 MAX: 285.7
FurMark FurMark 2 is a cross-platform GPU stress test that can exercise both OpenGL and Vulkan drivers/GPUs. FurMark 2 is the successor to the original FurMark benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better FurMark 2.1 Resolution: 1920 x 1080 - Demo: FurMark OpenGL - MSAA: 4 Ubuntu 23.10 Ubuntu 24.04 29 March 50 100 150 200 250 SE +/- 0.22, N = 3 SE +/- 0.22, N = 3 216.47 230.42 MIN: 211 / MAX: 231 MIN: 225 / MAX: 244
OpenBenchmarking.org FPS, More Is Better FurMark 2.1 Resolution: 1920 x 1080 - Demo: FurMark Vulkan - MSAA: 4 Ubuntu 23.10 Ubuntu 24.04 29 March 30 60 90 120 150 SE +/- 0.39, N = 3 SE +/- 0.36, N = 3 140.05 153.03 MIN: 136 / MAX: 152 MIN: 149 / MAX: 165
OpenBenchmarking.org FPS, More Is Better FurMark 2.1 Resolution: 1920 x 1080 - Demo: FurMark Knot OpenGL - MSAA: 4 Ubuntu 23.10 Ubuntu 24.04 29 March 30 60 90 120 150 SE +/- 0.56, N = 3 SE +/- 0.39, N = 3 104.47 114.29 MIN: 93 / MAX: 110 MIN: 113 / MAX: 119
OpenBenchmarking.org FPS, More Is Better FurMark 2.1 Resolution: 1920 x 1080 - Demo: Furmark Knot Vulkan - MSAA: 4 Ubuntu 23.10 Ubuntu 24.04 29 March 20 40 60 80 100 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 87.50 95.73 MIN: 85 / MAX: 94 MIN: 93 / MAX: 102
ParaView This test runs ParaView benchmarks: an open-source data analytics and visualization application. Paraview describes itself as "an open-source, multi-platform data analysis and visualization application. ParaView users can quickly build visualizations to analyze their data using qualitative and quantitative techniques." Learn more via the OpenBenchmarking.org test page.
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C Ubuntu 23.10 Ubuntu 24.04 29 March 20K 40K 60K 80K 100K SE +/- 41.91, N = 3 SE +/- 106.43, N = 3 115266.12 114935.25 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Ubuntu 23.10: Open MPI 4.1.5 3. Ubuntu 24.04 29 March: Open MPI 4.1.6
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C Ubuntu 23.10 Ubuntu 24.04 29 March 5K 10K 15K 20K 25K SE +/- 88.58, N = 3 SE +/- 56.39, N = 3 24627.86 24466.02 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Ubuntu 23.10: Open MPI 4.1.5 3. Ubuntu 24.04 29 March: Open MPI 4.1.6
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D Ubuntu 23.10 Ubuntu 24.04 29 March 2K 4K 6K 8K 10K SE +/- 83.77, N = 3 SE +/- 85.53, N = 3 9708.11 9723.94 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Ubuntu 23.10: Open MPI 4.1.5 3. Ubuntu 24.04 29 March: Open MPI 4.1.6
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C Ubuntu 23.10 Ubuntu 24.04 29 March 30K 60K 90K 120K 150K SE +/- 398.56, N = 3 SE +/- 144.28, N = 3 141501.22 142451.17 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Ubuntu 23.10: Open MPI 4.1.5 3. Ubuntu 24.04 29 March: Open MPI 4.1.6
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C Ubuntu 23.10 Ubuntu 24.04 29 March 10K 20K 30K 40K 50K SE +/- 90.18, N = 3 SE +/- 155.58, N = 3 47183.70 47534.30 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Ubuntu 23.10: Open MPI 4.1.5 3. Ubuntu 24.04 29 March: Open MPI 4.1.6
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C Ubuntu 23.10 Ubuntu 24.04 29 March 9K 18K 27K 36K 45K SE +/- 3.52, N = 3 SE +/- 37.03, N = 3 40335.38 40169.63 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Ubuntu 23.10: Open MPI 4.1.5 3. Ubuntu 24.04 29 March: Open MPI 4.1.6
Quicksilver Quicksilver is a proxy application that represents some elements of the Mercury workload by solving a simplified dynamic Monte Carlo particle transport problem. Quicksilver is developed by Lawrence Livermore National Laboratory (LLNL) and this test profile currently makes use of the OpenMP CPU threaded code path. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Figure Of Merit, More Is Better Quicksilver 20230818 Input: CTS2 Ubuntu 23.10 Ubuntu 24.04 29 March 4M 8M 12M 16M 20M SE +/- 44095.86, N = 3 SE +/- 14529.66, N = 3 20873333 20853333 1. (CXX) g++ options: -fopenmp -O3 -march=native
OpenBenchmarking.org Figure Of Merit, More Is Better Quicksilver 20230818 Input: CORAL2 P1 Ubuntu 23.10 Ubuntu 24.04 29 March 6M 12M 18M 24M 30M SE +/- 23094.01, N = 3 SE +/- 43588.99, N = 3 27780000 27710000 1. (CXX) g++ options: -fopenmp -O3 -march=native
OpenBenchmarking.org Figure Of Merit, More Is Better Quicksilver 20230818 Input: CORAL2 P2 Ubuntu 23.10 Ubuntu 24.04 29 March 4M 8M 12M 16M 20M SE +/- 18559.21, N = 3 SE +/- 10000.00, N = 3 20806667 20710000 1. (CXX) g++ options: -fopenmp -O3 -march=native
NAMD NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ns/day, More Is Better NAMD 3.0b6 Input: ATPase with 327,506 Atoms Ubuntu 23.10 Ubuntu 24.04 29 March 2 4 6 8 10 SE +/- 0.01381, N = 3 SE +/- 0.00329, N = 3 6.45088 6.42930
OpenBenchmarking.org ns/day, More Is Better NAMD 3.0b6 Input: STMV with 1,066,628 Atoms Ubuntu 23.10 Ubuntu 24.04 29 March 0.3632 0.7264 1.0896 1.4528 1.816 SE +/- 0.00352, N = 3 SE +/- 0.00337, N = 3 1.61432 1.60893
OpenRadioss OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Bumper Beam Ubuntu 23.10 Ubuntu 24.04 29 March 16 32 48 64 80 SE +/- 0.18, N = 3 SE +/- 0.09, N = 3 72.85 73.36
OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: INIVOL and Fluid Structure Interaction Drop Container Ubuntu 23.10 Ubuntu 24.04 29 March 30 60 90 120 150 SE +/- 0.91, N = 3 SE +/- 0.28, N = 3 118.72 118.97
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Crown Ubuntu 23.10 Ubuntu 24.04 29 March 20 40 60 80 100 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 93.12 92.89 MIN: 91.73 / MAX: 95.23 MIN: 91.4 / MAX: 95.18
OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon Ubuntu 23.10 Ubuntu 24.04 29 March 20 40 60 80 100 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 102.78 102.25 MIN: 101.98 / MAX: 104.09 MIN: 101.41 / MAX: 103.88
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Very Fast Ubuntu 23.10 Ubuntu 24.04 29 March 20 40 60 80 100 SE +/- 0.14, N = 3 SE +/- 0.36, N = 3 77.20 77.30 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Super Fast Ubuntu 23.10 Ubuntu 24.04 29 March 20 40 60 80 100 SE +/- 0.43, N = 3 SE +/- 0.30, N = 3 94.01 93.71 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Ubuntu 23.10 Ubuntu 24.04 29 March 20 40 60 80 100 SE +/- 0.58, N = 3 SE +/- 0.66, N = 3 96.41 97.79 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 4K Ubuntu 23.10 Ubuntu 24.04 29 March 20 40 60 80 100 SE +/- 0.53, N = 3 SE +/- 0.79, N = 3 94.84 93.79 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 4K Ubuntu 23.10 Ubuntu 24.04 29 March 40 80 120 160 200 SE +/- 1.55, N = 3 SE +/- 2.00, N = 3 193.04 197.68 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 4K Ubuntu 23.10 Ubuntu 24.04 29 March 40 80 120 160 200 SE +/- 2.10, N = 4 SE +/- 2.41, N = 4 187.72 199.52 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Super Fast Ubuntu 23.10 Ubuntu 24.04 29 March 16 32 48 64 80 SE +/- 0.25, N = 3 SE +/- 0.03, N = 3 73.18 73.17
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Ubuntu 23.10 Ubuntu 24.04 29 March 20 40 60 80 100 SE +/- 0.11, N = 3 SE +/- 0.10, N = 3 74.45 74.64
VVenC VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.11 Video Input: Bosphorus 4K - Video Preset: Fast Ubuntu 23.10 Ubuntu 24.04 29 March 3 6 9 12 15 SE +/- 0.047, N = 3 SE +/- 0.046, N = 3 8.979 9.003 1. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.11 Video Input: Bosphorus 4K - Video Preset: Faster Ubuntu 23.10 Ubuntu 24.04 29 March 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 18.76 19.06 1. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
x265 This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 4K Ubuntu 23.10 Ubuntu 24.04 29 March 9 18 27 36 45 SE +/- 0.07, N = 3 SE +/- 0.37, N = 3 35.62 39.55 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OSPRay Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: particle_volume/ao/real_time Ubuntu 23.10 Ubuntu 24.04 29 March 6 12 18 24 30 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 27.53 27.56
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: particle_volume/scivis/real_time Ubuntu 23.10 Ubuntu 24.04 29 March 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 27.62 27.54
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: particle_volume/pathtracer/real_time Ubuntu 23.10 Ubuntu 24.04 29 March 50 100 150 200 250 SE +/- 0.08, N = 3 SE +/- 0.21, N = 3 246.26 245.78
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: gravity_spheres_volume/dim_512/ao/real_time Ubuntu 23.10 Ubuntu 24.04 29 March 6 12 18 24 30 SE +/- 0.00, N = 3 SE +/- 0.06, N = 3 23.94 23.77
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time Ubuntu 23.10 Ubuntu 24.04 29 March 6 12 18 24 30 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 23.49 23.25
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time Ubuntu 23.10 Ubuntu 24.04 29 March 7 14 21 28 35 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 28.37 28.27
OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Decompression Rating Ubuntu 23.10 Ubuntu 24.04 29 March 120K 240K 360K 480K 600K SE +/- 838.51, N = 3 SE +/- 700.74, N = 3 562659 560711 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 300 600 900 1200 1500 SE +/- 0.88, N = 3 SE +/- 1.15, N = 3 1292 1298
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 300 600 900 1200 1500 SE +/- 1.86, N = 3 SE +/- 1.20, N = 3 1529 1538
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 4K 8K 12K 16K 20K SE +/- 15.14, N = 3 SE +/- 10.20, N = 3 20762 20867
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 10K 20K 30K 40K 50K SE +/- 36.01, N = 3 SE +/- 4.98, N = 3 45373 45722
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 5K 10K 15K 20K 25K SE +/- 13.25, N = 3 SE +/- 30.02, N = 3 24522 24676
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 11K 22K 33K 44K 55K SE +/- 106.34, N = 3 SE +/- 13.57, N = 3 53006 53377
GROMACS The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2024 Implementation: MPI CPU - Input: water_GMX50_bare Ubuntu 23.10 Ubuntu 24.04 29 March 2 4 6 8 10 SE +/- 0.003, N = 3 SE +/- 0.006, N = 3 7.585 7.534 1. (CXX) g++ options: -O3 -lm
PyTorch This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 256 - Model: ResNet-50 Ubuntu 23.10 Ubuntu 24.04 29 March 11 22 33 44 55 SE +/- 0.26, N = 3 SE +/- 0.34, N = 3 47.84 44.59 MIN: 43.7 / MAX: 48.82 MIN: 41.28 / MAX: 46.04
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 256 - Model: ResNet-152 Ubuntu 23.10 Ubuntu 24.04 29 March 5 10 15 20 25 SE +/- 0.09, N = 3 SE +/- 0.16, N = 3 18.93 17.70 MIN: 18.21 / MAX: 19.23 MIN: 16.58 / MAX: 18.19
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: AlexNet Ubuntu 23.10 Ubuntu 24.04 29 March 200 400 600 800 1000 SE +/- 1.32, N = 3 SE +/- 0.74, N = 3 1136.55 1115.86
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: GoogLeNet Ubuntu 23.10 Ubuntu 24.04 29 March 70 140 210 280 350 SE +/- 0.24, N = 3 SE +/- 0.16, N = 3 306.93 304.67
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: ResNet-50 Ubuntu 23.10 Ubuntu 24.04 29 March 20 40 60 80 100 SE +/- 0.05, N = 3 SE +/- 0.28, N = 3 88.90 88.12
RawTherapee RawTherapee is a cross-platform, open-source multi-threaded RAW image processing program. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better RawTherapee Total Benchmark Time Ubuntu 23.10 Ubuntu 24.04 29 March 10 20 30 40 50 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 42.42 41.76 1. Ubuntu 23.10: RawTherapee, version 5.9, command line. 2. Ubuntu 24.04 29 March: RawTherapee, version 5.10, command line.
Google Draco Draco is a library developed by Google for compressing/decompressing 3D geometric meshes and point clouds. This test profile uses some Artec3D PLY models as the sample 3D model input formats for Draco compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.5.6 Model: Lion Ubuntu 23.10 Ubuntu 24.04 29 March 900 1800 2700 3600 4500 SE +/- 1.76, N = 3 SE +/- 13.64, N = 3 4190 4072 1. (CXX) g++ options: -O3
OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.5.6 Model: Church Facade Ubuntu 23.10 Ubuntu 24.04 29 March 1200 2400 3600 4800 6000 SE +/- 6.66, N = 3 SE +/- 19.19, N = 3 5377 5286 1. (CXX) g++ options: -O3
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16 - Device: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 400 800 1200 1600 2000 SE +/- 1.44, N = 3 SE +/- 9.61, N = 3 1693.54 1622.44 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16 - Device: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.12, N = 3 18.85 19.62 MIN: 7.07 / MAX: 65.71 MIN: 5.81 / MAX: 38.14 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 20 40 60 80 100 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 85.24 84.75 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 80 160 240 320 400 SE +/- 0.16, N = 3 SE +/- 0.08, N = 3 374.33 376.51 MIN: 310.18 / MAX: 399.4 MIN: 334.15 / MAX: 400.64 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16 - Device: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 900 1800 2700 3600 4500 SE +/- 1.79, N = 3 SE +/- 2.98, N = 3 4379.19 4285.02 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16 - Device: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 4 8 12 16 20 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 14.60 14.76 MIN: 6.95 / MAX: 35.57 MIN: 6.9 / MAX: 27.38 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 3K 6K 9K 12K 15K SE +/- 9.62, N = 3 SE +/- 9.26, N = 3 15789.16 13670.94 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 0.9945 1.989 2.9835 3.978 4.9725 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 4.05 4.42 MIN: 2.51 / MAX: 27.48 MIN: 1.97 / MAX: 15.19 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 300 600 900 1200 1500 SE +/- 3.18, N = 3 SE +/- 1.44, N = 3 1336.25 1309.45 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 6 12 18 24 30 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 23.91 24.31 MIN: 11.87 / MAX: 49.81 MIN: 11.56 / MAX: 41.32 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 80 160 240 320 400 SE +/- 1.30, N = 3 SE +/- 1.32, N = 3 360.38 359.33 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 20 40 60 80 100 SE +/- 0.32, N = 3 SE +/- 0.33, N = 3 88.72 88.78 MIN: 38.59 / MAX: 119.29 MIN: 36.89 / MAX: 120.54 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 700 1400 2100 2800 3500 SE +/- 26.84, N = 15 SE +/- 28.92, N = 15 3479.92 3411.04 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 4 8 12 16 20 SE +/- 0.13, N = 15 SE +/- 0.15, N = 15 17.83 18.07 MIN: 7.34 / MAX: 114.8 MIN: 6.61 / MAX: 84.99 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16-INT8 - Device: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 500 1000 1500 2000 2500 SE +/- 0.65, N = 3 SE +/- 3.96, N = 3 2361.96 2290.49 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16-INT8 - Device: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 7 14 21 28 35 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 27.08 27.77 MIN: 15.63 / MAX: 48.21 MIN: 15.52 / MAX: 52.37 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 30K 60K 90K 120K 150K SE +/- 32.34, N = 3 SE +/- 45.99, N = 3 123608.15 128490.72 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 0.09 0.18 0.27 0.36 0.45 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.40 0.36 MIN: 0.18 / MAX: 26.18 MIN: 0.19 / MAX: 16.69 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
RocksDB This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Overwrite Ubuntu 23.10 Ubuntu 24.04 29 March 140K 280K 420K 560K 700K SE +/- 1878.55, N = 3 SE +/- 536.29, N = 3 637472 654919 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Random Read Ubuntu 23.10 Ubuntu 24.04 29 March 100M 200M 300M 400M 500M SE +/- 384615.20, N = 3 SE +/- 596367.62, N = 3 459425256 423040119 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Update Random Ubuntu 23.10 Ubuntu 24.04 29 March 130K 260K 390K 520K 650K SE +/- 1071.92, N = 3 SE +/- 717.15, N = 3 595447 623281 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Read While Writing Ubuntu 23.10 Ubuntu 24.04 29 March 3M 6M 9M 12M 15M SE +/- 33234.45, N = 3 SE +/- 129305.78, N = 5 13548278 11968393 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Read Random Write Random Ubuntu 23.10 Ubuntu 24.04 29 March 1.2M 2.4M 3.6M 4.8M 6M SE +/- 24377.73, N = 3 SE +/- 28033.13, N = 3 5201523 5609140 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Llamafile Mozilla's Llamafile allows distributing and running large language models (LLMs) as a single file. Llamafile aims to make open-source LLMs more accessible to developers and users. Llamafile supports a variety of models, CPUs and GPUs, and other options. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.6 Test: llava-v1.5-7b-q4 - Acceleration: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 21.64 21.69
OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.6 Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 13.36 13.37
OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.6 Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU Ubuntu 23.10 Ubuntu 24.04 29 March 1.0193 2.0386 3.0579 4.0772 5.0965 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 4.52 4.53
BRL-CAD BRL-CAD is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.38.2 VGR Performance Metric Ubuntu 23.10 Ubuntu 24.04 29 March 300K 600K 900K 1200K 1500K 1244893 1274397 1. (CXX) g++ options: -std=c++17 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lnetpbm -lregex_brl -lz_brl -lassimp -ldl -lm -ltk8.6
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 4.6.1 Test: Server Rack - Acceleration: CPU-only Ubuntu 24.04 29 March 0.0281 0.0562 0.0843 0.1124 0.1405 SE +/- 0.003, N = 15 0.125
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 4.6.1 Test: Server Room - Acceleration: CPU-only Ubuntu 24.04 29 March 0.3623 0.7246 1.0869 1.4492 1.8115 SE +/- 0.022, N = 3 1.610
Ubuntu 23.10 Processor: AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (FA Z5 BIOS), Chipset: AMD Device 14a4, Memory: 4 x 32GB DRAM-4800MT/s Micron MTC20F1045S1RC48BA2, Disk: 1000GB CT1000T700SSD5, Graphics: AMD Radeon Pro W7900 45GB (1760/1124MHz), Audio: AMD Device 14cc, Monitor: DELL P2415Q, Network: Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX210/AX211/AX411
OS: Ubuntu 23.10, Kernel: 6.5.0-26-generic (x86_64), Desktop: GNOME Shell 45.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 23.2.1-1ubuntu3.1 (LLVM 15.0.7 DRM 3.54), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105Graphics Notes: BAR1 / Visible vRAM Size: 46064 MB - vBIOS Version: 113-D7070600-101Python Notes: Python 3.11.6Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + 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 / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 27 March 2024 16:17 by user pts.
Ubuntu 24.04 29 March Processor: AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (FA Z5 BIOS), Chipset: AMD Device 14a4, Memory: 4 x 32GB DDR5-4800MT/s Micron MTC20F1045S1RC48BA2, Disk: 1000GB CT1000T700SSD5, Graphics: AMD Radeon Pro W7900 45GB, Audio: AMD Device 14cc, Monitor: DELL P2415Q, Network: Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6E
OS: Ubuntu 24.04, Kernel: 6.8.0-11-generic (x86_64), Desktop: GNOME Shell 45.3, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.0.3-1ubuntu3 (LLVM 17.0.6 DRM 3.57), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-5jjdWe/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-5jjdWe/gcc-13-13.2.0/debian/tmp-gcn/usr --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=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105Graphics Notes: BAR1 / Visible vRAM Size: 46064 MBPython Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + 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 / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 29 March 2024 14:39 by user phoronix.